{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T09:34:13Z","timestamp":1775727253214,"version":"3.50.1"},"reference-count":62,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T00:00:00Z","timestamp":1582329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["12\/RC\/2289-P2"],"award-info":[{"award-number":["12\/RC\/2289-P2"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001588","name":"Enterprise Ireland","doi-asserted-by":"publisher","award":["IR20140024"],"award-info":[{"award-number":["IR20140024"]}],"id":[{"id":"10.13039\/501100001588","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human activity recognition (HAR) has become an increasingly popular application of machine learning across a range of domains. Typically the HAR task that a machine learning algorithm is trained for requires separating multiple activities such as walking, running, sitting, and falling from each other. Despite a large body of work on multi-class HAR, and the well-known fact that the performance on a multi-class problem can be significantly affected by how it is decomposed into a set of binary problems, there has been little research into how the choice of multi-class decomposition method affects the performance of HAR systems. This paper presents the first empirical comparison of multi-class decomposition methods in a HAR context by estimating the performance of five machine learning algorithms when used in their multi-class formulation, with four popular multi-class decomposition methods, five expert hierarchies\u2014nested dichotomies constructed from domain knowledge\u2014or an ensemble of expert hierarchies on a 17-class HAR data-set which consists of features extracted from tri-axial accelerometer and gyroscope signals. We further compare performance on two binary classification problems, each based on the topmost dichotomy of an expert hierarchy. The results show that expert hierarchies can indeed compete with one-vs-all, both on the original multi-class problem and on a more general binary classification problem, such as that induced by an expert hierarchy\u2019s topmost dichotomy. Finally, we show that an ensemble of expert hierarchies performs better than one-vs-all and comparably to one-vs-one, despite being of lower time and space complexity, on the multi-class problem, and outperforms all other multi-class decomposition methods on the two dichotomous problems.<\/jats:p>","DOI":"10.3390\/s20041208","type":"journal-article","created":{"date-parts":[[2020,2,24]],"date-time":"2020-02-24T03:33:43Z","timestamp":1582515223000},"page":"1208","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Using Domain Knowledge for Interpretable and Competitive Multi-Class Human Activity Recognition"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2163-2168","authenticated-orcid":false,"given":"Sebastian","family":"Scheurer","sequence":"first","affiliation":[{"name":"Insight Centre for Data Analytics, School of Computer Science and Information Technology, University College Cork, T12 XF62 Cork, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7752-2240","authenticated-orcid":false,"given":"Salvatore","family":"Tedesco","sequence":"additional","affiliation":[{"name":"Tyndall National Institute, University College Cork, T12 R5CP Cork, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1853-0723","authenticated-orcid":false,"given":"Kenneth N.","family":"Brown","sequence":"additional","affiliation":[{"name":"Insight Centre for Data Analytics, School of Computer Science and Information Technology, University College Cork, T12 XF62 Cork, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5522-2597","authenticated-orcid":false,"given":"Brendan","family":"O\u2019Flynn","sequence":"additional","affiliation":[{"name":"Insight Centre for Data Analytics, School of Computer Science and Information Technology, University College Cork, T12 XF62 Cork, Ireland"},{"name":"Tyndall National Institute, University College Cork, T12 R5CP Cork, Ireland"},{"name":"CONNECT Centre for Future Networks and Communications, Tyndall National Institute, University College Cork, T12 R5CP Cork, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Karantonis, D.M., Narayanan, M.R., Mathie, M., Lovell, N.H., and Celler, B.G. (2006). Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. Trans. Inf. Technol. Biomed., 10.","DOI":"10.1109\/TITB.2005.856864"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Valero, E., Sivanathan, A., Bosch\u00e9, F., and Abdel-Wahab, M. (2016). Musculoskeletal disorders in construction. Appl. Ergon., 54.","DOI":"10.1016\/j.apergo.2015.11.020"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Peng, Y., Zhang, T., Sun, L., and Chen, J. (2015, January 23\u201325). A novel data mining method on falling detection and daily activities recognition. Proceedings of the IEEE International Conference on Tools with Artificial Intelligence, Ferrara, Italy.","DOI":"10.1109\/ICTAI.2015.102"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lara, O.D., and Labrador, M.A. (2013). A Survey on Human Activity Recognition using Wearable Sensors. Commun. Surv. Tutor., 15.","DOI":"10.1201\/b16098"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Bulling, A., Blanke, U., and Schiele, B. (2014). A Tutorial on Human Activity Recognition Using Body-worn Inertial Sensors. ACM Comput. Surv., 46.","DOI":"10.1145\/2499621"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"P\u00e4rkk\u00e4, J., Ermes, M., Korpip\u00e4\u00e4, P., M\u00e4ntyj\u00e4rvi, J., Peltola, J., and Korhonen, I. (2006). Activity classification using realistic data from wearable sensors. Trans. Inf. Technol. Biomed., 10.","DOI":"10.1109\/TITB.2005.856863"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Galar, M., Fern\u00e1ndez, A., Barrenechea, E., Bustince, H., and Herrera, F. (2011). An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes. Pattern Recognit., 44.","DOI":"10.1016\/j.patcog.2011.01.017"},{"key":"ref_8","unstructured":"Park, S.H. (2012). Efficient Decomposition-Based Multiclass and Multilabel Classification. [Master\u2019s Thesis, Technische Universit\u00e4t Darmstadt]."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Mathie, M.J., Celler, B.G., Lovell, N.H., and Coster, A.C.F. (2004). Classification of basic daily movements using a triaxial accelerometer. Med. Biol. Eng. Comput., 42.","DOI":"10.1007\/BF02347551"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Blanke, U., and Schiele, B. (2009, January 7\u20138). Daily Routine Recognition through Activity Spotting. Proceedings of the International Symposium on Location- and Context-Awareness, Tokyo, Japan.","DOI":"10.1007\/978-3-642-01721-6_12"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Fortino, G., and Gravina, R. (2015, January 28\u201330). Fall-MobileGuard: A Smart Real-Time Fall Detection System. Proceedings of the International Conference on Body Area Networks, Sydney, Australia.","DOI":"10.4108\/eai.28-9-2015.2261462"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The WEKA Data Mining Software: An Update","volume":"11","author":"Hall","year":"2009","journal-title":"SIGKDD Explor."},{"key":"ref_13","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_14","unstructured":"Friedman, J.H. (1996). Another Approach to Polychotomous Classification, Stanford University. Technical Report."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hastie, T., and Tibshirani, R. (1998). Classification by pairwise coupling. Ann. Stat., 26.","DOI":"10.1214\/aos\/1028144844"},{"key":"ref_16","unstructured":"Bouckaert, R.R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., and Scuse, D. (2016). WEKA Manual, WEKA."},{"key":"ref_17","unstructured":"Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., and Grobler, J. (2013, January 23\u201327). API design for machine learning software. Proceedings of the ECML PKDD Workshop: Languages for Data Mining and Machine Learning, Prague, Czech Republic."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G., and Bakiri, G. (1995). Solving multiclass learning problems via error-correcting output codes. J. Artif. Intell. Res., 2.","DOI":"10.1613\/jair.105"},{"key":"ref_19","first-page":"113","article-title":"Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers","volume":"1","author":"Allwein","year":"2000","journal-title":"J. Mach. Learn. Res."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pujol, O., Radeva, P., and Vitri\u00e0, J. (2006). Discriminant ECOC: A heuristic method for application dependent design of error correcting output codes. Trans. Pattern Anal. Mach. Intell.","DOI":"10.1109\/TPAMI.2006.116"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bautista, M.\u00c1., Escalera, S., Bar\u00f3, X., Radeva, P., Vitri\u00e0, J., and Pujol, O. (2012). Minimal design of error-correcting output codes. Pattern Recognit. Lett., 33.","DOI":"10.1016\/j.patrec.2011.09.023"},{"key":"ref_22","unstructured":"Fox, J. (1997). Applied Regression Analysis, Linear Models, and Related Methods, Sage."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Bergeron, F., Labelle, G., and Leroux, P. (1998). Combinatorial Species and Tree-Like Structures, Cambridge University Press.","DOI":"10.1017\/CBO9781107325913"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Frank, E., and Kramer, S. (2004, January 26\u201329). Ensembles of Nested Dichotomies for Multi-class Problems. Proceedings of the International Conference on Machine Learning, Shanghai, China.","DOI":"10.1145\/1015330.1015363"},{"key":"ref_25","unstructured":"Dong, L., Frank, E., and Kramer, S. (2004, January 20\u201324). Ensembles of Balanced Nested Dichotomies for Multi-class Problems. Proceedings of the European Conference on Principles and Practice of Knowledge Discovery in Databases, Pisa, Italy."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, J.J., Garc\u00eda-Osorio, C., and Maudes, J. (2010). Forests of nested dichotomies. Pattern Recognit. Lett., 31.","DOI":"10.1016\/j.patrec.2009.09.015"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, Y., Hao, S., Peng, X., and Hu, L. (2019). Deep learning for sensor-based activity recognition: A survey. Pattern Recognit. Lett., 119.","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"ref_28","unstructured":"Jiang, W., and Yin, Z. (July, January 29). Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks. Proceedings of the International Conference on Multimedia, Torino, Italy."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wu, X., and Luo, D. (2015, January 9\u201311). Recognizing Human Activities from Raw Accelerometer Data Using Deep Neural Networks. Proceedings of the IEEE International Conference on Machine Learning and Applications, Miami, FL, USA.","DOI":"10.1109\/ICMLA.2015.48"},{"key":"ref_30","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_31","unstructured":"Hammerla, N.Y., Halloran, S., and Pl\u00f6tz, T. (2016, January 9\u201316). Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), New York, NY, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S.T., Tr\u00f6ster, G., Mill\u00e1n, J.d.R., and Roggen, D. (2013). The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recognit. Lett., 34.","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"ref_33","unstructured":"Pl\u00f6tz, T., Hammerla, N.Y., and Olivier, P. (2011, January 16\u201322). Feature Learning for Activity Recognition in Ubiquitous Computing. Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI\/AAAI, IJCAI, Catalonia, Spain."},{"key":"ref_34","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra-Perez, X., and Reyes-Ortiz, J.L. (2013, January 24\u201326). A public domain dataset for human activity recognition using smartphones. Proceedings of the International European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"10146","DOI":"10.3390\/s140610146","article-title":"Fusion of Smartphone Motion Sensors for Physical Activity Recognition","volume":"14","author":"Shoaib","year":"2014","journal-title":"Sensors"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, M., and Sawchuk, A.A. (2012, January 5\u20138). USC-HAD: A Daily Activity Dataset for Ubiquitous Activity Recognition Using Wearable Sensors. Proceedings of the Conference on Ubiquitous Computing, UbiComp, Pittsburgh, PA, USA.","DOI":"10.1145\/2370216.2370438"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3605","DOI":"10.1016\/j.patcog.2010.04.019","article-title":"Comparative study on classifying human activities with miniature inertial and magnetic sensors","volume":"43","author":"Altun","year":"2010","journal-title":"Pattern Recognit."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Reiss, A., and Stricker, D. (2012, January 11\u201315). Introducing a New Benchmarked Dataset for Activity Monitoring. Proceedings of the IEEE International Symposium on Wearable Computers, ISWC, Boston, MA, USA.","DOI":"10.1109\/ISWC.2012.13"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bachlin, M., Roggen, D., Troster, G., Plotnik, M., Inbar, N., Meidan, I., Herman, T., Brozgol, M., Shaviv, E., and Giladi, N. (2009, January 4\u20137). Potentials of Enhanced Context Awareness in Wearable Assistants for Parkinson\u2019s Disease Patients with the Freezing of Gait Syndrome. Proceedings of the International Symposium on Wearable Computers, Linz, Austria.","DOI":"10.1109\/ISWC.2009.14"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Scheurer, S., Tedesco, S., Brown, K.N., and O\u2019Flynn, B. (2019, January 16\u201317). Subject-Dependent and -Independent Human Activity Recognition with Person-Specific and -Independent Models. Proceedings of the International Workshop on Sensor-based Activity Recognition and Interaction, iWOAR, Rostock, Germany.","DOI":"10.1145\/3361684.3361689"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Joseph, S.J., Robbins, K.R., Zhang, W., and Rekaya, R. (2010). Comparison of Two Output-Coding Strategies for Multi-Class Tumor Classification Using Gene Expression Data and Latent Variable Model as Binary Classifier. Cancer Inf., 9.","DOI":"10.4137\/CIN.S3827"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yeang, C.H., Ramaswamy, S., Tamayo, P., Mukherjee, S., Rifkin, R.M., Angelo, M., Reich, M., Lander, E., Mesirov, J., and Golub, T. (2001). Molecular classification of multiple tumor types. Bioinformatics, 17.","DOI":"10.1093\/bioinformatics\/17.suppl_1.S316"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/415436a","article-title":"Prediction of central nervous system embryonal tumour outcome based on gene expression","volume":"415","author":"Pomeroy","year":"2002","journal-title":"Nature"},{"key":"ref_44","unstructured":"Prieditis, A., and Russell, S. (1995). Fast Effective Rule Induction. Machine Learning Proceedings, Morgan Kaufmann."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Chen, Y., and Wang, J.Z. (2003). Support vector learning for fuzzy rule-based classification systems. Trans. Fuzzy Syst., 11.","DOI":"10.1109\/TFUZZ.2003.819843"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Raziff, A.R.A., Sulaiman, M.N., Mustapha, N., and Perumal, T. (2017, January 8\u201310). Single classifier, OvO, OvA and RCC multiclass classification method in handheld based smartphone gait identification. Proceedings of the International Conference on Applied Science and Technology, ICAST, Orlando, FL, USA.","DOI":"10.1063\/1.5005342"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zimek, A., Buchwald, F., Frank, E., and Kramer, S. (2010). A Study of Hierarchical and Flat Classification of Proteins. Trans. Comput. Biol. Bioinform., 7.","DOI":"10.1109\/TCBB.2008.104"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10618-010-0175-9","article-title":"A survey of hierarchical classification across different application domains","volume":"22","author":"Silla","year":"2011","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.jocs.2018.01.006","article-title":"Probabilistic class hierarchies for multiclass classification","volume":"26","author":"Ferri","year":"2018","journal-title":"J. Comput. Sci."},{"key":"ref_50","unstructured":"Dua, D., and Graff, C. (2017). UCI Machine Learning Repository, University of California."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Brahmi, I.H., Abbruzzo, G., Walsh, M., Sedjelmaci, H., and O\u2019Flynn, B. (2018, January 3\u20135). A fuzzy logic approach for improving the tracking accuracy in indoor localisation applications. Proceedings of the Wireless Days, Dubai, UAE.","DOI":"10.1109\/WD.2018.8361709"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Khodjaev, J., Tedesco, S., and O\u2019Flynn, B. (2016). Improved NLOS Error Mitigation Based on LTS Algorithm. Prog. Electromagn. Res. Lett., 58.","DOI":"10.2528\/PIERL15100103"},{"key":"ref_53","unstructured":"Tedesco, S., Khodjaev, J., and O\u2019Flynn, B. (December, January 30). A novel first responders location tracking system: Architecture and functional requirements. Proceedings of the IEEE Mediterranean Microwave Symposium, Lecce, Italy."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Scheurer, S., Tedesco, S., Brown, K.N., and O\u2019Flynn, B. (November, January 29). Sensor and feature selection for an emergency first responders activity recognition system. Proceedings of the 2017 IEEE Sensors, Glasgow, UK.","DOI":"10.1109\/ICSENS.2017.8234090"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Scheurer, S., Tedesco, S., Brown, K.N., and O\u2019Flynn, B. (2017, January 9\u201312). Human Activity Recognition for Emergency First Responders via Body-Worn Inertial Sensors. Proceedings of the IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN, Eindhoven, The Netherlands.","DOI":"10.1109\/BSN.2017.7935994"},{"key":"ref_56","unstructured":"Weston, J., and Watkins, C. (1998). Multi-class Support Vector Machines, Royal Holloway University of London. Technical Report."},{"key":"ref_57","first-page":"265","article-title":"On the Algorithmic Implementation of Multiclass Kernel-Based Vector Machines","volume":"2","author":"Crammer","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10994-009-5108-8","article-title":"Cutting-Plane Training of Structural SVMs","volume":"77","author":"Joachims","year":"2009","journal-title":"Mach. Learn."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/72.991427","article-title":"A comparison of methods for multiclass support vector machines","volume":"13","author":"Hsu","year":"2002","journal-title":"Trans. Neural Netw."},{"key":"ref_60","unstructured":"Platt, J.C. (1999). Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Advances in Large Margin Classifiers, MIT Press."},{"key":"ref_61","unstructured":"Tange, O. (2011). GNU Parallel\u2014The Command-Line Power Tool. USENIX Mag., 36."},{"key":"ref_62","unstructured":"R Core Team (2019). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/4\/1208\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:00:01Z","timestamp":1760173201000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/4\/1208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,22]]},"references-count":62,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["s20041208"],"URL":"https:\/\/doi.org\/10.3390\/s20041208","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,22]]}}}