Driver Behavior Classification in Electric Vehicles

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/303630
Download file(s):
File Description SizeFormat 
CSE 21-106 Comuni Meszaros.pdf3.26 MBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCOMUNI, FEDERICA-
dc.contributor.authorMÉSZÁROS, CHRISTOPHER-
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.date.accessioned2021-07-06T06:15:23Z-
dc.date.available2021-07-06T06:15:23Z-
dc.date.issued2021sv
dc.date.submitted2020-
dc.identifier.urihttps://hdl.handle.net/20.500.12380/303630-
dc.description.abstractStudies have shown that driving style affects the energy consumption of electric vehicles, with aggressive driving consuming up to 30% more energy than moderate driving. Therefore, modeling of aggressive driving can provide a more precise estimation of the energy consumption and the remaining range of a vehicle. This study proposes driver behavior classification on vehicle-based measurements through several deep learning models: convolutional neural networks, long short-term memory recurrent neural networks, and self-attention models. The networks have been trained on two naturalistic driving datasets: a labeled dataset generated from a test vehicle on-site at Volvo Cars and unlabeled data collected from co-development Volvo Cars vehicles. The latter dataset has been annotated following rules and driving parameters quantifying the aggressiveness of driving style. The implemented models achieve promising results on both datasets, with the one-dimensional convolutional neural network yielding the highest test accuracy throughout experiments. One of our contributions is to use self-attention and deep convolutional neural networks with joint recurrence plots, which are appropriate for longer sequences because they bypass sequential training. The study also explores several active learning techniques such as uncertainty sampling, query by committee, active deep dropout, gradual pseudo labeling, and active learning for time-series data. These techniques showed variable results, with uncertainty sampling performing consistently better than random sampling. This study confirms the effectiveness of machine learning models in classifying driver behavior. It also shows that active learning can considerably decrease the need for training data.sv
dc.language.isoengsv
dc.setspec.uppsokTechnology-
dc.subjectAggressive driver behaviorsv
dc.subjectDriver behavior classificationsv
dc.subjectSelf-attentionsv
dc.subjectRecurrence plotssv
dc.subjectactive learningsv
dc.subjectActive deep dropoutsv
dc.subjectGradual pseudo labelingsv
dc.titleDriver Behavior Classification in Electric Vehiclessv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH-
dc.contributor.examinerHaghir Chehreghani, Morteza-
dc.contributor.supervisorÅkerblom, Niklas-
dc.identifier.coursecodeMPALGsv
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.