Railway Detection Of Axle Detection Patterns Using The KNN Method

Fathurrozi Winjaya; Dara Aulia Feryando; Sultan Rasya Nair Al Ghifari; Saian Nur Fajri

doi:10.37367/jrtt.v4i1.47

Authors

Fathurrozi Winjaya Indonesia Railway Polytechnic
Dara Aulia Feryando Indonesia Railway Polytechnic
Sultan Rasya Nair Al Ghifari Indonesia Railway Polytechnic
Saian Nur Fajri Indonesia Railway Polytechnic

DOI:

https://doi.org/10.37367/jrtt.v4i1.47

Keywords:

KNN, Metal Detector, Railway Detector, Axle

Abstract

The track circuit is a device used to determine whether a vehicle is on the track. This device is installed on the track and needs to be monitored to ensure it functions properly. All objects detected in practice are considered railway vehicles, even though the detected objects may not be railway vehicles. Accurate and reliable detection technology is crucial for preventing accidents and keeping train traffic safe. This detection system uses metal sensors to identify objects as railway or non-railway assets. This is done based on two variables: the frequency of the object's metal and the object's speed. The test results show that this tool can classify objects according to their class. The class with no objects has an accuracy level of 100%, while the class of non-railway has an accuracy level of 86.67%. The railway class trials using the inspection train axle show an accuracy level of 93.33%.

References

Menteri Perhubungan, “UNDANG-UNDANG REPUBLIK INDONESIA NOMOR 23 TAHUN 2007,” 2007.

M. D. Puspitasari and F. H. Purwaka, “ANALISIS PERBANDINGAN PENDETEKSI SARANA PADA LINTAS SURABAYA – MADIUN,” Jurnal Perkeretaapian Indonesia, vol. Volume 1, no. Nomor 2, pp. 117–125, 2017.

F. Winjaya, A. P. E. Wibowo, and A. Darmawan, “Pendeteksi Kondisi Roda Gigi Motor Wesel Menggunakan K-Means,” INNOVATIVE: Journal Of Social Science Research, vol. Volume 3, no. Nomor 6, pp. 6068–6081, 2023.

L. Ariani, F. Winjaya, and N. F. Rachman, “Detection of Railways Through Axle Detection Patterns Using Inductive Proximity Sensors,” 2024, pp. 204–212. doi: 10.2991/978-94-6463-384-9_18.

M. Jin, H. Yuan, and J. Zhang, “An optimization method of railway identification based on BiSeNet,” Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language Processing, 2022, [Online]. Available: https://api.semanticscholar.org/CorpusID:257366541

Zulkarnain, A. Y. Zindani, A. Amalia, and F. W. Putro, “Pendeteksi Kendaraan Untuk Keamanan Perlintasan Kereta Api,” 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:229132238

W. Puspita Hidayanti, “Penerapan Algoritma K-Nearest Neighbor Untuk Klasifikasi Efektivitas Penjualan Vape (Rokok Elektrik) pada ‘Lombok Vape On,’” Jurnal Informatika dan Teknologi, vol. 3, no. 2, 2020.

E. Bisong, Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners. 2019. doi: 10.1007/978-1-4842-4470-8.

M. R. Alghifari and A. P. Wibowo, “Penerapan Metode K-Nearest Neighbor Untuk Klasifikasi Kinerja Satpam Berbasis Web,” 2019.

I. G. Widharma, “SENSOR EFFECT HALL PADA INDUSTRI OTOMOTIF,” 2020.

J. Zha, L. Linhui, L. Han, and Y. Chen, “Four-station laser tracer-based geometric error measurement of rotary table,” Meas Sci Technol, vol. 31, Oct. 2020, doi: 10.1088/1361-6501/ab64ab.