Time-Series Data Augmentation for Improving Multi-Class Classification Performance

Woo-Hyeon Kim (1), Geon-Woo Kim (2), Jaeyoon Ahn (3), Kyungyong Chung (4)
(1) Division of AI Computer Science and Engineering, Kyonggi University, Suwon, 16227, Republic of Korea
(2) Division of AI Computer Science and Engineering, Kyonggi University, Suwon, 16227, Republic of Korea
(3) Seoyoung Engineering Co., Ltd: Seongnam, 13595, Republic of Korea
(4) Division of AI Computer Science and Engineering, Kyonggi University, Suwon, 16227, Republic of Korea
Fulltext View | Download
How to cite (IJASEIT) :
Kim , Woo-Hyeon, et al. “Time-Series Data Augmentation for Improving Multi-Class Classification Performance”. International Journal on Advanced Science, Engineering and Information Technology, vol. 14, no. 3, June 2024, pp. 887-93, doi:10.18517/ijaseit.14.3.18550.
This paper proposes a new approach to classify and evaluate defects in concrete structures automatically. To overcome the limitations of defect detection methods that traditionally relied on expert visual observation, the reflection signal of electromagnetic pulses is extracted as time-series data and used to analyze the propagation characteristics of each defect. This study uses deep learning models to analyze these time-series data and classify defects. Since anomaly detection data has more normal data than anomaly data, data augmentation methods such as Time Warping, Noise Injection, Smoothing, Trend Shifting, etc., were applied to solve the problem of data imbalance and overfitting. Among them, Noise Injection showed the best performance. The generalization performance of the proposed method was evaluated through performance evaluation using LSTM, GRU, and TCN models, and LSTM models showed the highest performance. The study results show that the proposed method effectively classifies defect types in concrete structures and can solve the limitations of existing methods by automatic classification through deep learning models. In addition, it was confirmed that the model's performance could be improved by improving the amount and diversity of data by selecting and applying appropriate data augmentation methods. The contribution of the research is to present a new approach that automates the defect detection and classification task of concrete structures and provides high accuracy and efficiency.

M. Munir, S. A. Siddiqui, A. Dengel, and S. Ahmed, “DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series,” IEEE Access, vol. 7, pp. 1991–2005, 2019, doi:10.1109/access.2018.2886457.

H. Ismail Fawaz et al., “InceptionTime: Finding AlexNet for time series classification,” Data Mining and Knowledge Discovery, vol. 34, no. 6, pp. 1936–1962, Sep. 2020, doi: 10.1007/s10618-020-00710-y.

L. Bergman and Y. Hoshen, "Classification-based anomaly detection for general data," arXiv preprint arXiv:2005.02359, 2020.

M. Wiese, R. Knobloch, R. Korn, and P. Kretschmer, “Quant GANs: deep generation of financial time series,” Quantitative Finance, vol. 20, no. 9, pp. 1419–1440, Apr. 2020, doi:10.1080/14697688.2020.1730426.

C. Sun, S. Hong, M. Song and H. Li, "A review of deep learning methods for irregularly sampled medical time series data," arXiv preprint arXiv:2010.12493, 2020.

P. Hewage et al., “Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station,” Soft Computing, vol. 24, no. 21, pp. 16453–16482, Apr. 2020, doi: 10.1007/s00500-020-04954-0.

A. Copiaco et al., “An innovative deep anomaly detection of building energy consumption using energy time-series images,” Engineering Applications of Artificial Intelligence, vol. 119, p. 105775, Mar. 2023, doi: 10.1016/j.engappai.2022.105775.

Y. Liu et al., “Deep Anomaly Detection for Time-Series Data in Industrial IoT: A Communication-Efficient On-Device Federated Learning Approach,” IEEE Internet of Things Journal, vol. 8, no. 8, pp. 6348–6358, Apr. 2021, doi: 10.1109/jiot.2020.3011726.

B. K. Iwana and S. Uchida, “An empirical survey of data augmentation for time series classification with neural networks,” PLOS ONE, vol. 16, no. 7, p. e0254841, Jul. 2021, doi: 10.1371/journal.pone.0254841.

H. Li, “Time works well: Dynamic time warping based on time weighting for time series data mining,” Information Sciences, vol. 547, pp. 592–608, Feb. 2021, doi: 10.1016/j.ins.2020.08.089.

A. Camuto, M. Willetts, U. Simsekli, S. J. Roberts and C. C. Holmes, "Explicit regularisation in gaussian noise injections," In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 1393, 16603–16614, 2020.

C.-B. Zhang et al., “Delving Deep Into Label Smoothing,” IEEE Transactions on Image Processing, vol. 30, pp. 5984–5996, 2021, doi:10.1109/tip.2021.3089942.

M. Sayemuzzaman and M. K. Jha, “Seasonal and annual precipitation time series trend analysis in North Carolina, United States,” Atmospheric Research, vol. 137, pp. 183–194, Feb. 2014, doi:10.1016/j.atmosres.2013.10.012.

Q. Wen, L. Sun, F. Yang, X. Song, J. Gao, X. Wang and H. Xu, "Time series data augmentation for deep learning: A survey," arXiv preprint arXiv:2002.12478, 2020.

F. Karim, S. Majumdar, H. Darabi, and S. Chen, “LSTM Fully Convolutional Networks for Time Series Classification,” IEEE Access, vol. 6, pp. 1662–1669, 2018, doi: 10.1109/access.2017.2779939.

W. Zheng and G. Chen, “An Accurate GRU-Based Power Time-Series Prediction Approach With Selective State Updating and Stochastic Optimization,” IEEE Transactions on Cybernetics, vol. 52, no. 12, pp. 13902–13914, Dec. 2022, doi: 10.1109/tcyb.2021.3121312.

J. Fan, K. Zhang, Y. Huang, Y. Zhu, and B. Chen, “Parallel spatio-temporal attention-based TCN for multivariate time series prediction,” Neural Computing and Applications, vol. 35, no. 18, pp. 13109–13118, May 2021, doi: 10.1007/s00521-021-05958-z.

F. Ramzan et al., “A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer’s Disease Stages Using Resting-State fMRI and Residual Neural Networks,” Journal of Medical Systems, vol. 44, no. 2, Dec. 2019, doi: 10.1007/s10916-019-1475-2.

F. Wang, K. Li, and Y. Liu, “Optimal water-cement ratio of cement-stabilized soil,” Construction and Building Materials, vol. 320, p. 126211, Feb. 2022, doi: 10.1016/j.conbuildmat.2021.126211.

O. Lotfi-Omran, A. Sadrmomtazi, and I. M. Nikbin, “A comprehensive study on the effect of water to cement ratio on the mechanical and radiation shielding properties of heavyweight concrete,” Construction and Building Materials, vol. 229, p. 116905, Dec. 2019, doi:10.1016/j.conbuildmat.2019.116905.

X. Cai, T. Xu, J. Yi, J. Huang, and S. Rajasekaran, "Dtwnet: a dynamic time warping network," Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 1044, 11640–11650, 2019

Z. Zhao, Z. Wu, Y. Zheng, and P. Ma, “Recurrent neural networks for atmospheric noise removal from InSAR time series with missing values,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 180, pp. 227–237, Oct. 2021, doi: 10.1016/j.isprsjprs.2021.08.009.

S. Hansun, “A new approach of moving average method in time series analysis,” 2013 Conference on New Media Studies (CoNMedia), Nov. 2013, doi: 10.1109/conmedia.2013.6708545.

W. Yu, I. Y. Kim, and C. Mechefske, “Analysis of different RNN autoencoder variants for time series classification and machine prognostics,” Mechanical Systems and Signal Processing, vol. 149, p. 107322, Feb. 2021, doi: 10.1016/j.ymssp.2020.107322.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929-1958, 2014.

T. Szandała, “Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks,” Studies in Computational Intelligence, pp. 203–224, Jul. 2020, doi: 10.1007/978-981-15-5495-7_11.

L. Hui, M. Belkin, "Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks," arXiv preprint arXiv:2006.07322, 2020.

H. J. Kwon, M. J. Kim, J. W. Baek, and K. Chung, "Voice Frequency Synthesis using VAW-GAN based Amplitude Scaling for Emotion Transformation,” KSII Transactions on Internet and Information Systems, vol. 16, no. 2, Feb. 2022, doi: 10.3837/tiis.2022.02.018.

Y. Yu, X. Si, C. Hu, and J. Zhang, “A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures,” Neural Computation, vol. 31, no. 7, pp. 1235–1270, Jul. 2019, doi:10.1162/neco_a_01199.

K. Smagulova and A. P. James, “A survey on LSTM memristive neural network architectures and applications,” The European Physical Journal Special Topics, vol. 228, no. 10, pp. 2313–2324, Oct. 2019, doi:10.1140/epjst/e2019-900046-x.

B. U. Jeon, K. Chung, " “CutPaste-Based Anomaly Detection Model using Multi Scale Feature Extraction in Time Series Streaming Data,” KSII Transactions on Internet and Information Systems, vol. 16, no. 8, Aug. 2022, doi: 10.3837/tiis.2022.08.018, 2022

H. Yoo, R. C. Park, K. Chung, “IoT-Based Health Big-Data Process Technologies: A Survey,” KSII Transactions on Internet and Information Systems, vol. 15, no. 3, Mar. 2021, doi:10.3837/tiis.2021.03.009.

G.-I. Kim, H. Yoo, H.-J. Cho, and K. Chung, “Defect Detection Model Using Time Series Data Augmentation and Transformation,” Computers, Materials & Continua, vol. 78, no. 2, pp. 1713–1730, 2024, doi: 10.32604/cmc.2023.046324.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).