Sezaki & Nishiyama Laboratory
Institute of Industrial Science / Center for Spatial Information Science in The University of Tokyo
Institute of Industrial Science / Center for Spatial Information Science in The University of Tokyo
Zengyi Han, Hong Duc Nguyen, Shunsuke Aoki, Yuuki Nishiyama, Kaoru Sezaki
MiMoSense: An Open Crowdsensing Platform for Micro-Mobility Inproceedings
In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 1-6, IEEE, 2021.
Abstract | BibTeX | タグ: e-scooter, Micro-Mobility, Mobile Sensing Toolkit | Links:
@inproceedings{ieee_itsc_mimosense,
title = {MiMoSense: An Open Crowdsensing Platform for Micro-Mobility},
author = {Zengyi Han and Hong Duc Nguyen and Shunsuke Aoki and Yuuki Nishiyama and Kaoru Sezaki},
url = {https://2021.ieee-itsc.org/},
doi = {10.1109/ITSC48978.2021.9564524},
year = {2021},
date = {2021-09-19},
booktitle = {2021 IEEE International Intelligent Transportation Systems Conference (ITSC)},
pages = {1-6},
publisher = {IEEE},
abstract = {The use of micro-mobility (e.g., bicycle and scooter) and their data for urban sensing and rider assessment is becoming increasingly popular in research. However, different research topics require different sensor setups; no general data collecting tools for the micro-mobility makes the researcher who wishes to collect data has to build their own collecting system from scratch. To this end, we present MiMoSense, an open crowdsensing platform for micro-mobility. MiMoSense consists of two components: (1) MiMoSense server, which is set up on the cloud, and used to manage sensing studies and the collected data for research and sharing. (2) MiMoSense client, uses micro-mobility carrying various sensors and IoT devices to collect multiple kinds of data during traveling. As a reusable open-source software, MiMoSense shifts the researcher's focus from software development to sensing data analysis; it can help researchers quickly develop an extensible platform for collecting micro-mobility's raw sensing data and inferring traveling context. We have evaluated MiMoSense's battery consumption, message latency and discuss its use.},
keywords = {e-scooter, Micro-Mobility, Mobile Sensing Toolkit},
pubstate = {published},
tppubtype = {inproceedings}
}
Hidenaga Ushijima, Shunsuke Aoki, Peng Helinyi, Yuuki Nishiyama, Kaoru Sezaki
An Unsupervised Learning-based Approach for User Mobility Analysis of E-Scooter Sharing Systems Inproceedings
In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), IEEE, 2021.
BibTeX | タグ: data analysis, e-scooter | Links:
@inproceedings{itsc2021_ntf,
title = {An Unsupervised Learning-based Approach for User Mobility Analysis of E-Scooter Sharing Systems},
author = {Hidenaga Ushijima and Shunsuke Aoki and Peng Helinyi and Yuuki Nishiyama and Kaoru Sezaki
},
url = {https://2021.ieee-itsc.org/},
doi = {10.1109/ITSC48978.2021.9564616},
year = {2021},
date = {2021-09-19},
booktitle = {2021 IEEE International Intelligent Transportation Systems Conference (ITSC)},
journal = {2021 IEEE International Conference on Intelligent Transportation - ITSC},
publisher = {IEEE},
keywords = {data analysis, e-scooter},
pubstate = {published},
tppubtype = {inproceedings}
}
牛島秀暢, 青木俊介, 西山勇毅, 瀬崎薫
Non-Negative Tensor Factrization を用いたドックレス型マイクロモビリティの利用形態分類手法の検討 Conference AwardSelf Archive
研究報告高度交通システムとスマートコミュニティ(ITS), 2020-ITS-81 (1), 情報処理学会, 2020, ISSN: 2188-8965.
Abstract | BibTeX | タグ: e-scooter, ITS, Micromobility, Mobility-as-a-Service, 都市コンピューティング | Links:
@conference{ushijima2020_its,
title = {Non-Negative Tensor Factrization を用いたドックレス型マイクロモビリティの利用形態分類手法の検討},
author = {牛島秀暢 and 青木俊介 and 西山勇毅 and 瀬崎薫},
url = {http://id.nii.ac.jp/1001/00204626/
https://www.mcl.iis.u-tokyo.ac.jp/wp-content/uploads/2020/08/ITS81.pdf
},
issn = {2188-8965},
year = {2020},
date = {2020-05-21},
urldate = {2020-05-21},
booktitle = {研究報告高度交通システムとスマートコミュニティ(ITS)},
journal = {研究報告モバイルコンピューティングとパーベイシブシステム (MBL)},
volume = {2020-ITS-81},
number = {1},
pages = {1--8},
publisher = {情報処理学会},
abstract = {交通やインフラ,スマートフォンなどから得られる様々なデータを統合的に利活用し,都市計画の継続的な改善に役立てるという都市コンピューティングが注目されている.都市コンピューティングは少子高齢化と過疎化が進行する日本においても公共インフラを有効活用し都市を維持するためにも有効である.限られた公共インフラを活用するためには人々の移動目的を推定し,交通リソースを最適化する必要があるが,既存の IC カードなどの交通データでは推定粒度に限界があった.こうした状況の中,特定の返却場所を持たないドックレス型のマイクロモビリティが急速に普及している.ドックレス型マイクロモビリティは平均移動距離が 500m 程度と短く,直接目的地に向かうため,より詳細な移動行動が検出可能である.本研究では,マイクロモビリティが都市空間で離散的に分布する点に着目した.そして,細かく単発的な移動行動を大域的に分析することで潜在的な移動パターンがあることを,Non-Negative Tensor Factrization と呼ばれる教師なし学習を用いることで明らかにした.},
keywords = {e-scooter, ITS, Micromobility, Mobility-as-a-Service, 都市コンピューティング},
pubstate = {published},
tppubtype = {conference}
}