Deep Learning-Based Real-Time Driver’s Hands-On Detection: A Lightweight Time Series Approach Using CAN Data

Hyunwoo Yu; Seunghun Moon; Sunghoon Jung; Sangyoon Han; Suk-Ju Kang

doi:10.1109/access.2026.3676396

journal article Open Access Jan 01, 2026

Deep Learning-Based Real-Time Driver’s Hands-On Detection: A Lightweight Time Series Approach Using CAN Data

Hyunwoo Yu

Seunghun Moon

Sunghoon Jung

Sangyoon Han Suk-Ju Kang

IEEE Access Vol. 14 pp. 47903-47914 · Institute of Electrical and Electronics Engineers (IEEE)

View at Publisher Save 10.1109/access.2026.3676396

Topics

No keywords indexed for this article. Browse by subject →

References

53

[1]

Ziebinski "Review of advanced driver assistance systems (ADAS)"

[2]

(2021)

[3]

10.1109/itsc.2010.5625043

[4]

10.1109/cdc.2015.7402334

[5]

10.1109/tie.2021.3059537

[6]

10.1109/tits.2019.2956598

[7]

Chia Chieh "Driver fatigue detection using steering grip force"

[8]

10.1016/j.ergon.2021.103083

[9]

10.1109/date.2009.5090790

[10]

10.1109/sas.2016.7479878

[11]

Hollmer "Hands-on detection for steering wheels with neural networks" arXiv:2306.09044 (2023)

[12]

10.7717/peerj-cs.2110

[13]

10.1109/cvprw.2018.00158

[14]

10.1109/fg.2018.00090

[15]

10.1016/j.asoc.2020.106657

[16]

10.1117/1.jei.22.4.041119

[17]

Rangesh "Driver hand localization and grasp analysis: A vision-based real-time approach"

[18]

10.1007/0-8176-4404-0_32

[19]

Xing "The application of controller area network on vehicle"

[20]

10.1145/3696409.3700189

[21]

10.1109/tiv.2021.3122898

[22]

10.1109/icm.2018.8704009

[23]

Yang "Deep convolutional neural networks on multichannel time series for human activity recognition"

[24]

10.1007/s10618-020-00710-y

[25]

Wang "Encoding time series as images for visual inspection and classification using tiled convolutional neural networks"

[26]

10.1117/12.2309486

[27]

10.1109/tcyb.2020.3034755

[28]

Multivariate LSTM-FCNs for time series classification

Fazle Karim, Somshubra Majumdar, Houshang Darabi et al.

Neural Networks 10.1016/j.neunet.2019.04.014

[29]

10.1109/tkde.2022.3186963

[30]

Jaeger "The ‘echo state’ approach to analysing and training recurrent neural networks-with an erratum note" (2001)

[31]

10.1162/neco_a_00297

[32]

10.1109/tnnls.2020.3001377

[33]

10.1109/tnnls.2013.2256797

[34]

Chen "Model metric co-learning for time series classification"

[35]

10.1109/bigdia56350.2022.9874057

[36]

10.1109/tkde.2025.3542799

[37]

10.1007/s10115-020-01437-4

[38]

10.1145/882082.882086

[39]

10.1109/bibm.2018.8621092

[40]

10.1109/tii.2022.3188839

[41]

10.1109/wids-psu57071.2023.00030

[42]

10.3390/s23073610

[43]

10.1109/fpl57034.2022.00070

[44]

10.33093/jetap.2025.7.1.4

[45]

10.1016/j.hcc.2024.100207

[46]

Nie "A time series is worth 64 words: Long-term forecasting with transformers" arXiv:2211.14730 (2022)

[47]

Wu "TimesNet: Temporal 2D-variation modeling for general time series analysis" arXiv:2210.02186 (2022)

[48]

Lin "SegRNN: Segment recurrent neural network for long-term time series forecasting" arXiv:2308.11200 (2023)

[49]

Wang "MICN: Multi-scale local and global context modeling for long-term series forecasting"

[50]

Zhang "Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting"

Showing 50 of 53 references

Metrics

0

Citations

53

References

Details

Published: Jan 01, 2026
Vol/Issue: 14
Pages: 47903-47914
License: View

Authors

H

Hyunwoo Yu

Department of Electronic Engineering, Sogang University, Seoul, South Korea

S

Seunghun Moon

Department of Electronic Engineering, Sogang University, Seoul, South Korea

S

Sunghoon Jung

Department of Electronic Engineering, Sogang University, Seoul, South Korea

S

Sangyoon Han

Vehicle Motion Control Development Team, Hyundai Motor Company, Seoul, South Korea

S

Suk-Ju Kang

Department of Electronic Engineering, Sogang University, Seoul, South Korea

Funding

Korea government Award: IITP-2026-RS-2023-00260091

Ministry of Science and ICT

Korea Institute for Advancement of Technology (KIAT) grant

Hyundai Motor Company, the IITP (Institute of Information & Communications Technology Planning & Evaluation)-ITRC (Information Technology Research Center) grant

Korea Government [Ministry of Trade, industry and Energy (MOTIE)]

National R&D Program through the National Research Foundation of Kore

Cite This Article

Hyunwoo Yu, Seunghun Moon, Sunghoon Jung, et al. (2026). Deep Learning-Based Real-Time Driver’s Hands-On Detection: A Lightweight Time Series Approach Using CAN Data. IEEE Access, 14, 47903-47914. https://doi.org/10.1109/access.2026.3676396

Deep Learning-Based Real-Time Driver’s Hands-On Detection: A Lightweight Time Series Approach Using CAN Data

You May Also Like