Dampak Penggunaan Data Augmentasi Terhadap Akurasi MobileNetV2 Dalam Deteksi Mikrosleep Berbasis Rasio Aspek Mata
- Isa Iant Maulana Universitas Dian Nuswantoro, Semarang, Indonesia
- Muhammad Fatah Abiyyu Riadi Universitas Dian Nuswantoro, Semarang, Indonesia
- Farrikh Alzami Universitas Dian Nuswantoro, Semarang, Indonesia
-
Muhammad Naufal
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
- Harun Al Azies Universitas Dian Nuswantoro, Semarang, Indonesia
- Ricardus Anggi Pramunendar Universitas Dian Nuswantoro, Semarang, Indonesia
- Ruri Suko Basuki Universitas Dian Nuswantoro, Semarang, Indonesia (*) Corresponding Author
Abstract
Detecting microsleep is important in preventing accidents caused by decreased alertness, especially in activities that require high concentration such as driving. This study aims to develop an image-based microsleep detection model using the MediaPipe FaceMesh. The EAR value is only used for the tagging process that forms the basis for dataset creation. The main problem investigated is how to produce a classification model that can accurately distinguish between normal eye conditions and microsleep conditions using image data taken from eye area snippets. To address this issue, this study applies a series of stages, starting from dataset formation, initial processing in the form of image size adjustment, normalization, and quality improvement through data augmentation, to model training using the MobileNetV2 architecture with transfer learning and fine-tuning techniques. The results of the experiment show that the use of data augmentation strategies has a significant effect on improving model performance, with the best configuration producing a test accuracy of 87.54 percent, with other high performance metrics, namely Precision of 88.64 percent, Recall (Sensitivity) of 87.14 percent, and F1-Score of 87.34 percent. These findings prove that an eye area image-based approach combined with a convolutional neural network model is capable of providing promising performance in detecting microsleep conditions. These findings prove that an approach based on eye area images combined with a convolutional neural network model can deliver promising performance in detecting microsleep. This research is expected to form the basis for the development of a more effective microsleep detection system that can be implemented in real world environments.
Downloads
References
“Benarkah Microsleep Bisa Sebabkan Kecelakaan Lalu Lintas? | tempo.co,” Tempo. Diakses: 22 Juni 2025. [Daring]. Tersedia pada: https://www.tempo.co/otomotif/benarkah-microsleep-bisa-sebabkan-kecelakaan-lalu-lintas--71757
M. Ngxande, J. -R. Tapamo, dan M. Burke, “Driver drowsiness detection using behavioral measures and machine learning techniques: A review of state-of-art techniques,” dalam 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), Des 2017, hlm. 156–161. doi: 10.1109/RoboMech.2017.8261140.
T. Fonseca dan S. Ferreira, “Drowsiness Detection in Drivers: A Systematic Review of Deep Learning-Based Models,” Applied Sciences, vol. 15, no. 16, hlm. 9018, Jan 2025, doi: 10.3390/app15169018.
F. Majeed, U. Shafique, M. Safran, S. Alfarhood, dan I. Ashraf, “Detection of Drowsiness among Drivers Using Novel Deep Convolutional Neural Network Model,” Sensors (Basel), vol. 23, no. 21, hlm. 8741, Okt 2023, doi: 10.3390/s23218741.
F. Safarov, F. Akhmedov, A. B. Abdusalomov, R. Nasimov, dan Y. I. Cho, “Real-Time Deep Learning-Based Drowsiness Detection: Leveraging Computer-Vision and Eye-Blink Analyses for Enhanced Road Safety,” Sensors (Basel), vol. 23, no. 14, hlm. 6459, Jul 2023, doi: 10.3390/s23146459.
N. N. Alajlan dan D. M. Ibrahim, “DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning,” Sensors (Basel), vol. 23, no. 12, hlm. 5696, Jun 2023, doi: 10.3390/s23125696.
A. R. Hartono, M. Naufal, dan F. Alzami, “Optimalisasi Arsitektur LSTM dengan Pendekatan Bidirectional untuk Deteksi Kantuk Pengemudi Berbasis Fitur Wajah,” Building of Informatics, Technology and Science (BITS), vol. 7, no. 2, hlm. 1343–1354, Sep 2025, doi: 10.47065/bits.v7i2.8219.
J. S. Wijnands, J. Thompson, K. A. Nice, G. D. P. A. Aschwanden, dan M. Stevenson, “Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks,” Neural Computing and Applications, vol. 32, no. 13, hlm. 9731–9743, Jul 2020, doi: 10.1007/s00521-019-04506-0.
H. Z. Ilmadina, M. Naufal, dan D. S. Wibowo, “Drowsiness Detection Based on Yawning Using Modified Pre-trained Model MobileNetV2 and ResNet50,” MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, vol. 22, no. 3, hlm. 419–430, Jun 2023, doi: 10.30812/matrik.v22i3.2785.
F. Alzami dkk., “Bayesian-Optimized CLAHE for Enhanced Drowsiness Detection in Low-Light Conditions Using Time-Distributed MobileNetV2-GRU Architecture,” Statistics, Optimization & Information Computing, Okt 2025, doi: 10.19139/soic-2310-5070-3024.
S. Winarno, F. Alzami, M. Naufal, H. A. Azies, M. A. Soeleman, dan N. H. A. H. Malim, “EfficientNet-KNN for Real-Time Driver Drowsiness Detection via Sequential Image Processing.,” Ingénierie des Systèmes d’Information, vol. 30, no. 7, hlm. 1703, Jul 2025, doi: 10.18280/isi.300703.
A.-C. Phan, T.-N. Trieu, dan T.-C. Phan, “Driver drowsiness detection and smart alerting using deep learning and IoT,” Internet of Things, vol. 22, hlm. 100705, Jul 2023, doi: 10.1016/j.iot.2023.100705.
S. Alimoon dkk., “Vision-Based Driver Fatigue Detection Using Eye and Mouth Aspect Ratios with Machine Learning,” vol. 9, hlm. 29–32, Apr 2025.
D. Santos, Real-time Eye Blink Detection using Computer Vision and Machine Learning. 2024. doi: 10.20944/preprints202410.0131.v1.
F. Alzami, S. Winarno, M. Naufal, dan H. Al Azies, “Enhancing Driver Drowsiness Detection through GMM-Optimized CLAHE,” dalam 2024 International Seminar on Application for Technology of Information and Communication (iSemantic), Sep 2024, hlm. 212–217. doi: 10.1109/iSemantic63362.2024.10762529.
H. Z. Ilmadina, M. Naufal, dan D. Apriliani, “Microsleep detection on drowsy-driver using convolutional neural networks (CNN),” dalam AIP Conference Proceedings, AIP Publishing LLC, 2024, hlm. 030005.
M. F. Shakeel, N. A. Bajwa, A. M. Anwaar, A. Sohail, A. Khan, dan Haroon-ur-Rashid, “Detecting Driver Drowsiness in Real Time Through Deep Learning Based Object Detection,” dalam Advances in Computational Intelligence, I. Rojas, G. Joya, dan A. Catala, Ed., Cham: Springer International Publishing, 2019, hlm. 283–296.
F. Alzami, M. Naufal, H. Al Azies, S. Winarno, dan M. A. Soeleman, “Time Distributed MobileNetV2 with Auto-CLAHE for Eye Region Drowsiness Detection in Low Light Conditions.,” International Journal of Advanced Computer Science & Applications, vol. 15, no. 11, hlm. 488, Nov 2024, doi: 10.14569/ijacsa.2024.0151146.
S. Essahraui dkk., “Real-Time Driver Drowsiness Detection Using Facial Analysis and Machine Learning Techniques,” Sensors, vol. 25, no. 3, 2025, doi: 10.3390/s25030812.
M. N. Andrean dkk., “Comparing haar cascade and yoloface for region of interest classification in drowsiness detection,” Jurnal Media Informatika Budidarma, vol. 8, no. 1, hlm. 272–281, 2024, doi: 10.30865/mib.v8i1.7167.
J.-R. González-Rodríguez, D.-M. Cordova-Esparza, J. Terven, dan J.-A. Romero-González, “Towards a Bidirectional Mexican Sign Language–Spanish Translation System: A Deep Learning Approach,” Technologies, vol. 12, hlm. 7, Jan 2024, doi: 10.3390/technologies12010007.
C. Dewi, R.-C. Chen, C.-W. Chang, S.-H. Wu, X. Jiang, dan H. Yu, “Eye Aspect Ratio for Real-Time Drowsiness Detection to Improve Driver Safety,” Electronics, vol. 11, no. 19, hlm. 3183, Jan 2022, doi: 10.3390/electronics11193183.
K. Team, “Keras documentation: MobileNet, MobileNetV2, and MobileNetV3.” Diakses: 13 November 2025. [Daring]. Tersedia pada: https://keras.io/api/applications/mobilenet/
B. Kromydas, “Convolutional Neural Network: A Complete Guide.” Diakses: 13 November 2025. [Daring]. Tersedia pada: https://learnopencv.com/understanding-convolutional-neural-networks-cnn/
X. Jiao, Y. Luo, Y. Bi, dan T. Zhou, “Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms,” 11 November 2025, arXiv: arXiv:2511.05834. doi: 10.48550/arXiv.2511.05834.
P. Młodzianowski, “Weather Classification with Transfer Learning - InceptionV3, MobileNetV2 and ResNet50,” dalam Digital Interaction and Machine Intelligence, C. Biele, J. Kacprzyk, W. Kopeć, J. W. Owsiński, A. Romanowski, dan M. Sikorski, Ed., Cham: Springer International Publishing, 2022, hlm. 3–11. doi: 10.1007/978-3-031-11432-8_1.
D. Naveenprabhu, R. Naveen, B. N. Bharathi, dan M. Naveenkumar, “Comprehensive review of transfer learning,” AIP Conference Proceedings, vol. 2914, no. 1, hlm. 050028, Des 2023, doi: 10.1063/5.0175841.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Dampak Penggunaan Data Augmentasi Terhadap Akurasi MobileNetV2 Dalam Deteksi Mikrosleep Berbasis Rasio Aspek Mata
Pages: 1797-1808
Copyright (c) 2025 Isa Iant Maulana, Muhammad Fatah Abiyyu Riadi, Farrikh Alzami, Muhammad Naufal, Harun Al Azies, Ricardus Anggi Pramunendar, Ruri Suko Basuki
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
