Perancangan Sistem Deteksi Kondisi Microsleep Berbasis Sensor MPU6050 dan Support Vector Machine
DOI:
https://doi.org/10.63935/akiratech.v3i1.287Keywords:
Microsleep, Microsleep , Internet of Things , Wearable Device, Sensor MPU6050Abstract
Kecelakaan lalu lintas di Indonesia didominasi oleh kendaraan roda dua, di mana faktor kesalahan manusia seperti kelelahan dan microsleep menjadi penyebab utama. Kondisi microsleep terjadi dalam durasi singkat dan sering kali tidak disadari, sehingga sangat berbahaya bagi pengendara motor. Penelitian ini bertujuan untuk merancang sebuah sistem peringatan dini kondisi kantuk berbasis perangkat wearable yang terintegrasi pada helm. Sistem ini dirancang menggunakan sensor Inertial Measurement Unit (IMU) tipe MPU6050 untuk mendeteksi pola pergerakan kepala secara real-time. Data akselerasi dan orientasi kepala diproses menggunakan mikrokontroler ESP32 dengan menerapkan algoritma Machine Learning yaitu Support Vector Machine (SVM) untuk mengklasifikasikan kondisi sadar dan microsleep. Jika sistem mendeteksi indikasi microsleep, aktuator berupa buzzer dan motor getar akan aktif untuk memberikan peringatan kepada pengendara. Pendekatan perancangan ini menawarkan solusi yang ergonomis dan portabel dibandingkan metode deteksi berbasis kamera yang kurang efektif bagi pengendara bermotor.
Downloads
References
[1] Pusiknas Polri, “Data Kecelakaan Lalu Lintas 2023-2024, Kepolisian Negara Republik Indonesia,” https://pusiknas.polri.go.id/laka_lantas.
[2] I. K. Y. T. Pranata, C. Ramadhani, and G. Wahyu Wiriasto, “Menggunakan Metoda Facial Landmark Detection Berbasis Raspberry PI 3 Modul B,” Dielektrika - Department of Electrical Engineering University of Mataram, vol. 10, no. 2, pp. 100–111, 2023.
[3] Sugeng and H. Praminiarto, “Detection of Drowsiness in Drivers Using Image Processing and Support Vector Machine (SVM) Classification,” Jurnal Online Informatika, vol. 9, no. 2, pp. 238–248, Aug. 2024, doi: 10.15575/join.v9i2.1076.
[4] P. Prasetyawan, S. Samsugi, and R. Prabowo, “Internet of Thing Menggunakan Firebase dan Nodemcu untuk Helm Pintar,” Jurnal ELTIKOM, vol. 5, no. 1, pp. 32–39, Mar. 2021, doi: 10.31961/eltikom.v5i1.239.
[5] D. T. Utomo et al., “Development of IS-Candling (intelligent system for candling) web application for IoT-based hatch fertility detection,” BIO Web Conf., vol. 210, p. 05003, 2026, doi: 10.1051/bioconf/202621005003.
[6] M. Cesari et al., “A data-driven system to identify REM sleep behavior disorder and to predict its progression from the prodromal stage in Parkinson’s disease,” Sleep Med., vol. 77, pp. 238–248, Jan. 2021, doi: 10.1016/j.sleep.2020.04.010.
[7] S. H. Zaleha et al., “Microsleep Accident Prevention for SMART Vehicle via Image Processing Integrated with Artificial Intelligent,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Dec. 2021. doi: 10.1088/1742-6596/2129/1/012082.
[8] J. M. Sultan, N. H. Zani, M. Azuani, S. Z. Ibrahim, and A. Md Yusop, “Analysis of Inertial Measurement Accuracy using Complementary Filter for MPU6050 Sensor,” Jurnal Kejuruteraan, vol. 34, no. 5, pp. 959–964, Sep. 2022, doi: 10.17576/jkukm-2022-34(5)-24.
[9] S. A. Maqdis, A. Adiwilaga, and M. Munawir, “DESIGN OF MICROSLEEP DETECTION SYSTEM IN 32-BIT MICROCONTROLLER-BASED MOTORISTS WITH RANDOM FOREST METHOD,” JIKO (Jurnal Informatika dan Komputer), vol. 7, no. 2, pp. 131–137, Aug. 2024, doi: 10.33387/jiko.v7i2.8539.
[10] D. Hercog, T. Lerher, M. Truntič, and O. Težak, “Design and Implementation of ESP32-Based IoT Devices,” Sensors, vol. 23, no. 15, Aug. 2023, doi: 10.3390/s23156739.
[11] E. Rosdiana, F. Y. Ali, E. R. Pristiwaningsih, R. Purbaningtyas, D. R. Hartadi, and D. T. Utomo, “IoT for Agricultural Innovation: Enhancing Robusta Coffee Seedling Growth in Controlled Environments with Intelligent Air Quality Control System (IAQCS),” International Journal of Technology, Food and Agriculture, vol. 2, no. 1, pp. 1–9, Dec. 2024, doi: 10.25047/tefa.v2i1.5752.
[12] D. A. Pisner and D. M. Schnyer, “Support vector machine,” in Machine Learning: Methods and Applications to Brain Disorders, Elsevier, 2020, pp. 101–121. doi: 10.1016/B978-0-12-815739-8.00006-7.
[13] D. Valkenborg, A. J. Rousseau, M. Geubbelmans, and T. Burzykowski, “Support vector machines,” Nov. 01, 2023, Elsevier Inc. doi: 10.1016/j.ajodo.2023.08.003.
[14] D. M. Abdullah and A. M. Abdulazeez, “Machine Learning Applications based on SVM Classification: A Review,” Qubahan Academic Journal, vol. 1, pp. 81–90, Apr. 2021, doi: https://doi.org/10.48161/qaj.v1n2a50.
[15] W. P. P. Witra, I. G. Anugrah, S. U. Nuha, N. S. Wibowo, and D. T. Utomo, “RAD-UCD Implementation in Project Management Information System,” Journal of Development Research, vol. 8, no. 2, p. Process, Nov. 2024, doi: 10.28926/jdr.v8i2.398.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Achmad Bayhaqi Putra Adira, Denny Trias Utomo (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
