{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:54:47Z","timestamp":1790916887635,"version":"4.1.0"},"reference-count":49,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Driver drowsiness detection systems are often evaluated using data partitions that may retain observations from the same individuals across training and testing, making their ability to generalise to unseen drivers difficult to assess. This study investigates behavioural eye-based drowsiness detection under strict subject-independent evaluation using 65,929 facial image frames from four drivers in the NTHU Driver Drowsiness Detection dataset. Eye Aspect Ratio (EAR), Rolling Mean EAR, EAR Delta and an Eye Closure Indicator were represented over temporal windows of 10, 20 and 30 frames and evaluated using Logistic Regression, Random Forest, Long Short-Term Memory and Bidirectional Long Short-Term Memory classifiers under Leave-One-Driver-Out validation. Logistic Regression achieved the highest mean accuracy, whereas Random Forest at 30 frames produced the highest drowsy-class F1-score and Area under the Precision\u2013Recall Curve. Controlled baseline analysis showed that temporal context contributed more substantially to performance than the additional engineered EAR features, while recurrent architectures did not consistently outperform the classical classifiers. Performance also varied across unseen drivers, and the modest absolute accuracy cautions against interpreting the results as evidence of deployment-ready detection. The study demonstrates the importance of separating driver identities during evaluation and provides a reproducible framework for examining temporal behavioural representations under unseen-driver conditions.<\/jats:p>","DOI":"10.3390\/s26196193","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:17:27Z","timestamp":1790756247000},"page":"6193","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Subject-Independent Temporal Framework for Behavioural Eye-Based Driver Drowsiness Detection"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1411-117X","authenticated-orcid":false,"given":"Olusola Olajide","family":"Ajayi","sequence":"first","affiliation":[{"name":"F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7250-3665","authenticated-orcid":false,"given":"Anish Mathew","family":"Kurien","sequence":"additional","affiliation":[{"name":"F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Djouani","sequence":"additional","affiliation":[{"name":"F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"},{"name":"LISSI Laboratory, Universit\u00e9 Paris-Est Cr\u00e9teil, France, and, F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0175-0850","authenticated-orcid":false,"given":"Lamine","family":"Dieng","sequence":"additional","affiliation":[{"name":"F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"},{"name":"MAST Laboratory, Universit\u00e9 Gustave Eiffel, All. Des Ponts et Chaussees, 44340 Bouguenais, France and, F\u2019SATI, French South African Institute of Technology, Tshwane University of Technology, Pretoria 0183, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"ref_1","unstructured":"NHTSA (2024). Drowsy Driving: Avoiding Falling Asleep Behind the Wheel."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.trf.2008.11.005","article-title":"Driver fatigue: The importance of identifying causal factors of fatigue when considering detection and countermeasure technologies","volume":"12","author":"May","year":"2009","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Awais, M., Badruddin, N., and Drieberg, M. (2017). A hybrid approach to detect driver drowsiness utilizing physiological signals to improve system performance and wearability. Sensors, 17.","DOI":"10.3390\/s17091991"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rezaei, M., and Klette, R. (2014, January 23\u201328). Look at the driver, look at the road: No distraction! no accident!. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.24"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TIM.2015.2507378","article-title":"Yawning detection using embedded smart cameras","volume":"65","author":"Omidyeganeh","year":"2016","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S1369-8478(01)00008-0","article-title":"A sleep physiologist\u2019s view of the drowsy driver","volume":"3","author":"Johns","year":"2000","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1109\/TSMCA.2011.2164242","article-title":"On-line detection of drowsiness using brain and visual information","volume":"42","author":"Picot","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern.-Part A Syst. Hum."},{"key":"ref_8","unstructured":"Soukupova, T., and Cech, J. (2016, January 3\u20135). Eye blink detection using facial landmarks. Proceedings of the 21st Computer Vision Winter Workshop, Rimske Toplice, Slovenia."},{"key":"ref_9","first-page":"677","article-title":"Real-time smart driver sleepiness detection by eye aspect ratio using computer vision","volume":"14","author":"Yuen","year":"2024","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_10","unstructured":"Lyu, J., Yuan, Z., and Chen, D. (2018). Long-term multi-granularity deep framework for driver drowsiness detection. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ghoddoosian, R., Galib, M., and Athitsos, V. (2019, January 16\u201317). A realistic dataset and baseline temporal model for early drowsiness detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00027"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Eswaran, M., Balasubramanie, P., and Nandhini, V. (2024, January 24\u201326). Driver Drowsiness Detection using time lapse images by Deep Learning Approach. Proceedings of the 2024 Third International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Tiruchirappalli, India.","DOI":"10.1109\/ICEEICT61591.2024.10718503"},{"key":"ref_14","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_15","unstructured":"Dakshnakumar, G.S., and Anitha, J. (2023, January 10\u201311). Investigation on driver drowsiness detection using deep learning approaches. Proceedings of the 2023 International Conference on Circuit Power and Computing Technologies (ICCPCT), Kollam, India."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1186\/s44147-024-00457-z","article-title":"Drowsiness detection in real-time via convolutional neural networks and transfer learning","volume":"71","author":"Salem","year":"2024","journal-title":"J. Eng. Appl. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Muthuraja, M., Shanthi, N., Aravindhraj, N., Sarankanth, K., Vigas, M.S., and Shivaani, J. (2024, January 16\u201318). An Acceptable Deep Learning Approach for Detecting Drowsiness. Proceedings of the 2024 9th International Conference on Communication and Electronics Systems, Coimbatore, India.","DOI":"10.1109\/ICCES63552.2024.10859428"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Reddy, B., Kim, Y.H., Yun, S., Seo, C., and Jang, J. (2017, January 21\u201326). Real-time driver drowsiness detection for embedded system using model compression of deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.59"},{"key":"ref_19","first-page":"831","article-title":"Intelligent driver warning system using deep learning-based facial expression recognition","volume":"8","author":"Suchitra","year":"2019","journal-title":"Scopus"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1080\/08839514.2020.1723875","article-title":"Driver fatigue detection using viola jones and principal component analysis","volume":"34","author":"Fatima","year":"2020","journal-title":"Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3155","DOI":"10.1007\/s00521-020-05209-7","article-title":"Deep CNN models-based ensemble approach to driver drowsiness detection","volume":"33","author":"Dua","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, J., Yan, M., Zhu, F., Xu, J., Li, H., and Sun, X. (2022). Fatigue Driving Detection Method Based on Combination of BP Neural Network and Time Cumulative Effect. Sensors, 22.","DOI":"10.3390\/s22134717"},{"key":"ref_23","unstructured":"Jose, J., Raimond, K., and Vincent, S. (2022). SleepyWheels: An Ensemble Model for Drowsiness Detection leading to Accident Prevention. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"William, P., Shamim, M., Yeruva, A.R., Gangodkar, D., Vashisht, S., and Choudhury, A. (2022, January 10\u201312). Deep learning based drowsiness detection and monitoring using behavioural approach. Proceedings of the 2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan.","DOI":"10.1109\/ICTACS56270.2022.9987728"},{"key":"ref_25","first-page":"17","article-title":"Research on a driver fatigue detection model based on image processing","volume":"12","author":"Mu","year":"2022","journal-title":"Hum.-Centric Comput. Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.32604\/iasc.2023.039732","article-title":"Real-Time CNN-Based Driver Distraction & Drowsiness Detection System","volume":"37","author":"Almazroi","year":"2023","journal-title":"Intell. Autom. Soft Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5379","DOI":"10.1109\/TVT.2019.2908425","article-title":"Driver activity recognition for intelligent vehicles: A deep learning approach","volume":"68","author":"Xing","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.54060\/jieee.v4i1.84","article-title":"Drowsiness detection system in real time based on behavioural characteristics of driver using machine learning approach","volume":"4","author":"Adarsh","year":"2023","journal-title":"J. Inform. Electr. Electron. Eng. (JIEEE)"},{"key":"ref_29","first-page":"233","article-title":"Data augmentation for deep learning algorithms that perform driver drowsiness detection","volume":"14","author":"Mohamed","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zheng, H., Wang, Y., and Liu, X. (2023). Adaptive driver face feature fatigue detection algorithm research. Appl. Sci., 13.","DOI":"10.3390\/app13085074"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Rajak, A., Hatwar, P., Tiwari, A., Sahu, G., and Tripathi, R. (2024, January 15\u201316). Efficient Light-weight Deep Learning Models for Drowsiness Detection. Proceedings of the 2024 5th International Conference on Innovative Trends in Information Technology (ICITIIT), Kottayam, India.","DOI":"10.1109\/ICITIIT61487.2024.10580469"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Shokeen, I., Uday, K.M., and Venugopalan, M. (2024, January 4\u20136). Enhancing Driver Safety Using Deep Learning Models. Proceedings of the 2024 5th IEEE Global Conference for Advancement in Technology (GCAT), Bengaluru, India.","DOI":"10.1109\/GCAT62922.2024.10924076"},{"key":"ref_33","unstructured":"Ismail, Y., Essel, E., Abdelhamid, A., Darwich, M., Khalifa, F., and Lacy, F. (2024). High-Fidelity Machine Learning Techniques for Driver Drowsiness Detection, Southern University and A&M College."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Essel, E., Lacy, F., Albalooshi, F., Elmedany, W., and Ismail, Y. (2024). Drowsiness Detection in Drivers Using Facial Feature Analysis. Appl. Sci., 15.","DOI":"10.3390\/app15010020"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Jain, E., Kukreja, V., Saif, M., and Aneja, A. (2024, January 21\u201323). Robust Drowsiness Detection Using Convolutional Neural Networks: A Balanced Approach to Driver Fatigue Monitoring. Proceedings of the 2024 International Conference on Big Data Analytics in Bioinformatics (DABCon), Kolkata, India.","DOI":"10.1109\/DABCon63472.2024.10919423"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.asoc.2014.01.020","article-title":"Fully automated real time fatigue detection of drivers through fuzzy expert systems","volume":"18","author":"Azim","year":"2014","journal-title":"Appl. Soft Comput."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Bergasa, L.M., Almer\u00eda, D., Almaz\u00e1n, J., Yebes, J.J., and Arroyo, R. (2014, January 8\u201311). Drivesafe: An app for alerting inattentive drivers and scoring driving behaviors. Proceedings of the 2014 IEEE Intelligent Vehicles Symposium Proceedings, Dearborn, MI, USA.","DOI":"10.1109\/IVS.2014.6856461"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mehta, S., Dadhich, S., Gumber, S., and Bhatt, A.J. (2019, January 26\u201328). Real-Time Driver Drowsiness Detection System Using Eye Aspect Ratio and Eye Closure Ratio. Proceedings of the International Conference on Sustainable Computing in Science. Technology and Management, Jaipur, India.","DOI":"10.2139\/ssrn.3356401"},{"key":"ref_39","first-page":"49","article-title":"Driver drowsiness detection using gray wolf optimizer based on face and eye tracking","volume":"10","author":"Jasim","year":"2022","journal-title":"Aro-Sci. J. Koya Univ."},{"key":"ref_40","first-page":"720","article-title":"Efficient Driver Drowsiness Detection Using Spatiotemporal Features with Support Vector Machine","volume":"23","author":"Lamouchi","year":"2025","journal-title":"Int. J. Intell. Transp. Syst. Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e70052","DOI":"10.1049\/ipr2.70052","article-title":"Multi-Fatigue Feature Selection and Fuzzy Logic-Based Intelligent Driver Drowsiness Detection","volume":"19","author":"Arava","year":"2025","journal-title":"IET Image Process."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"59","DOI":"10.21608\/jer.2022.503725","article-title":"A cnn-lstm-based deep learning approach for driver drowsiness prediction","volume":"6","author":"Gomaa","year":"2022","journal-title":"J. Eng. Res."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Shen, Q., Zhao, S., Zhang, R., and Zhang, B. (2020, January 17\u201319). Robust two-stream multi-features network for driver drowsiness detection. Proceedings of the 2020 2nd International Conference on Robotics, Intelligent Control and Artificial Intelligence, Shanghai, China.","DOI":"10.1145\/3438872.3439093"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"688","DOI":"10.56578\/ijtdi090401","article-title":"Real-Time Driver Drowsiness Detection Using ViViT for In-Vehicle Monitoring Systems Under Diverse Driving Conditions","volume":"9","author":"Nurnaningsih","year":"2025","journal-title":"Int. J. Transp. Dev. Integr."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"107925","DOI":"10.1016\/j.cmpb.2023.107925","article-title":"Validation and interpretation of a multimodal drowsiness detection system using explainable machine learning","volume":"243","author":"Hasan","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"6568","DOI":"10.1109\/JBHI.2024.3446952","article-title":"Driving fatigue detection based on hybrid electroencephalography and eye tracking","volume":"28","author":"Lian","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Weng, C.H., Lai, Y.H., and Lai, S.H. (2016, January 20\u201324). Driver drowsiness detection via a hierarchical temporal deep belief network. Proceedings of the Asian Conference on Computer Vision, Taipei, Taiwan.","DOI":"10.1007\/978-3-319-54526-4_9"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1109\/TITS.2022.3216017","article-title":"Fatigueview: A multi-camera video dataset for vision-based drowsiness detection","volume":"24","author":"Yang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1038\/s41597-024-03137-y","article-title":"A multimodal driver monitoring benchmark dataset for driver modeling in assisted driving automation","volume":"11","author":"Nobari","year":"2024","journal-title":"Sci. Data"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6193\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:15:05Z","timestamp":1790914505000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":49,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196193"],"URL":"https:\/\/doi.org\/10.3390\/s26196193","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}