ADAMS: Data Archiving and Mining System for Transit Service Improvements
infrastructure - vehicle, planning - service improvement, planning - service quality, organisation - management, mode - mass transit
Vehicle locating systems, Transit, Software, Service quality, Quality of service, Public transit, Passenger service quality, Operational efficiency, Mass transit, Local transit, Data mining, Data management, Data collection, Data archiving, Data acquisition, AVL, Automatic vehicle location, Automatic passenger counting, Automatic location systems, Automatic fare collection
Business intelligence strategies, like data mining and analysis, can be used in public transportation to efficiently address various transit planning, scheduling, and operational issues. With the use of data mining and analysis technology, the ADAMS (APTS Data Archiving and Mining System) software was developed and implemented as part of the Research for Advanced Public Transit Systems (RAPTS) program. ADAMS contributes valuable knowledge for any transportation agency implementing advanced system technologies. ADAMS also is an effective tool for improving on-time performance, predicting possible results based on histogram data sets, and enhancing the amount and quality of data available for planning and operational analysis. A technology overview is given for data use in data mining and reporting for three primary APTS technologies: automatic passenger counters, automatic vehicle location, and electronic fare collection systems. Also described are the methodologies used to set up data management, data mining, reporting services, and performance measures. New software technology, which is able to process large amounts of data, is applied to implement the system. Results from this research promise to help improve operational efficiencies and quality of service.
Cevallos, Fabian, Wang, Xiaobo, (2008). ADAMS: Data Archiving and Mining System for Transit Service Improvements. Transportation Research Record: Journal of the Transportation Research Board, 2063, pp 43-51.