| Presentation | 2022-12-13 Learning-based human flow estimation using Wi-Fi access data Yuki Sakurai, Shingo Ata, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | People flow analysis, which visualizes and analyzes the movement and/or stay of people in various locations, is attracting attention. As a method to analyze people flow without human intervention, wireless sensing of mobile terminals owned by people via Wi-Fi or Bluetooth has been considered. However, in recent years, from the viewpoint of privacy protection, there has been concern about identifying individuals from their behavioral history through connections based on the physical addresses of wireless terminals. In addition, due to the anonymization of physical addresses in operating systems, it is not easy to use this method directly for people flow estimation. In this paper, we propose a learning-based algorithm to estimate people flow from the history of observed number of persons at a certain point in time, using training data that maps time-series data of the number of persons based on Wi-Fi connection information to the number of movements per unit of time. We also verify the effectiveness of the proposed method using log data from the campus-wide Wi-Fi service. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Wi-Fi / people flow grasp / regression analysis / people flow estimation / machine learning |
| Paper # | IN2022-48 |
| Date of Issue | 2022-12-05 (IN) |
| Conference Information | |
| Committee | IN / IA |
|---|---|
| Conference Date | 2022/12/12(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Higashi-Senda campus, Hiroshima Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Performance Analysis and Simulation, Robustness, Traffic and Throughput Measurement, Quality of Service (QoS) Control, Congestion Control, Overlay Network/P2P, IPv6, Multicast, Routing, DDoS, etc. |
| Chair | Kunio Hato(Internet Multifeed) / Tomoki Yoshihisa(Osaka Univ.) |
| Vice Chair | Tsutomu Murase(Nagoya Univ.) / Yusuke Sakumoto(Kwansei Gakuin Univ.) / Yuichiro Hei(KDDI Research) / Hiroshi Yamamoto(Ritsumeikan Univ.) |
| Secretary | Tsutomu Murase(KDDI Research) / Yusuke Sakumoto(Nagaoka Univ. of Tech.) / Yuichiro Hei(NTT) / Hiroshi Yamamoto(NTT) |
| Assistant | / Daisuke Kotani(Kyoto Univ.) / Ryo Nakamura(Fukuoka Univ.) / Ryo Nakamura(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Internet Architecture |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Learning-based human flow estimation using Wi-Fi access data |
| Sub Title (in English) | |
| Keyword(1) | Wi-Fi |
| Keyword(2) | people flow grasp |
| Keyword(3) | regression analysis |
| Keyword(4) | people flow estimation |
| Keyword(5) | machine learning |
| 1st Author's Name | Yuki Sakurai |
| 1st Author's Affiliation | Osaka Metropolitan University(Osaka Metropolitan Univ.) |
| 2nd Author's Name | Shingo Ata |
| 2nd Author's Affiliation | Osaka Metropolitan University(Osaka Metropolitan Univ.) |
| Date | 2022-12-13 |
| Paper # | IN2022-48 |
| Volume (vol) | vol.122 |
| Number (no) | IN-305 |
| Page | pp.pp.26-31(IN), |
| #Pages | 6 |
| Date of Issue | 2022-12-05 (IN) |