{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T14:35:37Z","timestamp":1777041337215,"version":"3.51.4"},"reference-count":54,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T00:00:00Z","timestamp":1599177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["2019000064"],"award-info":[{"award-number":["2019000064"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This study focuses on driver-behavior identification and its application to finding embedded solutions in a connected car environment. We present a lightweight, end-to-end deep-learning framework for performing driver-behavior identification using in-vehicle controller area network (CAN-BUS) sensor data. The proposed method outperforms the state-of-the-art driver-behavior profiling models. Particularly, it exhibits significantly reduced computations (i.e., reduced numbers both of floating-point operations and parameters), more efficient memory usage (compact model size), and less inference time. The proposed architecture features depth-wise convolution, along with augmented recurrent neural networks (long short-term memory or gated recurrent unit), for time-series classification. The minimum time-step length (window size) required in the proposed method is significantly lower than that required by recent algorithms. We compared our results with compressed versions of existing models by applying efficient channel pruning on several layers of current models. Furthermore, our network can adapt to new classes using sparse-learning techniques, that is, by freezing relatively strong nodes at the fully connected layer for the existing classes and improving the weaker nodes by retraining them using data regarding the new classes. We successfully deploy the proposed method in a container environment using NVIDIA Docker in an embedded system (Xavier, TX2, and Nano) and comprehensively evaluate it with regard to numerous performance metrics.<\/jats:p>","DOI":"10.3390\/s20185030","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T11:24:24Z","timestamp":1599218664000},"page":"5030","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Lightweight Driver Behavior Identification Model with Sparse Learning on In-Vehicle CAN-BUS Sensor Data"],"prefix":"10.3390","volume":"20","author":[{"given":"Shan","family":"Ullah","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Inha University, Incheon 22212, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6048-9392","authenticated-orcid":false,"given":"Deok-Hwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Inha University, Incheon 22212, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2863","DOI":"10.1007\/s00500-018-3274-y","article-title":"A \u201cpay-how-you-drive\u201d car insurance approach through cluster analysis","volume":"23","author":"Carfora","year":"2019","journal-title":"Soft Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1109\/TDSC.2010.71","article-title":"Pripayd: Privacy-friendly pay-as-you-drive insurance","volume":"8","author":"Troncoso","year":"2010","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Dai, R., Lu, Y., Ding, C., and Lu, G. (2017). The effect of connected vehicle environment on global travel efficiency and its optimal penetration rate. J. Adv. Transp., 2017.","DOI":"10.1155\/2017\/2697678"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.procir.2014.02.001","article-title":"Service innovation and smart analytics for industry 4.0 and big data environment","volume":"16","author":"Lee","year":"2014","journal-title":"Procedia CIRP"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kwak, B.I., Woo, J., and Kim, H.K. (2016, January 12\u201314). Know your master: Driver profiling-based anti-theft method. Proceedings of the 2016 IEEE 14th Annual Conference on Privacy, Security and Trust (PST), Auckland, New Zealand.","DOI":"10.1109\/PST.2016.7906929"},{"key":"ref_6","unstructured":"Kang, Y.G., Park, K.H., and Kim, H.K. (2019). Automobile theft detection by clustering owner driver data. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, Z., Li, F., Xie, C., Ren, T., Chen, J., and Liu, L. (2019). A deep learning framework for driving behavior identification on in-vehicle CAN-BUS sensor data. Sensors, 19.","DOI":"10.3390\/s19061356"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7406","DOI":"10.1109\/TVT.2019.2924906","article-title":"Improving driver identification for the next-generation of in-vehicle software systems","volume":"68","author":"Bouhoute","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"J\u00fanior, J.F., Carvalho, E., Ferreira, B.V., de Souza, C., Suhara, Y., Pentland, A., and Pessin, G. (2017). Driver behavior profiling: An investigation with different smartphone sensors and machine learning. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0174959"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1109\/TITS.2018.2836308","article-title":"Driving behavior analysis through CAN bus data in an uncontrolled environment","volume":"20","author":"Fugiglando","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/MITS.2014.2328673","article-title":"Driver behavior profiling using smartphones: A low-cost platform for driver monitoring","volume":"7","author":"Castignani","year":"2015","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_12","unstructured":"Park, K.H., and Kim, H.K. (2019). This car is mine!: Automobile theft countermeasure leveraging driver identification with generative adversarial networks. arXiv."},{"key":"ref_13","unstructured":"(2020, June 07). Androidauto-Connect Your Phone to Car Display. Available online: https:\/\/www.android.com\/auto\/."},{"key":"ref_14","unstructured":"(2020, June 07). Automotive Grade Linux. Available online: https:\/\/www.automotivelinux.org\/."},{"key":"ref_15","unstructured":"(2020, June 07). QNX in Automotive-QNX Software Systems. Available online: https:\/\/blackberry.qnx.com\/en\/software-solutions\/connected-autonomous-vehicles."},{"key":"ref_16","first-page":"2427","article-title":"Methodology and mobile application for driver behavior analysis and accident prevention","volume":"6","author":"Kashevnik","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/MITS.2019.2919516","article-title":"Clusters of driving behavior from observational smartphone data","volume":"11","author":"Warren","year":"2019","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, M.G., Jiang, B., Che, Z., Shi, X., Liu, M., Meng, Y., Ye, J., and Liu, Y. (2019, January 27\u201328). DBUS: Human driving behavior understanding system. Proceedings of the IEEE International Conference on Computer Vision Workshops, Seoul, Korea.","DOI":"10.1109\/ICCVW.2019.00298"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ramanishka, V., Chen, Y., Misu, T., and Saenko, K. (2018, January 18\u201322). Toward driving scene understanding: A dataset for learning driver behavior and causal reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00803"},{"key":"ref_20","unstructured":"Fridman, L., Brown, D.E., Glazer, M., Angell, W., Dodd, S., Jenik, B., Terwilliger, J., Kindelsberger, J., Ding, L., and Seaman, S. (2017). MIT autonomous vehicle technology study: Large-scale deep learning based analysis of driver behavior and interaction with automation. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"9731","DOI":"10.1007\/s00521-019-04506-0","article-title":"Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks","volume":"32","author":"Wijnands","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kim, W., Jung, W., and Choi, H.K. (2019). Lightweight driver monitoring system based on multi-task mobilenets. Sensors, 19.","DOI":"10.3390\/s19143200"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"170110","DOI":"10.1038\/sdata.2017.110","article-title":"A multimodal dataset for various forms of distracted driving","volume":"4","author":"Taamneh","year":"2017","journal-title":"Sci. Data"},{"key":"ref_24","first-page":"194","article-title":"A study of individual characteristics of driving behavior based on hidden Markov model","volume":"167","author":"Zhang","year":"2014","journal-title":"Sens. Transducers"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1109\/JPROC.2006.888405","article-title":"Driver modeling based on driving behavior and its evaluation in driver identification","volume":"95","author":"Miyajima","year":"2007","journal-title":"Proc. IEEE"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Van Ly, M., Martin, S., and Trivedi, M.M. (2013, January 23\u201326). Driver classification and driving style recognition using inertial sensors. Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, Australia.","DOI":"10.1109\/IVS.2013.6629603"},{"key":"ref_27","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20138). ImageNet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Harrahs adn Harverys, Lake Tahoe, CA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: A search space odyssey","volume":"28","author":"Greff","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ha, S., and Choi, S. (2016, January 24\u201329). Convolutional neural networks for human activity recognition using multiple accelerometer and gyroscope sensors. Proceedings of the 2016 IEEE International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727224"},{"key":"ref_30","unstructured":"Cui, Z., Chen, W., and Chen, Y. (2016). Multi-scale convolutional neural networks for time series classification. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/ACCESS.2017.2779939","article-title":"LSTM fully convolutional networks for time series classification","volume":"6","author":"Karim","year":"2017","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, T., Bao, J., Wang, J., and Zhang, Y. (2018). A hybrid CNN\u2013LSTM algorithm for online defect recognition of CO2 welding. Sensors, 18.","DOI":"10.3390\/s18124369"},{"key":"ref_33","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yan, W., and Oates, T. (2017, January 14\u201319). Time series classification from scratch with deep neural networks: A strong baseline. Proceedings of the 2017 IEEE International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"ref_35","first-page":"245","article-title":"Behavioural impacts of advanced driver assistance systems\u2014An overview","volume":"1","author":"Brookhuis","year":"2001","journal-title":"Eur. J. Transp. Infrastruct. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/MIS.2018.033001418","article-title":"Next-generation smart environments: From system of systems to data ecosystems","volume":"33","author":"Curry","year":"2018","journal-title":"IEEE Intell. Syst."},{"key":"ref_37","unstructured":"Hui, K., Le, M., and Tao, S. (2016, January 4\u20138). Container and microservice driven design for cloud infrastructure devops. Proceedings of the 2016 IEEE International Conference on Cloud Engineering (IC2E), Berlin, Germany."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/MCC.2014.51","article-title":"Containers and cloud: From lxc to docker to kubernetes","volume":"1","author":"Bernstein","year":"2014","journal-title":"IEEE Cloud Comput."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.sysarc.2019.01.011","article-title":"A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platform","volume":"97","author":"Mittal","year":"2019","journal-title":"J. Syst. Architect."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kim, C.E., Oghaz, M.M.D., Fajtl, J., Argyriou, V., and Remagnino, P. (2018). A comparison of embedded deep learning methods for person detection. arXiv.","DOI":"10.5220\/0007386304590465"},{"key":"ref_41","unstructured":"OCS Lab (2020, August 27). Driving Dataset. Available online: http:\/\/ocslab.hksecurity.net\/Datasets\/driving-dataset."},{"key":"ref_42","unstructured":"(2020, June 25). Information Protection R&D Data Challenge 2019. Available online: http:\/\/datachallenge.kr\/challenge18\/vehicle\/tutorial\/."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The WEKA data mining software: An update","volume":"11","author":"Hall","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_44","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_45","unstructured":"Rastgoo, M.N. (2019). Driver Stress Level Detection Based on Multimodal Measurements. [Ph.D. Thesis, Queensland University of Technology]. Available online: https:\/\/eprints.qut.edu.au\/134144\/."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Dehghani, A., Sarbishei, O., Glatard, T., and Shihab, E. (2019). A quantitative comparison of overlapping and non-overlapping sliding windows for human activity recognition using inertial sensors. Sensors, 19.","DOI":"10.3390\/s19225026"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ullah, S., and Kim, D.H. (2020, January 19\u201322). Benchmarking Jetson Platform for 3D Point-Cloud and Hyper-Spectral Image Classification. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea.","DOI":"10.1109\/BigComp48618.2020.00-21"},{"key":"ref_48","unstructured":"(2020, July 07). A Driver Identification Framework on AutoMotive Grade Linux. Available online: https:\/\/github.com\/vcar\/AGL."},{"key":"ref_49","unstructured":"Han, S., Mao, H., and Dally, W.J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2017.02.029","article-title":"Group sparse regularization for deep neural networks","volume":"241","author":"Scardapane","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_51","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning filters for efficient convnets. arXiv."},{"key":"ref_52","unstructured":"(2020, July 05). Keras-Surgeon, for Network Pruning Available on Github. Available online: https:\/\/github.com\/BenWhetton\/keras-surgeon."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Collins, M., and Darrell, T. (2008, January 23\u201328). Transfer learning for image classification with sparse prototype representations. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587637"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"3239","DOI":"10.1007\/s10489-020-01720-5","article-title":"Effective node selection technique towards sparse learning","volume":"50","author":"Ibrokhimov","year":"2020","journal-title":"Appl. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5030\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:06:49Z","timestamp":1760177209000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,4]]},"references-count":54,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20185030"],"URL":"https:\/\/doi.org\/10.3390\/s20185030","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,4]]}}}