A Multimodal Sensor-Based Self-Supervised Learning Framework for Low-Noise System State Prediction and Anomaly Detection
Sensors · 17.06.2026 · 26 (12) · 3851
DOI: 10.3390/s26123851 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.06.2026. Verfasst von Kexin Guo und 6 weiteren Autor:innen. Beteiligte Einrichtung: China Agricultural University, Beijing 100083, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
To address the challenges of strong signal noise, pronounced cross-modal asynchrony, high subjectivity in manually defined state labels, and insufficient model stability under extreme abnormal conditions in multi-source sensor systems, a low-noise system state prediction and anomaly detection method based on multimodal sensor signals and self-supervised representation learning is proposed. Environmental sensing data, device status data, network transmission data, operational behavior data, and event log data are uniformly modeled as system state perception signals. A temporal masking-based state structure modeling method, a state-oriented contrastive learning representation constraint mechanism, and a state representation and downstream prediction task alignment strategy are designed to learn stable, transferable, and interpretable system state features. Experimental results demonstrate that the proposed method achieves the best performance in multimodal sensor state prediction and anomaly detection tasks, with mean squared error (MSE), mean absolute error (MAE), and root mean square error (RMSE) values of 0.0167, 0.0856, and 0.1291, respectively, outperforming baseline models such as GARCH, MLP, LSTM, TCN, and Transformer. Meanwhile, IC, RankIC, and AUC reach 0.494, 0.460, and 0.815, respectively, indicating stronger state-ranking capability and improved discrimination between high-abnormality and low-abnormality states. At the classification recognition level, superior accuracy, precision, recall, and F1-score are also achieved by the proposed method, suggesting that potential abnormal states can be identified more accurately. Ablation experiments verify the effectiveness of multimodal fusion, temporal masking modeling, self-supervised contrastive constraints, and task alignment strategies. Robustness experiments further show that lower prediction errors and higher AUC can still be maintained under high-fluctuation and extreme-shock states, demonstrating strong noise resistance, stability, and practical application potential in complex sensor system scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- China Agricultural University, Beijing 100083, China.
- National School of Development, Peking University, Beijing 100871, China.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Guo, K., Wang, J., Lin, J., Chen, N., Chen, H., Zhou, Z., & Li, M. (2026). A Multimodal Sensor-Based Self-Supervised Learning Framework for Low-Noise System State Prediction and Anomaly Detection. Sensors, 26(12), 3851. https://doi.org/10.3390/s26123851
Vancouver
Guo K, Wang J, Lin J, Chen N, Chen H, Zhou Z, et al. A Multimodal Sensor-Based Self-Supervised Learning Framework for Low-Noise System State Prediction and Anomaly Detection. Sensors. 2026;26(12):3851. doi:10.3390/s26123851
BibTeX
@article{Guo2026,
author = {Guo, Kexin and Wang, Jingwen and Lin, Jiayu and Chen, Ningjing and Chen, Hengyuan and Zhou, Zilang and Li, Manzhou},
title = {A Multimodal Sensor-Based Self-Supervised Learning Framework for Low-Noise System State Prediction and Anomaly Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3851},
doi = {10.3390/s26123851}
}
EUVIMED