{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:46:32Z","timestamp":1782539192768,"version":"3.54.5"},"reference-count":44,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Driving behavior recognition plays a crucial role in intelligent driving systems and road traffic safety. Due to insufficient driving experience and limited ability to allocate visual attention, novice drivers are considered a high-risk group for traffic accidents. Existing approaches primarily focus on experienced drivers and rely on single-modal eye-tracking data, making it difficult to model spatial attention distributions and long-term temporal dependencies simultaneously. Moreover, these methods are often affected by modality asynchrony during multimodal fusion, further limiting performance gains. To address these challenges, this study proposes a novice driver behavior recognition method based on bimodal eye-tracking features and a gated cross-modal attention fusion (GCMAF) mechanism. The model adopts a spatial\u2013temporal dual-branch architecture. The spatial branch employs ResNet34 to extract eye-tracking heatmap features to represent the visual attention distribution. In contrast, the temporal branch integrates a 1D-CNN with the Mamba model to capture local dynamic patterns and long-range temporal dependencies. In the fusion stage, the GCMAF module is introduced to enhance cross-modal interactions, and a gating mechanism is further used to adaptively adjust modality weights, thereby mitigating the adverse effects of modality asynchrony. To validate the effectiveness and generalization ability of the proposed method, repeated experiments and five-fold cross-validation are conducted. The results demonstrate that the model achieves an average classification accuracy of 93.86% across four driving behavior categories, with standard deviations below 0.3%. Compared with baseline methods, paired t-test results show that the performance improvement is statistically significant (p &lt; 0.01). Ablation studies further confirm the independent contribution of each component. Overall, the proposed method outperforms existing approaches in terms of accuracy and stability, providing effective support for driving behavior assessment and proactive safety warning systems.<\/jats:p>","DOI":"10.3390\/computers15060397","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T01:03:23Z","timestamp":1782263003000},"page":"397","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Behavior Recognition of Novice Drivers Based on Bimodal Eye-Tracking Characteristics and a Parallel CNN-Mamba Model"],"prefix":"10.3390","volume":"15","author":[{"given":"Jianzhuo","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Baoji University of Arts and Sciences, Baoji 721016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panyu","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Baoji University of Arts and Sciences, Baoji 721016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiake","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Baoji University of Arts and Sciences, Baoji 721016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Baoji University of Arts and Sciences, Baoji 721016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.trf.2020.08.007","article-title":"Driver behavior and traffic accident involvement among professional urban bus drivers in China","volume":"74","author":"Han","year":"2020","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhang, X., Zhu, X., Luo, Y., and Luo, Y. (2019). Research on risky driving behavior of novice drivers. Sustainability, 11.","DOI":"10.3390\/su11205556"},{"key":"ref_3","unstructured":"Kotseruba, I., and Tsotsos, J.K. (2021). Behavioral research and practical models of drivers\u2019 attention. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"16386","DOI":"10.1109\/TITS.2022.3149994","article-title":"The alleviation of perceptual blindness during driving in urban areas guided by saccades recommendation","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1109\/TIV.2019.2960946","article-title":"Personalized driver workload estimation using deep neural network learning from physiological and vehicle signals","volume":"5","author":"Xie","year":"2019","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Arias-Portela, C.Y., Mora-Vargas, J., and Caro, M. (2024). Situational awareness assessment of drivers boosted by eye-tracking metrics: A literature review. Appl. Sci., 14.","DOI":"10.3390\/app14041611"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1109\/TIV.2022.3154426","article-title":"Human-machine shared driving: Challenges and future directions","volume":"7","author":"Ansari","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Warchol-Jakubowska, A., Krejtz, I., and Krejtz, K. (2023). An irrelevant look of novice tram driver: Visual attention distribution of novice and expert tram drivers. Proceedings of the 2023 Symposium on Eye Tracking Research and Applications, ACM.","DOI":"10.1145\/3588015.3589514"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.trf.2020.12.009","article-title":"A comparison of experienced and novice drivers\u2019 rear-end collision avoidance maneuvers under urgent decelerating events","volume":"76","author":"Yang","year":"2021","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1109\/TIV.2022.3200592","article-title":"Driving performance under violations of traffic rules: Novice vs. experienced drivers","volume":"7","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1177\/03611981241250023","article-title":"Cognitive workload estimation in conditionally automated vehicles using transformer networks based on physiological signals","volume":"2678","author":"Wang","year":"2024","journal-title":"Transp. Res. Rec."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"106851","DOI":"10.1016\/j.compbiomed.2023.106851","article-title":"Multi-modal biometrics based implicit driver identification system using multi-TF images of ECG and EMG","volume":"159","author":"Choi","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1109\/TBIOM.2024.3400866","article-title":"A survey of EEG-based driver state and behavior detection for intelligent vehicles","volume":"6","author":"Ju","year":"2024","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"ref_14","first-page":"100864","article-title":"A systematic review on detection and prediction of driver drowsiness","volume":"21","author":"Shaik","year":"2023","journal-title":"Transp. Res. Interdiscip. Perspect."},{"key":"ref_15","first-page":"1790","article-title":"A real-time vision transformers-based system for enhanced driver drowsiness detection and vehicle safety","volume":"12","author":"Jarndal","year":"2024","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hao, Z., Hu, J., Ran, J., Sun, X., Zheng, Y., and Li, C. (2025). Characterization of driver dynamic visual perception under different road linearity conditions. Appl. Sci., 15.","DOI":"10.3390\/app15116076"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hao, Z., Hu, J., Sun, X., Ran, J., Zheng, Y., Yang, B., and Tang, J. (2025). Study on the eye movement transfer characteristics of drivers under different road conditions. Appl. Sci., 15.","DOI":"10.3390\/app15158559"},{"key":"ref_18","first-page":"2284","article-title":"Using eye-tracking data to predict situation awareness in real time during takeover transitions in conditionally automated driving","volume":"21","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Navarro, J., Reynaud, E., Ouimet, M.C., and Schnebelen, D. (2023). Comparison of experienced and novice drivers\u2019 visual and driving behaviors during warned or unwarned near-forward collisions. Sensors, 23.","DOI":"10.3390\/s23198150"},{"key":"ref_20","first-page":"733","article-title":"The effects of the traffic signs information volume on the visual characteristics and workload of novice and experienced drivers","volume":"79","author":"Han","year":"2024","journal-title":"Work"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s41235-023-00501-1","article-title":"How do drivers mitigate the effects of naturalistic visual complexity? On attentional strategies and their implications under a change blindness protocol","volume":"8","author":"Kondyli","year":"2023","journal-title":"Cogn. Res. Princ. Implic."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lee, Y., and Jung, K. (2025). The effect of visual attention dispersion on cognitive response time. J. Eye Mov. Res., 18.","DOI":"10.3390\/jemr18050052"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.jer.2023.09.023","article-title":"Distraction and visual search characteristics of young drivers when using navigation system displays","volume":"12","author":"Yared","year":"2024","journal-title":"J. Eng. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"125975","DOI":"10.1016\/j.eswa.2024.125975","article-title":"Driver cognitive distraction detection based on eye movement behavior and integration of multi-view space-channel features","volume":"266","author":"Qiao","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rahman, H., Ahmed, M.U., Barua, S., Funk, P., and Begum, S. (2021). Vision-based driver\u2019s cognitive load classification considering eye movement using machine learning and deep learning. Sensors, 21.","DOI":"10.3390\/s21238019"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Chen, Y., and Zhang, Y. (2025). Driver distraction detection in conditionally automated driving using multimodal physiological and ocular signals. Electronics, 14.","DOI":"10.3390\/electronics14193811"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"18000","DOI":"10.1109\/ACCESS.2023.3245122","article-title":"Detection of driver cognitive distraction using machine learning methods","volume":"11","author":"Misra","year":"2023","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chung, J., Lee, H., Moon, H., and Lee, E. (2022). The static and dynamic analyses of drivers\u2019 gaze movement using VR driving simulator. Appl. Sci., 12.","DOI":"10.3390\/app12052362"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103085","DOI":"10.1016\/j.sysarc.2024.103085","article-title":"An efficient multi-task learning CNN for driver attention monitoring","volume":"148","author":"Yang","year":"2024","journal-title":"J. Syst. Archit."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"16203","DOI":"10.1109\/ACCESS.2023.3245146","article-title":"CNN-LSTM driving style classification model based on driver operation time series data","volume":"11","author":"Cai","year":"2023","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"132055","DOI":"10.1109\/ACCESS.2023.3335249","article-title":"Hybrid Swin transformer-based classification of gaze target regions","volume":"11","author":"Wu","year":"2023","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Piaseczna, N., Doniec, R., Duraj, K., Sieci\u0144ski, S., J\u0119drychowski, M., and Tkacz, E. (2025). Distinguishing drivers with smart glasses data and deep neural network. Proceedings of the IEEE EUROCON 2025\u201421st International Conference on Smart Technologies, IEEE.","DOI":"10.1109\/EUROCON64445.2025.11073507"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"103432","DOI":"10.1016\/j.trf.2025.103432","article-title":"Exploring visual attention dynamics in tram driving: Differentiating between expert and novice drivers for gaze-enhanced training","volume":"116","author":"Krejtz","year":"2026","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_34","unstructured":"Gu, A., and Dao, T. (2024). Mamba: Linear-time sequence modeling with selective state spaces. Proceedings of the First Conference on Language Modeling, OpenReview."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1109\/TNNLS.2025.3610435","article-title":"Vision mamba: A comprehensive survey and taxonomy","volume":"37","author":"Liu","year":"2026","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Kashevnik, A., Kovalenko, S., Mamonov, A., Hamoud, B., Bulygin, A., Kuznetsov, V., Shoshina, I., Brak, I., and Kiselev, G. (2024). Intelligent Human Operator Mental Fatigue Assessment Method Based on Gaze Movement Monitoring. Sensors, 24.","DOI":"10.3390\/s24216805"},{"key":"ref_37","first-page":"771","article-title":"Analysis of Boat\u2019s Operator Action Using Gaze-Data","volume":"19","author":"Yoshida","year":"2025","journal-title":"TransNav Int. J. Mar. Navig. Saf. Sea Transp."},{"key":"ref_38","first-page":"121","article-title":"Assessment of Driver Inattention State Using Multimodal Wearable Signals and Cross-Attention-Driven Hierarchical Fusion","volume":"323","author":"Pavan","year":"2025","journal-title":"Stud. Health Technol. Inform."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5259","DOI":"10.1167\/jov.23.9.5259","article-title":"Arousal Levels Modulates Saccadic Main Sequence and Stationary Gaze Entropy in Partially Sleep-Deprived Drivers","volume":"23","author":"Angioi","year":"2023","journal-title":"J. Vis."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ye, Z. (2024). A survey on visual mamba. Appl. Sci., 14.","DOI":"10.3390\/app14135683"},{"key":"ref_41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","first-page":"1","article-title":"Abnormal driving behavior recognition method based on smartphone sensor and CNN-LSTM","volume":"11","author":"Li","year":"2022","journal-title":"Int. J. Sci. Eng. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"148031","DOI":"10.1109\/ACCESS.2019.2932434","article-title":"Attention-based convolutional and recurrent neural networks for driving behavior recognition using smartphone sensor data","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Nan, Z., Yang, T., Liu, Y., and Zheng, N. (2020). A driving behavior recognition model with bi-LSTM and multi-scale CNN. Proceedings of the IEEE Intelligent Vehicles Symposium, IEEE.","DOI":"10.1109\/IV47402.2020.9304772"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/6\/397\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:59:42Z","timestamp":1782536382000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/6\/397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,21]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["computers15060397"],"URL":"https:\/\/doi.org\/10.3390\/computers15060397","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,21]]}}}