Abstract
Real-world classification problems present a certain degree of categorical imbalance, and due to the imbalance of data, this feature leads to many difficulties in classification, and it is important to adjust the indicators and methods appropriately to adapt to the target. The tabular dataset used for disk failure prediction presents an extremely imbalanced state, which poses great challenges in its failure prediction. In this paper, we balance the dataset based on integrated Generative Adversarial Networks (GAN) by learning the real dataset to generate synthetic data. After comparing the experimental data of back-propagation neural network, decision tree and Support Vector Machine (SVM) classical model before and after balancing, the balanced dataset based on integrated GAN shows higher prediction accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Prusa, J., Khoshgoftaar, T.M., Dittman, D.J., Napolitano, A.: Using random undersampling to alleviate class imbalance on tweet sentiment data. In: 2015 IEEE International Conference on Information Reuse and Integration, pp. 197−202. IEEE (2015)
Batista, G.E., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explor. Newslett. 6(1), 20–29 (2004)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Srinivas, C.G.P., Balachander, S., Singh Samant, Y.C., Hariharan, B. V., Devi, M.N.: Hardware trojan detection using XGBoost algorithm for IoT with data augmentation using CTGAN and smote. In: Kumar, N., Vinodhini, M., Venkatesha Prasad, R.R. (eds.) UBICNET 2021. LNICSSITE, vol. 383, pp. 116–127. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79276-3_10
Songyunhua. Research on predicting faulty disks based on SMART. Ph.D. thesis, NanJing University (2014)
Xie, X.: Classification of unbalanced data based on generative adversarial networks. Ph.D. thesis, Nanjing Post and Communications University (2020)
Wang, L., Han, M., Li, X., Zhang, N., Cheng, H.: A review of classification methods for unbalanced data sets. Comput. Eng. Appl. 57(22), 11 (2021)
Wang, Y., Dong, X., Wang, L., Chen, W., Zhang, X.: Optimizing small-sample disk fault detection based on LSTM-GAN model. In: ACM Transactions on Architecture and Code Optimization (TACO) (2022)
Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K.: Modeling tabular data using conditional gan. In: Advances in Neural Information Processing Systems 32 (2019)
LEE, J.S., LEE, O.: CTGAN vs TGAN? which one is more suitable for generating synthetic eeg data. J. Theor. Appl. Inf. Technol. 99(10) (2021)
D’Alessandro, B., O’Neil, C., Lagatta, T.: Conscientious classification: a data scientist’s guide to discrimination-aware classification. Big Data 5(2), 120–134 (2017)
Plesovskaya, E., Ivanov, S.: An empirical analysis of KDE-based generative models on small datasets. Procedia Comput. Sci. 193, 442–452 (2021)
Dong, Y., Jiang, Y.H., Yu-Tong, L.U., Zhou, E.Q.: Comparison of machine learning methods for disk failure prediction. Comput. Eng. Sci. 37, 2200–2207 (2015)
Xingli, J., Jianhui, W.: Prediction of disease classification based on decision tree algorithm. Inf. Comput. (2021)
Xuebing, Y., Jun, Z.: Decision tree algorithm and its core technology. Comput. Technol. Dev. 17(1), 3 (2007)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer science & business media, New York (1999). https://doi.org/10.1007/978-1-4757-3264-1
Bingpeng, Z.: Research on disk fault prediction method of large-scale storage system. Ph.D. thesis, Nankai University (2014)
Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Kubat, M., Matwin, S., et al.: Addressing the curse of imbalanced training sets: one-sided selection. In: ICML, vol. 97, p. 179. Citeseer (1997)
Tinglei, Z.: Research on hard disk fault prediction method based on improved random forest. Ph.D. thesis, Zhengzhou University (2019)
YongKang, L.: Disk fault prediction system based on machine learning. Ph.D. thesis, Huazhong University of Science and Technology (2015)
Acknowledgements
The research work was supported by the Shandong Provincial Natural Science Foundation of China (Grant No. ZR2019LZH003) in this paper. Peng Wu and Yuehui Chen are the authors to whom all correspondence should be addressed.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yuan, S., Wu, P., Chen, Y., Zhang, L., Wang, J. (2022). An Integrated GAN-Based Approach to Imbalanced Disk Failure Data. In: Huang, DS., Jo, KH., Jing, J., Premaratne, P., Bevilacqua, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2022. Lecture Notes in Computer Science, vol 13394. Springer, Cham. https://doi.org/10.1007/978-3-031-13829-4_53
Download citation
DOI: https://doi.org/10.1007/978-3-031-13829-4_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13828-7
Online ISBN: 978-3-031-13829-4
eBook Packages: Computer ScienceComputer Science (R0)