Abstract
Methods for extracting features from time series data using deep learning have been widely studied, but they still suffer from problems of severe loss of feature information across different network layers and parameter redundancy. Therefore, a new time-series data feature extraction model (CNN-CBAM) that integrates convolutional neural networks (CNN) and convolutional attention mechanisms (CBAM) is proposed. First, the parameters of the CNN and BiGRU prediction models are optimized through uniform design methods. Next, the CNN is used to extract features from the time series data, outputting multiple feature maps. These feature maps are then subjected to feature re-extraction by the CBAM attention mechanism at both the spatial and channel levels. Finally, the feature maps are input into the BiGRU model for prediction. Experimental results show that after CNN-CBAM processing, the stability and accuracy of the BiGRU prediction model improved by 77.6% and 76.3%, respectively, outperforming other feature extraction methods. Meanwhile, the training time of the model has only increased by 7.1%, demonstrating excellent time efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wan, T.H., Tsang, C.W., Hui, K., et al.: Anomaly detection of train wheels utilizing short-time Fourier transform and unsupervised learning algorithms. Eng. Appl. Artif. Intell. 122, 106037 (2023)
Zheng, Q., Chen, G., Jiao, A.: Chatter detection in milling process based on the combination of wavelet packet transform and PSO-SVM. Int. J. Adv. Manuf. Technol. 120(1–2), 1237–1251 (2022)
Yang, F., Ma, B., Wang, J., et al.: Target detection of UAV aerial image based on rotational invariant depth denoising automatic encoder. Xibei Gongye Daxue Xuebao/J. Northwestern Polytech. Univ. 38(6), 1345–1351 (2020)
Lei, F., Wang, X., Liu, Y.J., et al.: Study on feature extraction and classification of surface defects of refractory tiles based on self-encoder. Manuf. Autom. 44(12), 28–31+67 (2022)
Zha, W., Liu, Y., Wan, Y., et al.: Forecasting monthly gas field production based on the CNN-LSTM model. Energy 124889 (2022)
Kirisci, M., Cagcag, Y.O.: A new CNN-based model for financial time series: TAIEX and FTSE stocks forecasting. Neural Process. Lett. 54(4), 3357–3374 (2022)
Wang, D., Gan, J., Mao, J., et al.: Forecasting power demand in China with a CNN-LSTM model including multimodal information. Energy 263, 126012 (2023)
Yin, Z., Chen, M., Zhao, L., et al.: A novel automatic classification approach for microflaws on the large-aperture optics surface based on multilight source fusion and integrated deep learning architecture. J. Intell. Manuf. 1–16 (2022)
Bhimavarapu, U.: Prediction and classification of rice leaves using the improved PSO clustering and improved CNN. Multimedia Tools Appl. 1–14 (2023)
Agga, A., Abbou, A., Labbadi, M., et al.: CNN-LSTM: an efficient hybrid deep learning architecture for predicting short-term photovoltaic power production. Electr. Power Syst. Res. 208, 107908 (2022)
Zhang, C., Wang, D., Wang, L., et al.: Temporal data-driven failure prognostics using BiGRU for optical networks. J. Opt. Commun. Network. 12(8), 277–287 (2020)
Investing Homepage. https://cn.investing.com/economic-calendar. Accessed 23 Oct 2022
Cao, G., Wu, H., Wang, G., et al.: Selection of a suitable electrolyte for electrochemical grinding of high-speed steel roll material based on electrochemical techniques and uniform design machining experiments. Int. J. Adv. Manuf. Technol. 122(7–8), 3129–3147 (2022)
Liu, Y.M., Zhao, Z.Y., Zhang, S., et al.: Identification of abnormal processes with spatial-temporal data using convolutional neural networks. Processes 8(1), 73 (2020)
Liu, C., Hou, W.Y., Liu, D.Y.: Foreign exchange rates forecasting with convolutional neural network. Neural Process. Lett. 46(3), 1095–1119 (2017)
Zhang, Y., Yao, L., Zhang, L., et al.: Fault diagnosis of natural gas pipeline leakage based on 1D-CNN and self-attention mechanism. In: 2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp. 1282–1286. IEEE (2022)
He, X., Chen, Y.: Optimized input for CNN-based hyperspectral image classification using spatial transformer network. IEEE Geosci. Remote Sens. Lett. 16(12), 1884–1888 (2019)
Zhang, X., Ding, G., Li, J., et al.: Deep learning empowered MAC protocol identification with squeeze-and-excitation networks. IEEE Trans. Cogn. Commun. Network. 8(2), 683–693 (2021)
Yechuri, S., Vanambathina, S.: A nested U-net with efficient channel attention and D3Net for speech enhancement. Circuits Syst. Sig. Process. 1–21 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qin, J., Lang, D., Gao, C. (2023). Feature Extraction of Time Series Data Based on CNN-CBAM. In: Yu, Z., et al. Data Science. ICPCSEE 2023. Communications in Computer and Information Science, vol 1879. Springer, Singapore. https://doi.org/10.1007/978-981-99-5968-6_17
Download citation
DOI: https://doi.org/10.1007/978-981-99-5968-6_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5967-9
Online ISBN: 978-981-99-5968-6
eBook Packages: Computer ScienceComputer Science (R0)