TY - GEN
T1 - Multiclass Classification of Driver Perceived Workload Using Long Short-Term Memory based Recurrent Neural Network
AU - Manawadu, Udara E.
AU - Kawano, Takahiro
AU - Murata, Shingo
AU - Kamezaki, Mitsuhiro
AU - Muramatsu, Junya
AU - Sugano, Shigeki
N1 - Funding Information:
ACKNOWLEDGMENTS This research was supported by Toyota Motor Corporation, MEXT Japan, PRESTO JST and by the Research Institute for Science and Engineering, Waseda University.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/18
Y1 - 2018/10/18
N2 - Human sensing enables intelligent vehicles to provide driver-adaptive support by classifying perceived workload into multiple levels. Objective of this study is to classify driver workload associated with traffic complexity into five levels. We conducted driving experiments in systematically varied traffic complexity levels in a simulator. We recorded driver physiological signals including electrocardiography, electrodermal activity, and electroencephalography. In addition, we integrated driver performance and subjective workload measures. Deep learning based models outperform statistical machine learning methods when dealing with dynamic time-series data with variable sequence lengths. We show that our long short-term memory based recurrent neural network model can classify driver perceived-workload into five classes with an accuracy of 74.5%. Since perceived workload differ between individual drivers for the same traffic situation, our results further highlight the significance of including driver characteristics such as driving style and workload sensitivity to achieve higher classification accuracy.
AB - Human sensing enables intelligent vehicles to provide driver-adaptive support by classifying perceived workload into multiple levels. Objective of this study is to classify driver workload associated with traffic complexity into five levels. We conducted driving experiments in systematically varied traffic complexity levels in a simulator. We recorded driver physiological signals including electrocardiography, electrodermal activity, and electroencephalography. In addition, we integrated driver performance and subjective workload measures. Deep learning based models outperform statistical machine learning methods when dealing with dynamic time-series data with variable sequence lengths. We show that our long short-term memory based recurrent neural network model can classify driver perceived-workload into five classes with an accuracy of 74.5%. Since perceived workload differ between individual drivers for the same traffic situation, our results further highlight the significance of including driver characteristics such as driving style and workload sensitivity to achieve higher classification accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85056765504&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056765504&partnerID=8YFLogxK
U2 - 10.1109/IVS.2018.8500410
DO - 10.1109/IVS.2018.8500410
M3 - Conference contribution
AN - SCOPUS:85056765504
T3 - IEEE Intelligent Vehicles Symposium, Proceedings
SP - 2009
EP - 2014
BT - 2018 IEEE Intelligent Vehicles Symposium, IV 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Intelligent Vehicles Symposium, IV 2018
Y2 - 26 September 2018 through 30 September 2018
ER -