Controlling Animals and People Near Railway Tracks Using the Internet of Things

Year : 2025 | Volume : 12 | Issue : 02 | Page : 01 10
    By

    Vignesh V.,

  • Surya Vishnu K.,

  • Kavin Prasanth S.,

  • Nithish Kumar M.,

  • Muthukumar A.,

  1. Associate Professor, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  2. Student, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  3. Student, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  4. Student, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  5. Student, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India

Abstract

A lot of people are opting to use the train instead of the bus now as bus tickets have become so expensive. In order to keep the railroad network running well, it is necessary to constantly inspect and monitor the tracks. Till now, the train track inspection process and monitoring system are done manually, which is laborious and wasteful since human error is likely to happen at any point. Because of the great distances they cover, it is also impractical to use human power to constantly inspect and oversee the track. Animal conservation is of the utmost importance, and technology has been used extensively in many ways to achieve this goal. The railway system is also laid down over forest zones, interfering alongside the activities of the local fauna, since trains are truly a commonly used mode of transportation in Asian countries. Trains often kill larger animals when they run them over. Especially in the verdant southern portions of the nation, such catastrophes are commonplace in India. This work proposes a computer skilled method for finding animals at the problem’s origin by use of implanted recording devices. For this kind of animal identification in photos and videos, an inception model is recommended. Step one is to gather data and do any necessary pre-processing. Step two involves using a convolutional neural network to build a classification model. For the purpose of species classification in our proposed study, we employ a DenseNet model.

Keywords: Train track inspection, animal detection, convolutional neural network (CNN), DenseNet model, wildlife conservation

[This article belongs to Journal of Mobile Computing, Communications & Mobile Networks ]

How to cite this article:
Vignesh V., Surya Vishnu K., Kavin Prasanth S., Nithish Kumar M., Muthukumar A.. Controlling Animals and People Near Railway Tracks Using the Internet of Things. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(02):01-10.
How to cite this URL:
Vignesh V., Surya Vishnu K., Kavin Prasanth S., Nithish Kumar M., Muthukumar A.. Controlling Animals and People Near Railway Tracks Using the Internet of Things. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(02):01-10. Available from: https://journals.stmjournals.com/jomccmn/article=2025/view=222388


References

  1. Krishna Chythanya N, Madhavi K, Ramesh G. A Machine learning enabled IoT device to combat elephant mortality on railway tracks. In Innovative Data Communication Technologies and Application: Proceedings of ICIDCA 2020. Singapore: Springer; 2021; 531–541.
  2. Sudhashree R, Muthukumaran N. Analysis of Low Complexity Memory Footprint Reduction for Delay and Area Efficient Realization of 2D FIR Filters. Int J Appl Eng Res. 2015; 10(20): 16101–5.
  3. Sharkawy AN, Koustoumpardis PN, Aspragathos N. Human–robot collisions detection for safe human–robot interaction using one multi-input–output neural network. Soft Comput. 2020 May; 24(9): 6687–719.
  4. Nagendran GA, Singh H, Raj RJ, Muthukumaran N. Input assistive keyboards for people with disabilities: A survey. In 2021 IEEE Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV). 2021 Feb 4; 829–832.
  5. Devaraj GP, Kabilan R, Gabriel JZ, Muthuraman U, Muthukumaran N, Swetha R. Design and Analysis of Modified Pre-Charge Sensing Circuit for STT-MRAM. In 2021 IEEE Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV). 2021 Feb 4; 507–511.
  6. Praczyk T. Neural collision avoidance system for biomimetic autonomous underwater vehicle. Soft Comput. 2020 Jan; 24(2): 1315–33.
  7. Janani RP, Narayanan KL, Krishnan RS, Kannan P, Kabilan R, Muthukumaran N. Intelligent Drowsiness and Illness Detection Assist System for Drivers. In 2022 IEEE Second International Conference on Artificial Intelligence and Smart Energy (ICAIS). 2022 Feb 23; 1150–1155.
  8. Munaf RN, Karthikeyan K, Gnanaraj SJ, Sivakumar TA, Muthukumaran N. An ML Approach for Household Power Consumption. In 2022 IEEE International Conference on Sustainable Computing and Data Communication Systems (ICSCDS). 2022 Apr 7; 784–791.
  9. Backs JA, Nychka JA, Clair CS. Warning systems triggered by trains could reduce collisions with wildlife. Ecol Eng. 2017 Sep 1; 106: 563–9.
  10. Venkateswari P, Steffy EJ, Muthukumaran N. License Plate cognizance by Ocular Character Perception. Int Res J Eng Technol. 2018 Feb; 5(2): 536–42.
Regular Issue Subscription Review Article
Volume 12
Issue 02
Received 10/03/2025
Accepted 22/03/2025
Published 21/06/2025
Publication Time 103 Days
110

Login


My IP

PlumX Metrics