{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:08:30Z","timestamp":1760234910303,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T00:00:00Z","timestamp":1624579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903373"],"award-info":[{"award-number":["61903373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Recently, some researchers adopted the convolutional neural network (CNN) for time series classification (TSC) and have achieved better performance than most hand-crafted methods in the University of California, Riverside (UCR) archive. The secret to the success of the CNN is weight sharing, which is robust to the global translation of the time series. However, global translation invariance is not the only case considered for TSC. Temporal distortion is another common phenomenon besides global translation in time series. The scale and phase changes due to temporal distortion bring significant challenges to TSC, which is out of the scope of conventional CNNs. In this paper, a CNN architecture with an elastic matching mechanism, which is named Elastic Matching CNN (short for EM-CNN), is proposed to address this challenge. Compared with the conventional CNN, EM-CNN allows local time shifting between the time series and convolutional kernels, and a matching matrix is exploited to learn the nonlinear alignment between time series and convolutional kernels of the CNN. Several EM-CNN models are proposed in this paper based on diverse CNN models. The results for 85 UCR datasets demonstrate that the elastic matching mechanism effectively improves CNN performance.<\/jats:p>","DOI":"10.3390\/a14070192","type":"journal-article","created":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T11:07:40Z","timestamp":1624619260000},"page":"192","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Convolutional Neural Network with an Elastic Matching Mechanism for Time Series Classification"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5142-1687","authenticated-orcid":false,"given":"Kewei","family":"Ouyang","sequence":"first","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Yi","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Shilin","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Ye","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4788","DOI":"10.1109\/TIE.2018.2864702","article-title":"Time series classification with multivariate convolutional neural network","volume":"66","author":"Liu","year":"2018","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ord\u00f3\u00f1ez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., and Mohamed, A. (2013, January 8\u201313). Hybrid speech recognition with deep bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1954","DOI":"10.1016\/j.eswa.2007.02.006","article-title":"Wavelet\/mixture of experts network structure for EEG signals classification","volume":"34","year":"2008","journal-title":"Expert Syst. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1117\/12.571789","article-title":"Contour matching for a fish recognition and migration-monitoring system","volume":"Volume 5606","author":"Lee","year":"2004","journal-title":"Two-and Three-Dimensional Vision Systems for Inspection, Control, and Metrology II"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: A review","volume":"33","author":"Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_7","unstructured":"Cai, X., Xu, T., Yi, J., Huang, J., and Rajasekaran, S. (2019). DTWNet: A dynamic time warping network. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"107024","DOI":"10.1016\/j.patcog.2019.107024","article-title":"Time series classification using local distance-based features in multi-modal fusion networks","volume":"97","author":"Iwana","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.knosys.2014.04.035","article-title":"An empirical evaluation of similarity measures for time series classification","volume":"67","author":"Serra","year":"2014","journal-title":"Knowl.-Based Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.patcog.2017.09.020","article-title":"shapedtw: Shape dynamic time warping","volume":"74","author":"Zhao","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1109\/JAS.2019.1911747","article-title":"The UCR time series archive","volume":"6","author":"Dau","year":"2019","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1542","DOI":"10.14778\/1454159.1454226","article-title":"Querying and mining of time series data: Experimental comparison of representations and distance measures","volume":"1","author":"Ding","year":"2008","journal-title":"Proc. VLDB Endow."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1016\/j.patcog.2010.09.022","article-title":"Weighted dynamic time warping for time series classification","volume":"44","author":"Jeong","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","article-title":"Dynamic programming algorithm optimization for spoken word recognition","volume":"26","author":"Sakoe","year":"1978","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/TASSP.1975.1162641","article-title":"Minimum prediction residual principle applied to speech recognition","volume":"23","author":"Itakura","year":"1975","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1007\/s10618-012-0251-4","article-title":"Using derivatives in time series classification","volume":"26","year":"2013","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3760","DOI":"10.1109\/TNNLS.2019.2944933","article-title":"Deep Adaptive Input Normalization for Time Series Forecasting","volume":"31","author":"Passalis","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_18","unstructured":"Franceschi, J.Y., Dieuleveut, A., and Jaggi, M. (2019). Unsupervised scalable representation learning for multivariate time series. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_19","unstructured":"Dennis, D.K., Acar, D., Mandikal, V., Sadasivan, V., Simhadri, H., Saligrama, V., and Jain, P. (2019, January 8\u201314). Shallow RNNs: A method for accurate time-series classification on tiny devices. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada."},{"key":"ref_20","unstructured":"Vincent, L., and Thome, N. (2019). Shape and time distortion loss for training deep time series forecasting models. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, Z., Li, J., and Wu, J. (2018, January 19\u201323). Multilevel wavelet decomposition network for interpretable time series analysis. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.","DOI":"10.1145\/3219819.3220060"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yan, W., and Oates, T. (2017, January 14\u201319). Time series classification from scratch with deep neural networks: A strong baseline. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Iwana, B.K., and Uchida, S. (2017). Dynamic Weight Alignment for Convolutional Neural Networks. arXiv.","DOI":"10.1109\/ICDAR.2017.72"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: Finding alexnet for time series classification","volume":"34","author":"Fawaz","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gunasekar, S., Woodworth, B., Bhojanapalli, S., Neyshabur, B., and Srebro, N. (2018, January 11\u201316). Implicit regularization in matrix factorization. Proceedings of the 2018 Information Theory and Applications Workshop (ITA), San Diego, CA, USA.","DOI":"10.1109\/ITA.2018.8503198"},{"key":"ref_26","unstructured":"Liu, W., Liu, Z., Rehg, J.M., and Song, L. (2019). Neural similarity learning. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_27","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1007\/s10618-016-0483-9","article-title":"The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances","volume":"31","author":"Bagnall","year":"2017","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/s10618-015-0418-x","article-title":"Using dynamic time warping distances as features for improved time series classification","volume":"30","author":"Kate","year":"2016","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_30","unstructured":"Vlachos, M., Kollios, G., and Gunopulos, D. (March, January 26). Discovering similar multidimensional trajectories. Proceedings of the 18th International Conference on Data Engineering, San Jose, CA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, L., \u00d6zsu, M.T., and Oria, V. (2005, January 14\u201316). Robust and fast similarity search for moving object trajectories. Proceedings of the 2005 ACM SIGMOD International Conference on Management of Data, Baltimore, MD, USA.","DOI":"10.1145\/1066157.1066213"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1109\/TPAMI.2008.76","article-title":"Time warp edit distance with stiffness adjustment for time series matching","volume":"31","author":"Marteau","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TKDE.2012.88","article-title":"The move-split-merge metric for time series","volume":"25","author":"Stefan","year":"2012","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1007\/s10618-014-0361-2","article-title":"Time series classification with ensembles of elastic distance measures","volume":"29","author":"Lines","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lines, J., Taylor, S., and Bagnall, A. (2018). Time series classification with HIVE-COTE: The hierarchical vote collective of transformation-based ensembles. ACM Trans. Knowl. Discov. Data, 12.","DOI":"10.1145\/3182382"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Tanisaro, P., and Heidemann, G. (2016, January 18\u201320). Time series classification using time warping invariant echo state networks. Proceedings of the 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), Anaheim, CA, USA.","DOI":"10.1109\/ICMLA.2016.0149"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/7\/192\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:24:05Z","timestamp":1760163845000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/7\/192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,25]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["a14070192"],"URL":"https:\/\/doi.org\/10.3390\/a14070192","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2021,6,25]]}}}