摘要(英) |
With the development of smart manufacturing, many machines will be equipped with sensors to anomaly detection. However, anomaly detection has many problems, such as a large number of false positives, difficulty in parameter adjustment, required labeled normal and abnormal data, etc. One of the most common problems is data imbalance. This problem has a big impact on anomaly detection. Not only affecting the training of the model, but also inaccurate analysis results.
Time-series data means data will continue updating, such as sensor. In addition, if there is a large amount of data, and it is difficult to learn the pattern by manually extracting the feature space. Through the deep learning model to transform the data into a new feature space to learn the feature space. There are many studies that have found autoencoder that use unsupervised learning techniques. Because it has the ability to process spatial data through convolutional nerves to detect abnormal behaviors. Deep learning apply in image, text and classification. However, in this research is still an unexplored field.
This study proposes the concept of pre-training using autoencoder to dealing with data imbalance. Because autoencoder is an unsupervised learning neural network. Therefore, the autoencoder will try to find the best weight to training model. Therefore, the time series is reconstructed through the encoder and decoder. With the ability of long and LSTM to learn long-term data. It is suitable for time-series forecasting or anomaly detection. The trained Autoencoder-LSTM model can reconstruct time series data, and the neural network can effectively predict periodic time series data. Therefore, the goal of our research is using an autoencoder-long short-term memory network to solve the data imbalance. Let the model performance can effectively detect abnormal data and provide a new perspective to solve the data imbalance classification problem. |
參考文獻 |
Ahmad, S., et al. (2017). "Unsupervised real-time anomaly detection for streaming data." Neurocomputing 262: 134-147.
[2] Ali, A., et al. (2015). "Classification with class imbalance problem a review." Advance Soft Compute Appl.
[3] Barua, S., et al. (2014). "MWMOTE--Majority Weighted Minority Oversampling Technique for Imbalanced Data Set Learning." IEEE Transactions on Knowledge and Data Engineering 26(2): 405-425.
[4] Buda, T. S., et al. (2018). DeepAD: A Generic Framework Based on Deep Learning for Time Series Anomaly Detection. Advances in Knowledge Discovery and Data Mining: 577-588.
[5] Chalapathy, R. and S. Chawla (2019). "Deep learning for anomaly detection A survey.".
[6] Chawla, N. V., et al. (2002). "SMOTE Synthetic Minority Over-sampling Technique." Journal of Artificial Intelligence Research.
[7] Deng, J., et al. (2014). "Autoencoder-based Unsupervised Domain Adaptation for Speech Emotion Recognition." IEEE.
[8] FAHIM, M. and A. SILLITTI (2019). "Anomaly Detection, Analysis and Prediction Techniques in IoT Environment: A Systematic Literature Review." IEEE Access.
[9] Foxt, A. J. (1972). "Outliers in Time Series.".
[10] Galar, M., et al. (2012). "A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches." IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 42(4): 463-484.
[11] Goutte, C. and E. Gaussier (2005). "A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation."
[12] Hochreiter, S. and J. u. Schmidhuber (1997). "Long short-term memory."
[13] Kumar, P., et al. (2021). "Classification of Imbalanced Data:Review of Methods and Applications." IOP Conference Series: Materials Science and Engineering 1099(1)
[14] Laptev, N., et al. (2017). "Time-series extreme event forecasting with neural networks at uber." International Conference on Machine Learning.
[15] Lee, T., et al. (2016). "Performance of Machine Learning Algorithms for Class-Imbalanced Process Fault Detection Problems." IEEE Transactions on Semiconductor Manufacturing 29(4): 436-445.
[16] Malhotra, P., et al. (2016). "LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection."
[17] Ng, W. W. Y., et al. (2016). "Dual autoencoders features for imbalance classification problem." Pattern Recognition 60: 875-889.
[18] Nguyen, H. D., et al. (2021). "Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management." International Journal of Information Management 57.
[19] Nguyen, H. M., et al. (2009). "Borderline over-sampling for imbalanced data classification." IEEE.
[20] Ogunmolu, O. P., et al. (2016). "Nonlinear Systems Identification Using Deep Dynamic Neural Networks.".
[21] Ordonez, F. J. and D. Roggen (2016). "Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition." Sensors (Basel) 16(1).
[22] Pereira, J. and M. Silveira (2018). Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA): 1275-1282.
[23] Principi, E., et al. (2019). "Unsupervised electric motor fault detection by using deep autoencoders." IEEE/CAA Journal of Automatica Sinica 6(2): 441-451.
[24] Rifai, S., et al. (2011). "Contractive Auto-Encoders Explicit Invariance During Feature Extraction." Proceedings of the 28 th International Conference on Machine Learning.
[25] Saumya, S. and J. P. Singh (2020). "Spam review detection using LSTM autoencoder: an unsupervised approach." Electronic Commerce Research.
[26] Shao, H., et al. (2017). "A novel deep autoencoder feature learning method for rotating machinery fault diagnosis." Mechanical Systems and Signal Processing 95: 187-204.
[27] Shipmon, D. T., et al. (2017). "Time series anomaly detection; detection of anomalous drops with limited features and sparse examples in noisy highly periodic data.".
[28] Simard, B. and Frasconi (1994). "Learning long-term dependencies with gradient descent is difficult.".
[29] Singh, A. (2017). "Anomaly detection for temporal data using long short-term memory (LSTM)."
[30] Teng, M. (2010). "Anomaly Detection on Time Series." IEEE.
[31] Vincent, P., et al. (2010). "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion." Journal of Machine Learning Research 11: 3371-3408.
[32] Vuttipittayamongkol, P., et al. (2018). Overlap-Based Undersampling for Improving Imbalanced Data Classification. Intelligent Data Engineering and Automated Learning – IDEAL 2018: 689-697.
[33] Zhang, W., et al. (2018). "LSTM-Based Analysis of Industrial IoT Equipment." IEEE Access 6: 23551-23560.
[34] Zheng, L., et al. (2020). "Main Steam Temperature Prediction Modeling Based on Autoencoder and GRU.".
[35] Zhu, L. and N. Laptev (2017). Deep and Confident Prediction for Time Series at Uber. 2017 IEEE International Conference on Data Mining Workshops (ICDMW): 103-110. |