Abstract: A system, method and program product for implementing a sketch-based retrieval system. A system is disclosed that includes: an interface having a canvas for entering inputs including user generated strokes, and extracting features associated with the inputs; a hierarchy system for assigning an importance to the inputs; a matching system for retrieving matches from a database based on extracted features and importance associated with the extracted features; a feedback system that provides real-time feedback on the canvas to suggest improved inputs for the user; and a ranking system that ranks retrieved matches for output in the interface by incorporating user interaction history.

Abstract: A system, method and program product for implementing a sketch-based retrieval system. A system is disclosed that includes: an interface having a canvas for entering inputs including user generated strokes, and extracting features associated with the inputs; a hierarchy system for assigning an importance to the inputs; a matching system for retrieving matches from a database based on extracted features and importance associated with the extracted features; a feedback system that provides real-time feedback on the canvas to suggest improved inputs for the user; and a ranking system that ranks retrieved matches for output in the interface by incorporating user interaction history.

Abstract: A method for processing an attempted payment made using a mobile device includes receiving information about the attempted payment, receiving data indicative of a behavior of a user of the mobile device at the time of the attempted payment, computing a likelihood that the attempted payment is fraudulent, based on a comparison of the behavior of the user to an historical behavior pattern of the user, and sending an instruction indicating how to proceed with the attempted payment, based on the likelihood.

Abstract: Methods, systems, and computer program products for recommending activity sensor usage by image processing are provided herein. A computer-implemented method includes identifying, based on (i) sensor data from one or more sensors during a user activity and (ii) video data associated with the user performing the user activity, positioning of the one or more sensors with respect to the user; identifying the user activity being performed based on the video data; assessing data quality for the sensor data based on (i) the identified positioning of the one or more sensors and (ii) the identified user activity; and generating a recommendation for re-positioning at least one of the one or more sensors based on (i) the assessing and (ii) historical data pertaining to sensor data associated with the identified user activity.

Abstract: A method for processing an attempted payment made using a mobile device includes receiving information about the attempted payment, receiving data indicative of a behavior of a user of the mobile device at the time of the attempted payment, computing a likelihood that the attempted payment is fraudulent, based on a comparison of the behavior of the user to an historical behavior pattern of the user, and sending an instruction indicating how to proceed with the attempted payment, based on the likelihood.

Abstract: A notification including one or more policies of use of one or more devices in an environment is received. The one or more policies are generated based on a pattern of use detected based on interaction data obtained by one or more sensors in the environment. Operation of one or more functionalities in the one or more devices is adjusted based on the one or more policies.

Abstract: A computer-implemented method, an interruption management system and computer program product automatically determine when a user should not be interrupted in a collaborative work. An event is determined to be occurring. Physiological data of the user is captured. Complex task steps of the event are identified. When the user is determined to be performing a complex task step and the physiological data of the user is determined to be an outlier, a notification indicating that the user should not be interrupted is output to an interruptor indicator. The captured physiological data may include eye dilation, skin conductance, heart rate, eye tracking, glomerular filtration rate and skin temperature. The event may be pair programming, software support, hardware support, medical surgery, human-robot interaction or command center operation. The physiological data is determined to be an outlier using standard deviation. The notification is output as a visual indicator.

Abstract: A system, method and program product for implementing a sketch-based retrieval system. A system is disclosed that includes: an interface having a canvas for entering inputs including user generated strokes, and extracting features associated with the inputs; a hierarchy system for assigning an importance to the inputs; a matching system for retrieving matches from a database based on extracted features and importance associated with the extracted features; a feedback system that provides real-time feedback on the canvas to suggest improved inputs for the user; and a ranking system that ranks retrieved matches for output in the interface by incorporating user interaction history.

Abstract: A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.

Abstract: A method for identifying seismic horizons in digitized seismic images includes deploying a swarm of agents at an initial position in a seismic image to be analyzed, where the swarm of agents includes picking agents that define a direction for the swarm and averaging agents that smooth the direction of the swarm, identifying a direction to follow in the seismic image for each picking agent, and advancing each picking agent in the identified direction, and averaging, by the averaging agents, the directions identified by the picking agents, wherein if an information concentration measured by a picking agent at a current time step is greater than a previous time step, the picking agent keeps a previous direction, otherwise the picking agent changes direction according to the average current state of the set of averaging agents within its neighborhood.

Abstract: A system including at least one first sensor coupled to a tool, the at least one first sensor outputting data about an operation of the tool, at least one second sensor, the at least one second sensor outputting physiological data of a worker operating the tool, at least one environmental sensor outputting data about an environment of the worker operating the tool, a database device storing patterns including historic data of the operation of the tool, historic data of the physiological data in connection with operation of the tool and historic data of the environment of the worker, and a processor comparing the data about the operation of the tool, the physiological data of a worker operating the tool and the data about the environment of the worker operating the tool to the database of patterns, the processor detecting at least one anomaly and generating at least one alert.

Abstract: A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.

Abstract: A system, method and program product for a query-based interface in a cognitive computing platform. A system is provided that includes a query processor that inputs a query for an identified user and determines a set of results for inclusion in a cognitive response based on a set of information sources; a modality selection system that selects an interface modality for the cognitive response based on user profile data and at least one external input; and a response formatting system that determines a response format for the set of results in the cognitive response, wherein the response format is determined based on confidence levels determined from social networking information associated with the identified user.

Abstract: Interaction data from one or more sensors in an environment are obtained. One or more patterns of use of one or more devices in the environment based on the interaction data are detected. One or more policies of use of the one or more devices in the environment based on the detected pattern are generated. A notification of the one or more policies is provided in the environment.

Abstract: A notification including one or more policies of use of one or more devices in an environment is received. The one or more policies are generated based on a pattern of use detected based on interaction data obtained by one or more sensors in the environment. Operation of one or more functionalities in the one or more devices is adjusted based on the one or more policies.

Abstract: A user guided data mining system includes: a database storing a network graph comprising a plurality nodes and edges, node attributes for the nodes, and edge attributes for the edges; and a data mining module configured to: request feedback from a user indicating at least one of the node attributes, visualize the network graph considering the indicated attributes, request feedback from the user indicating a part of the visualized network graph and a class of graph mining algorithm, and rank a plurality of different graph mining algorithms of the indicated class based on the indicated part.

Abstract: A system for managing items. The system includes a sensor for identifying a first physical object and a second physical object in a building. A computer interface in communication with the sensor is configured to receive a first identification of the first physical object and a second identification of the second physical object. A computer with at least one central processing unit is configured to automatically search for trend information about the first physical object, determine a first interaction between the first physical object and the second physical object based on the first identification of the first physical object and the second identification of the second physical object, and recommend disposition of the first physical object based on the first interaction between the first physical object and the second physical object, and the trend information about the first physical object.

Abstract: Interaction data from one or more sensors in an environment are obtained. One or more patterns of use of one or more devices in the environment based on the interaction data are detected. One or more policies of use of the one or more devices in the environment based on the detected pattern are generated. A notification of the one or more policies is provided in the environment.

Abstract: A method for processing an attempted payment made using a mobile device includes receiving information about the attempted payment, receiving data indicative of a behavior of a user of the mobile device at the time of the attempted payment, computing a likelihood that the attempted payment is fraudulent, based on a comparison of the behavior of the user to an historical behavior pattern of the user, and sending an instruction indicating how to proceed with the attempted payment, based on the likelihood.

Abstract: A method for indexing a user interface test recording includes capturing, during a session, a recording of a plurality of interactions with the user interface, capturing, during the session, an event stream including a plurality of user interface events, synchronizing, in time, the plurality of interactions and the plurality of user interface events, identifying a point of interest in the event stream, wherein the point of interest is correlated to a time in the recording by the synchronization, and annotating the recording at a time correlated to when the point of interest occurred.