Study on IoT application and development of artificial neural networks in vehicle status diagnosis
Keywords:
IoT system, Artificial Neural Network, Weight detection, Learning rateAbstract
In the contemporary landscape, characterized by the robust advancements of IoT and AI in automation system control and monitoring, vehicle condition diagnostic systems, crucial for ensuring safe and efficient vehicle operation and management, are fully aligned with this technological trajectory. This paper outlines a proposed hardware system designed to facilitate the collection of vehicle parameters for IoT applications and the development of a vehicle condition recognition model utilizing Artificial Neural Network (ANN). The model incorporates two distinct training methodologies: the weight detection method and the learning rate adjustment method. A comparative analysis of these two methods will serve as the foundation for selecting a model that demonstrates superior quality, high accuracy, and optimal efficiency in terms of both time and training resources.
References
[1] U. Khadam, P. Davidsson, and R. Spalazzese, “Exploring the role of artificial intelligence in Internet of Things systems: A systematic mapping study,” Sensors, vol. 24. 2024.
[2] O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, N. A. Mohamed, H. Arshad, “State-of-the-art in artificial neural network applications: A survey,” Heliyon, 2018.
[3] C. Aciti, M. Urraco, E. Todorovich. “OBD-II vehicle data capture and monitoring system prototype,” XXIV Congreso Argentino de Ciencias de la Computación 2018, Argentina, 2018.
[4] H. M. Luu, T. B. N. Nguyen, T. D. Nguyen, “Research on IoT application in controlling and monitoring the CANBUS system on cars,” Proceedings of the 6th National conference on transportation science and technology 2025, Vietnam, Transport pulishing house, pp. 218-221,2025
[5] SAE International, “SAE J1979: E/E Diagnostic Test Modes,” Surface Vehicle Standard, America, May 2007.
[6] S. Roksic, “Controller Area Network (CAN) Bus Simulator and Data-logger for In-Vehicle Infotainment Testing,” Senior Project Report, Electrical Engineering Department, California Polytechnic State University, 2020.
[7] Y. Bai, “RELU-Function and Derived Function Review,” SHS Web of Conferences, 2022.
[8] N. A. Rahmi, S. Defit, Okfalisa, “The Use of Hyperparameter Tuning in Model Classification: A Scientific Work Area Identification,” JOIV: Int. J. Inform, Visualization, 2024.
[9] T. Akiba, S. Sano, T. Yanase, T. Ohta and M. Koyama, “Optuna: A Next-generation Hyperparameter Optimization Framework,” July 2019.
[10] Leslie N. Smith, “A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay,” USNaval Research Laboratory Technical Report 5510-026, April 2018.
[11] A. Crăciun, D. Ghoshdastidar, “On the Convergence of Gradient Descent for Large Learning Rates,” Cornell University Library, 2024, doi: https://doi.org/10.48550/arXiv.2402.13108.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Hoang-Minh Luu
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
