Integrated Feature-Enhanced Residual Networks for Time Series Classification
Keywords:
Time series classification, residual networks, deep learning, feature enhancementAbstract
Time series classification (TSC) plays a crucial role in various real-world applications, including finance, healthcare, and industrial monitoring. This paper proposes an innovative framework, Integrated Feature-Enhanced Residual Networks (IFER-Net), designed to improve classification accuracy by combining deep residual learning with advanced feature extraction mechanisms. The model integrates temporal and frequency-domain representations with residual connections to enhance learning efficiency and model interpretability. By incorporating attention-based feature enhancement modules and multi-scale convolutional blocks, the proposed network captures both short- and long-term temporal dependencies. Extensive experiments conducted on benchmark TSC datasets demonstrate that IFER-Net outperforms existing state-of-the-art models in terms of accuracy, robustness, and generalization capability. The architecture offers a scalable and effective solution for time-dependent data classification tasks across domains.
References
Afonso, L.C., Rosa, G.H., Pereira, C.R., Weber, S.A., Hook, C., Albuquerque, V.H.C.,Papa, J.P., 2019. A recurrence plot-based approach for Parkinson’s diseaseidentification. Future Gener. Comput. Syst. 94, 282–292.
Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E., 2017. The great time seriesclassification bake off: a review and experimental evaluation of recent algorithmicadvances. Data Min. Knowl. Discov. 31, 606–660.
Chen, W., Shi, K., 2019. A deep learning framework for time series classification usingrelative position matrix and convolutional neural network. Neurocomputing 359,384–394.
Chen, Y., Su, S., Yang, H., 2020. Convolutional neural network analysis of recurrenceplots for anomaly detection. Int. J. Bifurcation Chaos 30 (01), 2050002.
Dau, H.A., Bagnall, A., Kamgar, K., Yeh, C.C.M., Zhu, Y., Gharghabi, S., Ratanama-hatana, C.A., Keogh, E., 2019. The UCR time series archive. IEEE/CAA J. Autom.Sin. 6 (6), 1293–1305.
Du, M., Wei, Y., Zheng, X., Ji, C., 2023. Multi-feature based network for multivariatetime series classification. Inform. Sci. 639, 119009.
Eckmann, J.-P., Kamphorst, S.O., Ruelle, D., 1987. Recurrence plots of dynamicalsystems. Europhys. Lett. 4 (9), 973.
Farahani, M.A., McCormick, M., Harik, R., Wuest, T., 2025. Time-series classificationin smart manufacturing systems: An experimental evaluation of state-of-the-artmachine learning algorithms. Robot. Comput.-Integr. Manuf. 91, 102839.
Garcia-Ceja, E., Uddin, M.Z., Torresen, J., 2018. Classification of recurrence plots’distance matrices with a convolutional neural network for activity recognition.Procedia Comput. Sci. 130, 157–163.
Graves, A., Graves, A., 2012. Long short-term memory. In: Supervised SequenceLabelling with Recurrent Neural Networks. Springer, pp. 37–45.
Hao, C., Wang, R., Li, M., Ma, C., Cai, Q., Gao, Z., 2021. Convolutional neural networkbased on recurrence plot for EEG recognition. Chaos 31 (12).
Hatami, N., Gavet, Y., Debayle, J., 2018. Classification of time-series images usingdeep convolutional neural networks. In: Tenth International Conference on MachineVision. CMV 2017, SPIE, pp. 242–249.
Herrmann, M., Tan, C.W., Salehi, M., Webb, G.I., 2023. Proximity Forest 2.0: A neweffective and scalable similarity-based classifier for time series. arXiv preprintarXiv:2304.05800.
Homenda, W., Jastrzebska, A., Wrzesien, M., 2022. Time series classification usingimages.
Hsueh, Y., Ittangihala, V.R., Wu, W.B., Chang, H.C., Kuo, C.C., 2019. Condition monitorsystem for rotation machine by CNN with recurrence plot. Energies 12 (17), 3221.
Huang, S.H., Lingjie, X., Congwei, J., 2020. Residual attention net for superiorcross-domain time sequence modeling. arXiv preprintarXiv:2001.04077.
Huang, W., Xu, H., Yu, Y., 2023a. MRP-Net: Seizure detection method based onmodified recurrence plot and additive attention convolution neural network.Biomed. Signal Process. Control 86, 105165.
Huang, W., Yan, G., Chang, W., Zhang, Y., Yuan, Y., 2023b. EEG-based classificationcombining Bayesian convolutional neural networks with recurrence plot for motormovement/imagery. Pattern Recognit. 144, 109838.
Huang, W., Yan, G., Chang, W., Zhang, Y., Yuan, Y., 2023c. EEG-based classificationcombining Bayesian convolutional neural networks with recurrence plot for motormovement/imagery. Pattern Recognit. 144, 109838.
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller, P.A., 2019. Deeplearning for time series classification: a review. Data Min. Knowl. Discov. 33 (4),917–963.
Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D.F., Weber, J.,Webb, G.I., Idoumghar, L., Muller, P.A., Petitjean, F., 2020. Inceptiontime: Findingalexnet for time series classification. Data Min. Knowl. Discov. 34 (6), 1936–1962.
Ji, C., Du, M., Hu, Y., Liu, S., Pan, L., Zheng, X., 2022. Time series classification basedon temporal features. Appl. Soft Comput. 128, 109494.
Khan, M., Wang, H., Riaz, A., Elfatyany, A., Karim, S., 2021. Bidirectional LSTM-RNN-based hybrid deep learning frameworks for univariate time series classification. J.Supercomput. 77, 7021–7045.
Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprintarXiv:1412.6980.
Kirichenko, L., Radivilova, T., Stepanenko, J., 2021. Applying recurrence plots toclassify time series. In: Computational Linguistics and Intelligent Systems, 2021.pp. 16–26.
Kirichenko, L., Zinchenko, P., Radivilova, T., 2020. Classification of time realizationsusing machine learning recognition of recurrence plots. In: International ScientificConference ‘‘Intellectual Systems of Decision Making and Problem of ComputationalIntelligence’’. Springer, pp. 687–696.
LeCun, Y., Bengio, Y., Hinton, G., 2015. Deep learning. Nature 521 (7553), 436–444.
Lee, H., Lee, J., Shin, M., 2019. Using wearable ECG/PPG sensors for driver drowsinessdetection based on distinguishable pattern of recurrence plots. Electronics 8 (2),192.
Li, J., Fang, F., Mei, K., Zhang, G., 2018. Multi-scale residual network for image super-resolution. In: Proceedings of the European Conference on Computer Vision. ECCV,pp. 517–532.
Li, T., Zhang, Y., Wang, T., 2021. SRPM–CNN: A combined model based on slide relativeposition matrix and CNN for time series classification. Complex Intell. Syst. 7,1619–1631.
Michael, T., Spiegel, S., Albayrak, S., 2015. Time series classification using compressedrecurrence plots. In: Proceedings of ECML-PKDD.
Nakano, K., Chakraborty, B., 2019. Effect of data representation for time seriesclassification—A comparative study and a new proposal. Mach. Learn. Knowl. Extr.1 (4), 1100–1120.
Qin, Z., Zhang, Y., Meng, S., Qin, Z., Choo, K.K.R., 2020. Imaging and fusing timeseries for wearable sensor-based human activity recognition. Inf. Fusion 53, 80–87.
Ren, Y., Li, L., Yang, X., Zhou, J., 2022. Autotransformer: Automatic transformerarchitecture design for time series classification. In: Pacific-Asia Conference onKnowledge Discovery and Data Mining. Springer, pp. 143–155.
Shankar, A., Khaing, H.K., Dandapat, S., Barma, S., 2021. Analysis of epileptic seizuresbased on EEG using recurrence plot images and deep learning. Biomed. SignalProcess. Control 69, 102854.
Sharma, Y., Coronato, N., Brown, D.E., 2022. Encoding cardiopulmonary exercisetesting time series as images for classification using convolutional neural network.In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine& Biology Society. EMBC, IEEE, pp. 1611–1614.
Silva, D.F., De Souza, V.M., Batista, G.E., 2013. Time series classification using com-pression distance of recurrence plots. In: 2013 IEEE 13th International Conferenceon Data Mining. IEEE, pp. 687–696.
Song, J., Lee, Y.C., Lee, J., 2023. Deep generative model with time series-imageencoding for manufacturing fault detection in die casting process. J. Intell. Manuf.34 (7), 3001–3014.
Souza, V.M., Silva, D.F., Batista, G.E., 2014. Extracting texture features for time seriesclassification. In: 2014 22nd International Conference on Pattern Recognition. IEEE,pp. 1425–1430.
Spiegel, S., 2015. Discovery of driving behavior patterns. In: Smart Information Systems:Computational Intelligence for Real-Life Applications. Springer, pp. 315–343.
Spiegel, S., Marwan, N., 2016. Time and again: Time series mining via recurrence quan-tification analysis. In: Machine Learning and Knowledge Discovery in Databases:European Conference, ECML PKDD 2016, Riva Del Garda, Italy, September 19–23,2016, Proceedings, Part III 16. Springer, pp. 258–262.
Sreenivas, K.V., Ganesan, M., Lavanya, R., 2021. Classification of arrhythmia in timeseries ECG signals using image encoding and convolutional neural networks. In:2021 Seventh International Conference on Bio Signals, Images, and Instrumentation.ICBSII, IEEE, pp. 1–6.
Tan, C.W., Dempster, A., Bergmeir, C., Webb, G.I., 2022. MultiRocket: multiple poolingoperators and transformations for fast and effective time series classification. DataMin. Knowl. Discov. 36 (5), 1623–1646.
Wang, D.F., Guo, Y., Wu, X., Na, J., Litak, G., 2020a. Planetary-gearbox faultclassification by convolutional neural network and recurrence plot. Appl. Sci. 10(3), 932.
Wang, B., Jiang, T., Zhou, X., Ma, B., Zhao, F., Wang, Y., 2020b. Time-seriesclassification based on fusion features of sequence and visualization. Appl. Sci.10 (12), 4124.
Wang, Z., Oates, T., et al., 2015. Encoding time series as images for visual inspectionand classification using tiled convolutional neural networks. In: Workshops at theTwenty-Ninth AAAI Conference on Artificial Intelligence. AAAI Menlo Park, CA,USA.
Wang, Z., Yan, W., Oates, T., 2017. Time series classification from scratch with deepneural networks: A strong baseline. In: 2017 International Joint Conference onNeural Networks. IJCNN, IEEE, pp. 1578–1585.
Yang, C.L., Chen, Z.X., Yang, C.Y., 2019. Sensor classification using convolutional neuralnetwork by encoding multivariate time series as two-dimensional colored images.Sensors 20 (1), 168.
Yin, Y., Shang, P., 2016. Multiscale recurrence plot and recurrence quantificationanalysis for financial time series. Nonlinear Dynam. 85, 2309–2352.
Zhang, Y., Hou, Y., OuYang, K., Zhou, S., 2022. Multi-scale signed recurrence plot basedtime series classification using inception architectural networks. Pattern Recognit.123, 108385.
Zhang, Y., Hou, Y., Zhou, S., Ouyang, K., 2020. Encoding time series as multi-scalesigned recurrence plots for classification using fully convolutional networks. Sensors20 (14), 3818.
Zhao, Y., Dong, F., Sun, T., Ju, Z., Yang, L., Shan, P., Li, L., Lv, X., Lian, C., 2024. Imageexpression of time series data of wearable IMU sensor and fusion classification ofgymnastics action. Expert Syst. Appl. 238, 121978.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Dr. Emma R. Wallace, Prof. Lucas Stein
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain full copyright of their published work. By submitting to an ERDAST journal and upon acceptance of the article, the author(s) agree to grant the journal a non-exclusive license to publish, reproduce, distribute, and archive the article. All articles are published under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Under this license: Others may copy, distribute, display, remix, adapt, and build upon the work, even commercially, As long as proper credit is given to the original author(s) and source, A link to the license is provided, an, Any changes are clearly indicated.
???? License link: https://creativecommons.org/licenses/by/4.0/
