A monitoring system for railways based on WSN

Abd Alrahman, Zena; Adham, Ali

doi:10.22075/ijnaa.2023.7353

A monitoring system for railways based on WSN

Document Type : Research Paper

Authors

Zena Abd Alrahman ¹^{, 2}

Ali Adham ¹^{, 3}

¹ The Informatics Institute for Graduate Studies, Baghdad, Iraq

² Medical Instrumentation Engineering Department, AL-Esraa University College, Baghdad, Iraq

³ Al-Nahrain Center for Strategic Studies, Baghdad, Iraq

10.22075/ijnaa.2023.7353

Abstract

The process of controlling railway systems is one of the important and effective topics in the process of maintaining the flow of trains’ movement and organizing the travel process, as well as providing early readings of any defect or problem that occurs in the railway network to avoid, treat accidents and ensure a safe environment for the movement of train cars across the geographical area. Therefore, a continuous follow-up of the railway condition must be provided to ensure that services continue to be provided. Intelligent railway maintenance improves safety and efficiency. This work presents the design and implementation of a real-time monitoring system for railways based on WSN. This study proposes a system consisting of a base station server and a Rail controller. The Base Station (BS) can automatically monitor and control most railway paths. For that, a classification-based deep learning model for object detection near the railway and making appropriate decisions were proposed. To improve classification-model performance, the yolov3 algorithm for object detection was proposed. On the Rail controller side, the Raspberry Pi 4 was utilized as a low-cost processing unit that can be used as a control unit to control some processes, such as streaming video from a camera, gathering information from railway sensors, and sending data to the central station server (PC) by using WiFi protocol. The model can detect and control railway issues in real time by receiving streaming data and directly detecting, classifying issues, and making the best decisions. By alarming or controlling the desired train and stopping it.

Keywords

Railway Inspection

Real-Time Monitoring System

Deep Learning

object detection

YOLOV3

Raspberry pi 4

[1] Y. Xiao, Z. Tian, J. Yu, Y. Zhang, S. Liu, S. Du and X. Lan, A review of object detection based on deep learning, Multimed. Tools Appl. 79 (2020), no. 33–34, 23729–23791.
[2] G. Karimi, Introduction to Yolo algorithm for object detection, Section.io.https://www. section.io/engineering education/introduction-to-yolo-algorithm-for-objectdetection/, (2021).
[3] S.J. Agha, M. Schenke and K. Hartmann, Object detection using YOLOv3, Bachelor Thesis, Hochschulbibliothek, Hochschule Merseburg, 2021.
[4] V. Meel, How to analyze the performance of machine learning models, viso.ai. 2021.
[5] Y.Q. Huang, J.C. Zheng, S.D. Sun, C.F. Yang and J. Liu, Optimized YOLOv3 algorithm and its application in traffic flow detections, Appl. Sci. 10 (2020), no. 9.
[6] T. Mikkonen, Capacity monitoring using object detection algorithms, Bachelor’s Thesis, Metropolia Univ. Appl. Sci., 2021.
[7] A. Patel, What is object detection?, ML Research Lab, 2020.
[8] W.A. Ezat, M.M. Dessouky and N.A. Ismail, Evaluation of deep learning YOLOv3 algorithm for object detection and classification, Menoufia J. Electr. Eng. Res. 30 (2021), no. 1, 52–57.
[9] T. Wang, F. Yang and K.L. Tsui, Real-time detection of railway track component via one-stage deep learning networks, Sensors 20 (2020), no. 15, 1–15.
[10] H. Bandyopadhyay, YOLO: real-time object detection explained, www.v7labs.com, 2022.
[11] U. Almog, YOLO V3 explained, Towards Data Science, 2020.
[12] VOC, TensorFlow, https://www.tensorflow.org/datasets/catalog/voc#voc2007 default config, 2022.
[13] R.K. Singh, How to improve YOLOv3, https://blog.paperspace.com/improving-yolo/, 2020.
[14] T. He, Z. Zhang, H. Zhang, Z. Zhang, J. Xie and M. Li, Bag of tricks for image classification with convolutional neural networks, Proc. IEEE/CVF Conf. Comput. Vision Pattern Recog., 2019, pp. 558–567.
[15] H. Zhang, M. Cisse, Y.N. Dauphin and D. Lopez-Paz, Mixup: beyond empirical risk minimization, arXiv preprint arXiv:1710.09412, (2017).
[16] P. Shah, Label smoothing—make your model less (over)confident, Towards Data Science, 2021.
[17] S. Liu, D. Huang and Y. Wang, Learning spatial fusion for single-shot object detection, arXiv preprint arXiv:1911.09516, (2019).
[18] Y. Gao, A one-stage detector for extremely-small objects based on feature pyramid network, Yini Gao Kth Royal Institute of Technology School of Electrical Engineering and Computer Science, 2020.

[19] O. Kivrak and M.Z. G¨urb¨uz, Performance comparison of YOLOv3, YOLOv4 and YOLOv5 algorithms: a case study for poultry recognition, Avrupa Bilim Teknol. Dergisi 38 (2022), 392–397.