Mobile Application Development for Drowsy Driving Alert Using Convolutional Neural Networks
DOI:
https://doi.org/10.33795/jartel.v16i2.9761Keywords:
Android Application, Convolutional Neural Network, Drowsiness Detection, Hybrid Model, Mouth Aspect Ratio (MAR), Real-Time MonitoringAbstract
Drowsiness is a leading cause of traffic accidents globally, necessitating real-time detection systems to enhance driver safety. This study addresses this need by designing and developing an Android-based mobile application for drowsiness detection utilizing a hybrid Convolutional Neural Network (CNN) approach. The system employs two specialized CNN models: one for classifying eye states (open/closed) and another for mouth states (yawn/no_yawn). To improve accuracy and reduce false positives, particularly during speech, the system integrates a geometric filter based on Mouth Aspect Ratio (MAR) calculations. The application, built with Android Studio and Kotlin, uses the device's front camera for real-time monitoring and provides multi-modal alerts (audio, vibration, flashlight, notification) upon detecting drowsiness. Model training achieved high accuracies of 99.82% for eye detection and 98.02% for mouth detection. Real-world testing under normal lighting conditions (300-350 lux) yielded an average detection accuracy of 98.33%, while performance in low-light scenarios (10-25 lux) averaged 88.33%. The application successfully differentiates between drowsiness indicators and normal activities like talking and blinking, demonstrating its potential as a reliable and practical tool for mitigating drowsy driving incidents.
References
R. Rahmadiyani and A. Widyanti, “Prevalence of drowsy driving and modeling its intention: An Indonesian case study,” *Transportation Research Interdisciplinary Perspectives*, vol. 19, no. March, p. 100824, 2023, doi: 10.1016/j.trip.2023.100824.
H. Triamiyono, “Dalam Proses Belajar Mahasiswa,” *Upaya Mengatasi Rasa Kantuk Di Kelas Dalam Proses Belajar Mahasiswa Taruna Akademi Maritim Djadajat*, vol. 2, pp. 64–69, 2014.
E. Lety Istikhomah Puspita Sari, I. Ketut Agung Enriko, J. Gegerkalong Hilir No, J. DI Panjaitan No, and J. Tengah, “Sistem Peringatan Tersemat untuk Pengemudi Mengantuk Embedded Alert System for Drowsy Drivers,” *Jurnal Riset Rekayasa Elektro*, vol. 5, no. 1, 2023. [Online]. Available: [http://jurnalnasional.ump.ac.id/index.php/JRRE](http://jurnalnasional.ump.ac.id/index.php/JRRE)
Y. Jebraeily, Y. Sharafi, and M. Teshnehlab, “Driver Drowsiness Detection Based on Convolutional Neural Network Architecture Optimization Using Genetic Algorithm,” *IEEE Access*, vol. 12, no. April, pp. 45709–45726, 2024, doi: 10.1109/ACCESS.2024.3381999.
R. O. Alnashwan, S. A. Chelloug, N. S. Almalki, I. Issaoui, A. Motwakel, and A. Sayed, “Lighting Search Algorithm With Convolutional Neural Network-Based Image Captioning System for Natural Language Processing,” *IEEE Access*, vol. 11, no. November, pp. 142643–142651, 2023, doi: 10.1109/ACCESS.2023.3342703.
X. Li, S. Lai, and X. Qian, “DBCFace: Towards Pure Convolutional Neural Network Face Detection,” *IEEE Transactions on Circuits and Systems for Video Technology*, vol. 32, no. 4, pp. 1792–1804, 2022, doi: 10.1109/TCSVT.2021.3082635.
S. Hossain, S. Umer, R. K. Rout, and H. Al Marzouqi, “A Deep Quantum Convolutional Neural Network Based Facial Expression Recognition For Mental Health Analysis,” *IEEE Transactions on Neural Systems and Rehabilitation Engineering*, vol. 32, pp. 1556–1565, 2024, doi: 10.1109/TNSRE.2024.3385336.
D. Soydaner and J. Wagemans, “Multi-Task Convolutional Neural Network for Image Aesthetic Assessment,” *IEEE Access*, vol. 12, no. January, pp. 4716–4729, 2024, doi: 10.1109/ACCESS.2024.3349961.
Y. He, Y. Zhang, S. Chen, and Y. Hu, “Facial Expression Recognition Using Hierarchical Features With Three-Channel Convolutional Neural Network,” *IEEE Access*, vol. 11, no. July, pp. 84785–84794, 2023, doi: 10.1109/ACCESS.2023.3303402.
B. Fu, F. Boutros, C. T. Lin, and N. Damer, “A Survey on Drowsiness Detection: Modern Applications and Methods,” *IEEE Transactions on Intelligent Vehicles*, vol. 9, no. 11, pp. 7279–7300, 2024, doi: 10.1109/TIV.2024.3395889.
H. Z. Ilmadina, D. Apriliani, and D. S. Wibowo, “Deteksi Pengendara Mengantuk dengan Kombinasi Haar Cascade Classifier dan Support Vector Machine,” *Jurnal Informatika: Jurnal Pengembangan IT*, vol. 7, no. 1, pp. 1–7, 2022, doi: 10.30591/jpit.v7i1.3346.
P. K. Singh, A. Gupta, M. Upadhyay, A. Jain, M. Khari, and P. S. Lamba, “Multimodal Driver Drowsiness Detection From Video Frames,” *Journal of Mobile Multimedia*, vol. 19, no. 2, pp. 567–586, 2023, doi: 10.13052/jmm1550-4646.19210.
T. Sharma *et al*., “Deep Learning-Based Object Detection and Classification for Autonomous Vehicles in Different Weather Scenarios of Quebec, Canada,” *IEEE Access*, vol. 12, no. September 2023, pp. 13648–13662, 2024, doi: 10.1109/ACCESS.2024.3354076.
“View of Development of Smart Money Classifier & Location Tracker Application Based on Convolutional Neural Network (CNN) for The Visually Impaired.pdf.”
Q. Zhu and X. Zu, “Fully Convolutional Neural Network Structure and Its Loss Function for Image Classification,” *IEEE Access*, vol. 10, pp. 35541–35549, 2022, doi: 10.1109/ACCESS.2022.3163849.
R. Gelar Guntara, “Pemanfaatan Google Colab Untuk Aplikasi Pendeteksian Masker Wajah Menggunakan Algoritma Deep Learning YOLOv7,” *Jurnal Teknologi Dan Sistem Informasi Bisnis*, vol. 5, no. 1, pp. 55–60, 2023, doi: 10.47233/jteksis.v5i1.750.
