{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T13:52:29Z","timestamp":1765979549127,"version":"3.48.0"},"reference-count":60,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Time-series classification (TSC) is an important task across sciences. Symbolic representations (especially SFA) are very effective at combating noise. In this paper, we employ symbolic representations to create state-of-the-art time-series classifiers, with the aim to advance scalability without sacrificing accuracy. First, we create a graph representation of the time series based on SFA words. We use this representation together with graph kernels and an SVM classifier to create a scalable time-series classifier. Next, we use the graph representation together with a Graph Convolutional Neural Network to test how it fares against state-of-the-art time-series classifiers. Additionally, we devised deep neural networks exploiting the SFA representation, inspired by the text classification domain, to study how they fare against state-of-the-art classifiers. The proposed deep learning classifiers have been adapted and evaluated for the multivariate time-series case and also against state-of-the-art time-series classification algorithms based on symbolic representations.<\/jats:p>","DOI":"10.3390\/computers14120563","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T13:42:52Z","timestamp":1765978972000},"page":"563","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Univariate and Multivariate Time-Series Classifiers with Deep Learning Methods Exploiting Symbolic Representations"],"prefix":"10.3390","volume":"14","author":[{"given":"Apostolos","family":"Glenis","sequence":"first","affiliation":[{"name":"Department of Digital Systems, University of Piraeus, 185 34 Piraeus, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-622X","authenticated-orcid":false,"given":"George","family":"Vouros","sequence":"additional","affiliation":[{"name":"Department of Digital Systems, University of Piraeus, 185 34 Piraeus, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s10479-006-0076-x","article-title":"Electroencephalogram (EEG) time series classification: Applications in epilepsy","volume":"148","author":"Chaovalitwongse","year":"2006","journal-title":"Ann. Oper. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111564","DOI":"10.1016\/j.engstruct.2020.111564","article-title":"Applications of shapelet transform to time series classification of earthquake, wind and wave data","volume":"228","author":"Arul","year":"2021","journal-title":"Eng. Struct."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.ecoinf.2013.11.005","article-title":"Classifying insects on the fly","volume":"21","author":"Potamitis","year":"2014","journal-title":"Ecol. Inform."},{"key":"ref_4","unstructured":"Arghandeh, R., and Zhou, Y. (2018). Chapter 9\u2014Time-Series Classification Methods: Review and Applications to Power Systems Data. Big Data Application in Power Systems, Elsevier."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.A. (2018, January 16\u201320). Evaluating surgical skills from kinematic data using convolutional neural networks. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain. Proceedings, Part IV 11.","DOI":"10.1007\/978-3-030-00937-3_25"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tao, L., Elhamifar, E., Khudanpur, S., Hager, G.D., and Vidal, R. (2012, January 27). Sparse hidden markov models for surgical gesture classification and skill evaluation. Proceedings of the Information Processing in Computer-Assisted Interventions: Third International Conference, IPCAI 2012, Pisa, Italy. Proceedings 3.","DOI":"10.1007\/978-3-642-30618-1_17"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.jbi.2011.11.002","article-title":"Classification of surgical processes using dynamic time warping","volume":"45","author":"Forestier","year":"2012","journal-title":"J. Biomed. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1109\/TCYB.2014.2350774","article-title":"3-D human action recognition by shape analysis of motion trajectories on riemannian manifold","volume":"45","author":"Devanne","year":"2014","journal-title":"IEEE Trans. Cybern."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1007\/s10994-021-06055-x","article-title":"Deep learning and multivariate time series for cheat detection in video games","volume":"110","author":"Pinto","year":"2021","journal-title":"Mach. Learn."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Younis, R., Zerr, S., and Ahmadi, Z. (2022, January 13\u201316). Multivariate time series analysis: An interpretable cnn-based model. Proceedings of the 2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA), Shenzhen, China.","DOI":"10.1109\/DSAA54385.2022.10032335"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Madrid, F., Singh, S., Chesnais, Q., Mauck, K., and Keogh, E. (2019, January 5\u20138). Matrix profile xvi: Efficient and effective labeling of massive time series archives. Proceedings of the 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Washington, DC, USA.","DOI":"10.1109\/DSAA.2019.00061"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Devanne, M., R\u00e9my-N\u00e9ris, O., Le Gals-Garnett, B., Kermarrec, G., and Thepaut, A. (February, January 31). A co-design approach for a rehabilitation robot coach for physical rehabilitation based on the error classification of motion errors. Proceedings of the 2018 Second IEEE International Conference on Robotic Computing (IRC), Laguna Hills, CA, USA.","DOI":"10.1109\/IRC.2018.00074"},{"key":"ref_14","unstructured":"Sch\u00e4fer, P., and H\u00f6gqvist, M. (2012, January 27\u201330). SFA: A symbolic fourier approximation and index for similarity search in high dimensional datasets. Proceedings of the 15th International Conference on Extending Database Technology, Berlin, Germany."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Glenis, A., and Vouros, G.A. (2024). SCALE-BOSS-MR: Scalable Time Series Classification Using Multiple Symbolic Representations. Appl. Sci., 14.","DOI":"10.3390\/app14020689"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10618-007-0064-z","article-title":"Experiencing SAX: A novel symbolic representation of time series","volume":"15","author":"Lin","year":"2007","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Senin, P., and Malinchik, S. (2013, January 7\u201310). Sax-vsm: Interpretable time series classification using sax and vector space model. Proceedings of the 2013 IEEE 13th International Conference on Data Mining, Dallas, TX, USA.","DOI":"10.1109\/ICDM.2013.52"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1007\/s10618-014-0377-7","article-title":"The BOSS is concerned with time series classification in the presence of noise","volume":"29","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1007\/s10618-015-0441-y","article-title":"Scalable time series classification","volume":"30","year":"2016","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, P., and Leser, U. (2017, January 6\u201310). Fast and accurate time series classification with weasel. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore.","DOI":"10.1145\/3132847.3132980"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Glenis, A., and Vouros, G.A. (2020, January 19\u201321). Balancing between scalability and accuracy in time-series classification for stream and batch settings. Proceedings of the Discovery Science: 23rd International Conference, DS 2020, Thessaloniki, Greece. Proceedings 23.","DOI":"10.1007\/978-3-030-61527-7_18"},{"key":"ref_22","unstructured":"Nguyen, T.L., and Ifrim, G. (2021). MrSQM: Fast time series classification with symbolic representations. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Nguyen, T.L., and Ifrim, G. (2022, January 19\u201323). Fast time series classification with random symbolic subsequences. Proceedings of the International Workshop on Advanced Analytics and Learning on Temporal Data, Grenoble, France.","DOI":"10.1007\/978-3-031-24378-3_4"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Glenis, A., and Vouros, G.A. (2022, January 7\u20139). SCALE-BOSS: A framework for scalable time-series classification using symbolic representations. Proceedings of the 12th Hellenic Conference on Artificial Intelligence, Corfu, Greece.","DOI":"10.1145\/3549737.3549761"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, P., and Leser, U. (2023). WEASEL 2.0\u2013A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classification. arXiv.","DOI":"10.1007\/s10994-023-06395-w"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, P., and Leser, U. (2017). Multivariate time series classification with WEASEL+ MUSE. arXiv.","DOI":"10.1145\/3132847.3132980"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dempster, A., Schmidt, D.F., and Webb, G.I. (2021, January 14\u201318). Minirocket: A very fast (almost) deterministic transform for time series classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore.","DOI":"10.1145\/3447548.3467231"},{"key":"ref_29","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_30","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_32","unstructured":"Ioffe, S. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","unstructured":"Monti, F., Frasca, F., Eynard, D., Mannion, D., and Bronstein, M.M. (2019). Fake news detection on social media using geometric deep learning. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"162","DOI":"10.21629\/JSEE.2017.01.18","article-title":"Convolutional neural networks for time series classification","volume":"28","author":"Zhao","year":"2017","journal-title":"J. Syst. Eng. Electron."},{"key":"ref_36","unstructured":"Serra, J., Pascual, S., and Karatzoglou, A. (2018). Towards a universal neural network encoder for time series. Artificial Intelligence Research and Development, IOS Press."},{"key":"ref_37","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":"Lucas","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ismail-Fawaz, A., Devanne, M., Weber, J., and Forestier, G. (2022, January 17\u201320). Deep learning for time series classification using new hand-crafted convolution filters. Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.","DOI":"10.1109\/BigData55660.2022.10020496"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ismail-Fawaz, A., Devanne, M., Berretti, S., Weber, J., and Forestier, G. (2023, January 9\u201313). Lite: Light inception with boosting techniques for time series classification. Proceedings of the 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), Thessaloniki, Greece.","DOI":"10.1109\/DSAA60987.2023.10302569"},{"key":"ref_40","unstructured":"Cui, Z., Chen, W., and Chen, Y. (2016). Multi-scale convolutional neural networks for time series classification. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.patrec.2022.02.007","article-title":"Mixing up contrastive learning: Self-supervised representation learning for time series","volume":"155","author":"Kampffmeyer","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ordonez, P., Armstrong, T., Oates, T., and Fackler, J. (2011, January 11). Using modified multivariate bag-of-words models to classify physiological data. Proceedings of the 2011 IEEE 11th International Conference on Data Mining Workshops, Vancouver, BC, Canada.","DOI":"10.1109\/ICDMW.2011.174"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1007\/s10618-014-0349-y","article-title":"Learning a symbolic representation for multivariate time series classification","volume":"29","author":"Baydogan","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s10618-020-00727-3","article-title":"The great multivariate time series classification bake off: A review and experimental evaluation of recent algorithmic advances","volume":"35","author":"Ruiz","year":"2021","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_45","first-page":"2539","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","first-page":"18","article-title":"Generalization and network design strategies","volume":"19","author":"LeCun","year":"1989","journal-title":"Connect. Perspect."},{"key":"ref_47","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"Handb. Brain Theory Neural Netw."},{"key":"ref_48","unstructured":"Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). Learning Internal Representations by Error Propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations, MIT Press."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/S0166-4115(97)80111-2","article-title":"Serial order: A parallel distributed processing approach","volume":"121","author":"Jordan","year":"1997","journal-title":"Advances in Psychology"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_52","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv."},{"key":"ref_53","first-page":"1639","article-title":"Halting in random walk kernels","volume":"28","author":"Sugiyama","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_54","first-page":"1","article-title":"pyts: A Python Package for Time Series Classification","volume":"21","author":"Faouzi","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_55","first-page":"1","article-title":"Grakel: A graph kernel library in python","volume":"21","author":"Siglidis","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_56","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_57","unstructured":"Chollet, F. (2021). Deep Learning with Python, Simon and Schuster."},{"key":"ref_58","unstructured":"Data61, C. (2025, September 09). StellarGraph Machine Learning Library. Available online: https:\/\/github.com\/stellargraph\/stellargraph."},{"key":"ref_59","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_60","first-page":"1","article-title":"aeon: A Python toolkit for learning from time series","volume":"25","author":"Middlehurst","year":"2024","journal-title":"J. Mach. Learn. Res."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/563\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T13:48:32Z","timestamp":1765979312000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":60,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["computers14120563"],"URL":"https:\/\/doi.org\/10.3390\/computers14120563","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]}}}