International Business Machines Corporation

Globalfoundries Inc.

Qing He

Arun Hampapur

Xuan Liu

Songhua Xing

Hongfei Li

Dhaivat P Parikh

Zhiguo Li

Debarun Bhattacharjya

Laura Wynter

Ioannis Kamarianakis

Buyue Qian

Dongping Fang

Klayut Jintanakul

Geo-defect repair modeling is provided. A method includes logically dividing a railroad network according to spatial and temporal dimensions with respect to historical data collected. The spatial dimensions include line segments of a specified length and the temporal dimensions include inspection run data for inspections performed for each of the line segments over a period of time. The method also includes creating a track deterioration model from the historical data, identifying geo-defects occurring at each inspection run from the track deterioration model, calculating a track deterioration condition from the track deterioration model by analyzing quantified changes in the geo-defects measured at each inspection run, and calculating a derailment risk based on track conditions determined from the inspection run data and the track deterioration condition. The method further includes determining a repair decision for each of the geo-defects based on the derailment risk and costs associated with previous comparable repairs.

Railway track geometry defect modeling for predicting deterioration, derailment risk, and optimal repair

Predicting operational changes in a multi-detector environment includes generating, via a computer processing device, a factor matrix for each univariate time series data in a set of sparse time series data collected from data sources, identifying a subset of the time series data as a feature selection based on application of a loss function, and generating a predictive model from the subset of the time series data.

Large-scale multi-detector predictive modeling

Embodiments relate to traffic control resource planning. An aspect includes receiving information about available routes in a transportation network and receiving an estimate of a traffic demand in the transportation network. Traffic control planning is performed and it may include: simulating a traffic flow based on the available routes and the traffic demand; applying a model that varies traffic control agent (TCA) placement and traffic signal settings in the transportation network to minimize a cost associated with the traffic flow, the cost including a TCA deployment cost and a traffic delay cost; and outputting a traffic control plan based on the applying, the traffic control plan including a TCA placement and traffic signal setting plan.

Traffic control agency deployment and signal optimization for event planning

A method is provided to generate a heat map to show traffic congestion based on transit points. The method includes generating, by a processing device, a trajectory database from time-stamped global positioning system (GPS) sample points, and computing transit points for each trajectory in the trajectory database. The method further includes constructing a temporal transit graph. The transit graph captures the shortest paths among the transit points. The method further includes indexing and storing the transit graph in a spatial-temporal database for online analytic processing.

Mining trajectory for spatial temporal analytics

An aspect of an online learning system includes collecting data, via a computer processing device, from a plurality of data sources including multiple disparate detectors, the data including at least one of historical alarm data, failures, maintenance records, and environment observations. The data is stored in tables each corresponding to a subject of measurement. The online learning system also includes identifying common fields shared across the tables, merging at least a portion of the data across the tables having the common fields, and creating an integrated data model based on results of the merging.

Online learning using information fusion for equipment predictive maintenance in railway operations

Embodiments relate to traffic impact prediction in a transportation network. Link level background traffic demand in a transportation network may be estimated based on information about available routes, and based on expected background traffic volumes between origins and destinations. A background traffic flow model that optimizes a background flow of the expected background traffic volumes among the available routes to minimize a sum of background congestion costs, background path entropy, and errors between an observed background traffic flow and the optimized background flow may be applied. Alternative routes may be identified based on the available routes and event based control plans. Expected additional event based traffic volumes may be received. A link level total traffic demand in the transportation network may be estimated based on the expected additional event based traffic volumes, the identified alternative routes, and the estimated background traffic demand.

Traffic impact prediction for multiple event planning

A method, an apparatus and an article of manufacture for incident duration prediction. The method includes obtaining incident data for at least one traffic-related incident in a selected geographic area, obtaining traffic data for the selected geographic area, spatially and temporally associating the at least one traffic-related incident with the traffic data to generate incident duration data for the at least one traffic-related incident, and predicting incident duration of at least one additional traffic-related incident based on the incident duration data for the at least one traffic-related incident.

Growing community of inventors

East Amherst, NY, United States of America

Qing He