Abstract
Anomaly detection is the task of learning patterns of normal data and identifying data with other characteristics. As various types of sensors are attached to vehicle, healthcare equipment, production facilities, etc., detecting anomalies in multi-channel sensor data has become very important. In sensor data, abnormal signals occur temporally during certain intervals of a few channels. It is very important to capture the characteristics of individual channel and cross-channel relationship in order to detect abnormal signals that occur locally for a short time interval. We propose a channel-wise reconstruction-based anomaly detection framework which consists of two parts: channel-wise reconstruction part with convolutional autoencoder (CAE) and anomaly scoring part with machine learning algorithms, isolation forest (iForest) and local outlier factor (LOF). CAE learns the features of normal signal data and measures channel-wise reconstruction error. We applied the symmetric skip-connections technique to build a CAE model for higher reconstruction performance. Given the channel-wise reconstruction error as an input, iForest and LOF summarize it to anomaly score. We present our results on data collected from real sensors attached to vehicle and show that the proposed framework outperforms traditional reconstruction-based anomaly detection methods and one-class classification methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wulsin, D.F.: Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement. J. Neural Eng. 8(3), 036015 (2011)
Wang, K.: Research on healthy anomaly detection model based on deep learning from multiple time-series physiological signals. Sci. Program. 2016, 1–9 (2016)
Motoi, K., Tanaka, S.: Evaluation of a new sensor system for ambulatory monitoring of human posture and walking speed using accelerometers and gyroscope. In: SICE 2003 Annual Conference, vol. 2, pp. 1232–1235. IEEE (2003)
Khan, S.S.: Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders. Expert Syst. Appl. 87, 280–290 (2017)
Akhavian, R.: Construction equipment activity recognition for simulation input modeling using mobile sensors and machine learning classifiers. Adv. Eng. Inform. 29(4), 867–877 (2015)
Praveenkumar, T.: Fault diagnosis of automobile gearbox based on machine learning techniques. Procedia Eng. 97, 2092–2098 (2014)
Yang, J., Nguyen, M.N.: Deep convolutional neural networks on multichannel time series for human activity recognition. IJCAI 15, 3995–4001 (2015)
Wang, Z., Yan, W.: Time series classification from scratch with deep neural networks: a strong baseline. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1578–1585. IEEE (2017)
Zheng, Y.: Exploiting multi-channels deep convolutional neural networks for multivariate time series classification. Front. Comput. Sci. 10(1), 96–112 (2016)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. arXiv preprint, 1610-02357 (2017)
Ahmad, S.: Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262, 134–147 (2017)
Ferdousi, Z.: Unsupervised outlier detection in time series data. In: 22nd International Conference on Data Engineering Workshops 2006, Proceedings, pp. x121–x121. IEEE (2006)
Vahdatpour, A.: Unsupervised discovery of abnormal activity occurrences in multi-dimensional time series, with applications in wearable systems. In: Proceedings of the 2010 SIAM International Conference on Data Mining, pp. 641–652. Society for Industrial and Applied Mathematics (2010)
Sakurada, M.: Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, p. 4. ACM (2014)
Kiran, B.R.: An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos. J. Imaging 4(2), 36 (2018)
Vincent, P.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(Dec), 3371–3408 (2010)
Masci, J., Meier, U.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: International Conference on Artificial Neural Networks, pp. 52–59. Springer, Heidelberg (2011)
Mao, X.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Advances in Neural Information Processing Systems, pp. 2808–2810 (2016)
He, K.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Srivastava, R.K.: Training very deep networks. In: Advances in Neural Information Processing Systems, 2377–2385 (2015)
Ribeiro, M.: A study of deep convolutional auto-encoders for anomaly detection in videos. Pattern Recogn. Lett. 105, 13–22 (2018)
He, K., Zhang, X.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Han, D.: Comparison of commonly used image interpolation methods. In: ICCSEE, Hangzhou, pp. 1556–1559 (2013)
Rasmus, A., Raiko, T.: Denoising autoencoder with modulated lateral connections learns invariant representations of natural images. arXiv preprint (2014). arXiv:1412.7210
Liu, F.T., Ting, K.M.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422. IEEE (2008)
Breunig, M.: LOF: identifying density-based local outliers. ACM Sigmod Rec. 29(2), 93–104 (2000)
Dozat, T.: Incorporating nesterov momentum into adam (2016)
Sutskever, I., Martens, J.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139–1147 (2013)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Chollet, F.: Keras (2015)
Pedregosa, F.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(Oct), 2825–2830 (2011)
Joliffe, I.T.: Principal component analysis and exploratory factor analysis. Stat. Methods Med. Res. 1(1), 69–95 (1992)
Schölkopf, B., Smola, A.: Kernel principal component analysis. In: International Conference on Artificial Neural Networks, pp. 583–588. Springer, Heidelberg (1997)
Acknowledgments
This research was supported by the Ministry of Culture, Sports and Tourism and Korea Creative Content Agency in the Culture Technology Research & Development Program 2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kwak, M., Kim, S.B. (2020). Channel-Wise Reconstruction-Based Anomaly Detection Framework for Multi-channel Sensor Data. In: Bi, Y., Bhatia, R., Kapoor, S. (eds) Intelligent Systems and Applications. IntelliSys 2019. Advances in Intelligent Systems and Computing, vol 1038. Springer, Cham. https://doi.org/10.1007/978-3-030-29513-4_88
Download citation
DOI: https://doi.org/10.1007/978-3-030-29513-4_88
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29512-7
Online ISBN: 978-3-030-29513-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)