|
|||||
|
|
Optimal placement of omnidirectional sensors in a transportation network for effective emergency response and crash characterization |
|
| Affiliation: | 1. Department of Industrial and Systems Engineering, University at Buffalo (SUNY), Buffalo, NY, United States;2. Center for Transportation Injury Research, CUBRC, Buffalo, NY, United States;1. Mobile & Internet Systems Laboratory, Department of Computer Science, University College Cork, Ireland;2. Cork Constraint Computation Centre, Department of Computer Science, University College Cork, Ireland;1. National ICT for Australia (NICTA), School of Computer Science, RMIT University, Melbourne VIC 3001, Australia;2. University of Oklahoma, School of Computer Science, University of Oklahoma, Norman, OK 73019-6151, United States;1. The Hong Kong Polytechnic University, Department of Building Services Engineering, Hong Kong, China;2. University of Toulouse, INSA, 135 Avenue de Rangueil, 31077 Toulouse, France;3. Duke University, Department of Mechanical Engineering and Materials Science, Durham, NC 27708-0300, USA;1. School of Business, Macau University of Science and Technology, Macau, China;2. Department of Management, Bar Ilan University, Ramat Gan, Israel;3. School of Economics, Ashkelon Academic College, Ashkelon, Israel;4. Faculty of Business, The Hong Kong Polytechnic University, Hong Kong, China |
| Abstract: | Rapid motor vehicle crash detection and characterization is possible through the use of Intelligent Transportation Systems (ITS) and sensors are an integral part of any ITS system. The major focus of this paper is on developing optimal placement of accident detecting omnidirectional sensors to maximize incident detection capabilities and provide ample opportunities for data fusion and crash characterization. Both omnidirectional sensors (placed in suitable infrastructure locations) and mobile sensors are part of our analysis. The surrogates used are acoustic sensors (omnidirectional) and Advanced Automated Crash Notification (AACN) sensors (mobile). This data fusion rich placement is achieved through a hybrid optimization model comprising of an explicit–implicit coverage model followed by an evaluation and local search optimization using simulation. The compound explicit–implicit model delivers good initial solutions and improves the detection and data fusion capabilities compared to the explicit model alone. The results of the studies conducted quantify the use of a data fusion capable environment in crash detection scenarios, and the simulation tool developed helps a decision maker evaluate sensor placement strategy. |
| Keywords: | Sensor placement Data fusion Simulation Optimization methods |
| 本文献已被 ScienceDirect 等数据库收录！ | |