Conclusions
We propose a method based on intra-class similarity mixing, effectively alleviating the inability to improve the generalization of classification models. Its core concept involves improving the feature diversity and expanding the data scale by mixing local regions with similar features. The experimental results show that the proposed method can significantly outperform the similarity-based state-of-the-art methods. In future work, we will explore how to build and quantify the relationship between local similarity and lassification characteristics to further improve performance.
This is a preview of subscription content, log in via an institution to check access.
References
Buntine W. Machine learning after the deep learning revolution. Frontiers of Computer Science, 2020, 14(6): 146320
Zhang F, Ngo K H, Yang S, Nosratinia A. Transmit correlation diversity: Generalization, new techniques, and improved bounds. IEEE Transactions on Information Theory, 2022, 68(6): 3841–3869
Wei K, Li T, Huang F, Chen J, He Z. Cancer classification with data augmentation based on generative adversarial networks. Frontiers of Computer Science, 2022, 16(2): 162601
Ragab M, Eldele E, Tan W L, Foo C S, Chen Z, Wu M, Kwoh C K, Li X. ADATIME: a benchmarking suite for domain adaptation on time series data. ACM Transactions on Knowledge Discovery from Data, 2023, 17(8): 106
Kim B, Alawami M A, Kim E, Oh S, Park J, Kim H. A comparative study of time series anomaly detection models for industrial control systems. Sensors, 2023, 23(3): 1310
Li G, Jung J J. Deep learning for anomaly detection in multivariate time series: approaches, applications, and challenges. Information Fusion, 2023, 91: 93–102
Yun S, Han D, Chun S, Oh S J, Yoo Y, Choe J. CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019, 6022–6031
Bellos D, Basham M, Pridmore T, French A P. A convolutional neural network for fast upsampling of undersampled tomograms in X-ray CT time-series using a representative highly sampled tomogram. Journal of Synchrotron Radiation, 2019, 26(3): 839–853
Iwana B K, Uchida S. Time series data augmentation for neural networks by time warping with a discriminative teacher. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR). 2021, 3558–3565
Acknowledgment
This work was supported by the Fundamental Research Funds for the Central Universities (No. 2-9-2022-062).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests The authors declare that they have no competing interests or financial conflicts to disclose.
Electronic Supplementary Material
Rights and permissions
About this article
Cite this article
Liu, P., Wang, R., He, Y. et al. ISM: intra-class similarity mixing for time series augmentation. Front. Comput. Sci. 18, 186352 (2024). https://doi.org/10.1007/s11704-024-40110-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11704-024-40110-9