International Business Machines Corporation

Bradley Eck

Vincent Lonij

Sergiy Zhuk

Francesco Fusco

Pascal Pompey

Amadou Ba

Seshu Tirupathi

Akihiro Kishimoto

Thanh Lam Hoang

Ngoc Minh Tran

Joe Naoum-Sawaya

Albert Akhriev

Bissan Ghaddar

Mark Purcell

Tuan Dinh

Robert Gormally

A computer-implemented method, a computer program product, and a computer system for selecting predictions by models. A computer receives a request for a forecast of a dependent variable in a time domain, where the time domain includes first time periods that have normal labels due to normal predictor variable data and second time periods that have anomalous labels due to anomalous predictor variable data. The computer retrieves accuracy scores and robustness scores of models, where the accuracy scores indicate forecasting accuracy in the first time periods and the robustness scores indicate forecasting accuracy in the second time periods. For predictions in the first time period, the computer selects dependent variable values predicted by a first model that has highest values of the accuracy scores. For predictions in the second time periods, the computer selects dependent variable values predicted by a second model that has highest values of the robustness scores.

Selecting forecasting models by machine learning based on analysis of model robustness

Embodiments for intelligent unsupervised learning of visual alphabets by one or more processors are described. A visual three-dimensional (3D) alphabet may be learned from one or more images using a machine learning operations. A set of 3D primitives representing the visual 3D alphabet may be provided.

Unsupervised learning of three dimensional visual alphabet

A method for estimating a fluid flow velocity may include receiving, with a processing device, a plurality of observations corresponding to a concentration of a constituent of a flowing fluid mixture, and computing a final estimate of an average velocity of the flowing fluid mixture based at least in part on the observations, wherein the constituent is undergoing a chemical reaction and the computing implements a reactive transport model.

Computer based fluid flow velocity estimation from concentrations of a reacting constituent for products and services

Techniques that facilitate semantic and time series analysis using machine learning are provided. In one example, a system includes a data analysis component, a prediction component and a learning component. The data analysis component that establishes one or more relationships between one or more elements of semantic data, including one or more time series identifiers, and one or more elements of time series data in a relationship database. The prediction component generates one or more advisory outputs, wherein generation of the one or more advisory outputs is performed in response to a trigger event. A learning component that determines the one or more relationships in the relationship database, wherein determination of the one or more relationships is based on information indicative of whether the advisory outputs satisfy a defined criterion.

Machine learning for time series using semantic and time series data

Techniques that facilitate semantic and time series analysis using machine learning are provided. In one example, a system includes a data analysis component, a prediction component and a learning component. The data analysis component that establishes one or more relationships between one or more elements of semantic data, including one or more time series identifiers, and one or more elements of time series data in a relationship database. The prediction component generates one or more advisory outputs, wherein generation of the one or more advisory outputs is performed in response to a trigger event, a learning component that determines the one or more relationships in the relationship database, wherein determination of the one or more relationships is based on information indicative of whether the advisory outputs satisfy a defined criterion.

A sensor data fusion system includes a processor coupled to a plurality of sensors. The system is initialized by providing access to a data store storing at least one time series of sensor data; a semantic store storing semantic data including system variables, and relations between the system variables; and a mapping therebetween. A registration of a set of one or more variables of interest for which appropriate data is not available is obtained. An initially empty inference model is extended with the set of variables, to obtain an extended model. A request to observe a given one of the set of variables at a given timestamp is obtained. Responsive thereto, time series data for the set of registered variables is retrieved. The extended model is run with the retrieved data to obtain an estimate of the given one of the variables at the given timestamp.

Composable time-series observability in sensor data fusion

A social network platform and method thereof for providing Internet of Things (I-o-T) devices with social behavior for communicating natural language (NL) text messages. An I-o-T device is provided with a social device application to form a unit capable of: reading free form NL messages, and responsively perform an action. The social device application generates NL text in response to reading a text message and/or in response to receiving readings from a set of sensors. Types of messages generated include messages for initiating social relationships with other devices which may communicate an acceptance/declination. The platform may be centralized with a server for ranking the importance of read messages based on the relationships and addressing NL text messages to other social units or groups of social units based on the relationships. The platform further enables direct messaging between social unit devices, brokering trust, and moderating information flow between devices.

Cognitive device-to-device interaction and human-device interaction based on social networks

An apparatus, method and computer program product for scheduling on/off control of equipment. The method implements an iterative approach that uses one objective and sets a tolerance value on the other objectives. Initially, the method computes the value of the different objective functions given a current feasible solution. The different objective functions are iteratively evaluated with respect to the current solution and a margin is set for every objective at each iteration. The margin is a deviation measure indicating the acceptable range by which each objective can be worsened. The method iteratively optimizes each objective function with respect to one of the objectives, following an order, while enforcing a maximum deviation on the other objective functions by setting them as constraints. The allowable deviation margin is then decreased for all the objective functions. A final output schedule is provided from which signals may be generated to automatically turn on/off the equipment.

Growing community of inventors

Carpenterstown, Ireland

Bradley Eck