Development of a Real-Time Smartphone Based Drowsiness Detection System Using MobileNet and Google ML Kit

Ade Zulkarnain Hasibuan; Munjiat Setiani Asih

doi:10.35447/jitekh.v14i1.1374

Authors

Ade Zulkarnain Hasibuan Samudra University, Langsa
Munjiat Setiani Asih Harapan Medan University, Medan

DOI:

https://doi.org/10.35447/jitekh.v14i1.1374

Keywords:

Drowsiness Detection, MobileNetV1, Google ML Kit, Real-Time System, Android Application

Abstract

The rapid development of smartphone technology has increased the duration of device usage, which can lead to eye fatigue, decreased concentration, and drowsiness. Many users continue using smartphones despite experiencing signs of fatigue, potentially affecting health and productivity. Therefore, this study aims to develop a real-time drowsiness detection system for smartphone users based on Android using Google ML Kit and MobileNetV1. The system utilizes Google ML Kit for face detection and MobileNetV1 for classifying eye conditions into open and closed states. The dataset used is a combination of a public dataset from Kaggle (dataset_B_Eye_Images) and additional data collected independently to improve model generalization. The model was trained and further optimized through a fine-tuning process. Experimental results show that the model achieved an accuracy of approximately 96%, with balanced precision, recall, and F1-score values. The confusion matrix analysis indicates improved performance after fine-tuning. In real-time implementation, the system operates at 6.0–7.3 FPS with a latency of 60–72 ms per frame and a notification response time of less than 1 second. The system demonstrates robustness under varying lighting conditions, achieving accuracy up to 100% in bright conditions, 98% in normal conditions, and 95% in low-light conditions. However, performance decreases when users wear glasses due to reflection interference. Overall, the results indicate that MobileNetV1 is effective for real-time drowsiness detection on mobile devices, although further improvements are needed to enhance system robustness under diverse user conditions

Downloads

Download data is not yet available.

References

C. Dhasarathan et al., “Tensor RT optimized driver drowsiness detection system using edge device,” Ain Shams Eng. J., vol. 16, no. July, 2025, doi: https://doi.org/10.1016/j.asej.2025.103620.

D. Khetan, A. Nawani, A. Aggarwal, and M. S. Kaur, “Driver Drowsiness Detection in Real-time,” Fusion Pract. Appl., vol. 7, no. 2, pp. 91–99, 2022, doi: Doi : https://doi.org/10.54216/FPA.070203.

Y. Ling and X. Weng, “Efficient and Robust Driver Fatigue Detection Framework Based on the Visual Analysis of Eye States,” Promet ‒ Traffic&Transportation, vol. 35, no. 4, pp. 567–582, 2023.

Y. Wang, B. Liu, and H. Wang, “Fatigue Detection Based on Facial Feature Correction and Fusion,” in Journal of Physics: Conference Series, Purpose-Led Publishing, 2022. doi: 10.1088/1742-6596/2183/1/012022.

Z. Zhao, N. Zhou, L. Zhang, H. Yan, Y. Xu, and Z. Zhang, “Driver Fatigue Detection Based on Convolutional Neural Networks Using EM-CNN,” Hindawi Comput. Intell. Neurosci., no. 3, 2020, doi: 10.1155/2020/7251280.

N. Jamil, M. Haziq, M. Fadhil, and M. I. Ramli, “Comparing MobileNet-SSD and YOLO v3 Learning Architecture for Real- time Driver’s Fatigue Detection,” Int. J. Acad. Res. Bus. Soc. Sci., vol. 11, no. 12, pp. 2409–2419, 2021, doi: 10.6007/IJARBSS/v11-i12/11984.

M. Vimala, M. Nandhini, S. Jasmine, P. R. Kumar, and S. Ramasamy, “Franklin Open Implementation of a Lightweight Deep Learning Model for Detecting Driver Fatigue,” Franklin Open, vol. 15, 2026, doi: 10.1016/j.fraope.2026.100547.

M. A. B. Abbass and Y. Ban, “MobileNet-Based Architecture for Distracted Human Driver Detection of Autonomous Cars,” Electronics, pp. 1–14, 2024.

H. Z. Ilmadina, M. Naufal, and D. S. Wibowo, “Drowsiness Detection Based on Yawning Using Modified Pre-trained Model MobileNetV2 and ResNet50,” Matrik J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 22, no. 3, pp. 419–430, 2023, doi: 10.30812/matrik.v22i3.2785.

Z. Xiao, Z. Hu, L. Geng, F. Zhang, J. Wu, and Y. Li, “Fatigue Driving Recognition Network : Fatigue Driving Recognition Via Convolutional Neural Network and Long Short-Term Memory Units,” IET Intell. Transp. Syst., pp. 1–7, 2019, doi: 10.1049/iet-its.2018.5392.

S. Cao, P. Feng, W. Kang, Z. Chen, and B. Wang, “Optimized driver fatigue detection method using multimodal neural networks,” Sci. Rep., vol. 15, pp. 1–26, 2025.

O. Jagtap, S. Chaurasia, P. Choudhary, G. Buwade, M. Dhote, and U. B. Aher, “Driver Drowsiness Detection System using Arduino and Deep Learning,” Int. J. Innov. Eng. Sci., vol. 8, no. 10, pp. 6–19, 2023.

E. Prasetyo, R. Purbaningtyas, R. D. Adityo, N. Suciati, and C. Fatichah, “Combining MobileNetV1 and Depthwise Separable convolution bottleneck with Expansion for Classifying the Freshness of Fish Eyes,” in INFORMATION PROCESSING IN AGRICULTURE 9, 2022, pp. 485–496.

C. Zhang, T. Yang, and J. Yang, “Image Recognition of Wind Turbine Blade Defects Using Attention-Based MobileNetv1-YOLOv4 and Transfer Learning,” Sensors, vol. 22, pp. 1–18, 2022.

F. Su, Y. Zhao, G. Wang, P. Liu, Y. Yan, and L. Zu, “Tomato Maturity Classification Based on SE-YOLOv3-MobileNetV1 Network under Nature Greenhouse Environment,” Argonomy, vol. 12, pp. 1–15, 2022.

M. M. Mijwil, R. Doshi, K. K. Hiran, O. J. Unogwu, and I. Bala, “Mobilenetv1-Based Deep Learning Model for Accurate Brain Tumor Classification,” Mesopotamian J. Comput. Sci., vol. 2023, pp. 29–38, 2023.

A. Pundir et al., “Enhancing Gait Recognition by Multimodal Fusion of MobileNetv1 and Xception Features Via PCA for OaA ‑ SVM Classification,” Sci. Rep., vol. 14, pp. 1–17, 2024, doi: 10.1038/s41598-024-68053-y.

S. Zhao, Y. Peng, Y. Wang, G. Li, and M. Al-mahbashi, “Lightweight YOLOM-Net for Automatic Identification and Real-Time Detection of Fatigue Driving,” Comput Mater Contin, vol. 82, no. 3, 2025, doi: 10.32604/cmc.2025.059972.

A. A. Minhas, S. Jabbar, M. Farhan, and M. N. U. Islam, “A Smart Analysis of Driver Fatigue and Drowsiness Detection Using Convolutional Neural Networks,” Multimed. Tools Appl., vol. 81, pp. 26969–26986, 2022.

G. Zhou, J. You, Q. Wu, J. Liu, and Y. Luo, “MobileNet-AFF : Multi-Scale Feature Fusion for Fatigue Driving Detection,” in International Conference on Computer, Vision and Intelligent Technology, Associaton for Computing Machinery, 2023.