{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T09:38:00Z","timestamp":1780738680540,"version":"3.54.1"},"reference-count":42,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2017,6,7]],"date-time":"2017-06-07T00:00:00Z","timestamp":1496793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The design of multiple human activity recognition applications in areas such as healthcare, sports and safety relies on wearable sensor technologies. However, when making decisions based on the data acquired by such sensors in practical situations, several factors related to sensor data alignment, data losses, and noise, among other experimental constraints, deteriorate data quality and model accuracy. To tackle these issues, this paper presents a data-driven iterative learning framework to classify human locomotion activities such as walk, stand, lie, and sit, extracted from the Opportunity dataset. Data acquired by twelve 3-axial acceleration sensors and seven inertial measurement units are initially de-noised using a two-stage consecutive filtering approach combining a band-pass Finite Impulse Response (FIR) and a wavelet filter. A series of statistical parameters are extracted from the kinematical features, including the principal components and singular value decomposition of roll, pitch, yaw and the norm of the axial components. The novel interactive learning procedure is then applied in order to minimize the number of samples required to classify human locomotion activities. Only those samples that are most distant from the centroids of data clusters, according to a measure presented in the paper, are selected as candidates for the training dataset. The newly built dataset is then used to train an SVM multi-class classifier. The latter will produce the lowest prediction error. The proposed learning framework ensures a high level of robustness to variations in the quality of input data, while only using a much lower number of training samples and therefore a much shorter training time, which is an important consideration given the large size of the dataset.<\/jats:p>","DOI":"10.3390\/s17061287","type":"journal-article","created":{"date-parts":[[2017,6,7]],"date-time":"2017-06-07T10:01:20Z","timestamp":1496829680000},"page":"1287","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Wearable Sensor Data Classification for Human Activity Recognition Based on an Iterative Learning Framework"],"prefix":"10.3390","volume":"17","author":[{"given":"Juan","family":"Davila","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Universit\u00e9 du Qu\u00e9bec en Outaouais, Gatineau, QC J8Y 3G5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana-Maria","family":"Cretu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Universit\u00e9 du Qu\u00e9bec en Outaouais, Gatineau, QC J8Y 3G5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Zaremba","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Universit\u00e9 du Qu\u00e9bec en Outaouais, Gatineau, QC J8Y 3G5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2017,6,7]]},"reference":[{"key":"ref_1","unstructured":"Davila, J., Cretu, A.-M., and Zaremba, M. (2016, January 15\u201330). Iterative Learning for Human Activity Recognition from Wearable Sensor Data. Proceedings of the 3rd International Electronic Conference on Sensors and Applications, Barcelona, Spain."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/1743-0003-9-21","article-title":"A review of wearable sensors and systems with application in rehabilitation","volume":"9","author":"Patel","year":"2012","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1016\/j.patrec.2012.12.014","article-title":"The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition","volume":"34","author":"Chavarriaga","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","article-title":"Multisensor Data Fusion: A Review of the State-Of-The-Art","volume":"14","author":"Khaleghi","year":"2013","journal-title":"Inf. Fusion"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.patrec.2009.09.019","article-title":"Recognition of human activities using SVM multi-class classifier","volume":"31","author":"Qian","year":"2010","journal-title":"Pattern Recognit. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1109\/TBCAS.2011.2160540","article-title":"Sensor Positioning for Activity Recognition Using Wearable Accelerometers","volume":"5","author":"Atallah","year":"2011","journal-title":"IEEE Trans. Biomed. Circ. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sugiyama, M., and Kawanabe, M. (2012). Introduction and Problem Formulation. Machine Learning in Non-Stationary Environments, The MIT Press.","DOI":"10.7551\/mitpress\/9780262017091.001.0001"},{"key":"ref_8","unstructured":"Mohri, M., Rostamizadeh, A., and Talwalkar, A. (2012). Introduction and the PAC Learning Framework. Foundation of Machine Learning, The MIT Press."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s10994-011-5238-7","article-title":"Iterative learning from texts and counterexamples using additional information","volume":"84","author":"Jain","year":"2011","journal-title":"J. Mach. Learn."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1109\/THMS.2016.2545243","article-title":"Iterative Learning From Novice Human Demonstration for Output Tracking","volume":"46","author":"Warrier","year":"2016","journal-title":"IEEE Trans. Hum. Mach. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Watanabe, O., and Yokomori, T. (1999). On the Strength of Incremental Learning. Algorithmic Learning Theory; Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence), Springer.","DOI":"10.1007\/3-540-46769-6"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fern, A., and Yoon, S. (2010, January 12\u201316). Iterative Learning of Weighted Rule Sets for Greedy Search. Proceeding of the 20th International Conference on Automated Planning and Scheduling, Toronto, ON, Canada.","DOI":"10.1609\/icaps.v20i1.13416"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7299","DOI":"10.1109\/TGRS.2016.2599101","article-title":"An Iterative Learning Framework for Multimodal Chlorophyll-a Estimation","volume":"54","author":"Davila","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","first-page":"771","article-title":"A shore Introduction to Boosting","volume":"14","author":"Freund","year":"1999","journal-title":"J. Jpn. Soc. Artif. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","article-title":"A survey on human activity recognition using wearable sensors","volume":"15","author":"Lara","year":"2013","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_16","unstructured":"Munguia Tapia, E. (2008). Using Machine Learning for Real-Time Activity Recognition and Estimation of Energy Expenditure. [Ph.D. Thesis, School of Architecture and Planning, Massachusetts Institute of Technology]."},{"key":"ref_17","first-page":"50","article-title":"Applications and Challenges of Human Activity Recognition using Sensors in a Smart Environment","volume":"2","author":"Sunny","year":"2015","journal-title":"IJIRST Int. J. Innov. Res. Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, W.-Z., Guo, Y.-W., and Huang, B.-Y. (2011, January 3\u20135). Analysis of filtering methods for 3-axial acceleration signals in body sensor network. Proceedings of the International Symposium on Bioelectronics and Bio-Information, Suzhou, China.","DOI":"10.1109\/ISBB.2011.6107697"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5406","DOI":"10.3390\/s130505406","article-title":"A Survey of Body Sensor Networks","volume":"13","author":"Lai","year":"2013","journal-title":"Sensors"},{"key":"ref_20","unstructured":"(2016, October 10). Activity Recognition Challenge. Available online: http:\/\/opportunity-project.eu\/challenge."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/MRA.2011.940992","article-title":"Wearable Computing: Designing and Sharing Activity-Recognition Systems across Platforms","volume":"18","author":"Roggen","year":"2011","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1007\/s00779-011-0493-y","article-title":"Unsupervised adaptation for acceleration-based activity recognition: Robustness to sensor displacement and rotation","volume":"17","author":"Chavarriaga","year":"2013","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gjoreski, M., Gjoreski, H., Lu\u0161trek, M., and Gams, M. (2016). How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls?. Sensors, 16.","DOI":"10.3390\/s16060800"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/2345770.2345781","article-title":"Network-level power-performance trade-off in wearable activity recognition: A dynamic sensor selection approach","volume":"11","author":"Zappi","year":"2012","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"ref_25","unstructured":"(2017, June 01). Consortium Publications. Available online: http:\/\/www.opportunity-project.eu\/publications."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Roggen, D., B\u00e4chlin, M., and Schumm, J. (2010, January 7\u20139). An educational and research kit for activity and context recognition from on-body sensors. Proceedings of the International Conference on Body Sensor Networks, Singapore.","DOI":"10.1109\/BSN.2010.35"},{"key":"ref_27","unstructured":"Taylor, F. (2012). Finite Impulse Response Filter in Digital Filters: Principles and Applications with MATLAB. E-Book, Wiley-IEEE Press."},{"key":"ref_28","unstructured":"(2017, March 30). Basics of Instrumentation, Measurement and Analysis, Design of FIR Filters. Available online: http:\/\/www.vyssotski.ch\/basicsofinstrumentation.html."},{"key":"ref_29","unstructured":"(2017, March 30). Signals and Systems I, EECS 206 Laboratory, University of Michigan. Available online: http:\/\/www.eecs.umich.edu\/courses\/eecs206."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1016\/j.medengphy.2008.09.005","article-title":"Direct measurement of human movement by accelerometry","volume":"30","author":"Godfrey","year":"2008","journal-title":"Med. Eng. Phys."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s00779-010-0293-9","article-title":"Preprocessing techniques for context recognition from accelerometer data","volume":"14","author":"Figo","year":"2010","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Levinzon, F. (2015). Fundamental Noise Limit of an IEPE Accelerometer from Piezoelectric Accelerometers with Integral Electronics, Springer.","DOI":"10.1007\/978-3-319-08078-9"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Misiti, M., Misiti, Y., Oppenheim, G., and Poggi, J.-M. (2007). Guided Tour from Wavelet and Their Applications, Wiley.","DOI":"10.1002\/9780470612491"},{"key":"ref_34","first-page":"2047","article-title":"Performance Analysis of Wavelet Thresholding Methods in Denoising of Audio Signals of Some Indian Musical Instruments","volume":"4","author":"Verma","year":"2012","journal-title":"Int. J. Eng. Sci. Technol."},{"key":"ref_35","unstructured":"Vidakovic, B., and Mueller, P. (1991). Wavelet for Kids, a Tutorial Introduction, Duke University."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Al-Qazzaz, N.K., Ali, S., Ahmad, S.A., Islam, M.S., and Ariff, M.I. (2014, January 8\u201310). Selection of Mother Wavelets Thresholding Methods in De-noising Multi-channel EEG Signals during Working Memory Task. Proceedings of the IEEE Conference on Biomedical Engineering and Science, Miri, Sarawak, Malaysia.","DOI":"10.1109\/IECBES.2014.7047488"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5197","DOI":"10.1016\/j.eswa.2010.10.041","article-title":"Feature selection and parameter optimization for support vector machines: A new approach based on genetic algorithm with feature chromosomes","volume":"38","author":"Zhao","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"ref_38","first-page":"79","article-title":"Handling Missing Values in Exploratory Multivariate Data Analysis Methods","volume":"153","author":"Josse","year":"2012","journal-title":"J. Soc. Fr. Stat."},{"key":"ref_39","first-page":"31","article-title":"Methods for Large scale SVD with Missing Values","volume":"12","author":"Kurucz","year":"2007","journal-title":"Comput. Autom. Res. Inst. Hung. Acad. Sci."},{"key":"ref_40","unstructured":"Chang, C.-C., and Lin, C.-J. (2016, October 10). LIBSVM\u2014A Library for Support Vector Machines. Available online: http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm\/."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.asoc.2015.09.006","article-title":"Evolutionary wrapper approaches for training set selection as preprocessing mechanism for support vector machines: Experimental evaluation and support vector analysis","volume":"38","author":"Verbiest","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sokolova, M., Japkowicz, N., and Szpakowicz, S. (2006, January 4\u20138). Beyond Accuracy, F-score and ROC: A Family of Discriminant Measures for Performance Evaluation. Proceedings of the AI 2006: Advances in Artificial Intelligence, Hobart, Australia.","DOI":"10.1007\/11941439_114"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/6\/1287\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:38:13Z","timestamp":1760207893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/6\/1287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,7]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2017,6]]}},"alternative-id":["s17061287"],"URL":"https:\/\/doi.org\/10.3390\/s17061287","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6,7]]}}}