

Comprehensive Survey of Outlier Detection in Wireless Sensor Networks
Abstract
The recent advancements in outlier detection techniques for Wireless Sensor Networks emphasize their significance in enhancing data integrity and system reliability. It categorizes detection methods into centralized, distributed, and hybrid architectures, with a focus on approaches based on clustering, machine learning, deep learning, and federated learning. Particular attention is given to techniques that leverage spatio-temporal and multivariate correlations to distinguish between sensor faults and actual events. Key evaluation metrics, such as DR, FA rate, and energy efficiency, are discussed. The paper also outlines major research challenges, including the handling of high-dimensional data, real-time detection, and correlations of input and output variables, as well as research gaps, datasets, and key findings. A timeline of developments and a dataset comparison support the analysis, providing insights for future research in WSN anomaly detection. Additionally, a comparative assessment of datasets, architectures, and recent contributions from 2006 to 2024 is provided to identify research gaps and future directions. This paper aims to serve as a foundational reference for researchers and practitioners seeking to design robust, scalable, and resource-aware anomaly detection systems in modern WSN deployments.
References
A. Abid, S. E. Khediri, and A. Kachouri, "Improved approaches for density-based outlier detection in wireless sensor networks," Computing, vol. 103, pp. 2275–2292, 2021. doi: 10.1007/s00607-021-00939-5
M. Al Samara, I. Bennis, A. Abouaissa, and P. Lorenz, "Complete outlier detection and classification framework for WSNs based on OPTICS," J. Netw. Comput. Appl., vol. 211, p. 103563, 2023. doi: 10.1016/j.jnca.2022.103563
M. Al Samara, I. Bennis, A. Abouaissa, and P. Lorenz, "Enhanced efficient outlier detection and classification approach for WSNs," Simul. Model. Pract. Theory, vol. 120, p. 102618, 2022. doi: 10.1016/j.simpat.2022.102618
M. Al Samara, I. Bennis, A. Abouaissa, and P. Lorenz, "An enhanced online outlier detection and classification approach for WSN," J. Netw. Syst. Manag., vol. 32, p. 31, 2024.
A. A. A. Alkhatib and Q. Abed-Al, "Multivariate outlier detection for forest fire data aggregation accuracy," Intell. Autom. Soft Comput., vol. 31, no. 2, pp. 1071–1087, 2022. doi: 10.32604/iasc.2022.020461
S. Arul Jothi and R. Venkatesan, "A deep learning approach for efficient anomaly detection in WSNs," Int. J. Comput. Commun. Control, vol. 18, no. 1, p. 4756, 2023. doi: 10.15837/ijccc.2023.1.4756
S. Arul Jothi, R. Venkatesan, and V. Santhi, "Rule-based outlier detection with a modified variational autoencoder for enhancing data accuracy in wireless sensor networks," Int. J. Fuzzy Syst., vol. 25, no. 6, pp. 2191–2202, 2023. doi: 10.1007/s40815-023-01496-z
N. Berjab, H. H. Le, and H. Yokota, "A spatiotemporal and multivariate attribute correlation extraction scheme for detecting abnormal nodes in WSNs," IEEE Access, 2021. doi: 10.1109/ACCESS.2021.3115819
J. Chen, J. Zhang, R. Qian, J. Yuan, and Y. Ren, "An anomaly detection method for wireless sensor networks based on the improved isolation forest," Appl. Sci., vol. 13, no. 2, p. 702, 2023. doi: 10.3390/app13020702
S. Dogmechi, Z. Torabi, and N. Daneshpour, "An outlier detection method based on the hidden Markov model and copula for wireless sensor networks," Wireless Netw., vol. 30, pp. 4797–4810, 2022.
Refbacks
- There are currently no refbacks.