Sayeekumar Madheswaran; Karthik Govindan Manoharan; Syed Shameem; M. Arumugam; Kasukurthi Rambabu; V. Gokula Krishnan

Deep Dual Masked Transformer-Based Self-Supervised Anomaly Detection for Wireless Sensor Network Node Fault Diagnosis

PDF (736KB), PP.316-329

Views: 0 Downloads: 0

Author(s)

Sayeekumar Madheswaran ¹ Karthik Govindan Manoharan ^2,* Syed Shameem ³ M. Arumugam ⁴ Kasukurthi Rambabu ⁵ V. Gokula Krishnan ⁶

1. Department of Computer Science and Engineering – AIML, Global Campus, Jain Deemed-to-be-University, Bengaluru – 562112, Karnataka, India

2. School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Katpadi – Thiruvalam Road, Vellore – 632014, Tamil Nadu, India

3. Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur District – 522302, Andhra Pradesh, India

4. Department of Computer Technology–PG, Kongu Engineering College (Autonomous), Perundurai, Erode – 638060, Tamil Nadu, India

5. Department of Electrical and Electronics Engineering, Aditya University, Surampalem – 533437, Andhra Pradesh, India

6. Department of Computer Science and Engineering, Easwari Engineering College, Ramapuram, Chennai – 600089, Tamil Nadu, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijwmt.2026.05.19

Received: 9 Jul. 2026 / Revised: 7 Aug. 2026 / Accepted: 15 Sep. 2026 / Published: 8 Oct. 2026

Index Terms

Wireless Sensor Networks, Anomaly Detection, Self-Supervised Learning, Fault Diagnosis, Deep Representation Learning, Temporal Data Analysis

Abstract

Wireless sensor networks enable real-time monitoring in critical applications such as industrial automation, environmental sensing, healthcare, and infrastructure management. However, sensor node faults caused by hardware degradation, communication failures, and harsh operating conditions can significantly reduce data reliability and system performance. Existing anomaly detection approaches often depend on large amounts of labelled fault data and suffer from class imbalance, noise sensitivity, computational complexity, and limited generalization in dynamic environments, highlighting the need for adaptive and scalable fault diagnosis frameworks. To address these limitations, this study proposes a self-supervised deep anomaly detection framework for wireless sensor network node fault diagnosis. The proposed method integrates preprocessing and sliding-window segmentation with a Deep Dual Masked Transformer (DDMT) architecture to capture temporal dependencies and learn discriminative features without extensive labelled data. A self-supervised reconstruction objective with a 15% masking strategy is employed to optimize latent representations, while an adaptive anomaly-scoring mechanism generates reliable fault predictions. Experimental results on the Zidi wireless sensor network dataset demonstrate that the proposed method achieves an accuracy of 99.0%, a precision of 98.5%, a recall of 98.3%, an F1-score of 98.4%, and an ROC-AUC of 99.5%, outperforming existing baseline methods. By combining temporal modelling and representation learning within a unified framework, the proposed approach improves anomaly detection accuracy, robustness, scalability, and generalization capability while maintaining low false alarm rates in challenging wireless sensor network environments.

Cite This Paper

Sayeekumar Madheswaran, Karthik Govindan Manoharan, Syed Shameem, M. Arumugam, Kasukurthi Rambabu, V. Gokula Krishnan, "Deep Dual Masked Transformer-Based Self-Supervised Anomaly Detection for Wireless Sensor Network Node Fault Diagnosis", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.5, pp. 316-329, 2026. DOI:10.5815/ijwmt.2026.05.19

Reference

[1]K.-X. Shi, S.-M. Li, G.-W. Sun, Z.-C. Feng, and W. He, “Fault diagnosis of wireless sensor network nodes based on belief rule base with adaptive attribute weights,” Scientific Reports,2024, vol. 14, Art. no. 4038.
[2]M. M. Feghhi, R. M. Alsharfa, and M. H. Majeed, “Efficient Fault Detection in WSN Based on PCA-Optimized Deep Neural Network Slicing Trained with GOA,” arXiv preprint arXiv: 2505.07030, 2025.
[3]J. Xia, D. Zhan, and X. Wang, “Machine learning diagnosis of node failures based on wireless sensor networks,” Applied Mathematics and Nonlinear Sciences, 2024. vol. 9, no. 1.
[4]P. Iswarya and K. Manikandan, "Spatio-temporal multi-fault and severity aware diagnosis in WSN via GNN transformers," Scientific Reports, vol. 16, Art. no. 23945, 2026, doi: 10.1038/s41598-026-52619-z.
[5]G. Jiang, K. Shen, X. Liu, X. Cheng, and P. Xie, "Hierarchical spatiotemporal graph network for fault diagnosis of industrial processes," IEEE Internet of Things Journal, vol. 12, no. 3, pp. 3043-3054, 2025, doi: 10.1109/JIOT.2024.3476287.
[6]Y. Fan, T. Fu, N. I. Listopad, P. Liu, S. Garg, and M. M. Hassan, "Utilizing correlation in space and time: Anomaly detection for Industrial Internet of Things (IIoT) via spatiotemporal gated graph attention network," Alexandria Engineering Journal, vol. 106, pp. 560-570, 2024, doi: 10.1016/j.aej.2024.08.048.
[7]M. Ye, Q. Zhang, X. Xue, Y. Wang, Q. Jiang, and H. Qiu, "A novel self-supervised learning-based anomalous node detection method based on an autoencoder for wireless sensor networks," IEEE Systems Journal, vol. 18, no. 1, pp. 256-267, 2024, doi: 10.1109/JSYST.2023.3347435.
[8]M. Ye, J. Cui, Y. Huang, Q. He, Y. Wang, and J. Zhang, “A graph prompt fine-tuning method for WSN spatio-temporal correlation anomaly detection,” arXiv preprint arXiv: 2601. 2026, 12745.
[9]D. B. Mohan, P. Arumugam, and A. R. Anand, “Osprey optimization algorithm integrated with graph neural networks for intrusion detection in wireless sensor networks,” Scientific Reports, 2025, vol. 15, pp. 44849, doi: 10.1038/s41598-025-28359-x.
[10]Z. Wang, M. Ye, J. Cheng, C. Zhu, and Y. Wang, “An anomaly node detection method for wireless sensor networks based on deep metric learning with fusion of spatial–temporal features,” Sensors, 2025, vol. 25, no. 10, pp. 3033, doi: 10.3390/s25103033.
[11]A. Haque and H. Soliman, “A transformer-based autoencoder with isolation forest and XGBoost for malfunction and intrusion detection in wireless sensor networks for forest fire prediction,” Future Internet, 2025, vol. 17, no. 4, pp. 164, doi: 10.3390/fi17040164.
[12]S. Salmi and L. Oughdir, “Performance evaluation of deep learning techniques for DoS attacks detection in wireless sensor network,” Journal of Big Data, 2023, vol. 10, pp. 17, doi: 10.1186/s40537-023-00692-w.
[13]M. A. Talukder, M. Khalid, and N. Sultana, “A hybrid machine learning model for intrusion detection in wireless sensor networks leveraging data balancing and dimensionality reduction,” Scientific Reports, 2025,vol. 15, pp. 4617, doi: 10.1038/s41598-025-87028-1.
[14]T. M. Nguyen, H. H.-P. Vo, and M. Yoo, “Enhancing intrusion detection in wireless sensor networks using a GSWO-CatBoost approach,” Sensors, 2024, vol. 24, no. 11, pp. 3339, 2024, doi: 10.3390/s24113339.
[15]R. W. Anwar, M. Abrar, A. Salam, and F. Ullah, “Federated learning with LSTM for intrusion detection in IoT-based wireless sensor networks: A multi-dataset analysis,” PeerJ Computer Science, 2025, vol. 11, pp. e2751, doi: 10.7717/peerj-cs.2751.
[16]A. Alauthman and A. Al-Hyari, “Intelligent fault detection and self-healing mechanisms in wireless sensor networks using machine learning and flying fox optimization,” Computers, 2025, vol. 14, no. 6, pp. 233, doi: 10.3390/computers14060233.
[17]R. Ahmad and E. H. Alkhammash, “Online adaptive Kalman filtering for real-time anomaly detection in wireless sensor networks,” Sensors, 2024, vol. 24, no. 15, pp. 5046, doi: 10.3390/s24155046.
[18]Y. Sun, G. Pang, G. Ye, T. Chen, X. Hu, and H. Yin, “Unraveling the ‘Anomaly’ in Time Series Anomaly Detection: A Self-Supervised Tri-Domain Solution,” in Proc. IEEE 40th Int. Conf. Data Engineering (ICDE), Utrecht, Netherlands, May 2024, pp. 981–994, doi: 10.1109/ICDE60146.2024.00080.
[19]Y. Fang, J. Xie, Y. Zhao, L. Chen, Y. Gao, and K. Zheng, “Temporal-Frequency Masked Autoencoders for Time Series Anomaly Detection,” in Proc. IEEE 40th Int. Conf. Data Engineering (ICDE), Utrecht, Netherlands, May 2024, pp. 1228–1241, doi: 10.1109/ICDE60146.2024.00099.
[20]D. L. Marino, C. S. Wickramasinghe, C. Rieger, and M. Manic, “Self-Supervised and Interpretable Anomaly Detection Using Network Transformers,” IEEE Transactions on Industrial Informatics, vol. 21, no. 5, pp. 4252–4261, 2025, doi: 10.1109/TII.2025.3534443.
[21]Y. Dai, I. Spence, K. Rafferty, B. Quinn, J. Huang, and H. Wang, “TDSRL: Time Series Dual Self-Supervised Representation Learning for Anomaly Detection from Different Perspectives,” IEEE Internet of Things Journal, vol. 12, no. 17, pp. 35078–35096, 2025, doi: 10.1109/JIOT.2025.3577931.
[22]M. M. Zidi, T. Moulahi, and B. Alaya, “Fault detection in wireless sensor networks through SVM classifier,” IEEE Sensors Journal, Jan.2018, vol. 18, no. 1, pp. 340–347. doi: 10.1109/JSEN.2017.2771226.

International Journal of Wireless and Microwave Technologies (IJWMT)