Abstract: Embodiments select households using machine learning predictions. One or more trained machine learning models can be stored. For example, at least one machine learning model can be trained to predict household income using time-series energy usage data. Input data including time-series energy usage data for a plurality of households can be received. Using the trained machine learning models, a household income is predicted per household. A subset of the households with a predicted household income that meets one or more campaign criteria can be selected. For example, the selected subset of the households can be targeted by an energy campaign that corresponds to the campaign criteria, and the energy campaign comprise one or more actions to alter energy usage for the targeted households.

Abstract: System and method for robust machine learning (ML) includes an attack detector comprising one or more deep neural networks trained using adversarial examples generated from a generative adversarial network (GAN), producing an alertness score based on a likelihood of an input being adversarial. A dynamic ensemble of individually robust ML models of various types and sizes and all being trained to perform an ML-based prediction is dynamically adapted by types and sizes of ML models to be deployed during the inference stage of operation. The adaptive ensemble is responsive to the alertness score received from the attack detector. A data protector module with interpretable neural network models is configured to prescreen training data for the ensemble to detect potential data poisoning or backdoor triggers in initial training data.

Abstract: A system and method adaptively control a heterogeneous system of systems. A graph convolutional network (GCN) that receive a time series of graphs representing topology of an observed environment at a time moment and state of a system. Embedded features are generated having local information for each graph node. Embedded features are divided into embedded states grouped according to a defined grouping, such as node type. Each of several reinforcement learning algorithms are assigned to a unique group and include an adaptive control policy in which a control action is learned for a given embedded state. Reward information is received from the environment with a local reward related to performance specific to the unique group and a global reward related to performance of the whole graph responsive to the control action. Parameters of the GCN and adaptive control policy are updated using state information, control action information, and reward information.

Abstract: A computer-implemented method for analyzing log files generated by complex physical equipment includes receiving one or more log file generated by one or more components of physical equipment. Each of the log files comprises one or more log entries. A plurality of templates are extracted from each log file describing fixed portions of the log entries. The log entries are grouped in log files into a plurality of instances. Each instance corresponds to one of a plurality of partitions along one or more dimensions describing data in the log entries. A representation of each instance is created that describes a set of the templates included in the instance. A plurality of clusters are generated by applying a clustering process to the representations of the instances. A visual depiction of the clusters and the instances may then be created in a graphical user interface (GUI).

Abstract: Provided is a computer-implemented method for receiving the at least two log files; wherein each log file of the at least two log files includes at least one log entry with at least one time stamp and at least one message; wherein the at least two log files differ from one another with respect to at least one distinctive criteria; extracting at least one additional information of each log file of the at least two log files; and combining each log file of the at least two log files with the extracted additional information into at least two processed log files; wherein the at least two processed log files comply with a coherent representation. A corresponding computer program product and generating unit is also provided.

Abstract: Provided is a Computer-implemented method for Receiving the at least two log files; wherein each log file of the at least two log files includes at least one log entry with at least one time stamp and at least one message; wherein the at least two log files differ from one another with respect to at least one distinctive criteria; Extracting at least one additional information of each log file of the at least two log files; and Combining each log file of the at least two log files with the extracted additional information into at least two processed log tiles; wherein the at least two processed log files comply with a coherent representation. Further, the invention relates to a corresponding computer program product and generating unit.

Abstract: The present invention relates to a method for extracting an output data set, wherein the method includes the following steps receiving an input data set; wherein the input data set comprises at least one textual input data set and at least one visual input data set; processing the at least one textual input data set using natural language processing into at least one textual output data set; processing the at least one visual input data set using image processing into at least one visual output data set, and outputting the output data set, including the at least one textual output data set and/or the at least one visual output data set. Further, the present invention is related to a computer program product and system.

Abstract: Embodiments include methods, systems and computer program products for detecting an anomaly in data provided by each one of a plurality of correlated sensors. Aspects include receiving time series data sequences from each one of a plurality of correlated sensors, determining a numeric representation for each one of the time series data sequences, determining an anomaly score for each one of the time series data sequences using the determined numeric representation for each one of the time series data sequences, and determining a distribution of the determined anomaly scores under normal conditions.

Abstract: A method of building a model for predicting failure of a machine, including parsing (41) daily machine event logs of one or more machines to extract data for a plurality of features, parsing (42) service notifications for the one or more machine to extract failure information data, creating (43) bags from the daily machine event log data and failure information data for multiple instance learning by grouping daily event log data into the bags based on a predetermined predictive interval, labeling each bag with a with a known failure as positive, and bags without known failures as negative, where a bag is a set of feature vectors and an associated label, where each feature vector is an n-tuple of features, transforming (44) the multiple instance learning bags into a standard classification task form, selecting (45) a subset of features from the plurality of features, and training (46) a failure prediction model using the selected subset of features.

Abstract: The present invention relates to a method for extracting an output data set, wherein the method includes the following steps receiving an input data set; wherein the input data set comprises at least one textual input data set and at least one visual input data set; processing the at least one textual input data set using natural language processing into at least one textual output data set; processing the at least one visual input data set using image processing into at least one visual output data set, and outputting the output data set, including the at least one textual output data set and/or the at least one visual output data set. Further, the present invention is related to a computer program product and system.

Abstract: A method to build a failure predictive model includes: receiving an input of a set of event sequences, where each sequence is labeled as representing a failure or not representing a failure, extracting a single predictive closed pattern from among the input sequences that represents a failure, creating a root node with the single closed pattern, splitting the set of event sequences into a first set that includes the single closed pattern and a second set that excludes the single pattern, and processing each of the first and second sets until at least one child node is created that is labeled as either representing a failure or not representing a failure.

Abstract: A system for performing data mining on log record data includes a distributed processing system comprising a plurality of distributed nodes, each node having at least one of a storage device and a data processing device and a distributed data analytics processor configured to perform queries on a set of log records to select at least a portion of the log records and store the selected log records in a plurality of the distributed nodes, wherein the distributed data analytics processor is further configured to perform data analysis on the selected log records stored in the plurality of distributed nodes. The distributed nodes may be arranged in a cluster, with each node being in communication with each other node through a distributed file system. The processor may perform analysis on data stored across the distributed nodes with the processing being performed by a plurality of the distributed nodes in parallel.

Abstract: A method to build a failure predictive model includes: receiving an input of a set of event sequences, where each sequence is labeled as representing a failure or not representing a failure, extracting a single predictive closed pattern from among the input sequences that represents a failure, creating a root node with the single closed pattern, splitting the set of event sequences into a first set that includes the single closed pattern and a second set that excludes the single pattern, and processing each of the first and second sets until at least one child node is created that is labeled as either representing a failure or not representing a failure.

Abstract: A method of building a model for predicting failure of a machine, including parsing (41) daily machine event logs of one or more machines to extract data for a plurality of features, parsing (42) service notifications for the one or more machine to extract failure information data, creating (43) bags from the daily machine event log data and failure information data for multiple instance learning by grouping daily event log data into the bags based on a predetermined predictive interval, labeling each bag with a with a known failure as positive, and bags without known failures as negative, where a bag is a set of feature vectors and an associated label, where each feature vector is an n-tuple of features, transforming (44) the multiple instance learning bags into a standard classification task form, selecting (45) a subset of features from the plurality of features, and training (46) a failure prediction model using the selected subset of features.

Abstract: A method for identifying a plurality of patterns of events from within event log file data includes receiving a query comprising a plurality of patterns, each of the patterns comprising a plurality of events. One or more key events is determined from the plurality of patterns of events. The one or more key events is located within a database of stored event log file data. An event stream comprising the key events and all other events of the event log file data occurring within a predetermined time span from the time of the located one or more events is generated. Each of the plurality of patterns of the received query are searched for from within the event stream.

Abstract: A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT), echocardiography, or magnetic resonance (MR) image data of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A multi-component patient specific anatomical heart model is generated by integrating the individual models for each of the heart components. Fluid Structure Interaction (FSI) simulations are performed on the patient specific anatomical model, and patient specific clinical parameters are extracted based on the patient specific heart model and the FSI simulations. Disease progression modeling and risk stratification are performed based on the patient specific clinical parameters.

Abstract: A method for identifying a plurality of patterns of events from within event log file data includes receiving a query comprising a plurality of patterns, each of the patterns comprising a plurality of events. One or more key events is determined from the plurality of patterns of events. The one or more key events is located within a database of stored event log file data. An event stream comprising the key events and all other events of the event log file data occurring within a predetermined time span from the time of the located one or more events is generated. Each of the plurality of patterns of the received query are searched for from within the event stream.

Abstract: An approach is provided for condition monitoring from log messages and sensor trends based on time semi-intervals. The approach may be applied to machine condition monitoring. Patterns are mined from symbolic interval data that extends previous approaches by allowing semi-intervals and partially ordered patterns. The semi-interval patterns and semi-interval partial order patterns are less restrictive than patterns using Allen's relations. Combinations and adaptations of efficient algorithms from sequential pattern and itemset mining for discovery of semi-interval patterns are described.

Abstract: An approach is provided for condition monitoring from log messages and sensor trends based on time semi-intervals. The approach may be applied to machine condition monitoring. Patterns are mined from symbolic interval data that extends previous approaches by allowing semi-intervals and partially ordered patterns. The semi-interval patterns and semi-interval partial order patterns are less restrictive than patterns using Allen's relations. Combinations and adaptations of efficient algorithms from sequential pattern and itemset mining for discovery of semi-interval patterns are described.

Abstract: A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT), echocardiography, or magnetic resonance (MR) image data of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A multi-component patient specific anatomical heart model is generated by integrating the individual models for each of the heart components. Fluid Structure Interaction (FSI) simulations are performed on the patient specific anatomical model, and patient specific clinical parameters are extracted based on the patient specific heart model and the FSI simulations. Disease progression modeling and risk stratification are performed based on the patient specific clinical parameters.