ORIGINAL ARTICLE
A Hybrid Spiking Model for Anomaly Detection in Multivariate Time Series
Wei Zhang,
Ping He,
Shengrui Wang,
Fan Yang,
Ying Liu,
Wei Zhang
School of Electronic and Information Engineering, Hebei University of Technology, Tianjin, China
Search for more papers by this authorCorresponding Author
Ping He
School of Artificial Intelligence, Hebei University of Technology, Tianjin, China
Correspondence:
Ping He ([email protected])
Search for more papers by this authorShengrui Wang
Faculty of Sciences, University of Sherbrooke, Sherbrooke, Québec, Canada
Search for more papers by this authorFan Yang
School of Electronic and Information Engineering, Hebei University of Technology, Tianjin, China
Search for more papers by this authorYing Liu
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
Search for more papers by this authorWei Zhang,
Ping He,
Shengrui Wang,
Fan Yang,
Ying Liu,
Wei Zhang
School of Electronic and Information Engineering, Hebei University of Technology, Tianjin, China
Search for more papers by this authorCorresponding Author
Ping He
School of Artificial Intelligence, Hebei University of Technology, Tianjin, China
Correspondence:
Ping He ([email protected])
Search for more papers by this authorShengrui Wang
Faculty of Sciences, University of Sherbrooke, Sherbrooke, Québec, Canada
Search for more papers by this authorFan Yang
School of Electronic and Information Engineering, Hebei University of Technology, Tianjin, China
Search for more papers by this authorYing Liu
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
Search for more papers by this authorFirst published: 19 June 2025
Funding: This work was supported by the Natural Science Foundation of Hebei Province (Grant no. F2020202067) and the scholarship from China Scholarship Council (Grant no. 201975).
ABSTRACT
Deep neural networks have exhibited preeminent performance in anomaly detection, but they struggle to effectively capture changes over time in multivariate time-series data and suffer from resource consumption issues. Spiking neural networks address these limitations by capturing the change in time-varying signals and decreasing resource consumption, but they sacrifice performance. This paper develops a novel spiking-based hybrid model incorporated a temporal prediction network and a reconstruction network. It integrates a unique first-spike frequency encoding scheme and a firing rate based anomaly score method. The encoding scheme enhances the event representation ability, while the anomaly score enables efficient anomaly identification. Our proposed model not only maintains low resource consumption but also improves the ability of anomaly detection. Experiments on publicly real-world datasets confirmed that the proposed model acquires state-of-the-art performance superior to existing approaches. Remarkably, it costs 5.04× lower energy consumption compared with the artificial neural network version.
Conflicts of Interest
The authors declare no conflicts of interest.
Open Research
Data Availability Statement
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
- Abdulaal, A., Z. Liu, and T. Lancewicki. 2021. “ Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization.” In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2485–2494. ACM.
10.1145/3447548.3467174 Google Scholar
- Agebure, M. A., E. O. Oyetunji, and E. Y. Baagyere. 2020. “A Three-Tier Road Condition Classification System Using a Spiking Neural Network Model.” Journal of King Saud University, Computer and Information Sciences 34, no. 5: 1718–1729. https://doi.org/10.1016/j.jksuci.2020.08.012.
10.1016/j.jksuci.2020.08.012 Google Scholar
- Arribas, D., Y. Zhao, and I. M. Park. 2020. “Rescuing Neural Spike Train Models From Bad Mle.” Advances in Neural Information Processing Systems 33: 2293–2303.
- Audibert, J., P. Michiardi, F. Guyard, S. Marti, and M. A. Zuluaga. 2020. “ Usad: Unsupervised Anomaly Detection on Multivariate Time Series.” In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 3395–3404. ACM. https://doi.org/10.1145/3394486.3403392.
10.1145/3394486.3403392 Google Scholar
- Bai, S., J. Z. Kolter, and V. Koltun. 2018. “An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling.” arXiv preprint arXiv:1803.01271. https://doi.org/10.48550/arXiv.1803.01271.
10.48550/arXiv.1803.01271 Google Scholar
- Bäßler, D., T. Kortus, and G. Gühring. 2022. “Unsupervised Anomaly Detection in Multivariate Time Series With Online Evolving Spiking Neural Networks.” Machine Learning 111: 1–32. https://doi.org/10.1007/s10994-022-06129-4.
- Blázquez-García, A., A. Conde, U. Mori, and J. A. Lozano. 2021. “A Review on Outlier/Anomaly Detection in Time Series Data.” ACM Computing Surveys 54, no. 3: 1–33. https://doi.org/10.1145/3444690.
10.1145/3444690 Google Scholar
- Chambaret, G., L. Berti-Equille, F. Bouchara, E. Bruno, V. Martin, and F. Chaillan. 2022. “ Stochastic Pairing for Contrastive Anomaly Detection on Time Series.” In Pattern Recognition and Artificial Intelligence: Third International Conference, ICPRAI 2022, Paris, France, June 1–3, 2022, Proceedings, Part II, 306–317. Springer.
10.1007/978-3-031-09282-4_26 Google Scholar
- Dennler, N., G. Haessig, M. Cartiglia, and G. Indiveri. 2021. “ Online Detection of Vibration Anomalies Using Balanced Spiking Neural Networks.” In 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, 1–4. IEEE. https://doi.org/10.1109/AICAS51828.2021.9458403.
10.1109/AICAS51828.2021.9458403 Google Scholar
- Galeano, P., D. Peña, and R. S. Tsay. 2006. “Outlier Detection in Multivariate Time Series by Projection Pursuit.” Journal of the American Statistical Association 101, no. 474: 654–669. https://doi.org/10.2307/27590725.
- Hundman, K., V. Constantinou, C. Laporte, I. Colwell, and T. Soderstrom. 2018. “ Detecting Spacecraft Anomalies Using Lstms and Nonparametric Dynamic Thresholding.” In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 387–395. ACM.
10.1145/3219819.3219845 Google Scholar
- Jaoudi, Y., C. Yakopcic, and T. Taha. 2020. “ Conversion of an Unsupervised Anomaly Detection System to Spiking Neural Network for Car Hacking Identification.” In 2020 11th International Green and Sustainable Computing Workshops, 1–4. IEEE. https://doi.org/10.1109/IGSC51522.2020.9291232.
10.1109/IGSC51522.2020.9291232 Google Scholar
- Jeyasothy, A., S. Sundaram, and N. Sundararajan. 2018. “Sefron: A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification.” IEEE Transactions on Neural Networks and Learning Systems 30, no. 4: 1231–1240. https://doi.org/10.1109/tnnls.2018.2868874.
- Kamata, H., Y. Mukuta, and T. Harada. 2022. “ Fully Spiking Variational Autoencoder.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 7059–7067. AAAI. https://doi.org/10.1609/aaai.v36i6.20665.
10.1609/aaai.v36i6.20665 Google Scholar
- Kim, S., S. Park, B. Na, and S. Yoon. 2020. “ Spiking-Yolo: Spiking Neural Network for Energy-Efficient Object Detection.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, 11270–11277. AAAI. https://doi.org/10.1609/aaai.v34i07.6787.
- Kingma, D. P., and J. Ba. 2014. “Adam: A Method for Stochastic Optimization.” arXiv preprint arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980.
10.48550/arXiv.1412.6980 Google Scholar
- Kong, L., J. Yu, D. Tang, Y. Song, and D. Han. 2023. “Multivariate Time Series Anomaly Detection With Generative Adversarial Networks Based on Active Distortion Transformer.” IEEE Sensors Journal 23, no. 9: 9658–9668.
- Li, D., D. Chen, B. Jin, L. Shi, J. Goh, and S.-K. Ng. 2019. “ Mad-Gan: Multivariate Anomaly Detection for Time Series Data With Generative Adversarial Networks.” In International Conference on Artificial Neural Networks, 703–716. Springer. https://doi.org/10.1007/978-3-030-30490-4_56.
10.1007/978-3-030-30490-4_56 Google Scholar
- Li, Z., Y. Zhao, J. Han, et al. 2021. “ Multivariate Time Series Anomaly Detection and Interpretation Using Hierarchical Inter-Metric and Temporal Embedding.” In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3220–3230. ACM. https://doi.org/10.1145/3447548.3467075.
10.1145/3447548.3467075 Google Scholar
- Ma, J., and S. Perkins. 2003. “ Time-Series Novelty Detection Using One-Class Support Vector Machines.” In Proceedings of the International Joint Conference on Neural Networks, vol. 3, 1741–1745. IEEE. https://doi.org/10.1109/ijcnn.2003.1223670.
- Maciag, P. S., M. Kryszkiewicz, R. Bembenik, J. L. Lobo, and J. Del Ser. 2021. “Unsupervised Anomaly Detection in Stream Data With Online Evolving Spiking Neural Networks.” Neural Networks 139: 118–139. https://doi.org/10.1016/j.neunet.2021.02.017.
- McKennoch, S., D. D. Liu, and L. Bushnell. 2006. “ Fast Modifications of the Spikeprop Algorithm.” In The 2006 IEEE International Joint Conference on Neural Network Proceedings, 3970–3977. IEEE.
- Park, D., Y. Hoshi, and C. C. Kemp. 2018. “A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an Lstm-Based Variational Autoencoder.” IEEE Robotics and Automation Letters 3, no. 3: 1544–1551. https://doi.org/10.1109/lra.2018.2801475.
10.1109/lra.2018.2801475 Google Scholar
- Rathi, N., and K. Roy. 2021. “Diet-Snn: A Low-Latency Spiking Neural Network With Direct Input Encoding and Leakage and Threshold Optimization.” IEEE Transactions on Neural Networks and Learning Systems 34, no. 6: 3174–3182. https://doi.org/10.1109/TNNLS.2021.3111897.
- Shin, Y., S. Lee, S. Tariq, et al. 2020. “ Itad: Integrative Tensor-Based Anomaly Detection System for Reducing False Positives of Satellite Systems.” In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2733–2740. ACM. https://doi.org/10.1145/3340531.3412716.
10.1145/3340531.3412716 Google Scholar
- Shrestha, S. B., L. Zhu, and P. Sun. 2022. “Spikemax: Spike-Based Loss Methods for Classification.” arXiv preprint arXiv:2205.09845. https://doi.org/10.48550/arXiv.2205.09845.
10.48550/arXiv.2205.09845 Google Scholar
- Stratton, P., A. Wabnitz, and T. J. Hamilton. 2020. “ A Spiking Neural Network Based Auto-Encoder for Anomaly Detection in Streaming Data.” In 2020 IEEE Symposium Series on Computational Intelligence, 1981–1988. IEEE. https://doi.org/10.1109/ssci47803.2020.9308187.
- Su, Y., Y. Zhao, C. Niu, R. Liu, W. Sun, and D. Pei. 2019. “ Robust Anomaly Detection for Multivariate Time Series Through Stochastic Recurrent Neural Network.” In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2828–2837. ACM. https://doi.org/10.1145/3292500.3330672.
10.1145/3292500.3330672 Google Scholar
- Taherkhani, A., A. Belatreche, Y. Li, G. Cosma, L. P. Maguire, and T. M. McGinnity. 2020. “A Review of Learning in Biologically Plausible Spiking Neural Networks.” Neural Networks 122: 253–272. https://doi.org/10.1016/j.neunet.2019.09.036.
- Tax, D. M., and R. P. Duin. 2004. “Support Vector Data Description.” Machine Learning 54, no. 1: 45–66. https://doi.org/10.1023/b:mach.0000008084.60811.49.
- Wu, Y., L. Deng, G. Li, J. Zhu, and L. Shi. 2018. “Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks.” Frontiers in Neuroscience 12: 331. https://doi.org/10.3389/fnins.2018.00331.
- Wu, Y., L. Deng, G. Li, J. Zhu, Y. Xie, and L. Shi. 2019. “ Direct Training for Spiking Neural Networks: Faster, Larger, Better.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 1311–1318. AAAI. https://doi.org/10.1609/aaai.v33i01.33011311.
10.1609/aaai.v33i01.33011311 Google Scholar
- Xing, L., K. Demertzis, and J. Yang. 2020. “Identifying Data Streams Anomalies by Evolving Spiking Restricted Boltzmann Machines.” Neural Computing and Applications 32, no. 11: 6699–6713. https://doi.org/10.1007/s00521-019-04288-5.
- Xu, H., W. Chen, N. Zhao, et al. 2018. “ Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal Kpis in Web Applications.” In Proceedings of the 2018 World Wide Web Conference, 187–196. ACM. https://doi.org/10.1145/3178876.3185996.
10.1145/3178876.3185996 Google Scholar
- Yin, C., S. Zhang, J. Wang, and N. N. Xiong. 2020. “Anomaly Detection Based on Convolutional Recurrent Autoencoder for Iot Time Series.” IEEE Transactions on Systems, Man, and Cybernetics: Systems 52, no. 1: 112–122. https://doi.org/10.1109/tsmc.2020.2968516.
10.1109/tsmc.2020.2968516 Google Scholar
- Zanatta, L., F. Barchi, A. Burrello, A. Bartolini, D. Brunelli, and A. Acquaviva. 2021. “ Damage Detection in Structural Health Monitoring With Spiking Neural Networks.” In 2021 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT), 105–110. IEEE. https://doi.org/10.1109/MetroInd4.0IoT51437.2021.9488476.
10.1109/MetroInd4.0IoT51437.2021.9488476 Google Scholar
- Zhang, C., D. Song, Y. Chen, et al. 2019. “ A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 1409–1416. AAAI. https://doi.org/10.1609/aaai.v33i01.33011409.
10.1609/aaai.v33i01.33011409 Google Scholar
- Zhang, G., X. Gao, L. Wang, et al. 2022. “Probabilistic Autoencoder With Multi-Scale Feature Extraction for Multivariate Time Series Anomaly Detection.” Applied Intelligence 53, no. 12: 1–18.
- Zhang, J., B. Dong, H. Zhang, et al. 2022. “ Spiking Transformers for Event-Based Single Object Tracking.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8801–8810. IEEE.
- Zhang, M., J. Wu, Y. Chua, et al. 2019. “ Mpd-al: An Efficient Membrane Potential Driven Aggregate-Label Learning Algorithm for Spiking Neurons.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 1327–1334. AAAI. https://doi.org/10.1609/aaai.v33i01.33011327.
- Zhao, H., Y. Wang, J. Duan, et al. 2020. “ Multivariate Time-Series Anomaly Detection via Graph Attention Network.” In 2020 IEEE International Conference on Data Mining, 841–850. IEEE. https://doi.org/10.1109/icdm50108.2020.00093.
- Zhao, X., W. Chen, Q. Yin, B. Wang, Z. Li, and J. Wang. 2022. “ Bidirectional Deep Variational Rnn for Refining Anomaly Detection of Multivariate Time Series.” In 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference, vol. 10, 1504–1509. IEEE.
10.1109/ITAIC54216.2022.9836567 Google Scholar
- Zhu, L., X. Wang, Y. Chang, J. Li, T. Huang, and Y. Tian. 2022. “ Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3594–3604. IEEE. https://doi.org/10.48550/arXiv.2201.10943.
- Zong, B., Q. Song, M. R. Min, et al. 2018. “ Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection.” In International Conference on Learning Representations, 1–19. MIT Press.
- Zuo, L., F. Xu, C. Zhang, T. Xiahou, and Y. Liu. 2022. “A Multi-Layer Spiking Neural Network-Based Approach to Bearing Fault Diagnosis.” Reliability Engineering & System Safety 225: 108561. https://doi.org/10.1016/j.ress.2022.108561.
- Zuo, L., L. Zhang, Z.-H. Zhang, X.-L. Luo, and Y. Liu. 2021. “A Spiking Neural Network-Based Approach to Bearing Fault Diagnosis.” Journal of Manufacturing Systems 61: 714–724. https://doi.org/10.1016/j.jmsy.2020.07.003.
