Sistem Deteksi Kelelahan Pengemudi Berdasarkan Pengukuran Kedipan Mata Menggunakan Metode Manhattan Distance

Wulan Dwi Rahayu(1*),Elindra Ambar Pambudi(2),Agung Purwo Wicaksono(3),Feri Wibowo(4)
(1) Universitas Muhammadiyah Purwokerto
(2) Universitas Muhammadiyah Purwokerto
(3) Universitas Muhammadiyah Purwokerto
(4) Universitas Muhammadiyah Purwokerto
(*) Corresponding Author
DOI : 10.35889/jutisi.v13i1.1852

Abstract

Fatigue can result in a decrease in the driver's level of alertness and reaction time, threatening the safety of road users. This study focuses on developing a driver fatigue detection system that relies on eye blink measurements using the Manhattan Distance method. The main goal is to improve driving safety by accurately detecting the driver's fatigue level. The proposed system measures eye blinks and uses Manhattan Distance to transmit the difference between normal and drowsiness-affected eye blink patterns. Experiments show that the Manhattan Distance method effectively identifies driver fatigue based on eye blink patterns, achieving a satisfactory accuracy rate of 87.5%. Experimental results show that the Manhattan Distance method is effective in identifying driver fatigue based on eye blink patterns, with a satisfactory level of accuracy. With this success, this system could potentially be implemented in vehicles as part of a safety system, helping to reduce the risk of accidents due to driver fatigue in real-time.

Keywords: Fatigue; Manhattan; Eye; customer; Camera

 

Abstrak

Kelelahan dapat mengakibatkan penurunan tingkat kewaspadaan dan waktu reaksi pengemudi, mengancam keselamatan pengguna jalan.  Studi ini berfokus pada pengembangan sistem deteksi kelelahan pengemudi yang mengandalkan pengukuran kedipan mata menggunakan metode Manhattan Distance. Tujuan utamanya adalah meningkatkan keselamatan berkendara dengan mendeteksi tingkat kelelahan pengemudi secara akurat. Sistem yang diusulkan mengukur kedipan mata dan menggunakan Manhattan Distance untuk mengevaluasi perbedaan antara pola kedipan mata normal dan yang dipengaruhi oleh rasa kantuk. Eksperimen menunjukkan bahwa metode Manhattan Distance efektif mengidentifikasi kelelahan pengemudi berdasarkan pola kedipan mata, mencapai tingkat akurasi yang memuaskan sebesar 87,5%. Hasil eksperimen menunjukkan bahwa metode Manhattan Distance efektif dalam mengidentifikasi kelelahan pengemudi berdasarkan pola kedipan mata, dengan tingkat akurasi yang memuaskan. Dengan keberhasilan ini, sistem ini berpotensi diimplementasikan dalam kendaraan sebagai bagian dari sistem keamanan, membantu mengurangi risiko kecelakaan akibat kelelahan pengemudi secara real-time.

 

Keywords


Kelelahan; Manhattan; Mata; Pengemudi; Kamera

References


S.F.E. Mubalus, “Analisis Faktor-Faktor Penyebab Kecelakaan Lalu Lintas Di Kabupaten Sorong Dan Penanggulangannya,” SOSCIED, vol. 6, no. 1, pp. 182–197, Jul. 2023, doi: https://doi.org/10.32531/jsoscied.v6i1.624.

J. Homepage, B. Dwi, H. Puslitbang, T. Jalan, D. Perkeretaapian, and J. Medan, “Pengaruh Mengemudi Malam dan Kondisi Jalan Monoton Terhadap Tingkat Kelelahan Pengemudi dan Implikasinya Pada Kecelakaan,” Jurnal Penelitian Transportasi Darat, vol. 21, no. 2, pp. 117–124, Nov. 2019, doi: 10.25104/jptd.v21i2.1297.

C. K. U Nggiku and A. Rabi, “Deteksi Kantuk Pada Pengemudi Mobil Menggunakan Eye Aspect Ratio Dengan Metode Facial Landmark,” Deteksi Kantuk Pada Pengemudi Mobil Menggunakan Eye Aspect Ratio Dengan Metode Facial Landmark, vol. 5, no. 1, pp. 72–78, Dec. 2022, doi: https://doi.org/10.56795/sinarfe7.v5i1.

R. T. Puteri and F. Utaminingrum, “Deteksi Kantuk Menggunakan Kombinasi Haar Cascade dan Convolutional Neural Network,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 4, no. 3, pp. 816–821, Mar. 2020, [Online]. Available: http://j-ptiik.ub.ac.id

M. Verma, M. Srivastava, N. Chack, A. Kumar Diswar, and N. Gupta, “A Comparative Study of Various Clustering Algorithms in Data Mining,” International Journal of Engineering Research and Applications (IJERA), vol. 2, no. 3, pp. 1379–1384, May 2012, [Online]. Available: www.ijera.com

I. P. A. E. D. Udayana and I. K. D. G. Supartha, “Implementasi Kombinasi Metode Mean Denoising dan Convolutional Neural Network pada Facial Landmark Detection,” Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), vol. 10, no. 1, pp. 1–10, Apr. 2021, doi: 10.23887/janapati.v10i1.29779.

R. R. Hajar et al., “Deteksi Wajah Berbasis Facial Landmark Menggunakan Opencv Dan Dlib,” Jurnal Teknologi Informasi, vol. 5, no. 2, pp. 144–148, Dec. 2021, doi: https://doi.org/10.36294/jurti.v5i2.2220.

Fabian Friedrichs and Bin Yang, “Camera-based Drowsiness Reference for Driver State Classification under Real Driving Conditions,” 2010 IEEE Intelligent Vehicles Symposium, pp. 101–106, Jun. 2010, doi: 10.1109/IVS.2010.5548039.

Komang Yoga Tri Pranata, C. Ramadhani, and G. Wahyu Wiriasto, “Sistem Peringatan Dini Kantuk pada Pengemudi Malam Hari 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, Mar. 2023, doi: https://doi.org/10.29303/dielektrika.v10i2.352.

Nurmaleni and Asminah, “Klasifikasi Jenis Alpukat Dengan Image Processing Menggunakan Metode K-Nearest Neighbor (K-NN),” Jurnal Ilmiah Betrik, vol. 14, no. 02, pp. 423–435, Aug. 2023.

N. Amynarto, Y. A. Sari, and R. Cahyawihandika, “Pengenalan Emosi Berdasarkan Ekspresi Mikro Menggunakan Metode Local Binary Pattern,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 2, no. 10, pp. 3230–3238, Oct. 2018, doi: https://doi.org/10.54314/jssr.v6i3.1474.

M. Ahmad Kamran, M. M. N. Mannan, and M. Y. Jeong, “Drowsiness, Fatigue and Poor Sleep’s Causes and Detection: A Comprehensive Study,” IEEE Access, vol. 7, pp. 167172–167186, Oct. 2019, doi: 10.1109/ACCESS.2019.2951028.

F. Hariesugama, F. Bimantoro, and G. Satya Nugraha, “Pengenalan Wajah Dan Deteksi Kantuk Menggunakan Metode Haar Cascade Dan Convolutional Neural Network,” Universitas Mataram Repository, 2023, Accessed: Mar. 08, 2024. [Online]. Available: http://eprints.unram.ac.id/id/eprint/43567

R. Jabbar, K. Al-Khalifa, M. Kharbeche, W. Alhajyaseen, M. Jafari, and S. Jiang, “Real-time Driver Drowsiness Detection for Android Application Using Deep Neural Networks Techniques,” Procedia Comput Sci, vol. 130, pp. 400–407, 2018, doi: 10.1016/j.procs.2018.04.060.

I. Putu et al., “Detection of Student Drowsiness Using Ensemble Regression Trees in Online Learning During a COVID-19 Pandemic Deteksi Kantuk Peserta Didik Menggunakan Ensemble Regression Trees Pada Pembelajaran Daring Dimasa Pandemi COVID-19,” Jurnal Informatika dan Teknologi Informasi, vol. 19, no. 2, pp. 229–244, Jun. 2022, doi: 10.31515/telematika.v19i2.7044.

S. A. Lee, J. Kim, J. M. Lee, Y. J. Hong, I. J. Kim, and J. D. Lee, “Automatic Facial Recognition System Assisted-facial Asymmetry Scale Using Facial Landmarks,” Otology and Neurotology, vol. 41, no. 8, pp. 1140–1148, Sep. 2020, doi: 10.1097/MAO.0000000000002735.

G. Pangestu, F. Utaminingrum, and F. A. Bachtiar, “Eye state recognition using multiple methods for applied to control smart wheelchair,” International Journal of Intelligent Engineering and Systems, vol. 12, no. 1, pp. 232–241, Jun. 2019, doi: 10.22266/IJIES2019.0228.23.

A. Eviana, Abd. C. Fauzan, H. Harliana, and F. N. Putra, “Komparasi Jarak Euclidean dan Jarak Manhattan Untuk Deteksi Covid-19 Melalui Citra CT-Scan Paru-Paru,” Komputika: Jurnal Sistem Komputer, vol. 11, no. 2, pp. 121–129, Feb. 2022, doi: 10.34010/komputika.v11i2.5380.

R. Alya Shafira, Yahfizham, and A. Muliani Harahap, “Menentukan Jarak Terpendek Dalam Pengiriman Barang Dengan Perbandingan Euclidean Distance Dan Manhattan Distance,” Journal of Science and Social Research, vol. VI, no. 3, pp. 678–685, Oct. 2023, doi: https://doi.org/10.54314/jssr.v6i3.1474.

N. Wahyudiana and S. Budi, “Perbandingan Performa Pre-Trained Classifier dLib dan HAAR Cascade (OpenCV) Untuk Mendeteksi Wajah,” Jurnal Strategi, vol. 1, no. 2, pp. 374–385, Nov. 2019.


The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Full Text: File PDF

How To Cite This :

Refbacks

  • There are currently no refbacks.