Abstract: Embodiments for ensemble policy generation for prediction systems by a processor. Policies are generated and/or derived for a set of ensemble models to predict a plurality of target variables for streaming data such that the plurality of policies enables dynamic adjustment of the prediction system. One or more of the policies are updated according to one or more error states of the set of ensemble models.

Abstract: The technology includes an example method for determining matching items. In some implementations, the method may determine a first set and second set of attributes and attribute types associated with a first and second item, respectively, based on description data associated with the items. The method may determine an attribute-type indicator for a pairing of a first attribute of the first set with a second attribute of the second set based on attribute types of the attributes, compute an attribute value for the pairing based on a similarity between the first and second attribute, and compute a match score for a combination of the first and second items based on the attribute value and attribute-type indicator. The method may also, in response to receiving a data query identifying the first item, provide a graphical user interface including a graphical element representing the second item based on the match score.

Abstract: Embodiments for self-managed adaptable models for prediction systems by one or more processors. One or more adaptive models may be applied to data streams from a plurality of data sources according to one or more data recipes such that the one or more adaptive models predict a plurality of target variables.

Abstract: An aspect of providing job assignment optimization includes creating a feature vector from features extracted from a new job request. Each of the features is associated with a constraint on minimum requirements with respect to a level of experience of a potential candidate. An aspect further includes creating a feature vector for each employee that includes skills attributed to the employee and instances that each of the skills have been completed, searching feature vectors generated from the employee database for the minimum requirements indicated in the new job request feature vector, searching the feature vectors of the database for the minimum requirements indicated by constraints associated with the new job request, modeling aggregate utility of past experience of employees as a weighted sum of applied utility functions, and generating a score indicating a difference between a potential post assignment and a pre-assignment utility. An aspect also includes outputting qualified candidates.

Abstract: A method for forecasting time delays added to a scheduled start time and a scheduled end time of a task includes generating a stochastic model of the task and resources affecting the task, the stochastic model includes a reactionary delay component that is a function of previous task end times and a root cause delay component that is an independent random process at a specific time. The method further includes: calculating a probability distribution of time delays added to the scheduled start time as a combination of the reactionary delay component and the root cause delay component using the stochastic model to provide a probability distribution of start times; and calculating a probability distribution of time delays added to the scheduled end time as a combination of the reactionary delay component and the root cause delay component using the stochastic model to provide a probability distribution of end times.

Abstract: A method for forecasting time delays added to a scheduled start time and a scheduled end time of a task includes generating a stochastic model of the task and resources affecting the task, the stochastic model includes a reactionary delay component that is a function of previous task end times and a root cause delay component that is an independent random process at a specific time. The method further includes: calculating a probability distribution of time delays added to the scheduled start time as a combination of the reactionary delay component and the root cause delay component using the stochastic model to provide a probability distribution of start times; and calculating a probability distribution of time delays added to the scheduled end time as a combination of the reactionary delay component and the root cause delay component using the stochastic model to provide a probability distribution of end times.

Abstract: Performing data clustering in a model property vector space. Input data is received comprising a plurality of data instances in a data vector space. A model property vector specification is defined for a model vector. Information is identified from the input data, and a model property vector is created in the model property vector space for each of the plurality of data instances. A target number of clusters is identified and used to perform a data clustering procedure. An output is generated comprising a plurality of data segments and one or more clustering rules. For each data cluster, a predictive model is constructed for each data segment of the plurality of data segments.

Abstract: Charging of a mobile device in an ad hoc parked vehicle charging system. A plurality of mobile device users and associated mobile devices are registered in an ad hoc parked vehicle charging system with a charging profile. A plurality of charging vehicles are also registered in the system with a charge supply profile. A mobile device user and associated mobile device are authenticated as a registered user in the system. A plurality of the registered charging vehicles parked within a preset distance range of the authenticated user and associated mobile device are located and one of the parked registered charging vehicles is selected based on an energy allocation criteria. A charging connection is established between the authenticated mobile device and the selected parked vehicle and charging of the mobile device is automatically controlled according to the user's charging profile, the vehicle's charge supply profile and the energy allocation criteria.

Abstract: Embodiments for driver confidence evaluation while operating a vehicle by a processor. Driver confidence, based upon one or more psychophysical parameters of a driver, is combined and correlated with a plurality of environmental factors and route information. A confidence in vehicular operational capabilities of the driver may be detected according to the correlation.

Abstract: Embodiments for network reconstruction from message data by a processor. A digital map may be created using one or more messages of a plurality of vehicles obtained at a plurality of control points of a route network. The digital map may be analyzed to estimate a feasibility of simultaneous trajectories of the plurality of vehicles between selected locations in the route network.

Abstract: Performing data clustering in a model property vector space. Input data is received comprising a plurality of data instances in a data vector space. A model property vector specification is defined for a model vector. Information is identified from the input data, and a model property vector is created in the model property vector space for each of the plurality of data instances. A target number of clusters is identified and used to perform a data clustering procedure. An output is generated comprising a plurality of data segments and one or more clustering rules. For each data cluster, a predictive model is constructed for each data segment of the plurality of data segments.

Abstract: Embodiments for self-managed adaptable models for prediction systems by one or more processors. One or more adaptive models may be applied to data streams from a plurality of data sources according to one or more data recipes such that the one or more adaptive models predict a plurality of target variables.

Abstract: Charging of a mobile device in an ad hoc parked vehicle charging system. A plurality of mobile device users and associated mobile devices are registered in an ad hoc parked vehicle charging system with a charging profile. A plurality of charging vehicles are also registered in the system with a charge supply profile. A mobile device user and associated mobile device are authenticated as a registered user in the system. A plurality of the registered charging vehicles parked within a preset distance range of the authenticated user and associated mobile device are located and one of the parked registered charging vehicles is selected based on an energy allocation criteria. A charging connection is established between the authenticated mobile device and the selected parked vehicle and charging of the mobile device is automatically controlled according to the user's charging profile, the vehicle's charge supply profile and the energy allocation criteria.

Abstract: A system and method for charging of a mobile device in an ad hoc parked vehicle charging system. A plurality of mobile device users and charging vehicles are registered in the ad hoc parked vehicle charging system. The current charge of an authenticated mobile device user is monitoring and the user is automatically alerted the authenticated user that the current charge is below a threshold set in the user's charging profile. The method includes locating registered charging vehicles parked within a preset distance range of the authenticated user and sending the parked location information to the user, automatically enabling a wireless charging connection between the authenticated user's mobile device and a parked registered charging vehicle selected by the user and automatically controlling charging the authenticated user's mobile device according to the authenticated user's charging profile and the parked registered charging vehicle's charge supply profile.

Abstract: Embodiments for network reconstruction from message data by a processor. A digital map may be created using one or more messages of a plurality of vehicles obtained at a plurality of control points of a route network. The digital map may be analyzed to estimate a feasibility of simultaneous trajectories of the plurality of vehicles between selected locations in the route network.

Abstract: A method for localizing the source of air pollution that includes receiving pollution data from a network in communication with at least one air pollution sensor that is connected to at least one motor vehicle in a stationary position. Each stationary motor vehicle of the network is positioned at a different air pollution measurement location. The method may further include determining from the pollution data an origin of an air pollutant using an air pollution model provided by a pollutant source localization device including at least one hardware processor.

Abstract: Embodiments for driver confidence evaluation while operating a vehicle by a processor. Driver confidence, based upon one or more psychophysical parameters of a driver, is combined and correlated with a plurality of environmental factors and route information. A confidence in vehicular operational capabilities of the driver may be detected according to the correlation.

Abstract: Embodiments for ensemble policy generation for prediction systems by a processor. Policies are generated and/or derived for a set of ensemble models to predict a plurality of target variables for streaming data such that the plurality of policies enables dynamic adjustment of the prediction system. One or more of the policies are updated according to one or more error states of the set of ensemble models.

Abstract: A system and method for charging of a mobile device in an ad hoc parked vehicle charging system. A plurality of mobile device users and charging vehicles are registered in the ad hoc parked vehicle charging system. The current charge of an authenticated mobile device user is monitoring and the user is automatically alerted the authenticated user that the current charge is below a threshold set in the user's charging profile. The method includes locating registered charging vehicles parked within a preset distance range of the authenticated user and sending the parked location information to the user, automatically enabling a wireless charging connection between the authenticated user's mobile device and a parked registered charging vehicle selected by the user and automatically controlling charging the authenticated user's mobile device according to the authenticated user's charging profile and the parked registered charging vehicle's charge supply profile.

Abstract: A system and method for charging of a mobile device in an ad hoc charging system. A plurality of mobile device users are registered in the ad hoc charging system, each with a charging profile. A plurality of charging stations are registered in the ad hoc charging system, each with a charge supply profile. A mobile device user is authenticated as an ad hoc charging system registered user with one of the plurality of registered charging stations, thereby enabling a charging connection between the authenticated user and the one registered charging station. The charging of the authenticated user's mobile device is controlled according to the authenticated user's charging profile and the one registered charging station's charge supply profile. Energy monitoring, movement tracking, energy prediction, user notification and energy allocation features are also included.