Fault detection in wireless sensor networks with deep neural networks
70 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.CSCE7.2023.27-36Keywords:
Fault detection; Wireless sensor network; Machine learning; Recurrent neuron network; LSTM.Abstract
This paper addresses the challenge of fault detection in Wireless Sensor Networks (WSNs), commonly used in fields like environmental monitoring and healthcare. WSNs, prone to various faults due to their deployment in unpredictable environments, require effective solutions for fault detection. Traditional machine learning approaches show limitations such as unsuitability for streaming data and the detection of a single fault type. We propose the use of deep neural networks, particularly Recurrent Neural Networks (RNNs), for fault detection in WSNs, focusing on temperature and humidity data. The paper emphasizes the importance of careful model selection, tuning, and thorough evaluation to enhance the accuracy and robustness of fault detection in real-world WSN applications.
References
[1]. P. I. Priya, S. Muthurajkumar, and S. S. Daisy, “Data Fault Detection in Wireless Sensor Networks Using Machine Learning Techniques,” Wirel. Pers. Commun., vol. 122, no. 3, pp. 2441–2462, (2022), doi: 10.1007/s11277-021-09001-1. DOI: https://doi.org/10.1007/s11277-021-09001-1
[2]. S. A. Yadav and T. Poongodi, “A Review of ML Based Fault Detection Algorithms in WSNs,” in 2021 2nd International Conference on Intelligent Engineering and Management (ICIEM), pp. 615–618, (2021), doi: 10.1109/ICIEM51511.2021.9445384. DOI: https://doi.org/10.1109/ICIEM51511.2021.9445384
[3]. S. Zroug, I. Remadna, L. Kahloul, S. Benharzallah, and S. L. Terrissa, “Leveraging the Power of Machine Learning for Performance Evaluation Prediction in Wireless Sensor Networks,” in 2021 International Conference on Information Technology (ICIT), pp. 864–869, (2021), doi: 10.1109/ICIT52682.2021.9491722. DOI: https://doi.org/10.1109/ICIT52682.2021.9491722
[4]. L. Chen, G. Li, and G. Huang, “A hypergrid based adaptive learning method for detecting data faults in wireless sensor networks,” Inf. Sci. (Ny)., vol. 553, pp. 49–65, (2021), doi: https://doi.org/10.1016/j.ins.2020.12.011. DOI: https://doi.org/10.1016/j.ins.2020.12.011
[5]. T. Amarasimha and V. S. Rao, “Efficient Energy Conservation and Faulty Node Detection on Machine Learning-Based Wireless Sensor Networks,” Int. J. Grid High Perform. Comput., vol. 13, no. 2, pp. 1–20, (2021). DOI: https://doi.org/10.4018/IJGHPC.2021040101
[6]. Sudha, Y. Singh, H. Sehrawat, and V. Jaglan, “Approach of Machine Learning Algorithms to Deal with Challenges in Wireless Sensor Network,” in Soft Computing: Theories and Applications, pp. 375–395, (2022). DOI: https://doi.org/10.1007/978-981-16-1740-9_31
[7]. G. D. O’Mahony, P. J. Harris, and C. C. Murphy, “Detecting interference in wireless sensor network received samples: A machine learning approach,” in 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), pp. 1–6, (2020). DOI: https://doi.org/10.1109/WF-IoT48130.2020.9221332
[8]. D. Li, Y. Wang, J. Wang, C. Wang, and Y. Duan, “Recent advances in sensor fault diagnosis: A review,” Sensors Actuators A Phys., vol. 309, p. 111990, (2020). DOI: https://doi.org/10.1016/j.sna.2020.111990
[9]. S. Suthaharan, M. Alzahrani, S. Rajasegarar, C. Leckie, and M. Palaniswami, “Labelled data collection for anomaly detection in wireless sensor networks,” in 2010 sixth international conference on intelligent sensors, sensor networks and information processing, pp. 269–274, (2010). DOI: https://doi.org/10.1109/ISSNIP.2010.5706782
