물류운송사의 차량 관제 기반 AI 및 알고리즘 결합 탄소배출량 자동 분류 시스템

... 본 발명은 물류운송사의 차량 관리를 위한 탄소배출량 자동 분류 시스템에 관한 것으로, 차량 관제 시스템, AI 기반 탄소배출량 계산 모듈, 자체 개발 알고리즘에 의한 분류 시스템을 포함하여 구성된다. 이 시스템은 차량 운행 데이터와 외부 환경 변수를 분석하여 탄소배출량을 자동으로 계산하고, 이를 scope 1, 2, 3으로 분류함으로써, 기업별 탄소배출량을 보다 효율적으로 관리할 수 있도록 한다. 본 발명의 차량 관제 시스템은 차량의 위치, 속도, 운행 경로 등의 실시간 운행 데이터를 수집한다. AI 기반 탄소배출량 계산 모듈은 이러한 데이터와 함께 외부 환경 변수를 고려하여 탄소배출량을 정확하게 계산한다. 계산된 탄소배출량은 자체 개발된 알고리즘에 의해 자동으로 scope 1, 2, 3으로 분류되며, 이 과정을 통해 기업별 탄소배출량을 정확하게 관리할 수 있게 된다. 또한, 기계 학습 및 데이터 분석 모듈을 통해 시스템의 정확도와 효율성은 지속적으로 개선된다. 본 발명은 복잡한 환경 변화와 다양한 운행 조건에서도 정확한 탄소배출량 계산 및 분류를 가능하게 하며, 탄소배출량 관리의 시간 효율성과 정확도를 크게 향상시킨다. 이로 인해 기업의 환경적 책임 이행 및 지속 가능성 목표 달성에 기여하며, 탄소배출량 관리 및 보고의 정확성이 향상됨으로써 기업의 신뢰도를 높이는 효과가 있다.

Correlating data center resources in a multi-tenant execution environment using machine learning techniques

Methods, apparatus, and processor-readable storage media for correlating data center resources in a multi-tenant execution environment using machine learning techniques are provided herein. An example computer-implemented method includes obtaining multiple data streams pertaining to one or more data center resources in at least one multi-tenant executing environment; correlating one or more portions of the multiple data streams by processing at least a portion of the multiple data streams using at least one multi-tenant-capable search engine; determining one or more anomalies within the multiple data streams by processing the one or more correlated portions of the multiple data streams using a machine learning-based anomaly detection engine; and performing at least one automated action based at least in part on the one or more determined anomalies.

Optimizing mapping of ECG signals retrospectively by detecting inconsistency

A system includes signal acquisition circuitry and a processor. The signal acquisition circuitry is configured to receive multiple intra-cardiac signals acquired by multiple electrodes of an intra-cardiac probe in a heart of a patient. The processor is configured to perform a sequence of annotation-visualization operations at subsequent times, by performing, in each operation: extracting multiple annotation values from the intra-cardiac signals, selecting a group of the intra-cardiac signals, identifying in the group one or more annotation values that are statistically deviant by more than a predefined measure of deviation, and visualizing the annotation values to a user, while omitting and refraining from visualizing the statistically deviant annotation values. The processor is further configured to assess, over one or more of the annotation-visualization operations, a rate of omissions of annotation values, and to take a corrective action in response to detecting that the rate of omissions ...

Hardware-assisted malware detection using explainable machine learning

The present disclosure describes systems and methods for hardware-assisted malware detection. One such system comprises a memory; and a hardware processor of a computing device operatively coupled to the memory. The hardware processor is configured to execute a software application suspected of being malware; monitor behavior of the software application at run-time; and acquire an input time sequence of data records based on a trace analysis of the software application, wherein the input time sequence comprises a plurality of features of the software application. The hardware processor is further configured to classify the software application as being a malicious software application based on the plurality of features of the software application; and output a ranking of a subset plurality of features by their respective contributions towards the classification of the software application as being malicious software.

METHODS AND APPARATUS FOR INJURY PREDICTION BASED ON MACHINE LEARNING TECHNIQUES

Detecting adversary attacks on a deep neural network (DNN)

Systems and methods of dynamic outlier bias reduction in facility operating data

In at least one embodiment, the present description is directed to a computer system, having a processor to at least: electronically receive a model for one or more operating conditions, and facility operating data; iteratively perform one or more iterations of outlier bias reduction in the facility operating data based on the model, including: determining model predicted values, comparing the model predicted values to the facility operating data, removing bias facility operating data from the facility operating data of the plurality of facilities, and constructing, based at least in part on the non-biased facility operating a data, an updated model with one or more updated coefficients; determine, based on non-biased facility operating data, a non-biased performance standard for the one or more operating conditions; and track, based on the no-biased performance standard and the facility operating data, operating performance of each respective facility of the plurality of facilities.

Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models

Systems and methods include processors for receiving training data for a user activity; receiving bias criteria; determining a set of model parameters for a machine learning model including: (1) applying the machine learning model to the training data; (2) generating mode prediction errors; (3) generating a data selection vector to identify non-outlier target variables based on the model prediction errors; (4) utilizing the data selection vector to generate a non-outlier data set; (5) determining updated model parameters based on the non-outlier data set; and (6) repeating steps (1)-(5) until a censoring performance termination criterion is satisfied; training classifier model parameters for an outlier classifier machine learning model; applying the outlier classifier machine learning model to activity-related data to determine non-outlier activity-related data; and applying the machine learning model to the non-outlier activity-related data to predict future activity-related attributes ...

Machine learning-based root cause analysis of process cycle images

The technology disclosed relates to classification of process cycle images to predict success or failure of process cycles. The technology disclosed includes capturing and processing images of sections arranged on an image generating chip in genotyping process. Image description features of production cycle images are created and given as input to classifiers. A trained classifier separates successful production images from unsuccessful or failed production images. The failed production images are further classified by a trained root cause classifier into various categories of failure.

Providing human-interpretable explanation for model-detected anomalies

An anomaly detection system is disclosed capable of reporting anomalous processes or hosts in a computer network using machine learning models trained using unsupervised training techniques. In embodiments, the system assigns observed processes to a set of process categories based on the file system path of the program executed by the process. The system extracts a feature vector for each process or host from the observation records and applies the machine learning models to the feature vectors to determine an outlier metric each process or host. The processes or hosts with the highest outlier metrics are reported as detected anomalies to be further examined by security analysts. In embodiments, the machine learnings models may be periodically retrained based on new observation records using unsupervised machine learning techniques. Accordingly, the system allows the models to learn from newly observed data without requiring the new data to be manually labeled by humans.

Detecting adversary attacks on a deep neural network (DNN)

Protecting a DNN with one or more intermediate layers by recording a representation of activations associated with an intermediate layer, training a classifier for each of those, and using the trained classifier to detect an adversarial input. The classifier may generate a set of label arrays, a label array being a set of labels for the representation of activations associated with the intermediate layer. Using the classifiers may further include aggregating respective sets of the label arrays into an outlier detection model. The outlier detection model may generate a prediction, together with an indicator whether a given input is the adversarial input. The method may further include taking an action in response to detection of adversary attack, and the action may include issuing a notification, preventing an adversary from providing one or more additional inputs that are determined to be adversarial or taking an action to protect a deployed system associated with the DNN.

Standardization in the context of data integration

Techniques are described relating to automatic data standardization in a managed services domain of a cloud computing environment. An associated computer-implemented method includes receiving a dataset during a data onboarding procedure and classifying datapoints within the dataset. The method further includes applying a machine learning data standardization model to each classified datapoint within the dataset and deriving a proposed set of data standardization rules for the dataset based upon any standardization modification determined consequent to model application. Optionally, the method includes presenting the proposed set of data standardization rules for client review and, responsive to acceptance of the proposed set of data standardization rules, applying the proposed set of data standardization rules to the dataset. The method further includes, responsive to acceptance of the proposed set of data standardization rules, updating the machine learning data standardization model accordingly ...

Outlier detection in deep neural network

Outlier detection using a Deep Neural Network (DNN) includes running a trained DNN model on an received input item. A first feature vector is extracted from the input item and quantized to discrete values. A first number of special t-way feature combinations are computed in the input item and compared against a computed threshold. Based on the comparison, the input item is flagged as an outlier and an alert is generated notifying of the flagged input item.

Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models

Systems and methods include processors for receiving training data for a user activity; receiving bias criteria; determining a set of model parameters for a machine learning model including: (1) applying the machine learning model to the training data; (2) generating model prediction errors; (3) generating a data selection vector to identify non-outlier target variables based on the model prediction errors; (4) utilizing the data selection vector to generate a non-outlier data set; (5) determining updated model parameters based on the non-outlier data set; and (6) repeating steps (1)-(5) until a censoring performance termination criterion is satisfied; training classifier model parameters for an outlier classifier machine learning model; applying the outlier classifier machine learning model to activity-related data to determine non-outlier activity-related data; and applying the machine learning model to the non-outlier activity-related data to predict future activity-related attributes ...

Non-intrusive load monitoring method

Disclosed is a non-intrusive load monitoring system, comprising a device classification and prediction sub-flow, a new device identification sub-flow, and a classifier self-training sub-flow. By means of the configuration of these method flows, the defect in accuracy of identification of a new device in the prior art is overcome; and when a device other than the devices in a device database is detected, data of the device can be intercepted and stored in the device database, so that the function of accurately identifying existing devices in a device database can be achieved, and the device database can be automatically updated when a new device other than the devices in the device database is discovered.

A METHOD FOR LEARNING A VEHICLE BEHAVIOUR OF A MONITORED AUTOMOBILE AND A RESPECTIVE AUTOMOBILE

Machine learning model to identify and predict health and safety risks in electronic communications

Systems, methods, and other embodiments associated with a machine learning system that monitors and detects health and safety risks in electronic correspondence related to a target field are described. In one embodiment, a method includes monitoring email communications over a network to identify an email associated with a target field. A machine learning classifier is initiated that is configured to classify text from the email with a risk as being related to a safety risk or a non-risk. The machine learning classifier generates a probability risk value that the email is related to a safety risk and labels the email as safety risk or non-risk based at least in part on the probability risk value indicating that the email is a safety risk. An electronic notice is generated and transmitted to a remote device in response to the email being labeled as being safety risk to provide an alert.

Machine learning method for anomaly detection in an electrical system

Continuous condition monitoring of an electrical system, and in particular for early fault detection, is provided. The condition monitoring unit is formed with an interface to a memory in which a trained normal state model is stored as a one-class model that has been trained in a training phase with normal state data and represents a normal state of the electrical system. Further, the condition monitoring unit comprises a data interface for continuously acquiring sensor data of the electrical system by means of a set of sensors, an extractor for extracting features from the acquired sensor data, a differentiator for determining deviations of the extracted features from learned features of the normal state model by means of a distance metric (e.g., Euclidean norm, sum norm, maximum norm), a scoring for calculating an anomaly score from the determined deviations, and an output unit for outputting the calculated anomaly score.

Electronic device for removing advertisement thumbnail from display screen for providing list of live sports and operating method thereof

Provided are an electronic device for removing an advertisement thumbnail from a display screen for providing a list of sports and an operating method of the electronic device that may retrieve an image thumbnail extracted from a game video being broadcast live, determine whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model, and display the game thumbnail on a display screen when the image thumbnail is the game thumbnail and remove the advertisement thumbnail on the display screen when the image thumbnail is the advertisement thumbnail.

ABNORMALITY WARNING METHOD AND ABNORMALITY WARNING SYSTEM

SYSTEM AND METHOD FOR AUTOMATED FAULT DIAGNOSIS AND PROGNOSIS FOR ROTATING EQUIPMENT

머신러닝 기반의 의료 영상에 대한 반사광 제거 방법 및 이를 이용한 장치

... 본 발명은, 프로세서에 의해 구현되는 반사광 제거 방법으로서, 개체의 표적 부위를 포함하는 의료 동영상을 수신하는 단계, 의료 동영상을 입력으로 하여 반사광 영역, 반사광 영역을 제외한 의료 동영상 및 정지 의료 영상 중 적어도 하나의 영상 상태를 분류하도록 구성된 영상 분류 모델을 이용하여, 수신된 의료 동영상을 기초로 적어도 하나의 영상 상태를 분류하는 단계, 분류된 영상 상태에 기초하여 반사광이 제거된 합성 영상을 생성하는 단계를 포함하는, 반사광 제거 방법 및 이를 이용한 반사광 제거용 장치를 제공한다.

Upload management

Aspects of the present disclosure relate to managing the upload of media items to cloud storage. A model can be configured to distinguish between confidential and non-confidential media items. A media item to be uploaded to a cloud storage can be analyzed using the model to determine whether the media item is confidential. In response to determining that the media item is confidential, an upload control action can be issued on the media item.

Adaptive pattern recognition for a sensor network

Embodiments match sensor data output by a sensor to a trained pattern. Embodiments form a plurality of windows of an identified pattern from the sensor data, each of the plurality of windows having a substantially equal window length to a length of the trained pattern. For each of the windows, embodiments generate a corresponding first Symbolic Aggregate approximation (“SAX”) word, determine a Hamming distance between the first SAX word and a second SAX word corresponding to the trained pattern, and determine a final distance score based on coefficients between the first SAX word and the second SAX word. For each of the windows, embodiments determine a number of positions in the first SAX word that do not contribute to the final distance score, update the Hamming distance after eliminating the number of positions and determine an average distance based on the final distance score and the updated Hamming distance.

DEFECT DETECTION METHOD AND APPARATUS

DETECTION AND REPRESENTATION OF DECISION REGIONS GENERATED BY AI BASED CLASSIFICATION ALGORITHM

The invention discloses an automated method for detecting decision regions of an AI based classification algorithm, comprising: - providing measured sensor data as initial data, - classifying the initial data by applying the AI based classification algorithm, - randomly generating further data by applying a probability distribution on the initial data, - classifying the further data by applying the AI based classification algorithm, - detecting decision regions by a data clustering algorithm, whereby each decision region contains initial and further data of only one class. Uses of the disclosed method and a related system are disclosed as well.

TRAINING OF MACHINE-LEARNING ALGORITHMS FOR DIGITAL PATHOLOGY USING HEALTHY-TISSUE WHOLE SLIDE IMAGES

Various examples of the disclosure pertain to using whole-slide images that depict healthy tissue for a training process for at least one machine-learning algorithm for digital pathology. For instance, an autoencoder neural network can be trained based on the healthy tissue.

Neural network host platform for detecting anomalies in cybersecurity modules

Aspects of the disclosure relate to anomaly detection in cybersecurity training modules. A computing platform may receive information defining a training module. The computing platform may capture a plurality of screenshots corresponding to different permutations of the training module. The computing platform may input, into an auto-encoder, the plurality of screenshots corresponding to the different permutations of the training module, wherein inputting the plurality of screenshots corresponding to the different permutations of the training module causes the auto-encoder to output a reconstruction error value. The computing platform may execute an outlier detection algorithm on the reconstruction error value, which may cause the computing platform to identify an outlier permutation of the training module. The computing platform may generate a user interface comprising information identifying the outlier permutation of the training module. The computing platform may send the user interface ...

EXAMINATION SYSTEM AND EXAMINATION METHOD THEREOF

An examination system is provided. The examination system includes an optical detector and analyzer. The optical detector emits a detection light source toward a target object and detects a respondent light which is induced from the target object in response to the detection light source to generate image data. The image data indicates a detection image. The analyzer receives the image data and determines which region of the target object the detection image belongs to according to the image data. When the analyzer determines that the detection image belongs to a specific region of the target object, the analyzer extracts at least one feature of the image data to serve as a basis for classification of the specific region.

Low-light image selection for neural network training

This disclosure provides methods, devices, and systems for low-light imaging. The present implementations more specifically relate to selecting images that can be used for training a neural network to infer denoised representations of images captured in low light conditions. In some aspects, a machine learning system may obtain a series of images of a given scene, where each of the images is associated with a different SNR (representing a unique combination of exposure and gain settings). The machine learning system may identify a number of saturated pixels in each image and classify each of the images as a saturated image or a non-saturated image based on the number of saturated pixels. The machine learning system may then select the non-saturated image with the highest SNR as the ground truth image, and the non-saturated images with lower SNRs as the input images, to be used for training the neural network.

머신러닝 기반의 의료 영상에 대한 반사광 제거 방법 및 이를 이용한 장치

... 본 발명은, 프로세서에 의해 구현되는 반사광 제거 방법으로서, 개체의 표적 부위를 포함하는 의료 동영상을 수신하는 단계, 의료 동영상을 입력으로 하여 반사광 영역, 반사광 영역을 제외한 의료 동영상 및 정지 의료 영상 중 적어도 하나의 영상 상태를 분류하도록 구성된 영상 분류 모델을 이용하여, 수신된 의료 동영상을 기초로 적어도 하나의 영상 상태를 분류하는 단계, 분류된 영상 상태에 기초하여 반사광이 제거된 합성 영상을 생성하는 단계를 포함하는, 반사광 제거 방법 및 이를 이용한 반사광 제거용 장치를 제공한다.

ABNORMALITY DETECTION DEVICE AND ABNORMALITY DETECTION METHOD

REDUCED FALSE POSITIVE IDENTIFICATION FOR SPECTROSCOPIC QUANTIFICATION

A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.

DYNAMIC OUTLIER BIAS REDUCTION SYSTEM AND METHOD

... 기능 및 추세 선 특이치 바이어스를 감소시키기 위한 데이터 필터링을 위한 시스템 및 방법이 본원에 기재된다. 객관적 통계 방법을 통해 데이터 세트로부터 특이치가 제거된다. 바이어스는 절대 오차, 상대 오차, 또는 이 둘 모두를 기초로 결정된다. 오차 값이 데이터, 모델 계수, 또는 추세 선 계산으로부터 계산된다. 오차 값이 사용자-제공 기준보다 크거나 같을 때 특이치 데이터 레코드가 제거된다. 최적화 방법 또는 그 밖의 다른 반복 계산을 위해, 각각의 반복마다 제거된 데이터가 모델에 다시 적용되어 새로운 결과를 계산한다. 완전한 데이터 세트에 대한 모델 값을 이용하여, 새로운 오차 값이 계산되고 특이치 바이어스 감소 절차가 다시 적용된다. 사용자 정의 오차 개선 한계에 도달할 때까지, 반복 방식으로 모델 계수 및 특이치 제거 데이터를 위해 전체 오차가 최소화된다. 필터링된 데이터는 검증, 특이치 바이어스 감소, 및 데이터 품질 작업을 위해 사용될 수 있다.

TRAINING AND IMPLEMENTING A STEADY STATE LOG ANALYZER

The present disclosure relates to methods, systems, and computer readable media for analyzing log files for a wide variety of services (e.g., cloud computing services or microservices) to determine whether the services are operating as designed over some period of time associated with the log file(s). The present disclosure includes features and functionality for training or otherwise generating a model being configured to predict whether portions of an input log file include data reflective of normal operations of a corresponding service used to generate the input log file. The present disclosure provides a domain-agnostic approach to training an outlier detection model to analyze log files for a wide variety of services.

Cognitive data outlier pre-check based on data lineage

Methods, computer program products, and/or systems are provided that perform the following operations: obtaining pre-check data associated with specified data nodes; calculating outliers for each specified data node, wherein the outliers are calculated based on a unit of the pre-check data associated with each specified data node; backtracking the calculated outliers for each specified data node through an associated generating data link; selecting one or more data nodes associated with a set of largest outliers; selecting one or more data links associated with the set of largest outliers; and generating potential anomaly indications based on the one or more data nodes selected and the one or more data links selected.

Method and data processing system for providing explanatory radiomics-related information

A computer-implemented method is for providing radiomics-related information. In an embodiment, the computer-implemented method includes receiving radiomics-related data; determining, based on the radiomics-related data and an assistance algorithm, a function for processing the radiomics-related data; calculating, based on the radiomics-related data and the function for processing the radiomics-related data, the radiomics-related information; and providing the radiomics-related information.

System and Method for Dimensioning Target Objects

A method comprising obtaining, from a sensor, depth data representing a target object; selecting a model to fit to the depth data; for each data point in the depth data: defining a ray from a location of the sensor to the data point; and determining an error based on a distance from the data point to the model along the ray; when the depth data does not meet a similarity threshold for the model based on the determined errors, selecting a new model and repeating the error determination for the depth data based on the new model; when the depth data meets the similarity threshold for the model, selecting the model as representing the target object; and outputting the selected model representing the target object.

SELECTING EXTERIOR IMAGES OF A STRUCTURE BASED ON CAPTURE POSITIONS OF INDOOR IMAGES ASSOCIATED WITH THE STRUCTURE

Systems, computer-implemented methods, apparatus and/or computer program products are provided that facilitate improving the accuracy of global positioning system (GPS) coordinates of indoor photos. The disclosed subject matter further provides systems, computer-implemented methods, apparatus and/or computer program products that facilitate generating exterior photos of structures based on GPS coordinates of indoor photos.

COMPUTER-IMPLEMENTED METHOD FOR EVALUATING A THREE-DIMENSIONAL ANGIOGRAPHY DATASET, EVALUATION SYSTEM, COMPUTER PROGRAM AND ELECTRONICALLY READABLE STORAGE MEDIUM

Computer-implemented method for evaluating a three-dimensional angiography dataset (1), in particular computed tomography angiography dataset, of a blood vessel tree of a patient, in particular the coronary artery tree, wherein a variant information (5) describing the belonging to at least one anatomical variant class of a plurality of anatomical variant classes relating to anatomical variants of the blood vessel tree is determined based on a comparison of angiography information (2) of the angiography dataset (1) to reference information (3) describing at least one of the anatomical variant classes.

Automated and customized post-production release review of a model

A non-transitory computer readable medium includes computer executable instructions that, when executed, cause at least one processor to train a model to perform at least one of a prediction operation, a diagnostic operation, or a classification operation based on a training dataset, deploy the model in a production computer system to perform the at least one operation on field data, monitor signal data associated with the model, the signal data including specific or derived signal data representing characteristics of an ecosystem in which the model is deployed and new observations in incoming field data, monitor accuracy of the model by applying a statistical tool to a plurality of data points of the signal data, apply a secondary machine learning predictive engine to the plurality of data points of the signal data to predict future data points of the signal data, determine whether the signal data represents an unstable process by identifying future outlier data points from among the plurality ...

Abnormal user identification

User behavior data of multiple users is acquired, and multiple user eigenvalues of user behavior data of each user under preset multiple user behavior dimensions are extracted. A user eigenvector of each user is determined based on the multiple eigenvalues of this user. Multiple user classes are obtained by clustering the user eigenvectors of multiple users are clustered through a preset clustering algorithm. A central vector of each user class is determined based on the user eigenvectors included in this user class. A difference eigenvector of each user class is determined, wherein a distance between the difference eigenvector and a central vector of an aggregation class to which the difference eigenvector belongs is not within a preset distance range. A user characterized by the difference eigenvector is determined as an abnormal user.

SYSTEM AND METHOD FOR LOCALIZATION OF ANOMALOUS PHENOMENA IN ASSETS

Disclosed is a system (100, 200) comprising primary camera(s) (102, 204) arranged on vehicle (104, 202) that is employed for surveying real-world environment (106); secondary camera(s) (108, 206) coupled to steering unit(s) (110, 208) that is arranged on vehicle; geolocation sensor (112) that, in operation, detects geographical location and orientation of vehicle; and processor(s) (114) configured to receive primary image(s) captured by primary camera(s); process primary image(s) to detect assess) (P1, P2, P3, P4, X, Y) and location and orientation of asset(s); control steering unit(s) to adjust pose of secondary camera(s) based on location and orientation of asset(s) and geographical location and orientation of vehicle, for enabling secondary camera(s) to capture secondary image(s) of asset(s); receive secondary image(s) captured by secondary camera(s); process secondary image(s) to detect anomalous phenomena in asset(s); and locate anomalous phenomena based at least on location and orientation ...

Providing reduced training data for training a machine learning model

A method, computer system, and a computer program product for providing reduced training data for training a machine learning model (ML-model) is disclosed. The present invention may include generating the reduced training data dependent on a first two batches of data records of original training data. The present invention may include generating an updated version of the reduced training data dependent on the reduced training data and a further batch of the original training data, wherein a size of the updated version of the reduced training data is equal or less than a size of the limited storage capacity and less than a combined size of the reduced training data and the further batch together. The reading of a further batch of the data records of the original training data and the generating of an updated version of the reduced training data may be repeated.

Functional image archiving

Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.

System and method for controlling semiconductor manufacturing apparatus

The present disclosure provides a system and a method for controlling a semiconductor manufacturing apparatus. The system includes an inspection unit capturing at least one image of a wafer, a sensor interface generating at least one input signal for a database server, and a control unit. The control unit includes a front-end subsystem, a calculation subsystem, and a message and tuning subsystem. The front-end subsystem receives the at least one input signal from the database server and performs a front-end process to generate a data signal. The calculation subsystem performs an artificial intelligence analytical process to determine, according to the data signal, whether damage marks have been caused by the semiconductor manufacturing apparatus and to generate an output signal. The message and tuning subsystem generates an alert signal and a feedback signal according to the output signal and transmits the alert signal to a user.

Analysis and sorting in aquaculture

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for sorting fish in aquaculture. In some implementations, one or more images are obtained of a particular fish within a population of fish. Based on the one or more images of the fish, a data element is determined. The data element can include a first value that reflects a physical characteristic of the particular fish, and a second value that reflects a condition factor of the particular fish. Based on the data element, the fish is classified as a member of a particular subpopulation of the population of fish. An actuator of an automated fish sorter is controlled based on classifying the particular fish as a member of the particular subpopulation of the population of fish.

Device for managing environment of breeding farm

Provided according to an embodiment of the present invention is a device for managing the environment of a breeding farm, the device comprising: an imaging unit for capturing a thermal image of the inside of a breeding farm; an object detection unit for detecting an object from the captured image; an area division unit for dividing the captured image into multiple areas; a filtering unit for extracting, from the divided areas, a second area except a first area where the object is detected; and a control unit for comparing the temperature of the second area with a reference temperature to detect an abnormal situation.

SYSTEMS AND METHODS FOR ANOMALY DETECTION AND CORRECTION

Conventional task planners assume that the task-plans provided are executable, hence these are not task-aware. Present disclosure alleviates the downward refinability assumption, that is, planning can be decomposed separate symbolic and continuous planning steps by introducing bi-level planning, a plan which is a series of actions that the robot needs to take to achieve the goal task is curated. Firstly, abstract symbolic actions are converted to continuous vectors and used therein to enable interaction with an environment. Images of objects placed in the environment are captured and concepts are learnt from the captured images and attributes of objects are detected. A hierarchical scene graph is generated from the concepts and attributes wherein the graph includes interpretable sub-symbolic representations and from these interpretable symbolic representations are obtained for identifying goal task. Anomalies are detected from the scene graph and robotic actions are generated to correct ...

ANOMALY DETECTOR FOR DETECTING ANOMALY USING COMPLEMENTARY CLASSIFIERS

OUTLIER DETECTION FOR SPECTROSCOPIC CLASSIFICATION

In some implementations, a device may determine that an unknown sample is an outlier sample by using an aggregated classification model. The device may determine that one or more spectroscopic measurements are not performed accurately based on determining that the unknown sample is the outlier sample. The device may cause one or more actions based on determining the one or more spectroscopic measurements are not performed accurately.

REDUCED FALSE POSITIVE IDENTIFICATION FOR SPECTROSCOPIC CLASSIFICATION

A device may receive information identifying results of a set of spectroscopic measurements of a training set of known samples and a validation set of known samples. The device may generate a classification model based on the information identifying the results of the set of spectroscopic measurements, wherein the classification model includes at least one class relating to a material of interest for a spectroscopic determination, and wherein the classification model includes a no-match class relating to at least one of at least one material that is not of interest or a baseline spectroscopic measurement. The device may receive information identifying a particular result of a particular spectroscopic measurement of an unknown sample. The device may determine whether the unknown sample is included in the no-match class using the classification model. The device may provide output indicating whether the unknown sample is included in the no-match class.

COMPUTER-IMPLEMENTED, ADAPTED ANOMALY DETECTION METHOD FOR POWDER-BED-BASED ADDITIVE MANUFACTURING

AI-based image analysis for the detection of normal images

A system and method for identifying abnormal medical images. The system can be configured to receive a medical image, segment an anatomical structure from the medical image to define a segmented dataset, register the segmented dataset to a baseline dataset defining a normal anatomical structure, classify, by an abnormality classifier, whether the anatomical structure within the medical image as either abnormal or normal, wherein the abnormality classifier comprises a machine learning algorithm trained to distinguish between normal and abnormal versions of the anatomical structure in medical images, and based on whether the anatomical structure can be segmented from the medical image, whether the segmented dataset can be registered to the baseline dataset, or a classification associated with the medical image output by the abnormality classifier, flagging the medical image as either normal or abnormal.

Perception-based autonomous landing for aircraft

A method of supporting an aircraft approaching a runway is provided. Example implementations involve receiving a sequence of images, captured by a camera onboard the aircraft. Example implementations involve applying a received image to a machine learning model trained to detect the runway or a runway marking in the image, and to produce a mask that includes a segment of pixels of the image assigned to an object class for the runway or marking. Example implementations may also involve applying the mask to a corner detector to detect interest points on the mask and match the interest points to corresponding points on the runway or the marking that have known runway-framed local coordinates. Example implementations may also involve performing a perspective-n-point estimation to determine a current pose estimate of the aircraft relative to the runway or the marking and outputting the current pose estimate for use during final approach.

Reduced false positive identification for spectroscopic quantification

A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.

METHOD AND SYSTEM FOR TRAINING MACHINE LEARNING MODELS ON SENSOR NODES

Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. An indication is sent to the sensor node to initiate training by the sensor node to detect anomalies in object(s) in the environment based on sensor data generated by a sensor operable to detect signals from the one or more objects in the environment. After training is initiated, the sensor node automatically trains a model in communication with the sensor to detect anomalies in the one or more objects in the environment, wherein such training is based on the sensor data. After the model is trained, the model to detect anomalies in the object(s) in the environment is executed by the sensor node.

Method and non-transitory, computer-readable storage medium for deep learning model based product matching using multi modal data

Methods and systems for generating a plurality of matching items that match a reference item are disclosed. The method includes first determining reference attribute data for the reference item, where the reference attribute data is multimodal. Next, selecting a deep learning multimodal matching model from a plurality of candidate multimodal matching models. The selected deep learning multimodal matching model has a first deep learning neural network (DLNN) for processing data having a first data mode and a second DLNN analyzer for processing data having a second data mode. Then, matching a potential matching item to the reference item using the selected deep learning multimodal matching model to generate a match score, where the match score is computed based on the reference attribute data for the reference item and attribute data for the potential matching item. Finally, adding the potential matching item to the plurality of matching items based on the match score.

Methods and systems for informing product decisions

A system for informing product decisions, the system including a computing device configured to receive a conditional complaint relating to a user; select an article of interest intended to correct the conditional complaint; retrieve a biological extraction relating to the user; generate, a classifier, wherein the classifier comprises a machine-learning model trained by training data including a plurality of biological extractions and a plurality of correlated articles of interest, and wherein the classifier is configured to receive the user biological extraction as an input and output a tolerability score as a function of the training data; and display the tolerability score.

Machine learning system for analyzing the quality and efficacy of essays for higher education admissions

Systems and methods for the multifaceted analysis of a written work, such as an educational program admission essay, using machine learning, deep learning and natural language processing. Language, relevance, structure, and flows are evaluated for an overall impactful essay. Essay content is checked to evaluate whether the author has covered an essay's essential aspects. The essay is also analyzed for an effective structure for presenting details as per the essay type. The disclosure includes data preparation for the task, process of data tagging, feature engineering from the essay text, method for transfer learning and fine-tuning language model to adapt to the context of an essay. Finally, a process for building machine learning and deep learning models and technique for ensembling to use both models in combination is disclosed. The system may provide user-adapted feedback based on a persona created from the user profile.

METHODS AND SYSTEMS FOR IDENTIFYING PRESENCE OF ABNORMAL HEART SOUNDS OF A SUBJECT

Physical activity measurement and analysis

A method of physical activity measurement and analysis, the method comprising computer-executed steps of: receiving at least one value extracted from measurements of a physical activity of a first user, and detecting a deviation of the physical activity of the first user from at least one previous physical activity using the received at least one value and at least one reference value calculated over at least one value extracted from measurements of the at least one previous physical activity.

OUT-OF-DOMAIN DETECTION FOR IMPROVED AI PERFORMANCE

Systems and methods for determining input data is out-of-domain of an AI (artificial intelligence) based system are provided. Input data for inputting into an AI based system is received. An in-domain feature space of the AI based system and an out-of-domain feature space of the AI based system are modelled. The in-domain feature space corresponds to features of data that the AI based system is trained to classify. The out-of-domain feature space corresponds to features of data that the AI based system is not trained to classify. Probability distribution functions in the in-domain feature space and the out-of-domain feature space are generated for the input data and for the data that the AI based system is trained to classify. It is determined whether the input data is out-of-domain of the AI based system based on the probability distribution functions for the input data and for the data that the AI based system is trained to classify.

Manifold-anomaly detection with axis parallel

Systems, methods, and apparatuses for detecting and identifying anomalous data in an input data set are provided.

Neural Network Host Platform for Detecting Anomalies in Cybersecurity Modules

Aspects of the disclosure relate to anomaly detection in cybersecurity training modules. A computing platform may receive information defining a training module. The computing platform may capture a plurality of screenshots corresponding to different permutations of the training module. The computing platform may input, into an auto-encoder, the plurality of screenshots corresponding to the different permutations of the training module, wherein inputting the plurality of screenshots corresponding to the different permutations of the training module causes the auto-encoder to output a reconstruction error value. The computing platform may execute an outlier detection algorithm on the reconstruction error value, which may cause the computing platform to identify an outlier permutation of the training module. The computing platform may generate a user interface comprising information identifying the outlier permutation of the training module. The computing platform may send the user interface ...

Reduced false positive identification for spectroscopic classification

A device may receive information identifying results of a set of spectroscopic measurements of a training set of known samples and a validation set of known samples. The device may generate a classification model based on the information identifying the results of the set of spectroscopic measurements, wherein the classification model includes at least one class relating to a material of interest for a spectroscopic determination, and wherein the classification model includes a no-match class relating to at least one of at least one material that is not of interest or a baseline spectroscopic measurement. The device may receive information identifying a particular result of a particular spectroscopic measurement of an unknown sample. The device may determine whether the unknown sample is included in the no-match class using the classification model. The device may provide output indicating whether the unknown sample is included in the no-match class.

ANOMALY DETECTION FROM AGGREGATE STATISTICS USING NEURAL NETWORKS

Implementations disclosed describe systems and techniques to detect anomalies in a manufacturing operation. The techniques include generating, using a plurality of outlier detection models, a plurality of outlier scores. The outlier scores are representative of a degree of presence, in a plurality of sensor statistics, of an anomaly associated with the manufacturing operation. Individual outlier scores are generated using a respective one of the plurality of outlier detection models. The techniques further include determining, using the outlier scores, a likelihood of the anomaly associated with the manufacturing operation.

Updating data models to manage data drift and outliers

The present invention relates to a system and a method for updating data models. Input data received from a data source and/or prediction data obtained from a data model is reduced based on baseline reference data to obtain a plurality of representative points. The plurality of representative points are clustered to generate a plurality of clusters. An outlier cluster is detected from the plurality of clusters based on a maximum distance of the plurality of clusters from a highest density cluster and/or comparison of quantity and values of the plurality of representative points with predefined rules. Data drift is identified based on changes in densities of the plurality of clusters. The data model is updated using information corresponding to the outlier cluster and the data drift.

System and method for dimensioning target objects

A method comprising obtaining, from a sensor, depth data representing a target object; selecting a model to fit to the depth data; for each data point in the depth data: defining a ray from a location of the sensor to the data point; and determining an error based on a distance from the data point to the model along the ray; when the depth data does not meet a similarity threshold for the model based on the determined errors, selecting a new model and repeating the error determination for the depth data based on the new model; when the depth data meets the similarity threshold for the model, selecting the model as representing the target object; and outputting the selected model representing the target object.

Cyber security risk assessment and cyber security insurance platform

A cyber security risk assessment system is described. In an example implementation, the system may generate an input feature space including data associated with a computing system by collecting the data from a plurality of computer sources. The system may compute a likelihood of data-security breach incidents based on the input feature space using a first computer model, recognize events based on the input feature space using a second computer model, and determine a severity of the data-security breach incident or the event using a third computer model. In some instances, the system may generate risk factor scores based on the determined severity, data-security breach incident, and the event, where the risk factor scores indicate a computer security risk of a certain computer security aspect of the computing system. The system may then perform an action based on the risk factor scores.

Method and system for training machine learning models on sensor nodes

Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

Selecting exterior images of a structure based on capture positions of indoor images associated with the structure

Systems, computer-implemented methods, apparatus and/or computer program products are provided that facilitate improving the accuracy of global positioning system (GPS) coordinates of indoor photos. The disclosed subject matter further provides systems, computer-implemented methods, apparatus and/or computer program products that facilitate generating exterior photos of structures based on GPS coordinates of indoor photos.

Hierarchical processing of traffic signal face states

This document describes methods to assign a collective state to a group of traffic signal devices that are concurrently detected by multiple cameras. The states may be color states or other states. The system will process the images to identify states of each of the devices in the images. When the devices exhibit more than one state, the system will determine an overall state for the group by generating a confidence score for each of the states. The system will select, from the multiple states, the state having a confidence score that exceeds a threshold. The system will then use the selected state to assign an overall state to the group of traffic signal devices. The system may use the overall state to generate a signal that will cause the vehicle to perform an action such as a motion control action, or output of an audible or visual alert.

Disease detection with masked attention

A candidate generator generates a set of candidate three-dimensional image patches from an input volume. A candidate classifier classifies the set of candidate three-dimensional image patches as containing or not containing disease. Classifying the set of candidate three-dimensional image patches comprises generating an attention mask for each given candidate three-dimensional image patch within the set of candidate three-dimensional image patches to form a set of attention masks, applying the set of attention masks to the set of candidate three-dimensional image patches to form a set of masked image patches, and classifying the set of masked image patches as containing or not containing the disease. The candidate classifier applies soft attention and hard attention to the three-dimensional image patches such that distinctive image regions are highlighted proportionally to their contribution to classification while completely removing image regions that may cause confusion.

METHODS AND MECHANISMS FOR AUTOMATIC SENSOR GROUPING TO IMPROVE ANOMALY DETECTION

An electronic device manufacturing system configured to obtain, by a processor, a plurality of datasets associated with a process recipe, wherein each dataset of the plurality of datasets comprises data generated by a plurality of sensors during a corresponding process run performed using the process recipe. The processor is further configured to determine, using the plurality of data sets associated with the process recipe, a correlation value between two or more sensors of the plurality of sensors. Responsive to the correlation value satisfying a threshold criterion, the processor assigns the two or more sensors to a cluster. During a subsequent process run, the processor generates an anomaly score associated with the cluster and indicative of an anomaly associated with at least one step of the subsequent process run.

Adaptive pattern recognition for a sensor network

Embodiments match sensor data output by a sensor to a trained pattern. Embodiments form a plurality of windows of an identified pattern from the sensor data, each of the plurality of windows having a substantially equal window length to a length of the trained pattern. For each of the windows, embodiments generate a corresponding first Symbolic Aggregate approximation (“SAX”) word, determine a Hamming distance between the first SAX word and a second SAX word corresponding to the trained pattern, and determine a final distance score based on coefficients between the first SAX word and the second SAX word. For each of the windows, embodiments determine a number of positions in the first SAX word that do not contribute to the final distance score, update the Hamming distance after eliminating the number of positions and determine an average distance based on the final distance score and the updated Hamming distance.

Application programming interface anomaly detection

A method comprises collecting parameters corresponding to processing by a first application programming interface of at least one application programming interface transaction, analyzing the parameters using one or more machine learning algorithms, and predicting, based at least in part on the analyzing, whether the at least one application programming interface transaction is anomalous. In the method, the first application programming interface is designated as being in an anomalous state responsive to predicting that the at least one application programming interface transaction is anomalous. One or more application programming interface requests for the first application programming interface are routed to a second application programming interface responsive to the anomalous state designation.

Image reliability determination for instrument localization

A system includes one or more processors configured to execute instructions to cause the system to access a plurality of images generated by one or more imaging devices of an endoscope when the endoscope is disposed within anatomy of a patient, for each of the plurality of images, determine a value for each of one or more image reliability metrics, and determine a position of the endoscope within the anatomy of the patient based at least in part on the one or more image reliability metrics of each of the plurality of images.

Cyber security risk assessment and cyber security insurance platform

A cyber security risk assessment system is described. In an example implementation, the system may generate an input feature space including data associated with a computing system by collecting the data from a plurality of computer sources. The system may compute a likelihood of data-security breach incidents based on the input feature space using a first computer model, recognize events based on the input feature space using a second computer model, and determine a severity of the data-security breach incident or the event using a third computer model. In some instances, the system may generate risk factor scores based on the determined severity, data-security breach incident, and the event, where the risk factor scores indicate a computer security risk of a certain computer security aspect of the computing system. The system may then perform an action based on the risk factor scores.

Device, system and method for pulsatility detection

The present invention relates to a device, system and method for pulsatility detection. The proposed device comprises an input interface (30) for obtaining image data of a scene, said image data comprising a time sequence of image frames, an extraction unit (31) for extracting a time-varying signal indicative of a periodic physiological phenomenon from a region of interest of said image data, a transformation unit (32) for transforming said time-varying signal into a spectral signal, a partitioning unit (33) for partitioning the spectral signal into at least an in-band sub-signal covering a first frequency range of said spectral signal and an out-band sub-signal covering a second frequency range of said spectral signal, wherein said first frequency range comprises at least a frequency range of the periodic physiological phenomenon, an analysis unit (34) for separately deriving an in-band measure from the in-band sub-signal and an out-band measure from the out-band sub-signal, the in-band ...

Outlier detection for spectroscopic classification

In some implementations, a device may determine that an unknown sample is an outlier sample by using an aggregated classification model. The device may determine that one or more spectroscopic measurements are not performed accurately based on determining that the unknown sample is the outlier sample. The device may cause one or more actions based on determining the one or more spectroscopic measurements are not performed accurately.

Method, system and apparatus for determining a subject and a distractor in an image

A method of identifying a subject and a distractor in a target image is disclosed. The method receives a reference image comprising image content corresponding to image content of the target image. A first saliency map, which defines a distribution of visual attraction values identifying salient regions within the target image, and a second saliency map, which defines a distribution of visual attraction values identifying salient regions within the reference image, are determined. The method compares image content in salient regions of the first saliency map and the second saliency map. The subject is identified by a salient region of the target image sharing image content with a salient region of the reference image. The distractor is identified based on at least one remaining salient region of the target image.

Validation template for valuable media of multiple classes

A technique for use in automatic validation of a media item involves accessing a template that comprises multiple one-class classifiers, each corresponding to one of multiple classes to which the media item might belong, and then applying each of the one-class classifiers to an image of the media item to generate a result set for each of the multiple classes. The result set for each media class is then analyzed to assess whether the media item belongs to that class.

Methods and systems for fire detection

In accordance with various aspects of the present disclosure, methods and systems for fire detection are disclosed. In some embodiments, a method for fire detection includes: acquiring data related to a monitored area, wherein the data comprises image data related to the monitored area; determining, based on the acquired data, whether a first mode or a second mode is to be executed for fire detection, wherein the first mode comprises a first smoke detection, and the second mode comprises a first flame detection; and executing, by a hardware processor, at least one of the first mode or the second mode based on a result of the determination.

Anomaly detection

According to an exemplary embodiment of the present disclosure, disclosed is a computer program stored in a computer readable storage medium. When the computer program is executed in one or more processors, the computer program performs the following method for anomaly detection of data using a network function, and the method includes: generating an anomaly detection model including a plurality of anomaly detection sub models including a trained network function using a plurality of training data sub sets included in the training data set; calculating input data using at least one of the plurality of generated anomaly detection sub models; and determining whether there is an anomaly in the input data based on output data for input data of at least one of the plurality of generated anomaly detection sub models and the input data.

Detecting and responding to an anomaly in an event log

A method identifies and prioritizes anomalies in received monitoring logs from an endpoint log source. One or more processors identify anomalies in the monitoring logs by applying a plurality of disparate types of anomaly detection algorithms to the monitoring logs, and then determine a likelihood that the identified anomalies are anomalous based on outputs of the plurality of disparate types of anomaly detection algorithms. The processor(s) then prioritize the monitoring logs based on the likelihood that the identified anomalies are actually anomalous, and send prioritized monitoring logs that exceed a priority level to a security information and event management system (SIEM).

Image Processing

A method and apparatus for processing images, the method comprising: using a radar ( 4 ), generating a first image of an area of terrain ( 8 ); using a sensor ( 5 ), generating a second image of the area of terrain ( 8 ); performing an image segmentation process on the first image to identify a point in the first image as corresponding to a ground surface of the area of terrain ( 8 ); and projecting the identified point in the first image from the first image into the second image to identify a point in the second image as corresponding to the ground surface of the area of terrain ( 8 ). The method may further comprise: for the identified point in the second image, defining a sub-image of the second image containing that point; and performing a feature extraction process on the sub-image to identify points in the sub-image that correspond to the ground surface.

Device for managing environment of breeding farm

Provided according to an embodiment of the present invention is a device for managing the environment of a breeding farm, the device comprising: an imaging unit for capturing a thermal image of the inside of a breeding farm; an object detection unit for detecting an object from the captured image; an area division unit for dividing the captured image into multiple areas; a filtering unit for extracting, from the divided areas, a second area except a first area where the object is detected; and a control unit for comparing the temperature of the second area with a reference temperature to detect an abnormal situation.

Adaptive fault diagnostic system for motor vehicles

A method of using an adaptive fault diagnostic system for motor vehicles is provided. A diagnostic tool collects unlabeled data associated with a motor vehicle, and the unlabeled data is transmitted to a central computer. An initial diagnostic model and labeled training data associated with previously identified failure modes and known health conditions are transmitted to the central computer. The central computer executes a novelty detection technique to determine whether the unlabeled data is novelty data corresponding with a new failure mode or normal data corresponding with one of the previously identified failure modes or known health conditions. The central computer selects an informative sample from the novelty data. A repair technician inputs a label for the informative sample, and the central computer propagates the label from the informative sample to the associated novelty data. The central computer updates the labeled training data to include the labeled novelty data.

Instrument image reliability systems and methods

Described herein are systems and methods related to image management. A system may include an instrument that includes an elongate body and an imaging device. The elongate body can be configured to be inserted into a luminal network. The imaging device may be positioned at a distal tip of the elongate body. The system may receive from the imaging device one or more images captured when the elongate body is within the luminal network. For each of the images, the system may determine one or more metrics that are indicative of a reliability of an image for localization of the distal tip of the elongate body within the luminal network. The system may determine a reliability threshold value for each of the one or more metrics. The system can utilize the one or more images based on whether the one or more metrics meet corresponding reliability threshold values.

Selecting exterior images of a structure based on capture positions of indoor images associated with the structure

Systems, computer-implemented methods, apparatus and/or computer program products are provided that facilitate improving the accuracy of global positioning system (GPS) coordinates of indoor photos. The disclosed subject matter further provides systems, computer-implemented methods, apparatus and/or computer program products that facilitate generating exterior photos of structures based on GPS coordinates of indoor photos.

Manifold-anomaly detection with axis parallel explanations

Systems, methods, and apparatuses for detecting and identifying anomalous data in an input data set are provided.

Method and system for training machine learning models on sensor nodes

Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

Differential atlas for cancer assessment

Methods and apparatus associated with producing a quantification of differences associated with biochemical recurrence (BcR) in a region of tissue demonstrating prostate cancer (PCa) are described. One example apparatus includes a set of logics, and a data store that stores a set of magnetic resonance (MR) images acquired from a population of subjects. The set of logics includes an image acquisition logic that acquires a diagnostic image of a region of tissue in a patient demonstrating PCa, a morphology logic that extracts a shape feature, a volume feature, or an intensity feature from the diagnostic image or from a member of the set of MR images, a differential atlas construction logic that constructs a statistical shape differential atlas from the set of MR images, and a quantification logic that produces a quantification of differences based on the shape feature, the volume feature, or the intensity feature, and the differential atlas.

Apparatus and process for detecting network security attacks on iot devices

Some embodiments include a network attack detection process, including, for each of a plurality of IoT devices of a communications network: receiving corresponding network traffic data representing network traffic characteristics of a plurality of network traffic flows of the device; processing the network traffic data to generate a plurality of corresponding features for each of the network traffic flows; and applying a corresponding set of one-class flow classifiers to the generated features to classify network traffic flows of the device and assess whether the network traffic characteristics of the network traffic flows are indicative of the device being under attack or having been compromised; wherein the flow classifiers are trained with training data representing normal network traffic behaviour of the device in an uncompromised state.

Systems and methods for physical object analysis

Disclosed are devices, systems, apparatus, methods, products, and other implementations, including a method that includes obtaining physical object data for a physical object, determining a physical object type based on the obtained physical object data, and determining based on the obtained physical object data, using at least one processor-implemented learning engine, findings data comprising structural deviation data representative of deviation between the obtained physical object data and normal physical object data representative of normal structural conditions for the determined physical object type.

System for dispatching cognitive computing across multiple workers

The present design is directed to a system for dispatching cognitive computing across multiple workers, comprising a supervisory node configured to dispatch work to a plurality of compute servers forming interconnected knowledge nodes and a relevancy engine provided in at least one knowledge node. The relevancy engine comprises a rule package and a series of processors organized in a tree arrangement, the series of processors configured to perform functions according to the rule package.

Method and apparatus for detecting driver's abnormalities based on machine learning using vehicle can bus signal

Provided is a method for detecting a driver's abnormalities based on a CAN (Controller Area Network) bus network communicating with an ECU (Electronic Control Unit) of a vehicle. The method may include: acquiring a CAN bus signal related to an operation of the vehicle from the CAN bus network; extracting a detection vector from the CAN bus signal using an auto encoder; and detecting a driver's abnormality based on the detection vector.

System and method for automated fault diagnosis and prognosis for rotating equipment

Techniques, including systems and methods for monitoring a rotating equipment, are provided. A sensor that is in proximity of the rotating equipment senses vibrations of the rotating equipment. The sensor generates a digital signal corresponding to the vibrations of the rotating equipment and transmits the digital signal over a communication network. A server receives the digital signal and pre-processes the digital signal using ensemble empirical mean decomposition (EEMD) technique. The server processes the digital signal using wavelet neural network (WNN) to detect faults in the rotating equipment. Further, the server processes the digital signal using the wavelet neural network to predict remaining useful life (RUL) of the rotating equipment.

System and method for binned inter-quartile range analysis in anomaly detection of a data series

One embodiment provides a system for facilitating anomaly detection. During operation, the system determines, by a computing device, a set of testing data which includes a plurality of data points, wherein the set includes a data series for a first variable and one or more second variables, and wherein the one or more second variables are dependent on the first variable. The system divides the set of testing data into a number of groups based on a type of the data series. The system determines an inter-quartile range for a respective group. The system classifies a first testing data point in the respective group as an anomaly based on the inter-quartile range for the respective group, thereby enhancing data mining and outlier detection for the data series for multiple variables.

Systems and methods for detecting a point of interest change using a convolutional neural network

A method for detecting a point of interest (POI) change in a pair of inputted POI images. A first processor of the method: generates triplets of training POI images using a base of training POI images and trains a convolutional neural network (CNN) of three-stream Siamese type based on the triplets of training POI images. A second processor of the method: computes, for each image of the pair of inputted POI images, a descriptor of that image using a stream of the CNN of three-stream Siamese type, computes a similarity score based on the descriptors of the images of the pair of inputted POI images using a similarity score function, and selectively detects the POI change based on the similarity score. A third processor of the method generates the base of training POI images to include an initial set of POI images and a set of synthetic POI images.

Neural Network Host Platform for Detecting Anomalies in Cybersecurity Modules

Aspects of the disclosure relate to anomaly detection in cybersecurity training modules. A computing platform may receive information defining a training module. The computing platform may capture a plurality of screenshots corresponding to different permutations of the training module. The computing platform may input, into an auto-encoder, the plurality of screenshots corresponding to the different permutations of the training module, wherein inputting the plurality of screenshots corresponding to the different permutations of the training module causes the auto-encoder to output a reconstruction error value. The computing platform may execute an outlier detection algorithm on the reconstruction error value, which may cause the computing platform to identify an outlier permutation of the training module. The computing platform may generate a user interface comprising information identifying the outlier permutation of the training module. The computing platform may send the user interface to at least one user device.

Ground truth quality for machine learning models

Methods, systems and computer program products for improving ground truth quality for modeling are provided. Aspects include receiving a plurality of data inputs, wherein each of the plurality of data inputs has an associated label. Aspects also include training a model based on the plurality of data inputs. Aspects also include generating a plurality of vector representations corresponding to the plurality of data inputs based on the model. Aspects also include clustering the plurality of vector representations into one or more clusters. Aspects also include identifying at least one anomalous data input based on the one or more clusters. The at least one anomalous data input can be a data input of the plurality of data inputs that is mislabeled, contributes to an ambiguous class structure or is an outlier. Aspects also include outputting a notification that provides an indication of the at least one anomalous data input.

Method for physical system anomaly detection

A method for detecting anomalies in a physical system generates from a set of physics rules and a process graph representing the system a set of candidate physics models that assign physics rules to portions of the process graph representing sensors. Candidate physics models are rejected if an error between the models and sensor data exceed a predetermined error tolerance. Supervised learning is used to train a machine learning model to predict an error between the physics models and the sensor data. The predicted error and predicted sensor measurements from the physics models are then used to detect anomalies using unsupervised learning on a distribution of error between the predicted sensor measurements and the sensor data.

System and computer-implemented method for analyzing test automation workflow of robotic process automation (rpa)

A system and a computer-implemented method for analyzing workflow of test automation associated with a robotic process automation (RPA) application are disclosed herein. The computer-implemented method includes receiving the workflow of the test automation associated with the RPA application and analyzing, via an Artificial Intelligence (AI) model associated with a workflow analyzer module, the workflow of the test automation based on a set of pre-defined test automation rules. The computer-implemented method further includes determining one or more metrics associated with the analyzed workflow of the test automation and generating, via the AI model, corrective activity data based on the determined one or more metrics.

Computer-based systems for metadata-based anomaly detection and methods of use thereof

Systems and methods for providing metadata-based anomaly detection, comprising: storing a plurality of sets of electronic documents associated with a plurality of users; generating a set of metadata items for each document in each set of the plurality of sets of documents; determining a set of features based on the set of metadata items for each document in each set of the plurality of sets of documents; transforming the set of features into a set of feature vectors, each feature vector tagged to indicate a correspondence to a particular anomaly or not; and training, based at least in part on the set of features vectors, a data anomaly-detection machine learning model to obtain a trained data anomaly-detection machine learning model, the data anomaly-detection machine learning model comprising a set of triggering rules that are configured to determine a plurality of anomalies within a particular set of metadata items.

Scalable image matching

Various embodiments may increase scalability of image representations stored in a database for use in image matching and retrieval. For example, a system providing image matching can obtain images of a number of inventory items, extract features from each image using a feature extraction algorithm, and transform the same into their feature descriptor representations. These feature descriptor representations can be subsequently stored and used to compare against query images submitted by users. Though the size of each feature descriptor representation isn't particularly large, the total number of these descriptors requires a substantial amount of storage space. Accordingly, feature descriptor representations are compressed to minimize storage and, in one example, machine learning can be used to compensate for information lost as a result of the compression.

Apparatus for generating learning data for combustion optimization and method therefor

An apparatus and method for generating learning data for combustion optimization is provided. The apparatus includes a data pre-processor to collect raw data including currently measured real-time data for boiler combustion and previously measured past data for the boiler combustion, and to perform pre-processing for the collected raw data, and a data analyzer to derive learning data from the raw data by analyzing the raw data. An apparatus for combustion optimization includes a management layer to collect currently measured real-time data for boiler combustion, to determine whether to perform combustion optimization, and to determine whether to tune a combustion model and a combustion controller; a data layer to derive learning data from raw data; a model layer to generate the combustion model/controller through the learning data; and an optimal layer to calculate a target value for combustion optimization and to output a control signal according to the calculated target value.

Artificial intelligence system for inspecting image reliability

A system for inspecting the reliability of an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: obtaining a plurality of images; categorizing the images into a plurality of image classes; calculating a plurality of probability outcomes; determining whether highest predicted probabilities of the images are less than a first threshold and whether an entropy of a predicted density of the probability outcomes exceeds a second threshold; indicating whether the image is associated with the image classes; ranking, the image amongst the plurality of images; filtering, a plurality of low reliability images according to a third threshold; providing, a likelihood of whether a user scanned a vehicle object associated with the image; and identifying a percentage of user scan failures.

Reduced false positive identification for spectroscopic quantification

A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.

Systems and methods for detecting and coordinating changes in lexical items

Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.

Distinguishing - in an image - human beings in a crowd

The present disclosure relates to a method performed by a people distinguishing system (1) for in an image distinguishing human beings in a crowd. The people distinguishing system identifies (1001) one or more detected objects classified as human beings (2) in an image (3) derived from a thermal camera (10) adapted to capture a scene in an essentially forward-looking angle. The people distinguishing system further identifies at least a first grouping (4) of adjoining pixels in the image, not comprised in the one or more detected human beings, having an intensity within a predeterminable intensity range. Moreover, the people distinguishing system determines (1003) a grouping pixel area (40) of the at least first grouping in the image. Furthermore, the people distinguishing system determines (1004) for at least a first vertical position (yexpected) in the image, based on head size reference data (5), an expected pixel area (xexpected) of a human head at the at least first vertical position. The people distinguishing system further compares (1005) at least a portion of the grouping pixel area with the expected head pixel area for the at least first vertical position. Moreover, the people distinguishing system determines (1006) that the at least first grouping comprises at least a first overlapping human being (6), when at least a first comparison resulting from the comparing exceeds a predeterminable conformity threshold.The disclosure also relates to a people distinguishing system in accordance with the foregoing, a thermal camera comprising such people distinguishing system, and a respective corresponding computer program product and non-volatile computer readable storage medium.

Anomaly detection method and apparatus

In an apparatus for detecting an anomaly of an evaluation target condition of a road, a storage stores a reference data set correlating to a predetermined attribute and being comprised of reference data samples. An anomaly level calculator obtains, from target vehicles, an evaluation data set correlating to the predetermined attribute and being comprised of evaluation data samples. The evaluation data samples are collected from the respective target vehicles as target driving data items at the predetermined attribute under the evaluation target condition of the road. The target driving data item for each of the target vehicles represents at least one driving operation of the corresponding one of the target vehicles. The anomaly level calculator compares the reference data set with the evaluation data set to thereby calculate an anomaly level of the evaluation target condition of the road.

Abnormal User Identification

User behavior data of multiple users is acquired, and multiple user eigenvalues of user behavior data of each user under preset multiple user behavior dimensions are extracted. A user eigenvector of each user is determined based on the multiple eigenvalues of this user. Multiple user classes are obtained by clustering the user eigenvectors of multiple users are clustered through a preset clustering algorithm. A central vector of each user class is determined based on the user eigenvectors included in this user class. A difference eigenvector of each user class is determined, wherein a distance between the difference eigenvector and a central vector of an aggregation class to which the difference eigenvector belongs is not within a preset distance range. A user characterized by the difference eigenvector is determined as an abnormal user.

Edge-cloud collaboration platform for intelligent coking monitoring of cracking furnace tubes and working method thereof

The edge-cloud collaboration platform for intelligent coking monitoring of cracking furnace tubes includes an edge layer and a cloud layer, which can store and analyze big data, propose suggestions on optimization and improvement, and feed the suggestions back to the edge layer. The edge layer includes an intelligent temperature measuring device for an outer surface of a cracking furnace tube and/or an ethylene DCS/data acquisition device; the cloud layer includes a cracking furnace safety warning device, an intelligent coking diagnosis and prediction device for a cracking furnace tube, a hybrid job scheduling device, a multi-workflow scheduling device, a virtualized resource scheduling device, and a virtual resource optimization device; and the intelligent temperature measuring device for an outer surface of a cracking furnace tube includes an identification device for furnace tube and overlapped tube, and an abnormal data detection device.

System, Method and Computer Program Product For Wellbore Event Modeling Using Rimlier Data

A data mining and analysis system which analyzes clusters of outlier data (i.e., rimliers) to detect and/or predict downhole events.

Devices and Methods to Navigate in Areas using a Machine Learning Model

A system and method of navigating in areas. A machine learning model is trained in multiple levels with data concerning basic interpretation of sensors and with analysis of the layout of areas. The model is downloaded to a second processor which may further train the model with sensor data gathered after the download. Additional sensor data along with data from a server or other sources may be used as an input to the model and the second or another processor evaluates the model with the inputs to create outputs which determine the state of compliance. Specific applications include movement around in areas of interest. A vehicle which is controlled by a driver or by data from the machine loading model and it's analysis may be included. The model is used to calculate a path which may be displayed in visual, auditory or tactile modes.

Network computer system for analyzing driving actions of drivers on road segments of a geographic region

Examples include a network computer system and/or service which operates to remotely monitor vehicles to detect and characterize driving actions of drivers with respect to specific road segments of a roadway.

System and method for detecting anomalies including detection and removal of outliers associated with network traffic to cloud applications

An anomaly detection system is provided and includes a processor, a memory and a security application stored in the memory and including instructions. The instructions are for collecting behavior data corresponding to users of an organization accessing cloud applications. The behavior data includes parameters tracked over time for the users. The instructions are for: creating a first model based on the behavior data tracked for the users; creating a second model corresponding to a first user based on the parameters tracked for the users except the first user, where the second model excludes behavior data pertaining to the first user; scoring the second model based on the first model to generate a first score; determining whether the first user is an outlier based on the first score; and removing the behavior data corresponding to the first user from the first model if the first user is an outlier.

Anomaly detection using image-based physical characterization

An aspect of the invention includes reading a scale in image data representing an image of physical characteristics and resizing at least a portion of the image data to align with target image data representing a target image based at least in part on the scale to form resized image data representing one or more resized images. Noise reduction is applied to the resized image data to produce test image data representing one or more test images. A best fit analysis is performed on the test image data with respect to the target image data. Test image data having the best fit are stored with training image data representing classification training images indicative of one or more recognized features. An anomaly in unclassified image data representing an unclassified image is identified based at least in part on an anomaly detector as trained using the classification training images.

Interactive method and interactive system for smart watch

An interactive method of a smart watch includes the following steps: S 1. acquiring a vibration signal of an accelerometer and a gyroscope of a smart watch based on a vibration signal transmitted by a human body; S 2. identifying the vibration signal by using an anomaly detection algorithm; S 3. pre-processing the vibration signal, and further classifying and identifying the vibration signal by using an improved algorithm of a k-nearest neighbor algorithm; S 4. analyzing the user's feedback on the results and correcting them in time to maintain a stable identification accuracy. The present disclosure also discloses an interactive system, including a signal detection module, an identification and classification module, and a real-time feedback module. In the present disclosure, the human body part is regarded as a virtual screen based on the vibration signal transmitted by the human body.

Systems and methods for equipment maintenance

Disclosed are systems and methods for an industry-wide and predictive approach to maintenance of commercial equipment. In one embodiment, multiple instances of a frontend infrastructure can be deployed to various sites where one or more physical parameters of industrial equipment are monitored with wireless sensors and routed to a backend infrastructure. The backend infrastructure can process the sensor data received from the multiple sites and generate predictive maintenance notifications.

Shape Inspecting Device And Shape Inspecting Method

Information concerning a height of a shape of a workpiece is acquired accurately at high speed. A plurality of segments arrayed in one direction are set on a distance image including height information in a surface shape of a workpiece (S 1 ). A type of a representative value concerning height information in each pixel included in each segment is selected, and this selected representative value is obtained for each segment (S 2 ). An abnormality in a specific representative value is detected from an acquired trend, and is outputted (S 4 ).

Method and apparatus for work quality control

A method for work quality control of a worker in work where repetitive operation is performed which includes: a model construction step of statistically constructing, from past path data of the worker, past intermediate quality data on a product to be subjected to the work, and past final quality data on the product to be subjected to the work, a prediction model that receives the path data and the intermediate quality data and outputs the final quality data; a worker position recognition step of recognizing a position of the worker from image data on the work captured; and an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the model constructed in the model construction step, to determine whether the position of the target worker is a usual one or an unusual one.

Methods and apparatus for fraud detection

This application relates to apparatus and methods for identifying fraudulent transactions. A computing device receives return data identifying the return of at least one item. The computing device obtains modified strategy data identifying at least one rule of a modified strategy. The rule may be based on the application of at least one discrete stochastic gradient descent algorithm to an initial strategy. The computing device applies the modified strategy to the received return data identifying the return of the at least one item, and determines whether the return of the at least one item is fraudulent based on the application of the modified strategy. The computing device generates fraud data identifying whether the return of the at least one item is fraudulent based on the determination, and may transmit the fraud data to another computing device to indicate whether the return is fraudulent.

Persisted machine learning-based sensing of rf environments

A RF Environment Learning Module includes a machine learning/artificial intelligence sensing controller process that schedules feature vector extractors and one or more machine learning (ML) signal classifiers in order to classify received radio signals and a ML-based validation process that reasons over the classification results to determine if they are valid or reasonable.

Feature set optimization in vision-based positioning

In one embodiment, a method for optimizing a set of matched features is provided. The method includes matching features between an optical image and a geo-referenced orthoimage to produce an initial set of matched features. An initial position solution is then determined for the optical image using the initial set of N matched features. The initial set of N matched features are then optimized based on a set of N sub-solutions and the initial position solution, wherein each of the N sub-solutions is a position solution using a different set of (N−1) matched features. A refined position solution is then calculated for the optical image using the optimized set of matched features.

Abnormality detection device

An abnormality detection device, method, or a storage medium acquires learning target data and monitoring target data, generates a state observer by using a variable in an input variable configuration, generates a threshold, calculates an abnormality degree by combining a second state observation value and the monitoring target data and inputting a combined result to the competitive neural network, and calculates a determination result.

Tunable generative adversarial networks

A method of tuning a generative model may be provided. A method may include receiving, at a first generative adversarial network (GAN), a first input identifying an item and at least one user-defined attribute for the item. The method may also include generating, via the first GAN, a first image of the item based on the first input. Further, the method may include receiving, at a second GAN, the first image and a second input indicative of a desire for more or less of the at least one user-defined attribute. Moreover, the method may include generating, via the second GAN, a second image of the item based on the first image and the second input.

Method and apparatus for an adaptive threshold based object detection

A method, non-transitory computer readable medium, and apparatus for detecting an object in an image are disclosed. For example, the method receives the image, calculates a score for each one of a plurality of locations in the image, performs a box plot of the score of the each one of the plurality of locations of the image, identifies an outlier score that falls outside of the box plot, determines that a distance ratio of the outlier score is less than a predefined distance ratio and detects the object in a location of the plurality of locations of the image corresponding to the outlier score.

System and method for optical character recognition

This disclosure relates to system and method for optical character recognition. In one embodiment, the method comprises providing an image data to a plurality of customized machine learning algorithms or various customized neural networks, configured to recognize a set of pre-defined characters. The method comprises presenting one or more suggestions for the character to the user in response to negative character recognition, and training a customized machine learning algorithm corresponding to the character if one of the suggestions is identified by the user. If the suggestions are rejected by the user, the method comprises prompting the user to identify the character and determining presence of the character in the set of pre-defined characters. The method further comprises training a customized machine learning algorithm corresponding to the character if the character is present, or dynamically creating a customized machine learning algorithm corresponding to the character if the character is not present.

Automated outlier detection

An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Method of identifying and tracking sensitive data and system thereof

Methods and systems for identifying sensitive data (SD) stored on data repositories is disclosed. The data is processed to calculate a plurality of float feature (FF) vectors associated with the data. The FF vectors are clustered into a plurality of clusters, each cluster associated with a respective subset of the data. A DNA vector representative of the cluster is generated for each cluster. The DNA vectors of respective clusters are compared to one or more FF vectors calculated for a respective one or more user supplied examples of SD. One or more clusters are classified as SD based on the result of the comparing, thereby identifying respective subsets of data as SD.

Abnormality detection device, abnormality detection method, and storage medium

An abnormality detection device calculates high-dimensional feature values from real world data; projects, by using a matrix generated from real world data collected for learning so as to project the feature values onto an abnormality discriminant space, feature values calculated from real world data which is input for inspection onto an abnormality discriminant space, the abnormality discriminant space being used for determining presence or absence of an abnormality; judges the presence or absence of an abnormality from a distribution in the abnormality discriminant space; identifies, if an abnormality is found and if the abnormality is a known abnormality, the content of the abnormality from a trend of a distribution in the abnormality discriminant space and presenting the content of the abnormality; and visually displays a distribution in the abnormality discriminant space as a detection result of an abnormality.

Intelligent Sensor System

A sensor system and method of using the system synergistically to improve the accuracy and usefulness of measured results is described. The system is comprised of electronically linked components that act as markers to trigger events, producers that gather data from sensors and aggregators that combine the data from a plurality of producers using triggers from marker devices to select the data of interest. The system is shown to be applicable to selection of data regions of interest and to analysis of the data to improve accuracy. The analysis of the data of any particular sensor within the system makes use of extrinsic data, being data generated by other sensors and intrinsic data, that is data or data limits that are known to be true from nature, laws of physics or just the particular information the user wants to acquire. The system is demonstrated on the analysis of Doppler radar measurements of a thrown object.

Medical image assessment with classification uncertainty

Medical images may be classified by receiving a first medical image. The medical image may be applied to a machine learned classifier. The machine learned classifier may be trained on second medical images. A label of the medical image and a measure of uncertainty may be generated. The measure of uncertainty may be compared to a threshold. The first medical image and the label may be output when the measure of uncertainty is within the threshold.

Information processing apparatus, control method, and storage medium

A server receives an input image group from an MFP. The server decides a reference image from the input image group, and generates rotated images by deforming the reference image. The server calculates image feature amounts from the reference image and the rotated images, and generates direction determiners using the image feature amounts. With respect to each of images of the input image group, the server determines the directions of the images by applying the direction determiners, and when the directions of the images are different from the direction of the reference image, the images are rotated to the direction of the reference image, and the directions of each of the images of the input image group are unified. The server generates a classification rule to be used in classification of images using the input image group in which the directions are unified.

Anomalous object interaction detection and reporting

Techniques are disclosed for analyzing a scene depicted in an input stream of video frames captured by a video camera. The techniques include evaluating sequence pairs representing segments of object trajectories. Assuming the objects interact, each of the sequences of the sequence pair may be mapped to a sequence cluster of an adaptive resonance theory (ART) network. A rareness value for the pair of sequence clusters may be determined based on learned joint probabilities of sequence cluster pairs. A statistical anomaly model, which may be specific to an interaction type or general to a plurality of interaction types, is used to determine an anomaly temperature, and alerts are issued based at least on the anomaly temperature. In addition, the ART network and the statistical anomaly model are updated based on the current interaction.

Utilizing a machine learning model to automatically correct rejected data

A device receives data from data sources. The device may reject a portion of the data as rejected data, and may accept a remaining portion of the data as accepted data. The device may process the rejected data, with a machine learning model, to correct the rejected data and to generate corrected data, and may determine whether the corrected data satisfies a threshold. The device may provide the corrected data to a client device when the corrected data fails to satisfy the threshold, and may receive, from the client device, feedback on the corrected data provided to the client device. The device may modify the corrected data, based on the feedback, to generate modified data, and may store the accepted data and the modified data in a data structure. The device updates the machine learning model, based on the modified data, to handle the rejected data at a later time.

Predicting local layout effects in circuit design patterns

A method for predicting local layout effect in a circuit design pattern includes obtaining a plurality of circuit design patterns, generating layout images from the circuit design patterns, extracting feature vectors from the layout images by processing the layout images in a computer vision machine learning algorithm, comparing the feature vector extracted from a selected layout image to clusters of feature vectors extracted from the layout images, wherein the clusters of feature vectors include an in-range cluster and an outlier cluster, and labelling a circuit design pattern corresponding to the selected layout image, for which threshold voltage has not been experimentally measured, as being an in-range circuit design pattern or an outlier circuit design pattern, in response to the selected layout image respectively correlating with the in-range cluster or with the outlier cluster.

Method, System and Apparatus for Gap Detection in Support Structures with Peg Regions

A method of detecting gaps on a support structure includes: obtaining, at an imaging controller, (i) a plurality of depth measurements representing the support structure according to a common frame of reference, and (ii) a plurality of label indicators each defining a label position in the common frame of reference; for each of the label indicators: classifying the label indicator as either a peg label or a shelf label, based on a portion of the depth measurements selected according to the label position and a portion of the depth measurements adjacent to the label position; generating an item search space in the common frame of reference according to the class of the label indicator; and determining, based on a subset of the depth measurements within the item search space, whether the item search space contains an item.

Hazard detection through computer vision

Systems and methods for detecting a hazard in a facility include the use of one or more cameras coupled with a hazard detection server. The hazard detection server is adapted to analyze images from the cameras, determine probabilities of hazards being present in the images, and provide an alert to a manager or workers when the probabilities exceed a hazard threshold.

Measuring crop residue from imagery using a machine-learned classification model in combination with principal components analysis

The present disclosure provides systems and methods that measure crop residue in a field from imagery of the field. In particular, the present subject matter is directed to systems and methods that include or otherwise leverage a machine-learned crop residue classification model to determine a crop residue parameter value for a portion of a field based at least in part on imagery of such portion of the field captured by an imaging device. Furthermore, principal components analysis, such as projecting image patches onto Eigen-images, can be performed to reduce the dimensionality of the feature vector provided to the classification model.

一种机械设备健康状态评估方法

本发明公开了一种机械设备健康状态评估方法。首先利用传感器采集机械设备上主要零部件的状态数据，然后进行特征提取获得特征参数；接着通过离群点检测算法提取出噪声数据和故障数据，仅保留后者；随后进行降维处理获得最终进行评估的特征向量；最后进行设备的状态评估，通过健康状态数据和失效状态数据建立自组织映射神经网络模型，通过熵权理论计算每一组待评估数据的速率影响因子，并带入神经网络进行健康因子计算。本发明实现了对于机械设备的全面状态评估，为机械设备的健康维护提供了依据，避免了不必要的经济损失。

设备故障类型的分析方法、装置、储存介质和电子设备

本公开涉及一种设备故障类型的分析方法、装置、储存介质和电子设备，该方法包括：确定与当前数据点相匹配的目标数据簇，该目标数据簇为所有数据簇中与该当前数据点具有最大匹配概率的数据簇；确定该目标数据簇中与该目标数据簇具有最小匹配概率的第一数据点；根据该目标数据簇的故障状态，该第一数据点与该目标数据簇的匹配概率以及该当前数据点与该目标数据簇的匹配概率的对比结果，确定该当前数据点的故障类型。能够通过设备历史数据的故障状态以及与当前设备数据匹配程度，预测当前设备数据的故障状态和倾向的故障类型，以提醒设备管理者针对该故障倾向进行干预，增加设备异常预测的针对性，提高设备运维的效率。

状态评估方法、装置、设备及存储介质

本申请涉及一种状态评估方法、装置、设备及存储介质，所述方法包括：获取晶闸管样本的状态参数，晶闸管样本包括多个待评估晶闸管及预设晶闸管；预设晶闸管为处于正常状态的晶闸管；针对各晶闸管样本，根据晶闸管样本的状态参数，计算晶闸管样本对应的局部离群点因子；局部离群点因子用于表征晶闸管样本的当前工作状态；基于晶闸管样本的局部离群点因子，确定晶闸管样本的当前工作状态。本申请实施例提供的技术方案可以提高对晶闸管进行状态评估的准确性。

一种机械设备健康状态评估方法

本发明公开了一种机械设备健康状态评估方法。首先利用传感器采集机械设备上主要零部件的状态数据，然后进行特征提取获得特征参数；接着通过离群点检测算法提取出噪声数据和故障数据，仅保留后者；随后进行降维处理获得最终进行评估的特征向量；最后进行设备的状态评估，通过健康状态数据和失效状态数据建立自组织映射神经网络模型，通过熵权理论计算每一组待评估数据的速率影响因子，并带入神经网络进行健康因子计算。本发明实现了对于机械设备的全面状态评估，为机械设备的健康维护提供了依据，避免了不必要的经济损失。

A kind of failure modes diagnostic method generating model based on multiple errors

本发明公开一种基于多个误差生成模型的故障分类诊断方法，通过多个单分类的模型实施故障诊断。首先，本发明方法将每种故障类型可用训练数据转换成能体现变量间相互关系特征的误差，然后对各个故障训练数据转换后误差分别建立单分类匹配模型。在线故障类型识别时，先将在线故障样本按不同故障类型对应的误差生成模型转换为误差后，在计算相应的统计指标数值，并依据统计指标最小数值识别故障类型。与传统方法相比，本发明方法针对各测量变量单独建立一个偏最小二乘模型以生成误差，体现出了分散式建模的特点。此外，本发明方法将故障分类诊断的多分类问题转换成了多个单分类模型实施故障分类。因此，本发明方法是一种更为优选的故障分类诊断方法。

Apparatus for generating learning data for combustion optimization and method thereof

학습 데이터를 생성하기 위한 장치는 보일러 연소에 대해 현재 측정되는 실시간 데이터와, 상기 보일러 연소에 대해 과거 측정된 과거 데이터를 포함하는 원시 데이터를 수집하고, 수집된 원시 데이터에 대해 전처리를 수행하는 전처리부와, 상기 원시 데이터를 분석하여 상기 원시 데이터로부터 학습 데이터를 도출하는 분석부를 포함한다. The apparatus for generating learning data is a preprocessing unit that collects raw data including real-time data currently measured on boiler combustion and past data measured in the past on the boiler combustion, and performs preprocessing on the collected raw data. And an analysis unit for analyzing the raw data to derive training data from the raw data.

Method and system for identifying anomalies in medical images especially those including one of a pair of symmetric body parts

Method for locating anomalous features in medical images in which medical images are supplied by an external source. A sequence of specific measurements is executed on the supplied data to obtain image-related metrics. The metrics are compared to corresponding values in a database resulting in an anomalous/not anomalous determination. Anomalous determinations are presented to the test operator for analysis along with supplemental historical data. In application to all types of medical imagery, potential anomalies are located resulting in an efficient and accurate diagnosis. For paired body parts having symmetrical properties, as a pre-screening stage, a line of symmetry between the body parts is determined and symmetric regions of the two body parts on opposite sides of the determined line of symmetry are analyzed for differences. The metric comparison using the database is performed between both symmetric regions only when differences between the symmetric regions of the subject medical image are present.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Classifying image features

Methods are disclosed for classifying different parts of a sample into respective classes based on an image stack that includes one or more images.

Method of determining depth map for image and device for implementation thereof

FIELD: physics.SUBSTANCE: invention relates to computer engineering. Technical result consists in improvement of quality of perceived image. Device comprises an image unit which supplies an image with a corresponding depth map, a probability unit determining a probability map for the image, having probability values indicating the probability that the pixels belong to the text object of the image, depth unit creates a modified depth map, in which the determined depth values are determined in the form of weighted associations of input values and the value of the depth of the text object of the image corresponding to the preferred depth for the text. Weighing depends on probability of value for said pixels.EFFECT: such approach provides a softer change of depth for text objects, which leads to reduction of artefacts and distortions, for example, when performing shift of views using depth maps.15 cl, 5 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 718 423 C2 (51) МПК G06T 5/00 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06T 7/00 (2019.08); G06K 9/00 (2019.08); G06T 5/30 (2019.08); H04N 13/00 (2019.08) (21)(22) Заявка: 2017144798, 06.05.2016 (24) Дата начала отсчета срока действия патента: (73) Патентообладатель(и): КОНИНКЛЕЙКЕ ФИЛИПС Н.В. (NL) Дата регистрации: 02.04.2020 Приоритет(ы): (30) Конвенционный приоритет: 21.05.2015 EP 15168577.3 (43) Дата публикации заявки: 24.06.2019 Бюл. № 18 (45) Опубликовано: 02.04.2020 Бюл. № 10 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 21.12.2017 2 7 1 8 4 2 3 (56) Список документов, цитированных в отчете о поиске: US2013156294 A1, 20.06.2013. WO2014072926 A1, 15.05.2014. WO2008062351 A1, 29.05.2008. US2013084007 A1, 04.04.2013. WO2006117707 A2, 09.11.2006. R U 06.05.2016 (72) Автор(ы): ВАРЕКАМП Кристиан (NL) EP 2016/060221 (06.05.2016) C 2 C 2 (86) Заявка PCT: (87) Публикация заявки PCT: R U 2 7 1 8 4 2 3 WO 2016/184700 (24.11.2016) Адрес для ...

Measuring crop residue from imagery using a machine-learned classification model in combination with principal components analysis

The present disclosure provides systems and methods that measure crop residue in a field from imagery of the field. In particular, the present subject matter is directed to systems and methods that include or otherwise leverage a machine-learned crop residue classification model to determine a crop residue parameter value for a portion of a field based at least in part on imagery of such portion of the field captured by an imaging device. Furthermore, principal components analysis, such as projecting image patches onto Eigen-images, can be performed to reduce the dimensionality of the feature vector provided to the classification model.

Warning methods, devices, servers, systems, devices, storage media, and programs for dangerous road activities

Device and system for detecting abnormality

An abnormality detection device 30 includes small motion sensors 25 a˜ 25 c that detect small motions of a person in a house, a data collecting unit 32 that collects and stores sensor signals from the small motion sensors 25 a˜ 25 c as sensor patterns, a Markov chain operating unit 33 that transforms the sensor patterns into a cluster sequence by vector-quantizing input patterns which are obtained by averaging and normalizing the sensor patterns and calculates a transition number matrix and a duration time distribution of a Markov chain and so on using a Markov chain model, a comparing unit 34 that calculates characteristic amount (Euclid distance and average log likelihood in appearance frequency of a Markov chain and average log likelihood to the duration time distribution of a Markov chain) of a sample activity as against a daily activity based on the obtained transition number matrix and the duration time distribution and so on, and others.

Object detection method, object detection device and image pickup device

本申请涉及一种对象检测方法、对象检测设备及图像拾取设备，该对象检测方法包括：对象检测步骤，通过特定对象检测器在图像中检测特定对象；场景模型获取步骤，获取表征图像中的特定对象的背景的场景模型；以及过滤步骤，用所述场景模型对对象检测步骤的对象检测结果进行过滤以确定特定对象。

Automatic extraction method for road surface and marking line thereof

本发明涉及移动激光雷达数据处理领域，公开了一种通用的移动激光雷达数据道路面的自动提取方法，包括：步骤1，利用统计滤波法剔除离群点，并根据轨迹数据和高程信息从激光雷达数据中提取道路面候选点；步骤2，沿着车辆前进方向，将候选点分割成若干条伪扫描线，并将点云的坐标系统转换为基于伪扫描线的局部坐标系统；步骤3，通过检测道路面与路缘石或排水沟之间的高度突变，实现道路面提取。本发明还公开了一种道路面标志线的自动提取方法。本发明综合利用了轨迹数据，点云的三维坐标、强度信息和强度梯度信息，对不同类型的移动激光雷达数据实现了有效地组织，及道路面与标志线自动化地提取，普适于不同类型的移动激光雷达系统。

Lane line processing method and device

本发明实施例提出一种车道线处理方法和装置。该方法包括：对第一图像进行二值化处理，得到二值图像，所述第一图像中包括车道线点和非车道线点；对所述二值图像进行连通域分析，得到所述二值图像中的一个或多个连通域，每个连通域中包括相互邻接的多个车道线点；利用各所述连通域确定各车道线对应的分组中包括的车道线点；利用各所述分组中包括的车道线点得到各所述分组对应的车道线的表示信息。本发明实施例，利用连通域分析方法对二值图像上的车道线点进行分组，得到的分组准确，不受图像质量的影响，具有较高的鲁棒性。

The training of machine recognition model and machine identification method, device, electronic equipment

本公开实施例公开了一种机器识别模型的训练及机器识别方法、装置、电子设备。该方法包括获取训练样本；其中，所述训练样本包括多个正训练样本和多个第一负训练样本；所述正训练样本为人类行为在显示界面上生成的移动轨迹，所述第一负训练样本为机器模拟人类在显示界面上生成的移动轨迹；对所述正训练样本进行机器模拟，得到多个第二负训练样本；利用所述正训练样本、第一负训练样本和第二负训练样本进行模型训练，得到机器识别模型。本公开实施例可以利用正训练样本机器模拟出更多的负训练样本，在通过检测机器攻击得到的负训练样本较少或者覆盖面不全的情况下，能够扩充负训练样本的数量以及覆盖面，使得训练得到的机器识别模型的识别能力更强。

Exception handling method and device for federated learning and electronic equipment

本说明书实施例提供一种联邦学习的异常处理方法、装置及电子设备。方法包括：基于目标联邦学习的第一目标成员对象与目标联邦学习的第二目标成员对象在参与目标联邦学习时的通信记录，确定第一目标成员对象与第二目标成员对象之间的通信特征序列。将第一目标成员对象与第二目标成员对象之间的通信特征序列输入至异常识别模型，得到第一目标成员对象与第二目标成员对象的异常识别结果，异常识别模型是基于样本数据和预先为样本数据标注的异常分类标签训练得到的，样本数据包括第一样本成员对象在远程控制第二样本成员时，与第二样本成员对象之间的通信特征序列。对第一目标成员对象和/或第二目标成员对象执行与异常识别结果相匹配的风控决策。

A kind of fold bill discrimination method and device

本发明涉及一种褶皱票据鉴别方法和装置。该装置包括一票据输入口、一信号采集模块、一信号鉴别模块以及一接收/拒收模块，其中，该信号鉴别模块进一步包括一高通滤波第一单元、一低通滤波第一单元、一高通滤波第二单元、一低通滤波第二单元、一差分滤波图单元、一特征提取第一单元、一特征提取第二单元、一特征提取第三单元及一鉴别决策单元。由于采用高/低通滤波的方式对特征进行有效分类，提升了特征的可区分性。特别是不同类型的特征对应不同的分类器，而分类器之间又具有类似Adaboost分类器的功能，能够保证鉴别置信度，使得鉴别系统更为鲁棒地兼容外部环境干扰、票据本身污染等复杂情况，整个褶皱票据解决方法及装置能够有效地鉴别褶皱票据。

Methods and apparatus for classifying different parts of a sample into respective classes

公开了分类方法和分类设备，用于把样本的不同区域分类到相应类别，其中分类方法包含：把样本的光谱图像集合分解为解混和图像集合，其中解混和图像集合的每一个成员对应于来自样本中不同成分的光谱贡献；基于包含样本的一个或更多个图像的图像堆栈，把样本的不同区域分类到相应类别，其中，用于分类的图像堆栈中的图像包含一个或更多个解混和图像。

Detection of abnormal signals in the data set

본 발명은 데이터 세트, 특히 타겟 분석물질에 대한 데이터 세트에서 비정상적인 시그널을 검출하는 방법에 관한 것이다. 본 발명에 따르면, 정상 스코어를 사용하여 데이터 세트에서 비정상적인 시그널을 나타내는 사이클 번호(들)를 정확히 결정할 수 있을 뿐만 아니라, 후보 사이클 번호가 비정상적인 시그널을 나타내는 것으로 결정되면, 사이클 번호에서의 비정상적인 시그널 값이 정상적인 시그널 값으로 대체된 보정된 데이터 세트를 제공할 수 있다. The present invention relates to a method of detecting anomalous signals in a data set, in particular a data set for a target analyte. According to the present invention, not only can the cycle number(s) representing an abnormal signal in the data set be accurately determined using the normal score, but also, if the candidate cycle number is determined to represent an abnormal signal, the abnormal signal value in the cycle number is It is possible to provide a corrected data set that has been replaced with a normal signal value.

Reduced false positive identification for spectroscopic quantification

장치는 미지의 샘플에 수행된 분광 측정의 결과를 식별하는 정보를 수신할 수 있다. 상기 장치는, 정량화 모델의 제1 복수의 트레이닝 세트 샘플이 판정 경계 내에 있고 상기 정량화 모델의 제2 복수의 트레이닝 세트 샘플이 상기 판정 경계 내에 있지 않도록 구성 가능한 파라미터에 기초하여 상기 정량화 모델의 판정 경계를 결정할 수 있다. 상기 장치는 상기 판정 경계에 대해 상기 미지의 샘플에 수행된 분광 측정의 거리 메트릭을 결정할 수 있다. 상기 장치는 상기 판정 경계에 대해 상기 정량화 모델의 제2 복수의 트레이닝 세트 샘플의 복수의 거리 메트릭을 결정할 수 있다. 상기 장치는 상기 미지의 샘플에 수행된 분광 측정이 상기 정량화 모델에 대응하는지 여부를 나타내는 정보를 제공할 수 있다.

METHOD FOR DETERMINING A DEPTH MAP FOR IMAGE AND A DEVICE FOR ITS IMPLEMENTATION

РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2017 144 798 A (51) МПК G06T 5/00 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ЗАЯВКА НА ИЗОБРЕТЕНИЕ (21)(22) Заявка: 2017144798, 06.05.2016 (71) Заявитель(и): КОНИНКЛЕЙКЕ ФИЛИПС Н.В. (NL) Приоритет(ы): (30) Конвенционный приоритет: (72) Автор(ы): ВАРЕКАМП Кристиан (NL) 21.05.2015 EP 15168577.3 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 21.12.2017 R U (43) Дата публикации заявки: 24.06.2019 Бюл. № 18 (86) Заявка PCT: (87) Публикация заявки PCT: WO 2016/184700 (24.11.2016) A Адрес для переписки: 129090, Москва, ул. Б. Спасская, 25, стр. 3, ООО "Юридическая фирма Городисский и Партнеры" R U (57) Формула изобретения 1. Устройство для определения карты глубин для изображения, причем устройство содержит: блок (105) изображений для снабжения первого изображения соответствующей картой глубин, содержащей первые значения глубин, для, по меньшей мере, некоторых пикселей первого изображения; блок (107) вероятностей для определения карты вероятностей для первого изображения, содержащей значения вероятности для, по меньшей мере, некоторых пикселей изображения, причем значение вероятности для пикселя указывает вероятность того, что этот пиксель принадлежит текстовому объекту изображения; блок (109) глубин для создания измененной карты глубин для первого изображения, причем блок глубин выполнен с возможностью определения измененного значения глубины для, по меньшей мере, первого пикселя в виде взвешенного объединения первого значения глубины соответствующей карты глубин для первого пикселя и значения глубины текстового объекта изображения, одинакового для множества пикселей, причем упомянутое взвешивание зависит от значения вероятности для первого пикселя. 2. Устройство по п. 1, в котором блок (107) вероятностей выполнен с возможностью определения групп пикселей для первого изображения, причем каждая группа пикселей Стр.: 1 A 2 0 1 7 1 4 4 7 9 8 (54) СПОСОБ ОПРЕДЕЛЕНИЯ КАРТЫ ГЛУБИН ДЛЯ ИЗОБРАЖЕНИЯ И ...

Outlier discovery system selection

Systems, device and techniques are disclosed for outlier discovery system selection. A set of time series data including time series data objects may be received. A sample of time series data objects may be extracted from the time series data. The sample of time series data objects may be decomposed into sub-components. Statistical classification may be used to select an outlier discovery system based on the sub-components. A neural network may be used to select an outlier discovery system based on the sub-components. A level of error of the neural network may be determined based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network. Weight of the neural network may be updated based on the level of error of the neural network.

Technology to detect information processing devices that have malfunctioned

Abnormal data detection method, device, equipment and storage medium

本申请实施例提供了一种异常数据检测方法、装置、设备及存储介质；所述方法包括：获取待监控对象在预设历史时长内的历史状态数据；基于历史状态数据，预测当前状态数据的走势基线；基于走势基线和历史状态数据，预测走势基线的第一边界值和第二边界值；在同一时刻上，第一边界值大于走势基线中的数据值，第二边界值小于走势基线中的数据值；基于第一边界值和第二边界值，对当前状态数据进行检测，得到检测结果；在检测结果表明当前状态数据为异常数据的情况下，输出用于提示出现异常数据的告警信息；如此，采用实时确定的走势基线的两个边界值，对当前状态数据进行检测，以确定当前状态数据是否为异常数据；如此，能够提高异常检测的准确性。

3-Dimensional Space Modeling Method based on the Geotechnical Information

본 발명은 지반정보에 기초한 3차원 공간 모델링 방법에 관한 것으로서, 구체적으로는 조사대상지역 내 다수 시추공에 대한 이상치 분석(Outlier Analysis)을 통해 정보 수집 대상 시추공을 선별하고, 선별된 시추공의 시추정보 및 상기 조사대상지역에 대한 물리탐사 자료를 통합한 배리오그램(Variogram) 모델링을 통해 조사대상지역에 대한 3차원적 지반정보를 생성한 후 상기 지반정보에 기초한 공간 보간을 통해 조사대상지역에 대한 3차원 모델을 생성하는 방법에 관한 것이다. 본 발명은 위 사항을 반영하여 「(A) 조사대상지역 내 다수 시추공에 대한 이상치 분석(Outlier Analysis)을 통해 정보 수집 대상 시추공을 선별하는 단계; (B) 상기 (A)단계를 통한 선별 시추공의 시추정보 및 상기 조사대상지역에 대한 물리탐사 자료를 통합한 배리오그램(Variogram) 모델링을 통해 조사대상지역에 대한 3차원적 지반정보를 생성하는 단계; 및 (C) 상기 지반정보를 고려하여 3차원 그리드 사이즈를 결정하고, 상기 3차원 그리드에 의해 영역화된 셀(Cell)별로 대표 프로파일과 동적 특성을 분류한 DB를 구축하고, 상기 DB에 기초한 공간 보간을 통해 조사대상지역에 대한 3차원 모델을 생성하는 단계; 를 포함하는 지반정보에 기초한 3차원 공간 모델링 방법」을 제공한다. Field of the Invention The present invention relates to a three-dimensional space modeling method based on geotechnical information, and more specifically, to a method for modeling a three-dimensional space modeling method based on geotechnical information, After generating three-dimensional ground information for the survey area through the Variogram modeling that integrates the geophysical data for the survey area, the three-dimensional ground information is generated by the space interpolation based on the ground information, And a method for generating a dimensional model. According to the present invention, there is provided a method of analyzing a plurality of boreholes, comprising the steps of: (A) selecting an information collection target borehole through outlier analysis for a plurality of boreholes in the survey area; (B) generating three-dimensional ground information for the survey area through a variogram modeling which integrates drilling information of the selective borehole through the step (A) and physical exploration data for the survey area step; (C) determining a three-dimensional grid size in consideration of the ground information, constructing a DB in which representative profiles and dynamic characteristics are classified for each of the cells segmented by the three-dimensional grid, ...

Anti-noise hand motion track rapid identification method

本发明提供了一种抗噪的手部运动轨迹快速识别方法，使用隔离林算法计算轨迹中的离群点；使用卡尔曼滤波方法预测当前轨迹终点后下一个轨迹点的位置；检测起点是否为离群点；与前后两点距离是否都小于阈值来确定保留点和舍弃点；判断重点是否为离群点，并且行列最大距离都是大于最小直径阈值；确定统计方向角变化均值判断轨迹顺逆时针，或者根据横纵向运动幅度与距离阈值和波动阈值的关系，预测位置和当前位置关系判断移动方向或判断为静止，最后结束；本发明可以识别上下左右移动和顺逆时针的手部运动轨迹，具有对硬件配置要求低、计算速度快、抗噪声能力强、鲁棒性好等优点。

Telemetry signal outlier removing method, device and medium based on deconvolution reconstruction network

本发明实施例公开了一种基于反卷积重建网络的遥测信号野值去除方法、装置及介质；该方法包括：基于卷积构建与反卷积重建构造一反卷积重建网络；通过由已有的实测遥测信号数据及对应的实测遥测信号数据时间戳组成的训练数据对所述反卷积重建网络进行训练，获得训练后的反卷积重建网络；将原始遥测信号数据时间戳输入至所述训练后的反卷积重建网络，以获得与所述原始遥测信号数据时间戳对应的预测的遥测信号数据；计算所述原始遥测信号数据时间戳对应的原始遥测信号数据与所述预测的遥测信号数据之间的距离；当所述距离大于设定的阈值，确定所述原始遥测信号数据时间戳对应的原始遥测信号数据为野值，并将所述野值进行去除。

Vehicle track clustering method based on outlier removal

本发明公开一种基于带离群点去除的车辆轨迹聚类方法，主要解决现有技术聚类时间复杂度高和聚类质量差的问题。其实现方案为：通过GPS采集车辆轨迹数据；整理轨迹数据格式并对数据清洗形成轨迹数据集；使用A‑MDL算法对轨迹数据进行轨迹段划分；采用带有离群因子LOF的DBSCAN算法对轨迹段数据集聚簇；使用引入了中心轨迹子轨迹段最大置信长度Z的扫描线方法确定轨迹簇的中心轨迹；通过坐标系旋转得到中心轨迹的实际坐标，各个轨迹簇的中心轨迹即为最终的车辆轨迹聚类的结果。本发明降低了轨迹聚类的时间复杂度，消除了离群轨迹的影响，提高了轨迹聚类的质量和聚类结果的平滑度，可用于城市交通管理和道路养护。

Defect inspection method and apparatus

Method, system and apparatus for gap detection in support structures with peg regions

A method of detecting gaps on a support structure includes: obtaining, at an imaging controller, (i) a plurality of depth measurements representing the support structure according to a common frame of reference, and (ii) a plurality of label indicators each defining a label position in the common frame of reference; for each of the label indicators: classifying the label indicator as either a peg label or a shelf label, based on a portion of the depth measurements selected according to the label position and a portion of the depth measurements adjacent to the label position; generating an item search space in the common frame of reference according to the class of the label indicator; and determining, based on a subset of the depth measurements within the item search space, whether the item search space contains an item.