Lumina Alert: A YOLOv11n-Based Embedded System for Real-Time Driver Drowsiness Detection and Multi-Modal Intervention


Authors : Elijah L. Boon; Grazielle Nychole Dela Cruz; Chaz B. Honrada; Trishia Jane T. Javier; Paolo Roberto O. Lozada; Tommy A. Ditucalan

Volume/Issue : Volume 11 - 2026, Issue 2 - February


Google Scholar : https://tinyurl.com/ms6djw4j

Scribd : https://tinyurl.com/4cwumntk

DOI : https://doi.org/10.38124/ijisrt/26feb752

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.


Abstract : Driver fatigue accounts for approximately 10–20% of road accidents worldwide. This paper presents Lumina Alert, an AI-based in-vehicle driver drowsiness detection and intervention system deployed on a Toyota Avanza (2007). The system is implemented on a Jetson Orin Nano and uses a YOLOv11n-based facial monitoring model to detect drowsiness indicators such as eye closure and yawning. Upon detection, the system applies multi-modal interventions including auditory alerts, voice prompts, and ignition lockout. Experimental results show an overall detection accuracy of 93.1%, with performance exceeding 90% under occlusion conditions involving sunglasses and eyeglasses. The ignition lockout mechanism successfully prevented vehicle startup in 95% of drowsy cases, while auditory and voice alerts effectively refocused drivers in 92% of trials. The system achieved over 90% reliability in both daytime and nighttime conditions with a minimum response time of 7 ms, enabling real-time operation.

Keywords : Driver Drowsiness Detection; YOLO-Based Facial Monitoring; Embedded AI Systems; Ignition Lockout; Automated Interventions; Intelligent Vehicle Safety.

References :

  1. Brake, “Driver fatigue,” Brake, Jun. 26, 2023. https://www.brake.org.uk/get-involved/take-action/mybrake/knowledge-centre/driver-fatigue
  2. National Sleep Foundation, “What is Microsleep?,” National Sleep Foundation, Oct. 17, 2024. https://www.thensf.org/what-is-microsleep/
  3. Ryder, “A guide to combating truck driver fatigue,” Ryder Website, Dec. 13, 2024. https://www.ryder.com/en-us/insights/blogs/transportation/combating-driver-fatigue
  4. DOST, “DOST builds on ‘AI’ national strategy,” May 02, 2025. https://www.dost.gov.ph/knowledge-resources/news/86-2025-news/3989-dost-builds-on-ai-national-strategy.html
  5. K. Santos, “10 Common causes of road crashes in the Philippines,” https://www.topgear.com.ph, May 20, 2025. https://www.topgear.com.ph/features/feature-articles/common-causes-of-road-crashes-in-the-philippines-a4682-20250514-lfrm
  6. E. Ares, “Drowsy driving: Tips to manage fatigue to avoid road accidents,” Cebu Daily News, Sep. 16, 2024. https://cebudailynews.inquirer.net/595167/drowsy-driving-tips-to-manage-fatigue-to-avoid-road-accidents
  7. BusinessWorld, “DoTr orders shorter driving hours, regular drug testing for public utility drivers,” BusinessWorld Online, May 05, 2025. https://www.bworldonline.com/the-nation/2025/05/05/670450/dotr-orders-shorter-driving-hours-regular-drug-testing-for-public-utility-drivers/
  8. Z. Sarao, “LTFRB requires safety training for PUV drivers, conductors,” INQUIRER.net, Mar. 06, 2025. [Online]. Available: https://newsinfo.inquirer.net/2040705/ltfrb-requires-safety-training-for-puv-drivers-conductors
  9. H. Respicio, “Criminal liability for vehicular accident resulting in death in the Philippines,” RESPICIO & CO., Apr. 01, 2025. https://www.respicio.ph/commentaries/criminal-liability-for-vehicular-accident-resulting-in-death-in-the-philippines
  10. GMA Integrated News, “Driver who fell asleep in moving pick-up told to explain by LTO,” GMA News Online, Mar. 28, 2025. [Online]. Available: https://www.gmanetwork.com/news/topstories/nation/940937/lto-driver-falls-asleep-while-driving-pick-up-truck-viral/story/
  11. Brigada, “Sleepy driver crashes in Davao,” Brigada News, Apr. 07, 2025. https://www.brigadanews.ph/sleepy-driver-crashes-in-davao/
  12. GMA Integrated News, “SUV rams into five vehicles after driver allegedly fell asleep ,” GMA News Online, Apr. 11, 2025. [Online]. Available: https://www.gmanetwork.com/news/topstories/metro/942478/suv-rams-into-five-vehicles-after-driver-allegedly-fell-asleep/story/
  13. J. Manahan, “SCTEX bus driver’s maintenance meds may have caused sleepiness: LTFRB | ABS-CBN News,” ABS-CBN, May 07, 2025. [Online]. Available: https://www.abs-cbn.com/news/nation/2025/5/7/sctex-bus-driver-s-maintenance-meds-may-have-caused-sleepiness-ltfrb-1540
  14. D. Salem and M. Waleed, “Drowsiness detection in real-time via convolutional neural networks and transfer learning,” Journal of Engineering and Applied Science, vol. 71, no. 1, May 2024, doi: 10.1186/s44147-024-00457-z.
  15. A. K. Biswal, D. Singh, B. K. Pattanayak, D. Samanta, and M.-H. Yang, “IoT‐Based Smart Alert System for drowsy driver detection,” Wireless Communications and Mobile Computing, vol. 2021, no. 1, Jan. 2021, doi: 10.1155/2021/6627217.
  16. A. Singh, S. Samuel, J. Singh, and Y. K. Dhabi, “Internet of Things (IoT) based Drowsiness Detection and Intervention System,” AHFE International, Jan. 2023, doi: 10.54941/ahfe1002955.
  17. V. Badami, “Proven 5 Best Practices for testing Object Detection models: How to ensure all objects are accurately detected,” Miami Federal, Sep. 22, 2025. https://miamifed.com/object-detection-models/
  18. M. Gupta and A. Verma, “Drowsiness Detection System: combining YOLO pytorch, and python for enhanced road safety,” 2024. http://www.ir.juit.ac.in:8080/jspui/handle/123456789/11376
  19. C. Chen, X. Liu, M. Zhou, Z. Li, Z. Du, and Y. Lin, “Lightweight and Real-Time Driver Fatigue Detection Based on MG-YOLOv8 with Facial Multi-Feature Fusion,” Journal of Imaging, vol. 11, no. 11, p. 385, Nov. 2025, doi: 10.3390/jimaging11110385.
  20. B. Fu, F. Boutros, C.-T. Lin, and N. Damer, “A Survey on Drowsiness Detection – Modern Applications and Methods,” Aug. 23, 2024. https://arxiv.org/html/2408.12990v1
  21. A. a B. S. Shankar Vishnuvardhan M, Yadam Karthik* and Saisuraj, “Enhancing road safety: integrating advanced technologies for driver drowsiness and alcohol impairment detection,” Mar. 24, 2025. https://www.interesjournals.org/articles/enhancing-road-safety-integrating-advanced-technologies-for-driver-drowsiness-and-alcohol-impairment-detection-114097.html
  22. G. Hamza, M. Z. Es-Sadek, and Y. Taher, “Enhancing road safety: a Multi-Modal drowsiness detection system for drivers,” International Journal of Advanced Computer Science and Applications, vol. 16, no. 1, Jan. 2025, doi: 10.14569/ijacsa.2025.0160197.
  23. E. Papachristos, T. Merritt, E. Schneiders, D. Jahanshiri, A. Pir, and A. Ciobanu, “Sound Strategies for Safe Driving: Exploring Auditory Interventions to Counteract Passive Driver Fatigue,” ACM Digital Library, pp. 1–6, Sep. 2024, doi: 10.1145/3686038.3686042.
  24. P. Oberndorfer, “Live latency analysis of IP cameras in camera monitor systems,” University of Applied Sciences Upper Austria, 2025. https://pure.fh-ooe.at/en/studentTheses/live-latency-analysis-of-ip-cameras-in-camera-monitor-systems/
  25. Google, “Classification: Accuracy, recall, precision, and related metrics,” Google for Developers, Jan. 12, 2026. https://developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall
  26. R. Kundu, “F1 Score in Machine Learning: Intro & Calculation,” V7, Dec. 16, 2022. https://www.v7labs.com/blog/f1-score-guide
  27. Ultralytics, “Model Prediction with Ultralytics YOLO,” Ultralytics YOLO Docs, Jan. 21, 2026. https://docs.ultralytics.com/modes/predict/

Driver fatigue accounts for approximately 10–20% of road accidents worldwide. This paper presents Lumina Alert, an AI-based in-vehicle driver drowsiness detection and intervention system deployed on a Toyota Avanza (2007). The system is implemented on a Jetson Orin Nano and uses a YOLOv11n-based facial monitoring model to detect drowsiness indicators such as eye closure and yawning. Upon detection, the system applies multi-modal interventions including auditory alerts, voice prompts, and ignition lockout. Experimental results show an overall detection accuracy of 93.1%, with performance exceeding 90% under occlusion conditions involving sunglasses and eyeglasses. The ignition lockout mechanism successfully prevented vehicle startup in 95% of drowsy cases, while auditory and voice alerts effectively refocused drivers in 92% of trials. The system achieved over 90% reliability in both daytime and nighttime conditions with a minimum response time of 7 ms, enabling real-time operation.

Keywords : Driver Drowsiness Detection; YOLO-Based Facial Monitoring; Embedded AI Systems; Ignition Lockout; Automated Interventions; Intelligent Vehicle Safety.

Paper Submission Last Date
31 - March - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe