{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T12:15:21Z","timestamp":1776341721118,"version":"3.51.2"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The purpose of this research study is to establish a practical independent drowsy eye detection method with deep learning (DL) techniques. This detection technique will assist in determining the drowsiness state of drivers by visually detecting their drowsy eye condition to provide for early warning systems and improve the safety of the vehicle and passengers in areas such as driver monitoring and the assessment of fatigue.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials<\/jats:title>\n                    <jats:p>A publicly available dataset is employed in this study, which includes 49,793 images of different eye conditions captured in various settings. In preparation for model training, the dataset must be processed through initial preprocessing steps, which include image size reduction, image normalization, and augmentation to help increase the model's ability to generalize and reduce the risk of the model becoming too specialized or over-fitting. Once the dataset has been processed, it will then be divided into 70% training, 15% validation, and 15% testing subsets. Additionally, a tenfold cross-validation approach will also be used to evaluate the model and ensure its reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The experimental framework includes the evaluation of five different DL architectures: ConvNeXt-Base, ResNeSt101, CaiT-S36, Twins-SVT-Base, and the developed architecture\u2014DrowSFormer. In each of these architectures, the models were trained for 50 epochs with a batch size of 64 on the pre-processed dataset. The experimental framework consists of three primary stages in order to train and test the models; training phase, validation phase, and testing phase. The performance of the models was evaluated using various classification metrics to assess their effectiveness. Finally, the use of Grad-CAM (Gradient-weighted Class Activation Mapping) has been implemented as an XAI tool to provide explanations of the contribution of specific areas to the prediction made by the models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The experimental evaluation reveals that the proposed DrowSFormer model achieves the highest testing performance among all models, with an obtained accuracy of 99.58%. This result significantly surpasses the baseline and state-of-the-art (SOTA) models used in the study, including transformer-based and convolutional neural networks (ConvNet) based models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study successfully demonstrates the effectiveness of transformer-based architectures for standalone drowsy eye detection. The proposed DrowSFormer model, supported by thorough training and evaluation procedures, exhibits outstanding performance across all evaluation metrics. With the integration of Grad-CAM visualizations, the system not only delivers high accuracy but also provides interpretability, reinforcing user trust and offering insights into the model\u2019s decision-making process.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11063-026-11841-6","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:43:42Z","timestamp":1773085422000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DrowSFormer-XAI: A Cross-Attentive Neural Network-Transformer Fusion Framework for Drowsiness Detection with Explainable AI"],"prefix":"10.1007","volume":"58","author":[{"given":"Kathirvel","family":"Rajalingam","sequence":"first","affiliation":[]},{"given":"Saravanan","family":"Srinivasan","sequence":"additional","affiliation":[]},{"given":"Sakthi","family":"Govindaraju","sequence":"additional","affiliation":[]},{"given":"Sandeep Kumar","family":"Mathivanan","sequence":"additional","affiliation":[]},{"given":"Sangeetha","family":"Ramaswamy","sequence":"additional","affiliation":[]},{"given":"Usha","family":"Moorthy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"issue":"3","key":"11841_CR1","doi-asserted-by":"publisher","first-page":"9441","DOI":"10.1007\/s11042-023-15054-0","volume":"83","author":"SA El-Nabi","year":"2023","unstructured":"El-Nabi SA, El-Shafai W, El-Rabaie EM, Ramadan KF, El-Samie FEA, Mohsen S (2023) Machine learning and DL techniques for driver fatigue and drowsiness detection: a review. Multimed Tools Appl 83(3):9441\u20139477. https:\/\/doi.org\/10.1007\/s11042-023-15054-0","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"11841_CR2","doi-asserted-by":"publisher","DOI":"10.3390\/s21010056","volume":"21","author":"Q Abbas","year":"2020","unstructured":"Abbas Q, Alsheddy A (2020) Driver fatigue detection systems using multi-sensors, smartphone, and cloud-based computing platforms: a comparative analysis. Sensors 21(1):56. https:\/\/doi.org\/10.3390\/s21010056","journal-title":"Sensors"},{"issue":"1","key":"11841_CR3","doi-asserted-by":"publisher","first-page":"329","DOI":"10.15379\/ijmst.v10i1.1815","volume":"10","author":"K Ahmad","year":"2023","unstructured":"Ahmad K, Em PP, Aziz NaA (2023) Machine learning approaches for detecting driver drowsiness: a critical review. Int J Membr Sci Technol 10(1):329\u2013346. https:\/\/doi.org\/10.15379\/ijmst.v10i1.1815","journal-title":"Int J Membr Sci Technol"},{"issue":"5","key":"11841_CR4","doi-asserted-by":"publisher","DOI":"10.3390\/s22052069","volume":"22","author":"Y Albadawi","year":"2022","unstructured":"Albadawi Y, Takruri M, Awad M (2022) A review of recent developments in driver drowsiness detection systems. Sensors 22(5):2069. https:\/\/doi.org\/10.3390\/s22052069","journal-title":"Sensors"},{"key":"11841_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19738-z","author":"M Kamboj","year":"2024","unstructured":"Kamboj M, Kadian K, Dwivedi V, Wary A, Ojha S (2024) Advanced detection techniques for driver drowsiness: a comprehensive review of machine learning, DL, and physiological approaches. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-024-19738-z","journal-title":"Multimed Tools Appl"},{"issue":"11","key":"11841_CR6","doi-asserted-by":"publisher","first-page":"7279","DOI":"10.1109\/TIV.2024.3395889","volume":"9","author":"F Biying","year":"2024","unstructured":"Biying F, Boutros F, Lin C-T, Damer N (2024) A survey on drowsiness detection: modern applications and methods. IEEE Trans Intell Veh 9(11):7279\u20137300","journal-title":"IEEE Trans Intell Veh"},{"issue":"5","key":"11841_CR7","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1007\/s11571-022-09898-9","volume":"17","author":"AA Saleem","year":"2022","unstructured":"Saleem AA, Siddiqui HUR, Raza MA, Rustam F, Dudley S, Ashraf I (2022) A systematic review of physiological signals based driver drowsiness detection systems. Cogn Neurodyn 17(5):1229\u20131259. https:\/\/doi.org\/10.1007\/s11571-022-09898-9","journal-title":"Cogn Neurodyn"},{"key":"11841_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19890-6","author":"EM Bearly","year":"2024","unstructured":"Bearly EM, Chitra R (2024) A systematic review on analysis of automatic drowsiness detection for preventing road accidents. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-024-19890-6","journal-title":"Multimed Tools Appl"},{"key":"11841_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2023.100864","volume":"21","author":"ME Shaik","year":"2023","unstructured":"Shaik ME (2023) A systematic review on detection and prediction of driver drowsiness. Transp Res Interdiscip Perspect 21:100864. https:\/\/doi.org\/10.1016\/j.trip.2023.100864","journal-title":"Transp Res Interdiscip Perspect"},{"issue":"15","key":"11841_CR10","doi-asserted-by":"publisher","first-page":"20425","DOI":"10.1007\/s11042-022-12433-x","volume":"81","author":"SS Husain","year":"2022","unstructured":"Husain SS, Mir J, Anwar SM, Rafique W, Ullah MO (2022) Development and validation of a DL-based algorithm for drowsiness detection in facial photographs. Multimedia Tools Appl 81(15):20425\u201320441. https:\/\/doi.org\/10.1007\/s11042-022-12433-x","journal-title":"Multimedia Tools Appl"},{"issue":"11","key":"11841_CR11","doi-asserted-by":"publisher","DOI":"10.3390\/s21113786","volume":"21","author":"I Stancin","year":"2021","unstructured":"Stancin I, Cifrek M, Jovic A (2021) A review of EEG signal features and their application in driver drowsiness detection systems. Sensors 21(11):3786. https:\/\/doi.org\/10.3390\/s21113786","journal-title":"Sensors"},{"key":"11841_CR12","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2594","volume":"11","author":"J Xiong","year":"2025","unstructured":"Xiong J, Dai W, Wang Q, Dong X, Ye B, Yang J (2025) A review of DL in blink detection. PeerJ Comput Sci 11:e2594. https:\/\/doi.org\/10.7717\/peerj-cs.2594","journal-title":"PeerJ Comput Sci"},{"issue":"6","key":"11841_CR13","doi-asserted-by":"publisher","first-page":"2339","DOI":"10.1109\/tits.2018.2868499","volume":"20","author":"G Sikander","year":"2018","unstructured":"Sikander G, Anwar S (2018) Driver fatigue detection systems: a review. IEEE Trans Intell Transp Syst 20(6):2339\u20132352. https:\/\/doi.org\/10.1109\/tits.2018.2868499","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11841_CR14","doi-asserted-by":"publisher","unstructured":"Dipu MTA, Hossain SS, Arafat Y, Rafiq FB (2021) Real-time driver drowsiness detection using DL. Int J Adv Comput Sci Appl. https:\/\/doi.org\/10.14569\/ijacsa.2021.0120794","DOI":"10.14569\/ijacsa.2021.0120794"},{"key":"11841_CR15","doi-asserted-by":"publisher","unstructured":"Latreche I, Slatnia S, Kazar O, Barka E, Harous S (2024) A review on DL techniques for EEG-based driver drowsiness detection systems. Informatica. https:\/\/doi.org\/10.31449\/inf.v48i3.5056","DOI":"10.31449\/inf.v48i3.5056"},{"key":"11841_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-02111-x","author":"OF Hassan","year":"2025","unstructured":"Hassan OF, Ibrahim AF, Gomaa A, Makhlouf MA, Hafiz B (2025) Real-time driver drowsiness detection using transformer architectures: a novel DL approach. Sci Rep. https:\/\/doi.org\/10.1038\/s41598-025-02111-x","journal-title":"Sci Rep"},{"issue":"3","key":"11841_CR17","first-page":"59","volume":"6","author":"M Gomaa","year":"2022","unstructured":"Gomaa M (2022) A CONVNET-LSTM-based DL approach for driver drowsiness prediction. J Eng Res 6(3):59\u201370","journal-title":"J Eng Res"},{"key":"11841_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-20546-8","author":"A Gomaa","year":"2025","unstructured":"Gomaa A, Saad OM (2025) Residual channel-attention (RCA) network for remote sensing image scene classification. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-024-20546-8","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"11841_CR19","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1007\/s11554-022-01211-5","volume":"19","author":"S Saurav","year":"2022","unstructured":"Saurav S, Gidde P, Saini R, Singh S (2022) Real-time eye state recognition using dual convolutional neural network ensemble. J Real-Time Image Process 19(3):607\u2013622. https:\/\/doi.org\/10.1007\/s11554-022-01211-5","journal-title":"J Real-Time Image Process"},{"issue":"3","key":"11841_CR20","doi-asserted-by":"publisher","DOI":"10.3390\/app12031145","volume":"12","author":"E Mag\u00e1n","year":"2022","unstructured":"Mag\u00e1n E, Sesmero MP, Alonso-Weber JM, Sanchis A (2022) Driver drowsiness detection by applying DL techniques to sequences of images. Appl Sci 12(3):1145. https:\/\/doi.org\/10.3390\/app12031145","journal-title":"Appl Sci"},{"issue":"14","key":"11841_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/s23146459","volume":"23","author":"F Safarov","year":"2023","unstructured":"Safarov F, Akhmedov F, Abdusalomov AB, Nasimov R, Cho YI (2023) Real-time DL-based drowsiness detection: leveraging computer-vision and eye-blink analyses for enhanced road safety. Sensors 23(14):6459. https:\/\/doi.org\/10.3390\/s23146459","journal-title":"Sensors"},{"issue":"3","key":"11841_CR22","doi-asserted-by":"publisher","DOI":"10.3390\/safety9030065","volume":"9","author":"MIB Ahmed","year":"2023","unstructured":"Ahmed MIB, Alabdulkarem H, Alomair F, Aldossary D, Alahmari M, Alhumaidan M, Alrassan S, Rahman A, Youldash M, Zaman G (2023) A deep-learning approach to driver drowsiness detection. Safety 9(3):65. https:\/\/doi.org\/10.3390\/safety9030065","journal-title":"Safety"},{"issue":"12","key":"11841_CR23","doi-asserted-by":"publisher","first-page":"3711","DOI":"10.3390\/s25123711","volume":"25","author":"SH Al-Gburi","year":"2025","unstructured":"Al-Gburi SH, Al-Sammak KA, Marghescu I, Oprea CC, Dr\u0103gulinescu AC, Alduais NaM, Alheeti KMA, Al-Sammak NaH (2025) EFFRES-DrowsyNet: a novel hybrid DL model combining EfficientNetB0 and RESNET50 for driver drowsiness detection. Sensors 25(12):3711. https:\/\/doi.org\/10.3390\/s25123711","journal-title":"Sensors"},{"issue":"13","key":"11841_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/app13137849","volume":"13","author":"R Florez","year":"2023","unstructured":"Florez R, Palomino-Quispe F, Coaquira-Castillo RJ, Herrera-Levano JC, Paix\u00e3o T, Alvarez AB (2023) A CONVNET-based approach for driver drowsiness detection by real-time eye state identification. Appl Sci 13(13):7849. https:\/\/doi.org\/10.3390\/app13137849","journal-title":"Appl Sci"},{"issue":"16","key":"11841_CR25","doi-asserted-by":"publisher","first-page":"48261","DOI":"10.1007\/s11042-023-17272-y","volume":"83","author":"EM Bearly","year":"2023","unstructured":"Bearly EM, Chitra R (2023) Automatic drowsiness detection for preventing road accidents via 3dgan and three-level attention. Multimed Tools Appl 83(16):48261\u201348274. https:\/\/doi.org\/10.1007\/s11042-023-17272-y","journal-title":"Multimed Tools Appl"},{"key":"11841_CR26","unstructured":"Drowsy Detection\u2014DRi, NDi, OEi and CEi dataset. (2025b). Kaggle. https:\/\/www.kaggle.com\/datasets\/saravanansri\/drowsy-detection-dri-ndi-oei-and-cei-dataset."},{"key":"11841_CR27","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.isprsjprs.2022.11.006","volume":"195","author":"S Chen","year":"2022","unstructured":"Chen S, Ogawa Y, Zhao C, Sekimoto Y (2022) Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach. ISPRS J Photogramm Remote Sens 195:129\u2013152. https:\/\/doi.org\/10.1016\/j.isprsjprs.2022.11.006","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"11841_CR28","doi-asserted-by":"publisher","unstructured":"Zhang H, Wu C, Zhang Z, Zhu Y, Lin H, Zhang Z, Sun Y, He T, Mueller J, Manmatha R, Li M, Smola A (2020) RESNEST: split-attention networks. arXiv (Cornell University). https:\/\/doi.org\/10.48550\/arxiv.2004.08955","DOI":"10.48550\/arxiv.2004.08955"},{"key":"11841_CR29","doi-asserted-by":"crossref","unstructured":"Zhao Z, Chuah JH, Chow C, Xia K, Tee YK, Hum YC, Lai KW (n.d.) Machine learning approaches in comparative studies for Alzheimer\u2019s diagnosis using 2D MRI slices. T\u00dcB\u0130TAK Academic J. https:\/\/journals.tubitak.gov.tr\/elektrik\/vol32\/iss1\/6\/","DOI":"10.55730\/1300-0632.4057"},{"key":"11841_CR30","unstructured":"Chu X, Tian Z, Wang Y, Zhang B, Ren H, Wei X, Xia H, Shen C (2021) Twins: revisiting the design of spatial attention in vision transformers. In: NIPS'21: proceedings of the 35th international conference on neural information processing systems. 716, 9355\u20139366"},{"issue":"3","key":"11841_CR31","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.3390\/app15031102","volume":"15","author":"TS Delwar","year":"2025","unstructured":"Delwar TS, Singh M, Mukhopadhyay S, Kumar A, Parashar D, Lee Y, Rahman MH, Sejan MaS, Ryu JY (2025) AI- and DL-powered driver drowsiness detection method using facial analysis. Appl Sci 15(3):1102. https:\/\/doi.org\/10.3390\/app15031102","journal-title":"Appl Sci"},{"key":"11841_CR32","doi-asserted-by":"publisher","DOI":"10.1186\/s40648-025-00307-4","author":"A Bhanja","year":"2025","unstructured":"Bhanja A, Parhi D, Gajendra D, Sinha K, Sahoo AK (2025) Driver drowsiness shield (DDSH): a real-time driver drowsiness detection system. ROBOMECH J. https:\/\/doi.org\/10.1186\/s40648-025-00307-4","journal-title":"ROBOMECH J"},{"issue":"3","key":"11841_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/s25030812","volume":"25","author":"S Essahraui","year":"2025","unstructured":"Essahraui S, Lamaakal I, Hamly IE, Maleh Y, Ouahbi I, Makkaoui KE, Bouami MF, P\u0142awiak P, Alfarraj O, El-Latif AaA (2025) Real-time driver drowsiness detection using facial analysis and machine learning techniques. Sensors 25(3):812. https:\/\/doi.org\/10.3390\/s25030812","journal-title":"Sensors"},{"key":"11841_CR34","doi-asserted-by":"publisher","unstructured":"Bakheet S, Al-Hamadi A, Alanazi A (2025) An effective approach for real-time drowsy driving prediction using quantized fisher-Gabor features and latent-dynamic conditional random fields. Front Comput Sci. https:\/\/doi.org\/10.3389\/fcomp.2025.1437084","DOI":"10.3389\/fcomp.2025.1437084"},{"key":"11841_CR35","doi-asserted-by":"publisher","unstructured":"Pathak AK, Singh AK, Kumar P, Bhatia V, Krejcar O (2025) Real-time anti-sleep alert algorithm to prevent road accidents to ensure road safety. Front Fut Transp. https:\/\/doi.org\/10.3389\/ffutr.2025.1545411","DOI":"10.3389\/ffutr.2025.1545411"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-026-11841-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-026-11841-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-026-11841-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T11:34:55Z","timestamp":1776339295000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-026-11841-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["11841"],"URL":"https:\/\/doi.org\/10.1007\/s11063-026-11841-6","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"assertion":[{"value":"17 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"30"}}