{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:24:13Z","timestamp":1768404253015,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T00:00:00Z","timestamp":1602028800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T00:00:00Z","timestamp":1602028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recent developments of sensors that allow tracking of human movements and gestures enable rapid progress of applications in domains like medical rehabilitation or robotic control. Especially the inertial measurement unit (IMU) is an excellent device for real-time scenarios as it rapidly delivers data input. Therefore, a computational model must be able to learn gesture sequences in a fast yet robust way. We recently introduced an echo state network (ESN) framework for continuous gesture recognition (Tietz et al., 2019) including novel approaches for gesture spotting, i.e., the automatic detection of the start and end phase of a gesture. Although our results showed good classification performance, we identified significant factors which also negatively impact the performance like subgestures and gesture variability. To address these issues, we include experiments with Long Short-Term Memory (LSTM) networks, which is a state-of-the-art model for sequence processing, to compare the obtained results with our framework and to evaluate their robustness regarding pitfalls in the recognition process. In this study, we analyze the two conceptually different approaches processing continuous, variable-length gesture sequences, which shows interesting results comparing the distinct gesture accomplishments. In addition, our results demonstrate that our ESN framework achieves comparably good performance as the LSTM network but has significantly lower training times. We conclude from the present work that ESNs are viable models for continuous gesture recognition delivering reasonable performance for applications requiring real-time performance as in robotic or rehabilitation tasks. From our discussion of this comparative study, we suggest prospective improvements on both the experimental and network architecture level.<\/jats:p>","DOI":"10.1007\/s12559-020-09754-0","type":"journal-article","created":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T05:03:45Z","timestamp":1602047025000},"page":"1427-1439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Echo State Networks and Long Short-Term Memory for Continuous Gesture Recognition: a Comparative Study"],"prefix":"10.1007","volume":"15","author":[{"given":"Doreen","family":"Jirak","sequence":"first","affiliation":[]},{"given":"Stephan","family":"Tietz","sequence":"additional","affiliation":[]},{"given":"Hassan","family":"Ali","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,7]]},"reference":[{"key":"9754_CR1","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1038\/s42256-019-0110-8","volume":"1","author":"P Antonik","year":"2019","unstructured":"Antonik P, Marsal N, Brunner D, Rontani D. Human action recognition with a large-scale brain-inspired photonic computer. Nat Mach Intell 2019;1:530\u2013537. https:\/\/doi.org\/10.1038\/s42256-019-0110-8.","journal-title":"Nat Mach Intell"},{"key":"9754_CR2","doi-asserted-by":"publisher","first-page":"8487","DOI":"10.1038\/s41598-018-26927-y","volume":"8","author":"A Argyris","year":"2018","unstructured":"Argyris A, Bueno J, Fischer I. Photonic machine learning implementation for signal recovery in optical communications. Scientific Reports 2018;8:8487. https:\/\/doi.org\/10.1038\/s41598-018-26927-y.","journal-title":"Scientific Reports"},{"key":"9754_CR3","doi-asserted-by":"crossref","unstructured":"Bengio Y, Boulanger-Lewandowski N, Pascanu R. Advances in optimizing recurrent networks. IEEE International conference on acoustics, speech and signal processing; 2013. p. 8624\u20138628.","DOI":"10.1109\/ICASSP.2013.6639349"},{"issue":"2","key":"9754_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 1994;5(2):157\u2013166. https:\/\/doi.org\/10.1109\/72.279181.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"9754_CR5","doi-asserted-by":"crossref","unstructured":"Carfi A, Motolese C, Bruno B, Mastrogiovanni F. Online human gesture recognition using recurrent neural networks and wearable sensors. 2018 27Th IEEE international symposium on robot and human interactive communication RO-MAN; 2018. p. 188\u2013195.","DOI":"10.1109\/ROMAN.2018.8525769"},{"issue":"4","key":"9754_CR6","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s12530-013-9080-y","volume":"4","author":"S Dasgupta","year":"2013","unstructured":"Dasgupta S, W\u00f6rg\u00f6tter F., Manoonpong P. Information dynamics based self-adaptive reservoir for delay temporal memory tasks. Evolving Systems 2013;4(4):235\u2013249.","journal-title":"Evolving Systems"},{"key":"9754_CR7","doi-asserted-by":"crossref","unstructured":"Escalera S, Bar\u00f3 X., Gonz\u00e0lez J., Bautista MA, Madadi M, Reyes M, Ponce-L\u00f3pez V., Escalante HJ, Shotton J, Guyon I. Chalearn looking at people challenge 2014: Dataset and results. Computer vision - ECCV 2014 workshops. In: Agapito L., Bronstein M. M., and Rother C., editors. Cham: Springer International Publishing; 2015. p. 459\u2013473.","DOI":"10.1007\/978-3-319-16178-5_32"},{"key":"9754_CR8","unstructured":"Gallicchio C, Micheli A. A reservoir computing approach for human gesture recognition from kinect data. S. Bandini, G. Cortellessa, F. Palumbo (eds.) Proceedings of the Artificial Intelligence for Ambient Assisted Living 2016 co-located with 15th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2016), Genova, Italy, November 28th, 2016, CEUR Workshop Proceedings, vol. 1803, pp. 33\u201342. CEUR-WS.org; 2016."},{"key":"9754_CR9","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.neunet.2018.08.002","volume":"108","author":"C Gallicchio","year":"2018","unstructured":"Gallicchio C, Micheli A, Pedrelli L. Design of deep echo state networks. Neural Netw 2018; 108:33\u201347. https:\/\/doi.org\/10.1016\/j.neunet.2018.08.002.","journal-title":"Neural Netw"},{"issue":"16","key":"9754_CR10","doi-asserted-by":"publisher","first-page":"6425","DOI":"10.1109\/JSEN.2016.2581023","volume":"16","author":"HP Gupta","year":"2016","unstructured":"Gupta HP, Chudgar HS, Mukherjee S, Dutta T, Sharma K. A continuous hand gestures recognition technique for human-machine interaction using accelerometer and gyroscope sensors. IEEE Sensors J 2016;16(16):6425\u20136432. https:\/\/doi.org\/10.1109\/JSEN.2016.2581023.","journal-title":"IEEE Sensors J"},{"key":"9754_CR11","first-page":"11","volume":"19","author":"H Han","year":"2019","unstructured":"Han H, Yoon SW. Gyroscope-based continuous human hand gesture recognition for multi-modal wearable input device for human machine interaction. Sensors 2019;19:11.","journal-title":"Sensors"},{"issue":"2","key":"9754_CR12","doi-asserted-by":"publisher","first-page":"e52946","DOI":"10.1371\/journal.pone.0052946","volume":"8","author":"X Hinaut","year":"2013","unstructured":"Hinaut X, Dominey PF. Real-time parallel processing of grammatical structure in the fronto-striatal system: a recurrent network simulation study using reservoir computing. PloS one 2013;8(2):e52946.","journal-title":"PloS one"},{"key":"9754_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation 1997;9:1735\u201380.","journal-title":"Neural computation"},{"key":"9754_CR14","unstructured":"Jaeger H. 2002. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the\u201d echo state network\u201d approach GMD-Forschungszentrum Informationstechnik."},{"key":"9754_CR15","unstructured":"Jirak D, Barros P, Wermter S. Dynamic gesture recognition using echo state networks. Proceedings of the European Symposium of Artificial Neural Networks and Machine Learning, pp. 475\u2013480; 2015."},{"key":"9754_CR16","unstructured":"Kingma DP, Ba J. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"9754_CR17","unstructured":"Lee MC, Cho SB. Mobile gesture recognition using hierarchical recurrent neural network with bidirectional long short-term memory. Proceedings of UBICOMM; 2012. p. 138\u2013141."},{"key":"9754_CR18","doi-asserted-by":"crossref","unstructured":"Li Y, Wang T, Khan A, Li L, Li C, Yang Y, Liu L. 2018. Hand gesture recognition and real-time game control based on a wearable band with 6-axis sensors.","DOI":"10.1109\/IJCNN.2018.8489743"},{"issue":"6","key":"9754_CR19","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1016\/j.pmcj.2009.07.007","volume":"5","author":"J Liu","year":"2009","unstructured":"Liu J, Zhong L, Wickramasuriya J, Vasudevan V. uwave: Accelerometer-based personalized gesture recognition and its applications. Pervasive and Mobile Computing 2009;5(6):657\u2013675. PerCom 2009.","journal-title":"Pervasive and Mobile Computing"},{"issue":"3","key":"9754_CR20","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","volume":"3","author":"M Luko\u0161evi\u010dius","year":"2009","unstructured":"Luko\u0161evi\u010dius M., Jaeger H. Reservoir computing approaches to recurrent neural network training. Computer Science Review 2009;3(3):127\u2013149. https:\/\/doi.org\/10.1016\/j.cosrev.2009.03.005.","journal-title":"Computer Science Review"},{"issue":"2","key":"9754_CR21","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TNNLS.2016.2514275","volume":"28","author":"J Qiao","year":"2017","unstructured":"Qiao J, Li F, Han H, Li W. Growing echo-state network with multiple subreservoirs. IEEE Trans Neural Netw Learn Syst 2017;28(2):391\u2013404. https:\/\/doi.org\/10.1109\/TNNLS.2016.2514275.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"9754_CR22","doi-asserted-by":"crossref","unstructured":"Sosin I, Kudenko D, Shpilman A. Continuous gesture recognition from semg sensor data with recurrent neural networks and adversarial domain adaptation. 2018 15Th international conference on control, automation, robotics and vision (ICARCV); 2018. p. 1436\u20131441.","DOI":"10.1109\/ICARCV.2018.8581206"},{"key":"9754_CR23","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2019.03.005","volume":"115","author":"G Tanaka","year":"2019","unstructured":"Tanaka G, Yamane T, H\u00e9roux JB, Nakane R, Kanazawa N, Takeda S, Numata H, Nakano D, Hirose A. Recent advances in physical reservoir computing: A review. Neural Networks 2019; 115:100\u2013123.","journal-title":"Neural Networks"},{"key":"9754_CR24","doi-asserted-by":"crossref","unstructured":"Tietz S, Jirak D, Wermter S. A reservoir computing framework for continuous gesture recognition. Tetko, I. V., V. ku\u0307rkov\u00e1, P. Karpov, F. Theis. Artificial neural networks and machine learning \u2013 ICANN 2019: workshop and special sessions, pp. 7\u201318 Springer International Publishing Cham; 2019.","DOI":"10.1007\/978-3-030-30493-5_1"},{"key":"9754_CR25","unstructured":"Triefenbach F, Jalalvand A, Schrauwen B, Pierre Martens J. Phoneme recognition with large hierarchical reservoirs. J.D. Lafferty, C.K.I. Williams, J. Shawe-Taylor, R.S. Zemel, A. Culotta (eds.) Advances in Neural Information Processing Systems 23, pp. 2307\u20132315. Curran Associates, Inc. http:\/\/papers.nips.cc\/paper\/4056-phoneme-recognition-with-large-hierarchical-reservoirs.pdf; 2010."},{"issue":"3","key":"9754_CR26","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.neunet.2007.04.003","volume":"20","author":"D Verstraeten","year":"2007","unstructured":"Verstraeten D, Schrauwen B, D\u2019Haene M, Stroobandt D. An experimental unification of reservoir computing methods. Neural Networks 2007;20(3):391\u2013403. Echo State Networks and Liquid State Machines.","journal-title":"Neural Networks"},{"key":"9754_CR27","doi-asserted-by":"publisher","unstructured":"Wang Y, Ma H. Real-time continuous gesture recognition with wireless wearable imu sensors. 2018 IEEE 20Th international conference on e-health networking, applications and services (healthcom); 2018. p. 1\u20136. https:\/\/doi.org\/10.1109\/HealthCom.2018.8531095.","DOI":"10.1109\/HealthCom.2018.8531095"},{"key":"9754_CR28","doi-asserted-by":"crossref","unstructured":"Wyffels F, Schrauwen B. Design of a central pattern generator using reservoir computing for learning human motion. 2009 Advanced technologies for enhanced quality of life, pp. 118\u2013122; 2009.","DOI":"10.1109\/AT-EQUAL.2009.32"},{"key":"9754_CR29","doi-asserted-by":"crossref","unstructured":"Yang J, Pan J. Li, j.: semg-based continuous hand gesture recognition using gmm-hmm and threshold model. 2017 IEEE International conference on robotics and biomimetics (ROBIO), pp. 1509\u20131514; 2017.","DOI":"10.1109\/ROBIO.2017.8324631"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-020-09754-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-020-09754-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-020-09754-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T02:23:20Z","timestamp":1695608600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-020-09754-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,7]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["9754"],"URL":"https:\/\/doi.org\/10.1007\/s12559-020-09754-0","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,7]]},"assertion":[{"value":"20 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}