| Presentation | 2022-03-12 A Method and Evaluation of Train Congestion Estimation Using BLE Signals Eigo Taya, Yuji Kanamitsu, Koki Tachibana, Yugo Nakamura, Matsuda Yuki, Suwa Hirohiko, Keiichi Yasumoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Trains play an essential role in transportation in supporting people's lives. In recent years, it has become necessary to estimate the degree of congestion in each train vehicle to prevent the pandemic of COVID-19 and improve passengers' comfort. However, it is difficult to estimate the degree of congestion without violating passengers' privacy. We have developed and evaluated a system to estimate the degree of bus congestion while protecting passengers' privacy by using BLE signals. This paper used the above system to collect BLE signals on a train cooperating with Kintetsu Railway Co., Ltd. The congestion of each train vehicle is then estimated using a machine learning regression model. The results show that the MAE and MAPE can be estimated with an accuracy of 0.56 and 0.27, respectively. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | BLE / Train / Public transportation / Congestion estimation / Machine learning |
| Paper # | AI2021-30 |
| Date of Issue | 2022-03-05 (AI) |
| Conference Information | |
| Committee | AI / JSAI-SAI / JSAI-KBS / JSAI-DOCMAS / IPSJ-ICS |
|---|---|
| Conference Date | 2022/3/12(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | WSSIT2022 |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Social System and Information Technology |
| Chair | Yuichi Sei(Univ. of Electro-Comm.) |
| Vice Chair | Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.) |
| Secretary | Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.) |
| Assistant | Kazutaka Matsuzaki(Chuo Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing / Special Interest Group on Society and Artificial Intelligence / Special Interest Group on Knowledge-Based Systems / Special Interest Group on Data Oriented Constructive Mining and Simulation / Special Interest Group on Intelligence and Complex Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Method and Evaluation of Train Congestion Estimation Using BLE Signals |
| Sub Title (in English) | |
| Keyword(1) | BLE |
| Keyword(2) | Train |
| Keyword(3) | Public transportation |
| Keyword(4) | Congestion estimation |
| Keyword(5) | Machine learning |
| 1st Author's Name | Eigo Taya |
| 1st Author's Affiliation | Nara Institute of Science and Technology/RIKEN Center(NAIST) |
| 2nd Author's Name | Yuji Kanamitsu |
| 2nd Author's Affiliation | Nara Institute of Science and Technology/RIKEN Center(NAIST) |
| 3rd Author's Name | Koki Tachibana |
| 3rd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 4th Author's Name | Yugo Nakamura |
| 4th Author's Affiliation | Kyushu University(QU) |
| 5th Author's Name | Matsuda Yuki |
| 5th Author's Affiliation | Nara Institute of Science and Technology/RIKEN Center/Japan Science and Technology Agency(NAIST/RIKEN/JST PRESTO) |
| 6th Author's Name | Suwa Hirohiko |
| 6th Author's Affiliation | Nara Institute of Science and Technology/RIKEN Center(NAIST/RIKEN) |
| 7th Author's Name | Keiichi Yasumoto |
| 7th Author's Affiliation | Nara Institute of Science and Technology/RIKEN Center(NAIST/RIKEN) |
| Date | 2022-03-12 |
| Paper # | AI2021-30 |
| Volume (vol) | vol.121 |
| Number (no) | AI-439 |
| Page | pp.pp.25-30(AI), |
| #Pages | 6 |
| Date of Issue | 2022-03-05 (AI) |