| Presentation | 2020-01-31 [Poster Presentation] Preliminary study on time series forecasting of road traffic at multiple locations for applying to traffic congestion mitigation with adaptive vehicle speed control Satoshi Watanabe, Ryusei Aiura, Hiroaki Morino, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We previously proposed a method to solve a traffic jam early by carrying out an appropriate speed control of a vehicle running behind congested vehicle platoon at a place where natural traffic congestion is likely to occur, such as the highway sag. In this method, it is important to detect the occurrence of congested vehicle platoon as early as possible by some means. In this paper, we report a basic study on a method to predict the congestion time at a location in real time by time series forecasting using velocity data collected at two locations including the target location and its downstream one. Here, we assume distance between two locations is relatively small (Approximately 1 km). As a prediction technique to deal with multiple time series data, we focus on VAR (Vector Auto-regression model) which is one of the autoregressive models and multivariate LSTM (Long Short Time Memory). Evaluation results using velocity data obtained by traffic flow simulation with actual highway vehicle data show that both methods achieve the same level of prediction accuracy, and that the prediction accuracy is improved in comparison with the case of predicting only from one time series data (In this case, the past time series data of the point to be predicted) using AR model and univariate LSTM. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sag sections / Time series prediction / Machine Learning / VAR / LSTM |
| Paper # | SeMI2019-107 |
| Date of Issue | 2020-01-23 (SeMI) |
| Conference Information | |
| Committee | SeMI |
|---|---|
| Conference Date | 2020/1/30(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Susumu Ishihara(Shizuoka Univ.) |
| Vice Chair | Kazuya Monden(Hitachi) / Koji Yamamoto(Kyoto Univ.) |
| Secretary | Kazuya Monden(Kyoto Univ.) / Koji Yamamoto(NTT DOCOMO) |
| Assistant | Akira Uchiyama(Osaka Univ.) / Kenji Kanai(Waseda Univ.) / Masafumi Hashimoto(Osaka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Poster Presentation] Preliminary study on time series forecasting of road traffic at multiple locations for applying to traffic congestion mitigation with adaptive vehicle speed control |
| Sub Title (in English) | |
| Keyword(1) | Sag sections |
| Keyword(2) | Time series prediction |
| Keyword(3) | Machine Learning |
| Keyword(4) | VAR |
| Keyword(5) | LSTM |
| 1st Author's Name | Satoshi Watanabe |
| 1st Author's Affiliation | Shibaura Institute of Technology(SIT) |
| 2nd Author's Name | Ryusei Aiura |
| 2nd Author's Affiliation | Shibaura Institute of Technology(SIT) |
| 3rd Author's Name | Hiroaki Morino |
| 3rd Author's Affiliation | Shibaura Institute of Technology(SIT) |
| Date | 2020-01-31 |
| Paper # | SeMI2019-107 |
| Volume (vol) | vol.119 |
| Number (no) | SeMI-406 |
| Page | pp.pp.43-44(SeMI), |
| #Pages | 2 |
| Date of Issue | 2020-01-23 (SeMI) |