Embodiments of the disclosure are directed towards electricity fraud detection systems that involve a behavioral detection ecosystem to improve the detection rate of electricity fraud while reducing the rate of false-positives. More specifically, machine learning algorithms are eschewed in favor of two separate models that are applied sequentially. The first model is directed to improving the detection rate of electricity fraud through the use of detectors to identify customers engaging in suspicious behavior based on the demand profiles of those customers. The second model is directed to reducing the rate of false-positives by identifying potential legitimate explanations for any suspicious behavior. Subtracting away the suspicious behavior with legitimate explanations leaves only the identified, unexplained suspicious behavior that is highly likely to be associated with fraudulent activity.

The present disclosure provides for one-handed, touch-free interaction with smartwatches. An optical sensor in the smartwatch detects a user's hand and finger movements on the arm wearing the smartwatch. The gesture detection and recognition approaches in this design are lightweight and efficient to operate on small devices.

A system and/or method configured to determine highlight segments. Content files that define content in a content segment set may be obtained. A highlight segment set may be determined from the content segment set. Determining the highlight segment set may include iterating (a)-(c) for multiple iterations. At (a), individual content segments included in the content segment set may be selected as a selected content segment for inclusion in the highlight segment set. At, (b) diversity scores for content segments that are (i) included in the content segment set and (ii) not yet selected for inclusion in the highlight segment set may be determined. At (c), one or more of the content segments may be disqualified for inclusion in the highlight segment set for future iterations based on the diversity scores.

Touch input processing for touch-sensitive devices can be improved by filtering unintended contact detected on a touch-sensitive surface. In wet environments in particular, water on the touch-sensitive surface can be erroneously detected as touch input and degrade touch performance. In some examples, input patches can be classified as touch patches or non-touch patches prior to computationally-intensive touch processing. Filtering out unintended touches classified as non-touch patches can reduce processing requirements and save power. Additionally, classifying input patches can improve touch performance in wet environments. In some examples, input patches can be classified as touch patches or non-touch patches based on characteristics of edge touch nodes. In some examples, input patches can be classified as touch patches or non-touch patches based on a state-based signal threshold.

An authentication method comprising creating electrocardiogram data of users; calculating a similarity between electrocardiogram data of each user and template data created by averaging electrocardiogram data of each user; creating and training a first NNmodel for every user by using similarities between electrocardiogram data of a user and template data of the same user and similarities between electrocardiogram data of a user and template data of another user, and creating and training second NNmodels for users by using similarities between electrocardiogram data of a user and template data of the user and similarities between electrocardiogram data of the user and template data of another user; and executing a first step in which the similarities calculated using electrocardiogram data for authentication of a user to be authenticated and template data are input to the first NNmodel, and executing a second step in which the similarities are input to the second NNmodels.

When a brain fingerprint is detected, a predetermined visual stimuli is output on a screen of a display, causal connectivity formed by unique EEG signals of a subject between two or more brain regions from among a predetermined plurality of brain regions is detected on the basis of the EEG signals of the subject who selectively attends to a part corresponding to a letter or symbol conceived by the subject from among the visual stimuli output on the screen of the display, an activation pattern of causal connectivity between brain regions is recognized on the basis of the detected causal connectivity, and the subject is identified by using the recognized unique activation pattern of causal connectivity between brain regions as a brain fingerprint.

An artificial intelligence-based interference recognition method for an electrocardiogram, comprising: cutting and sampling heart beat data of a first data amount, and inputting the heart beat data to be recognized that is obtained by cutting and sampling into an interference recognition binary classification model for interference recognition; in a sequence of the heart beat data, performing signal anomaly determination on a heart beat data segment where an inter-beat interval is greater than or equal to a preset interval determination threshold value, so as to determine whether the heart beat data segment is an abnormal signal; if the heart beat data segment is not an abnormal signal, determining a starting data point and an ending data point of sliding sampling in the heart beat data segment according to a set time with a preset time width, and performing sliding sampling on the data segment from the starting data point until the ending data point so as to obtain multiple sampling data segments; and using each sampling data segment as heart beat data to be recognized for interference recognition.

The system receives exemplary time-series sensor signals comprising ground truth versions of signals generated by a monitored system associated with a target use case and a synchronization objective, which specifies a desired tradeoff between synchronization compute cost and synchronization accuracy for the target use case. The system performance-tests multiple synchronization techniques by introducing randomized lag times into the exemplary time-series sensor signals to produce time-shifted time-series sensor signals, and then uses each of the multiple synchronization techniques to synchronize the time-shifted time-series sensor signals across a range of different numbers of time-series sensor signals, and a range of different numbers of observations for each time-series sensor signal. The system uses the synchronization objective to evaluate results of the performance-testing in terms of compute cost and synchronization accuracy. Finally, the system selects one of the multiple synchronization techniques for the target use case based on the evaluation.

A data recognition method includes: extracting a feature map from input data based on a feature extraction layer of a data recognition model; pooling component vectors from the feature map based on a pooling layer of the data recognition model; and generating an embedding vector by recombining the component vectors based on a combination layer of the data recognition model.

A method of processing sensor logs is described. The method includes accessing a first sensor log and a corresponding first reference log. Each of the first sensor log and the first reference log includes a series of measured values of a parameter according to a first time series. The method also includes accessing a second sensor log and a corresponding second reference log. Each of the second sensor log and the second reference log includes a series of measured values of a parameter according to a second time series. The method also includes dynamically time warping the first reference log and/or and second reference log by a first transformation between the first time series and a common time-frame and/or a second transformation between the second time series and the common time-frame. The method also includes generating first and second warped sensor logs by applying the or each transformation to the corresponding ones of the first and second sensor logs.