{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:18:12Z","timestamp":1773825492292,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Key Research and Development Projects of Zhejiang Province","award":["2023C01062"],"award-info":[{"award-number":["2023C01062"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Dangerous driving behavior is a major contributing factor to road traffic accidents. Identifying and intervening in drivers\u2019 unsafe driving behaviors is thus crucial for preventing accidents and ensuring road safety. However, many of the existing methods for monitoring drivers\u2019 behaviors rely on computer vision technology, which has the potential to invade privacy. This paper proposes a radar-based deep learning method to analyze driver behavior. The method utilizes FMCW radar along with TOF radar to identify five types of driving behavior: normal driving, head up, head twisting, picking up the phone, and dancing to music. The proposed model, called RFDANet, includes two parallel forward propagation channels that are relatively independent of each other. The range-Doppler information from the FMCW radar and the position information from the TOF radar are used as inputs. After feature extraction by CNN, an attention mechanism is introduced into the deep architecture of the branch layer to adjust the weight of different branches. To further recognize driving behavior, LSTM is used. The effectiveness of the proposed method is verified by actual driving data. The results indicate that the average accuracy of each of the five types of driving behavior is 94.5%, which shows the advantage of using the proposed deep learning method. Overall, the experimental results confirm that the proposed method is highly effective for detecting drivers\u2019 behavior.<\/jats:p>","DOI":"10.1007\/s40747-023-01236-8","type":"journal-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T05:01:52Z","timestamp":1695704512000},"page":"1517-1530","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RFDANet: an FMCW and TOF radar fusion approach for driver activity recognition using multi-level attention based CNN and LSTM network"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0484-3219","authenticated-orcid":false,"given":"Minming","family":"Gu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8305-9678","authenticated-orcid":false,"given":"Kaiyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhixiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,26]]},"reference":[{"key":"1236_CR1","unstructured":"World Health Organization (2018) Global Safety Report on Road Safety. https:\/\/www.who.int\/publications\/i\/item\/9789241565684"},{"key":"1236_CR2","first-page":"2609","volume":"31","author":"P Wu","year":"2019","unstructured":"Wu P, Liu J, Shen F (2019) A deep one-class neural network for anomalous event detection in complex scenes. IEEE Trans Neural Netw Learn Syst 31:2609\u20132622","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1236_CR3","doi-asserted-by":"publisher","unstructured":"Liu T, Lam K, Kong J (2023) Distilling privileged knowledge for anomalous event detection from weakly labeled videos. IEEE Trans Neural Netw Learn Syst, pp 1\u201315. https:\/\/doi.org\/10.1109\/TNNLS.2023.3263966","DOI":"10.1109\/TNNLS.2023.3263966"},{"key":"1236_CR4","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc O, Zheng J, Xu H, Rigoll G (2021) Driver anomaly detection: a dataset and contrastive learning approach. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) , 2021: IEEE, pp 91\u2013100","DOI":"10.1109\/WACV48630.2021.00014"},{"key":"1236_CR5","unstructured":"Santokh S (2018) Critical Reasons for Crashes Investigated in the National Motor Vehicle Crash Causation Survey. Natl. Highw. Traffic Saf. Adm"},{"issue":"106972","key":"1236_CR6","first-page":"1","volume":"183","author":"Z Su","year":"2023","unstructured":"Su Z, Woodman R, Smyth J, Elliott M (2023) The relationship between aggressive driving and driver performance: a systematic review with meta-analysis. Accident Anal Prev 183(106972):1\u201313","journal-title":"Accident Anal Prev"},{"key":"1236_CR7","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1016\/j.ins.2022.07.118","volume":"609","author":"J Lu","year":"2022","unstructured":"Lu J (2022) Symbolic aggregate approximation based data fusion model for dangerous driving behavior detection. Inf Sci 609:626\u2013642","journal-title":"Inf Sci"},{"key":"1236_CR8","doi-asserted-by":"publisher","first-page":"19374","DOI":"10.1109\/TITS.2022.3166208","volume":"23","author":"T Huang","year":"2022","unstructured":"Huang T, Fu R (2022) Driver distraction detection based on the true driver\u2019s focus of attention. IEEE Trans Intell Transp Syst 23:19374\u201319386","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1236_CR9","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.1109\/TITS.2020.2979527","volume":"22","author":"G Du","year":"2021","unstructured":"Du G, Li T, Liu P, Li D (2021) Vision-based fatigue driving recognition method integrating heart rate and facial features. IEEE Trans Intell Transp Syst 22:3089\u20133100","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1236_CR10","first-page":"1","volume":"33","author":"Y Tian","year":"2021","unstructured":"Tian Y, Cao J (2021) Fatigue driving detection based on electrooculography: a review. EURASIP J Image Video Process 33:1\u201317","journal-title":"EURASIP J Image Video Process"},{"issue":"105908","key":"1236_CR11","first-page":"1","volume":"150","author":"H Singh","year":"2021","unstructured":"Singh H, Kathuria A (2021) Analyzing driver behavior under naturalistic driving conditions: a review. Accident Anal Prev 150(105908):1\u201321","journal-title":"Accident Anal Prev"},{"issue":"8","key":"1236_CR12","doi-asserted-by":"publisher","first-page":"10957","DOI":"10.1109\/TITS.2021.3098309","volume":"23","author":"S Ansari","year":"2022","unstructured":"Ansari S, Naghdy F, Du H, Pahnwar Y (2022) Driver Mental Fatigue Detection Based on Head Posture Using New Modified reLU-BiLSTM Deep Neural Network. IEEE Transactions on Intelligent Transportation System 23(8):10957\u201310969","journal-title":"IEEE Transactions on Intelligent Transportation System"},{"key":"1236_CR13","doi-asserted-by":"crossref","unstructured":"Shen N, Zhu Y, Oroni C, Wang L (2021) Analysis of drivers\u2019 eye movements with different experience and genders in straight-line driving. In: 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC\/PiCom\/CBDCom\/CyberSciTech), 2021: IEEE, pp 907\u2013911","DOI":"10.1109\/DASC-PICom-CBDCom-CyberSciTech52372.2021.00151"},{"issue":"12355","key":"1236_CR14","first-page":"1","volume":"14","author":"W Liu","year":"2022","unstructured":"Liu W, Li H, Zhang H (2022) Dangerous driving behavior recognition based on hand trajectory. Sustainability 14(12355):1\u201316","journal-title":"Sustainability"},{"issue":"9931","key":"1236_CR15","first-page":"1","volume":"22","author":"C Nakagawa","year":"2022","unstructured":"Nakagawa C, Yamada S, Hirata D, Shintani A (2022) Differences in driver behavior between manual and automatic turning of an inverted pendulum vehicle. Sensors 22(9931):1\u201321","journal-title":"Sensors"},{"issue":"5741","key":"1236_CR16","first-page":"1","volume":"22","author":"Y Kajiwara","year":"2022","unstructured":"Kajiwara Y, Murata E (2022) Effect of behavioral precaution on braking operation of elderly drivers under cognitive workloads. Sensors 22(5741):1\u201316","journal-title":"Sensors"},{"key":"1236_CR17","first-page":"1","volume":"6","author":"M Tabatabaie","year":"2022","unstructured":"Tabatabaie M, He S, Yang X (2022) Driver Maneuver identification with multi-representation learning and meta model update designs. Proc ACM Interact Mob Wear Ubiquit Technol 6:1\u201323","journal-title":"Proc ACM Interact Mob Wear Ubiquit Technol"},{"issue":"106830","key":"1236_CR18","first-page":"1","volume":"178","author":"K Lu","year":"2022","unstructured":"Lu K, Dahlman A, Karlsson J, Candefjord S (2022) Detecting driver fatigue using heart rate variability: a systematic review. Accid Anal Prev 178(106830):1\u201310","journal-title":"Accid Anal Prev"},{"key":"1236_CR19","doi-asserted-by":"publisher","first-page":"168080","DOI":"10.1109\/ACCESS.2021.3133797","volume":"9","author":"A Ezzouhri","year":"2021","unstructured":"Ezzouhri A, Charouh Z, Ghogho M, Guennoun Z (2021) Robust deep learning-based driver distraction detection and classification. IEEE Access 9:168080\u2013168092","journal-title":"IEEE Access"},{"key":"1236_CR20","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.cviu.2014.10.003","volume":"134","author":"E Ohn-Bar","year":"2015","unstructured":"Ohn-Bar E, Tawari A, Martin S, Trivedi M (2015) On surveillance for safety critical events: in-vehicle video networks for predictive driver assistance systems. Comput Vis Image Underst 134:130\u2013140","journal-title":"Comput Vis Image Underst"},{"key":"1236_CR21","doi-asserted-by":"crossref","unstructured":"Lashkov I, Kashevnik A, Shilov N, Parfenov V, Shabaev A (2019) Driver dangerous state detection based on OpenCV& Dlib libraries using mobile video Processing. In: 2019 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), IEEE, pp 74\u201379","DOI":"10.1109\/CSE\/EUC.2019.00024"},{"key":"1236_CR22","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.aap.2017.11.010","volume":"116","author":"L Yang","year":"2017","unstructured":"Yang L, Ma R, Zhang H, Guan W, Jiang S (2017) Driving behavior recognition using EEG data from a simulated car-following experiment. Accident Anal Prev 116:30\u201340","journal-title":"Accident Anal Prev"},{"issue":"5551","key":"1236_CR23","first-page":"1","volume":"23","author":"R Doniec","year":"2023","unstructured":"Doniec R, Konior J, Sieci \u00b4nski S, Piet A, Irshad M, Piaseczna N, Hasan M, Li F, Nisar M, Grzegorzek M (2023) Sensor-based classification of primary and secondary car driver activities using convolutional neural networks. Sensors (Basel, Switzerland) 23(5551):1\u201319","journal-title":"Sensors (Basel, Switzerland)"},{"issue":"3","key":"1236_CR24","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1109\/JBHI.2021.3096984","volume":"26","author":"M Shahbakhti","year":"2022","unstructured":"Shahbakhti M, Beiramvand M, Rejer I, Augustyniak P, Broniec-W\u00f3jcik A, Wierzchon M, Marozas V (2022) Simultaneous eye blink characterization and elimination from low-channel prefrontal EEG signals enhances driver drowsiness detection. IEEE J Biomed Health Inform 26(3):1001\u20131012","journal-title":"IEEE J Biomed Health Inform"},{"key":"1236_CR25","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TNSRE.2021.3089594","volume":"29","author":"G Zhang","year":"2021","unstructured":"Zhang G, Etemad A (2021) Capsule attention for multimodal EEG-EOG representation learning with application to driver vigilance estimation. IEEE Trans Neural Syst Rehabil Eng 29:1138\u20131149","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"1236_CR26","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MSP.2018.2890128","volume":"36","author":"S Gurbuz","year":"2019","unstructured":"Gurbuz S, Amin M (2019) Radar-based human-motion recognition with deep learning: promising applications for indoor monitoring. IEEE Signal Process Mag 36:16\u201328","journal-title":"IEEE Signal Process Mag"},{"key":"1236_CR27","doi-asserted-by":"publisher","DOI":"10.1201\/9781315155340","volume-title":"Radar for indoor monitoring: detection, classification, assessment","author":"M Amin","year":"2017","unstructured":"Amin M (2017) Radar for indoor monitoring: detection, classification, assessment. CRC Press, Boca Raton"},{"issue":"14","key":"1236_CR28","doi-asserted-by":"publisher","first-page":"16043","DOI":"10.1109\/JSEN.2021.3075909","volume":"21","author":"P Rai","year":"2021","unstructured":"Rai P, Ids\u00f8e H, Yakkati R, Kumar A, Khan M, Yalavarthy P, Cenkeramaddi L (2021) Localization and activity classification of unmanned aerial vehicle using mmWave FMCW radars. IEEE Sens J 21(14):16043\u201316053","journal-title":"IEEE Sens J"},{"key":"1236_CR29","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1049\/rsn2.12223","volume":"16","author":"H Nguyen","year":"2022","unstructured":"Nguyen H, Lee S, Nguyen T, Kim Y (2022) One shot learning based drivers head movement identification using a millimetre wave radar sensor. IET Radar Sonar Navig 16:825\u2013836","journal-title":"IET Radar Sonar Navig"},{"key":"1236_CR30","doi-asserted-by":"crossref","unstructured":"Chae R, Wang A, Li C (2019) FMCW radar driver head motion monitoring based on Doppler spectrogram and range-Doppler evolution. In: IEEE Topical Conf. Wireless Sensors Sensor Netw. (WiSNet), 2019: IEEE, pp 1\u20134","DOI":"10.1109\/WISNET.2019.8711807"},{"key":"1236_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3227998","volume":"72","author":"V Varela","year":"2023","unstructured":"Varela V, Rodrigues D, Zeng L, Li C (2023) Multitarget physical activities monitoring and classification using a V-band FMCW radar. IEEE Trans Instrum Meas 72:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"issue":"9","key":"1236_CR32","doi-asserted-by":"publisher","first-page":"8648","DOI":"10.1109\/JSEN.2022.3156762","volume":"22","author":"F Abdu","year":"2022","unstructured":"Abdu F, Zhang Y, Deng Z (2022) Activity Classification based on feature fusion of FMCW radar human motion micro-doppler signatures. IEEE Sens J 22(9):8648\u20138662","journal-title":"IEEE Sens J"},{"key":"1236_CR33","doi-asserted-by":"publisher","first-page":"100472","DOI":"10.1109\/ACCESS.2021.3096465","volume":"9","author":"D Bresnahan","year":"2021","unstructured":"Bresnahan D, Li Y (2021) Classification of driver head motions using a mm-wave FMCW radar and deep convolutional neural network. IEEE Access 9:100472\u2013100479","journal-title":"IEEE Access"},{"issue":"113240","key":"1236_CR34","first-page":"1","volume":"149","author":"M Shahverdy","year":"2020","unstructured":"Shahverdy M, Fathy M, Berangi R, Sabokrou M (2020) Driver behavior detection and classification using deep convolutional neural networks. Expert Syst Appl 149(113240):1\u201312","journal-title":"Expert Syst Appl"},{"issue":"1","key":"1236_CR35","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TITS.2020.3008210","volume":"23","author":"S S\u00e1nchez","year":"2022","unstructured":"S\u00e1nchez S, Pozo R, G\u00f3mez L (2022) Driver identification and verification from smartphone accelerometers using deep neural networks. IEEE Trans Intell Transp Syst 23(1):97\u2013109","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"119629","key":"1236_CR36","first-page":"1","volume":"219","author":"I Jeham","year":"2023","unstructured":"Jeham I, Alouani I, Khalifa A, Mahjoub M (2023) Deep learning-based hard spatial attention for driver in-vehicle action monitoring. Expert Syst Appl 219(119629):1\u201311","journal-title":"Expert Syst Appl"},{"key":"1236_CR37","first-page":"1","volume":"19","author":"R Li","year":"2022","unstructured":"Li R, Wang X, Wang J, Song Y, Lei L (2022) SAR target recognition based on efficient fully convolutional attention block CNN. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"1236_CR38","first-page":"1","volume":"60","author":"Y Xu","year":"2022","unstructured":"Xu Y, Zhang Y, Yu C, Chao Ji, Yue T, Li H (2022) Residual spatial attention kernel generation network for hyperspectral image classification with small sample size. IEEE Trans Geosci Remote Sens 60:1\u201314","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"6","key":"1236_CR39","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1109\/TCSVT.2021.3104651","volume":"32","author":"T Liu","year":"2022","unstructured":"Liu T, Lam K, Zhao R, Kong J (2022) Enhanced attention tracking with multi-branch network for egocentric activity recognition. IEEE Trans Circuits Syst Video Technol 32(6):1587\u20133602","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"3","key":"1236_CR40","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1049\/ell2.12076","volume":"57","author":"M Shahverdy","year":"2021","unstructured":"Shahverdy M, Fathy M, Berangi R, Sabokrou M (2021) Driver behaviour detection using 1D convolutional neural networks. Electron Lett 57(3):119\u2013122","journal-title":"Electron Lett"},{"issue":"6","key":"1236_CR41","doi-asserted-by":"publisher","first-page":"5379","DOI":"10.1109\/TVT.2019.2908425","volume":"68","author":"Y Xing","year":"2019","unstructured":"Xing Y, Lv C, Wang H, Cao D, Velenis E, Wang F (2019) Driver activity recognition for intelligent vehicles: a deep learning approach. IEEE Trans Veh Technol 68(6):5379\u20135390","journal-title":"IEEE Trans Veh Technol"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01236-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01236-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01236-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T22:38:07Z","timestamp":1707604687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01236-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1236"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01236-8","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,26]]},"assertion":[{"value":"9 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Corresponding authors declare on behalf of all authors that there is no conflict of interest. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The experiments were conducted under the guidance of Zhejiang Sci-Tech University.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All procedures involving human research conformed to the ethical standards of Zhejiang Sci-Tech University and followed <i>Declaration of Helsinki<\/i>.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participant"}}]}}