Abstract: A computer-implemented method, a computer program product, and a computer system for using a time-window based attention long short-term memory (TW-LSTM) network to analyze sequential data with time irregularity. A computer splits elapsed time into a predetermined number of time windows. The computer calculates average values of previous cell states in respective ones of the time windows and sets the average values as aggregated cell states for the respective ones of the time windows. The computer generates attention weights for the respective ones of the time windows. The computer calculates a new previous cell state, based on the aggregated cell states and the attention weights for the respective ones of the time windows. The computer updates a current cell state, based on the new previous cell state.

Abstract: Target characteristic data may be predicted using an apparatus including a processor and one or more computer readable mediums collectively including instructions. When executed by the processor, the instructions cause the processor to obtain a plurality of physical structure data and a plurality of characteristic data, estimate at least one structural similarity between at least two physical structures that correspond with physical structure data among the plurality of physical structure data, and generate an estimation model for estimating a target characteristic data from a target physical structure data by using at least one characteristic data and corresponding at least one structural similarity between the target physical structure data and each of the plurality of the physical structure data.

Abstract: Described are techniques for fair anomaly detection. The techniques include generating an anomaly detection model based on a Gaussian distribution of historical data, a mean vector of the Gaussian distribution, and a precision matrix of the Gaussian distribution. The mean vector and the precision matrix can be generated by reducing a function below a threshold, where the function can include the Gaussian distribution, a first regularization term configured to generate similar anomaly scores for inputs with similar fair features and independent of unfair features, and a second regularization term configured to generate similar anomaly localization scores for the inputs with the similar fair features and independent of the unfair features. The techniques further include inputting a new data to the anomaly detection model and generating an anomaly score and an anomaly localization score associated with the new data based on the Gaussian distribution, the mean vector, and the precision matrix.

Abstract: Optimized learning settings of neural networks are efficiently determined by an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to train a first neural network with a learning setting; extract tentative weight data from the first neural network with the learning setting; calculate an evaluation value of the first neural network with the learning setting; and generate a predictive model for predicting an evaluation value of a second neural network with a new setting based on tentative weight data of the second neural network by using a relationship between the tentative weight data of the first neural network and the evaluation value of the first neural network.

Abstract: A method including receiving designation of an input node for which a node value is generated from collected data, an option node to which a node value is arbitrarily provided, and an estimation target node to be a target of a node value estimation, in a graph including nodes and directional edges; and identifying a directional edge for which a conditional probability is to be acquired to measure the node value of the estimation target node, from among the directional edges, by traversing a directional edge that can propagate an effect to a node value from the estimation target node. The identifying includes, for the option node, traversing both a directional edge that can propagate an effect if a node value is provided to the option node and a directional edge that can propagate an effect if a node value is not provided to the option node.

Abstract: A computer-implemented method of predicting a risk of an accident is disclosed. The method includes computing an anomaly score based on sensor data to obtain a series of anomaly scores. The method also includes processing the anomaly score to limit a processed anomaly score below a predetermined value. The method further includes calculating an accident risk score at time of prediction by using a series of processed anomaly scores up to the time of the prediction. The method includes further outputting a prediction result based on the accident risk score.

Abstract: Anomalous sensors are detected using an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to obtain a plurality of healthy sensor data, wherein each of the healthy sensor data includes a plurality of sensed values of a corresponding sensor among a plurality of sensors in normal operation, generate a healthy data distribution of at least two sensors among the plurality of sensors based on the plurality of healthy sensor data, and generate a function of a parameter probability distribution of the plurality of sensors under a condition of sensor data of the plurality of sensors based on the healthy data distribution, each parameter indicating whether the corresponding sensor is healthy or anomalous.

Abstract: Methods and apparatus are provided for estimating anomalous sensors. The apparatus includes a target data acquiring section to acquire a plurality of sets of target data serving as an examination target, each set of target data being output by a plurality of sensors. The apparatus further includes a calculating section to calculate, for each of a plurality of sensor groups such that each sensor group includes at least two sensors among the plurality of sensors, a degree of difference of a target data distribution of the plurality of sets of target data relative to a reference data distribution of output from the sensor group. The apparatus additionally includes an estimating section to estimate one or more sensors among the plurality of sensors to be a source of outlierness, based on a calculation result of the calculating section.

Abstract: A method including receiving designation of an input node for which a node value is generated from collected data, an option node to which a node value is arbitrarily provided, and an estimation target node to be a target of a node value estimation, in a graph including nodes and directional edges; and identifying a directional edge for which a conditional probability is to be acquired to measure the node value of the estimation target node, from among the directional edges, by traversing a directional edge that can propagate an effect to a node value from the estimation target node. The identifying includes, for the option node, traversing both a directional edge that can propagate an effect if a node value is provided to the option node and a directional edge that can propagate an effect if a node value is not provided to the option node.

Abstract: A method is provided for clustering data elements to extract specific patterns. The method specifies some data elements with a uniform distribution as a mini-batch and performs a single-pass cluster initialization by selecting a respective data element from the mini-batch as a respective initial cluster center to obtain cluster centers for clusters. The method assigns each data element in the mini-batch to a closest cluster by calculating a distance between each of the data elements in the mini-batch and each of the clusters. The method assigns k-minimum new centers by calculating an averaged distance to each data element in a same cluster. The method repeats the specifying step and the assigning steps responsive to a dissatisfaction of loop stop criteria which is based on distances between the centers and the K-minimum new centers. The method outputs a cluster id sequence responsive to a satisfaction of the loop stop criteria.

Abstract: A computer-implemented method for learning a model to predict movements of a person in bed is presented. The method includes receiving first data from a plurality of first sensors installed on a bed patient support apparatus, receiving second data from a plurality of second sensors installed on the person, and learning a model to predict the second data based on the first data by assuming a sensing range of motion intensity by the plurality of first sensors is greater than a sensing range of motion intensity by the plurality of second sensors.

Abstract: An assistance strategy may be generated with a generating apparatus including a processor, and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to create a reward estimation model for estimating a reward for assisting at least one subject by analyzing a history of input by the subject, create a decision making model including a plurality of forms of assistance and estimated rewards for each form of assistance based on the reward estimation model and the history of input by the subject, and generate an assistance strategy based on the decision making model.

Abstract: Predicting simulation parameters is performed by obtaining a plurality of datasets, each dataset including simulation parameters, time series data and a label. Wherein the time series data represents a simulation status for each time and the label represents a simulation result. Learning a metric of the simulation parameters including two datasets of the plurality of datasets. Wherein the metric imitates the similarity of time series data of the two datasets, and training a model for predicting the label for simulation parameters by using the metric.

Abstract: A computer-implemented method for detecting an operation tendency is disclosed. The method includes preparing a general model for generating a general anomaly score. The method also includes preparing a specific model, for generating a specific anomaly score, trained with a set of a plurality of operation data related to operation by a target operator. The method further includes receiving input operation data. The method includes also calculating a detection score related to the operation tendency by using a general anomaly score and a specific anomaly score generated for the input operation data. Further the method includes outputting a result based on the detection score.

Abstract: An apparatus obtains waveforms representing measurements of a physical characteristic of a machine's operation and performance results of the machine corresponding respectively to the waveforms, each of the performance results being indicative of the machine's performance under conditions at which the measurement represented by the corresponding waveform was made. The apparatus calculates, for each of at least interval associated with each of the waveforms, an influence value that represents a degree of influence of the waveforms on the performance results over the interval.

Abstract: Anomalous sensors are detected using an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to: obtain a plurality of healthy sensor data, wherein each of the healthy sensor data includes a plurality of sensed values of a corresponding sensor among a plurality of sensors in normal operation, generate a healthy data distribution of at least two sensors among the plurality of sensors based on the plurality of healthy sensor data, and generate a function of a status probability distribution of the plurality of sensors with respect to time under the condition of sensor data with respect to time based on the healthy data distribution.

Abstract: A computer-implemented method is disclosed. The method includes preparing a base of an anomaly detection model for generating a score that indicates an estimation of a concentration decline. The anomaly detection model has parameters affecting the score. The method also includes preparing a set of training data, each of which includes a sequence of sensor data relating to activity performed by an individual. The method also includes optimizing the parameters of the anomaly detection model using the set of the training data so as to make a score for longer cumulative activity high as compared to shorter cumulative activity. The method further includes outputting the parameters of the anomaly detection model, in which the anomaly detection model having the parameters is used for detecting a concentration decline of a target individual.

Abstract: A computer-implemented method is provided for machine prediction. The method includes forming, by a hardware processor, a Convolutional Dynamic Boltzmann Machine (C-DyBM) by extending a non-convolutional DyBM with a convolutional operation. The method further includes generating, by the hardware processor using the convolution operation of the C-DyBM, a prediction of a future event at time t from a past patch of time-series of observations. The method also includes performing, by the hardware processor, a physical action responsive to the prediction of the future event at time t.

Abstract: A method is provided for creating a prediction model that predicts chemical properties of a compound from sequence data as feature vectors describing the compound. The sequence data includes multiple data sequences. The method includes generating a probabilistic prediction model y* for predicting an objective variable y and learned using Bayesian criterion and variational approximation. The method includes configuring the model to (i) assign one of multiple prediction functions for each of the feature vectors extracted from the sequence data, (ii) identify a relationship between a t-th vector in an i-th data and the objective variable y, and (iii) identify similarities of relationships between the feature vectors and the objective variable y. The method includes identifying, using the model, a sequence length which is variable between the multiple data sequences. The method includes predicting the objective variable y as a chemical property of the compound based on the model.

Abstract: A computer-implemented method is presented for discovering new material candidates from a chemical database. The method includes extracting a feature vector from a chemical formula, learning a prediction model for predicting property values from the feature vector with a sparse kernel model employing the chemical database, selecting an existing material from a list of existing materials sorted in descending order based on the predicted property values by the prediction model learned in the learning step, selecting a basis material from a list of basis materials sorted in descending order of absolute reaction magnitudes to the selected existing material, and generating the new material candidates as variants of the selected existing material with consideration of the selected basis material.