International Business Machines Corporation

Eric P Bouillet

Zhen Liu

Anton Viktorovich Riabov

Thanh Lam Hoang

Rahul Nair

Francesco Calabrese

Parijat Dube

Anand Ranganathan

Mark David Feblowitz

Kay Schwendimann Anderson

Dimitrios Pendarakis

Bei Chen

Olivier Verscheure

Joseph Phillip Bigus

Pascal Pompey

Randall Lee Cogill

Alessandra Pascale

Marco Laumanns

John Sheehan

Adi Ionel Botea

Michele Berlingerio

Hanhua Feng

Fabio Pinelli

Mathieu Sinn

William Karol Lynch

Lea A Deleris

Donna Leigh Gresh

Ji W Yoon

Li Feng Zhang

Clea Anne Zolotow

Tedrick Neal Northway

Randy Scott Johnson

Deepak Srinivas Turaga

Nagui Halim

Octavian Udrea

Lisa Amini

Michail Vlachos

David Alson George

Martin Stephenson

Vibhore Kumar

Laurent Sebastien Mignet

Tim Nonner

Bissan Ghaddar

Jacint Szabo

Karol W Lynch

Olivier Versheure

Kuldeep K Nigam

Swati Shah

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.

Ensemble model policy generation for prediction systems

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.

Self-managed adaptable models for prediction systems

Embodiments for targeted learning and recruitment by a processor. Attributes obtained from a user profile are used to identify a user as a potential candidate for performing an activity related to either the recruiting or the learning and providing a customized learning experience with targeted course suggestions for the user.

Targeted learning and recruitment

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.

Predictive model clustering

A diagnosis system for an adaptive signal control system in a network, the diagnosis system including a traffic state identification device configured to estimate a traffic state describing a supply-demand mismatch by identifying a relationship between real time data feed from a sensor and a control strategy of the adaptive signal control system and a network transition model device configured to diagnose the supply-demand mismatch and an evolution of the supply-demand mismatch on a network level based on the relationship and infrastructure data of the network.

Diagnostic system, method, and recording medium for signalized transportation networks

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.

Network map reconstruction from message data

A diagnosis system for an adaptive signal control system in a network, the diagnosis system including a traffic state identification device configured to estimate a traffic state describing a supply-demand mismatch by identifying a relationship between real time data feed from a sensor and a control strategy of said adaptive signal control system and a network transition model device configured to diagnose the supply-demand mismatch and an evolution of the supply-demand mismatch on a network level based on said relationship and infrastructure data of the network.

Embodiments of the disclosure include a method for journey planning including receiving a journey planning request, the journey planning request having an origin and a destination in a transportation network. The method also includes calculating an optimized journey plan by identifying a plurality of routes through the transportation network from the origin to the destination and determining an uncertainty associated with each of the plurality of routes. Calculating an optimized journey plan also includes evaluating a robustness of each of the plurality of routes to the uncertainty associated with each of the plurality of routes and selecting the optimized journey plan based on the journey planning request and the robustness of each of the plurality of routes.

Hedging risk in journey planning

Embodiments of the disclosure include a computer system for journey planning, the computer system includes a journey planning server configured to perform a method. The method includes receiving a journey planning request, the journey planning request having an origin and a destination in a transportation network. The method also includes calculating an optimized journey plan by identifying a plurality of routes through the transportation network from the origin to the destination and determining an uncertainty associated with each of the plurality of routes. Calculating an optimized journey plan also includes evaluating a robustness of each of the plurality of routes to the uncertainty associated with each of the plurality of routes and selecting the optimized journey plan based on the journey planning request and the robustness of each of the plurality of routes.

Embodiments of the disclosure include a method for journey planning including receiving a journey planning request. The request includes an origin and a destination in a transportation network. The method also includes calculating an optimized journey plan based on the journey planning request and a route map corresponding to the transportation network and identifying a potential event in the transportation. The method further includes monitoring the transportation network for the potential event and based on detecting an execution of the potential event, calculating an improved journey plan.

Journey computation with re-planning based on events in a transportation network

Embodiments of the disclosure include a method for providing a consolidated estimated time of arrival in a scheduled transportation system. The method includes receiving at least one of a scheduled time of arrival, a real-time estimated time of arrival and a predictive estimated time of arrival and assigning a weight to each of the scheduled time of arrival, the real-time estimated time of arrival and the predictive estimated time of arrival. The method also includes calculating a confidence level and the consolidated estimated time of arrival based on the weights and the scheduled time of arrival, the real-time estimated time of arrival and the predictive estimated time of arrival.

Estimation of arrival times at transit stops

A method and computer program product for assembling and deploying multi-platform flow based applications. An information processing flow that produces a result is assembled, the information processing flow includes components connected by data links, a component includes software code that describes at least one of an input constraint or an output constraint of the component, and at least two of the components are deployable on different computing platforms. The information processing flow is partitioned into sub-flows, such that for each sub-flow every component in the sub-flow is deployable on the same computing platform. The sub-flows are deployed on their respective computing platforms.

Assembly and deployment of multi-platform flow-based applications

A system and method for workload generation include a processor for identifying a workload model by determining each of a hierarchy for workload generation, time scales for workload generation, and states and transitions at each of the time scales, and defining a parameter by determining each of fields for user specific attributes, application specific attributes, network specific attributes, content specific attributes, and a probability distribution function for each of the attributes; a user level template unit corresponding to a relatively slow time scale in signal communication with the processor; an application level template corresponding to a relatively faster time scale in signal communication with the processor; a stream level template corresponding to a relatively fastest time scale in signal communication with the processor; and a communications adapter in signal communication with the processor for defining a workload generating unit responsive to the template units.

Template-based approach for workload generation

Growing community of inventors

Jersey City, NJ, United States of America

Eric P Bouillet