Jardin, Philippe ; Moisidis, Ioannis ; Kartal, Kürsat ; Rinderknecht, Stephan (2022)
Adaptive Driving Style Classification through Transfer Learning with Synthetic Oversampling.
In: Vehicles, 4 (4)
doi: 10.3390/vehicles4040069
Artikel, Bibliographie

Kurzbeschreibung (Abstract)

Driving style classification does not only depend on objective measures such as vehicle speed or acceleration, but is also highly subjective as drivers come with their own definition. From our perspective, the successful implementation of driving style classification in real-world applications requires an adaptive approach that is tuned to each driver individually. Within this work, we propose a transfer learning framework for driving style classification in which we use a previously developed rule-based algorithm for the initialization of the neural network weights and train on limited data. Therefore, we applied various state-of-the-art machine learning methods to ensure robust training. First, we performed heuristic-based feature engineering to enhance generalized feature building in the first layer. We then calibrated our network to be able to use its output as a probabilistic metric and to only give predictions above a predefined neural network confidence. To increase the robustness of the transfer learning in early increments, we used a synthetic oversampling technique. We then performed a holistic hyperparameter optimization in the form of a random grid search, which incorporated the entire learning framework from pretraining to incremental adaption. The final algorithm was then evaluated based on the data of predefined synthetic drivers. Our results showed that, by integrating these various methods, high system-level performance and robustness were met with as little as three new training and validation data samples in each increment.

Typ des Eintrags:	Artikel
Erschienen:	2022
Autor(en):	Jardin, Philippe ; Moisidis, Ioannis ; Kartal, Kürsat ; Rinderknecht, Stephan
Art des Eintrags:	Bibliographie
Titel:	Adaptive Driving Style Classification through Transfer Learning with Synthetic Oversampling
Sprache:	Englisch
Publikationsjahr:	2022
Ort:	Darmstadt
Verlag:	MDPI
Titel der Zeitschrift, Zeitung oder Schriftenreihe:	Vehicles
Jahrgang/Volume einer Zeitschrift:	4
(Heft-)Nummer:	4
DOI:	10.3390/vehicles4040069
Zugehörige Links:	TUprints Zweitveröffentlichung
Kurzbeschreibung (Abstract):	Driving style classification does not only depend on objective measures such as vehicle speed or acceleration, but is also highly subjective as drivers come with their own definition. From our perspective, the successful implementation of driving style classification in real-world applications requires an adaptive approach that is tuned to each driver individually. Within this work, we propose a transfer learning framework for driving style classification in which we use a previously developed rule-based algorithm for the initialization of the neural network weights and train on limited data. Therefore, we applied various state-of-the-art machine learning methods to ensure robust training. First, we performed heuristic-based feature engineering to enhance generalized feature building in the first layer. We then calibrated our network to be able to use its output as a probabilistic metric and to only give predictions above a predefined neural network confidence. To increase the robustness of the transfer learning in early increments, we used a synthetic oversampling technique. We then performed a holistic hyperparameter optimization in the form of a random grid search, which incorporated the entire learning framework from pretraining to incremental adaption. The final algorithm was then evaluated based on the data of predefined synthetic drivers. Our results showed that, by integrating these various methods, high system-level performance and robustness were met with as little as three new training and validation data samples in each increment.
Freie Schlagworte:	driving style classification, transfer learning, oversampling, feature engineering, individual adaption
Zusätzliche Informationen:	This article belongs to the Special Issue Driver-Vehicle Automation Collaboration
Sachgruppe der Dewey Dezimalklassifikatin (DDC):	600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau
Fachbereich(e)/-gebiet(e):	16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Institut für Mechatronische Systeme im Maschinenbau (IMS)
Hinterlegungsdatum:	02 Aug 2024 12:46
Letzte Änderung:	02 Aug 2024 12:46
PPN:
Export:	T2T_XMLEndNoteEP3 XMLHTML CitationAtomSimple MetadataBibTeXRDF+XMLMODSMultiline CSVDublin CoreJSONASCII CitationIBW_RDA
Suche nach Titel in:	TUfind oder in Google

Verfügbare Versionen dieses Eintrags

• Adaptive Driving Style Classification through Transfer Learning with Synthetic Oversampling. (deposited 19 Dez 2022 12:30)
  • Adaptive Driving Style Classification through Transfer Learning with Synthetic Oversampling. (deposited 02 Aug 2024 12:46) [Gegenwärtig angezeigt]

Frage zum Eintrag

Optionen (nur für Redakteure)

Redaktionelle Details anzeigen