- AutorIn
- Philipp Grubitzsch Technische Universität Dresden, Institute of Systems Architecture, Chair of Computer Networks
- Elias WernerTechnische Universität Dresden, Center for Information Services and High Performance Computing (ZIH)
- Daniel MatusekTechnische Universität Dresden, Institute of Systems Architecture, Chair of Computer Networks
- Viktor Stojanov
- Markus Hähnel
- Titel
- AI-Based Transport Mode Recognition for Transportation Planning Utilizing Smartphone Sensor Data From Crowdsensing Campaigns
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-854542
- Konferenz
- International Conference on Intelligent Transportation. Indianapolis, 19.-22. September 2021
- Quellenangabe
- 2021 IEEE International Intelligent Transportation Systems Conference (ITSC)
Erscheinungsort: New York
Verlag: IEEE
Erscheinungsjahr: 2021
Seiten: 1306-1313
ISBN: 978-1-7281-9142-3 - Erstveröffentlichung
- 2021
- Abstract (EN)
- Utilizing smartphone sensor data from crowdsen-sing (CS) campaigns for transportation planning (TP) requires highly reliable transport mode recognition. To address this, we present our RNN-based AI model MovDeep, which works on GPS, accelerometer, magnetometer and gyroscope data. It was trained on 92 hours of labeled data. MovDeep predicts six transportation modes (TM) on one second time windows. A novel postprocessing further improves the prediction results. We present a validation methodology (VM), which simulates unknown context, to get a more realistic estimation of the real-world performance (RWP). We explain why existing work shows overestimated prediction qualities, when they would be used on CS data and why their results are not comparable with each other. With the introduced VM, MovDeep still achieves 99.3 % F1 -Score on six TM. We confirm the very good RWP for our model on unknown context with the Sussex-Huawei Locomotion data set. For future model comparison, both publicly available data sets can be used with our VM. In the end, we compare MovDeep to a deterministic approach as a baseline for an average performing model (82 - 88 % RWP Recall) on a CS data set of 540 k tracks, to show the significant negative impact of even small prediction errors on TP.
- Andere Ausgabe
- Link zum Artikel, der zuerst bei IEEExplore erschienen ist.
DOI: 10.1109/ITSC48978.2021.9564502 - Freie Schlagwörter (DE)
- Ausbildung, Glättungsmethoden, Einschätzung, Transport, Vorhersagemodelle, Datenmodelle, Planung
- Freie Schlagwörter (EN)
- Training, Smoothing methods, Estimation, Transportation, Predictive models, Data models, Planning
- Klassifikation (DDC)
- 004
- Verlag
- IEEE, New York
- Förder- / Projektangaben
- Bundesministerium für Digitales und Verkehr (BMDV)
Movebis
ID: 19F2011B - Version / Begutachtungsstatus
- angenommene Version / Postprint / Autorenversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-854542
- Veröffentlichungsdatum Qucosa
- 11.05.2023
- Dokumenttyp
- Konferenzbeitrag
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis