{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:51:06Z","timestamp":1776365466546,"version":"3.51.2"},"reference-count":51,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2018,6,6]],"date-time":"2018-06-06T00:00:00Z","timestamp":1528243200000},"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":["61571336 and 61502360"],"award-info":[{"award-number":["61571336 and 61502360"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Mobile activity recognition is significant to the development of human-centric pervasive applications including elderly care, personalized recommendations, etc. Nevertheless, the distribution of inertial sensor data can be influenced to a great extent by varying users. This means that the performance of an activity recognition classifier trained by one user\u2019s dataset will degenerate when transferred to others. In this study, we focus on building a personalized classifier to detect four categories of human activities: light intensity activity, moderate intensity activity, vigorous intensity activity, and fall. In order to solve the problem caused by different distributions of inertial sensor signals, a user-adaptive algorithm based on K-Means clustering, local outlier factor (LOF), and multivariate Gaussian distribution (MGD) is proposed. To automatically cluster and annotate a specific user\u2019s activity data, an improved K-Means algorithm with a novel initialization method is designed. By quantifying the samples\u2019 informative degree in a labeled individual dataset, the most profitable samples can be selected for activity recognition model adaption. Through experiments, we conclude that our proposed models can adapt to new users with good recognition performance.<\/jats:p>","DOI":"10.3390\/s18061850","type":"journal-article","created":{"date-parts":[[2018,6,6]],"date-time":"2018-06-06T07:38:15Z","timestamp":1528270695000},"page":"1850","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["A User-Adaptive Algorithm for Activity Recognition Based on K-Means Clustering, Local Outlier Factor, and Multivariate Gaussian Distribution"],"prefix":"10.3390","volume":"18","author":[{"given":"Shizhen","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Logistics Engineering, Wuhan University of Technology, Wuhan 430070, China"}]},{"given":"Wenfeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Logistics Engineering, Wuhan University of Technology, Wuhan 430070, China"}]},{"given":"Jingjing","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Logistics Engineering, Wuhan University of Technology, Wuhan 430070, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,6,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Davila, J.C., Cretu, A.M., and Zaremba, M. (2017). Wearable Sensor Data Classification for Human Activity Recognition Based on an Iterative Learning Framework. Sensors, 17.","DOI":"10.3390\/s17061287"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Crispim-Junior, C.F., G\u00f3mez Ur\u00eda, A., Strumia, C., Koperski, M., K\u00f6nig, A., Negin, F., Cosar, S., Nghiem, A.T., Chau, D.P., and Charpiat, G. (2017). Online Recognition of Daily Activities by Color-Depth Sensing and Knowledge Models. Sensors, 17.","DOI":"10.3390\/s17071528"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Janidarmian, M., Roshan Fekr, A., Radecka, K., and Zilic, Z. (2017). A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition. Sensors, 17.","DOI":"10.3390\/s17030529"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/TPAMI.2016.2565479","article-title":"Super normal vector for human activity recognition with depth cameras","volume":"39","author":"Yang","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Li, W., Wong, Y., Liu, A.A., Li, Y., Su, Y.T., and Kankanhalli, M. (2017, January 24\u201331). Multi-camera action dataset for cross-camera action recognition benchmarking. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.","DOI":"10.1109\/WACV.2017.28"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4405","DOI":"10.1007\/s11042-015-3177-1","article-title":"A survey of depth and inertial sensor fusion for human action recognition","volume":"76","author":"Chen","year":"2017","journal-title":"Multimedia Tools Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.dcan.2015.02.006","article-title":"A review on radio based activity recognition","volume":"1","author":"Wang","year":"2015","journal-title":"Digital Commun. Netw."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Medrano, C., Plaza, I., Igual, R., S\u00e1nchez, \u00c1., and Castro, M. (2016). The effect of personalization on smartphone-based fall detectors. Sensors, 16.","DOI":"10.3390\/s16010117"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chen, Y., and Xue, Y. (2015, January 9\u201312). A deep learning approach to human activity recognition based on single accelerometer. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Kowloon, China.","DOI":"10.1109\/SMC.2015.263"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1088\/0967-3334\/30\/4\/R01","article-title":"Activity identification using body-mounted sensors\u2014A review of classification techniques","volume":"30","author":"Preece","year":"2009","journal-title":"Physiol. Meas."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Safi, K., Attal, F., Mohammed, S., Khalil, M., and Amirat, Y. (2015, January 16\u201318). Physical activity recognition using inertial wearable sensors\u2014A review of supervised classification algorithms. Proceedings of the International Conference on Advances in Biomedical Engineering (ICABME), Beirut, Lebanon.","DOI":"10.1109\/ICABME.2015.7323315"},{"key":"ref_12","unstructured":"Weiss, G.M., and Lockhart, J.W. (2012). The Impact of Personalization on Smartphone-Based Activity Recognition, American Association for Artificial Intelligence."},{"key":"ref_13","first-page":"1","article-title":"Activity recognition from user-annotated acceleration data","volume":"3001","author":"Ling","year":"2004","journal-title":"Proc. Pervasive"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Saez, Y., Baldominos, A., and Isasi, P. (2017). A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition. Sensors, 17.","DOI":"10.3390\/s17010066"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Okeyo, G.O., Chen, L., Wang, H., and Sterritt, R. (2011, January 18). Time handling for real-time progressive activity recognition. Proceedings of the 2011 International Workshop on Situation Activity & Goal Awareness, Beijing, China.","DOI":"10.1145\/2030045.2030056"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1109\/TITB.2010.2055060","article-title":"Personalization algorithm for real-time activity recognition using PDA, wireless motion bands, and binary decision tree","volume":"14","author":"Cluitmans","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, C.T., and Chan, C.T. (2016). A Fuzzy Logic Prompting Mechanism Based on Pattern Recognition and Accumulated Activity Effective Index Using a Smartphone Embedded Sensor. Sensors, 16.","DOI":"10.3390\/s16081322"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1109\/TBME.2011.2178070","article-title":"Multisensor data fusion for physical activity assessment","volume":"59","author":"Liu","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"11305","DOI":"10.1007\/s11042-016-3444-9","article-title":"Multi-level assessment model for wellness service based on human mental stress level","volume":"76","author":"Jung","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_20","unstructured":"Fahim, M., Khattak, A.M., Chow, F., and Shah, B. (February, January 31). Tracking the sedentary lifestyle using smartphone: A pilot study. Proceedings of the International Conference on Advanced Communication Technology, Pyeongchang, Korea."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ma, C., Li, W., Gravina, R., Cao, J., Li, Q., and Fortino, G. (2017). Activity level assessment using a smart cushion for people with a sedentary lifestyle. Sensors, 17.","DOI":"10.3390\/s17102269"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1109\/JSEN.2013.2245231","article-title":"Hmm-based human fall detection and prediction method using tri-axial accelerometer","volume":"13","author":"Tong","year":"2013","journal-title":"IEEE Sens. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.medengphy.2006.12.001","article-title":"A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor","volume":"30","author":"Bourke","year":"2008","journal-title":"Med. Eng. Phys."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sucerquia, A., L\u00f3pez, J.D., and Vargas-Bonilla, J.F. (2018). Real-Life\/Real-Time Elderly Fall Detection with a Triaxial Accelerometer. Sensors, 18.","DOI":"10.20944\/preprints201711.0087.v3"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s11517-016-1504-y","article-title":"A comparison of accuracy of fall detection algorithms (threshold-based vs. Machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials","volume":"55","author":"Aziz","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mao, A., Ma, X., He, Y., and Luo, J. (2017). Highly Portable, Sensor-Based System for Human Fall Monitoring. Sensors, 17.","DOI":"10.3390\/s17092096"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shi, G., Zhang, J., Dong, C., Han, P., Jin, Y., and Wang, J. (2015, January 8\u201312). Fall detection system based on inertial mems sensors: Analysis design and realization. Proceedings of the IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, Shenyang, China.","DOI":"10.1109\/CYBER.2015.7288226"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhao, S., Li, W., Niu, W., Gravina, R., and Fortino, G. (2018, January 26\u201329). Recognition of human fall events based on single tri-axial gyroscope. Proceedings of the 15th IEEE International Conference on Networking, Sensing and Control, Zhuhai, China.","DOI":"10.1109\/ICNSC.2018.8361365"},{"key":"ref_29","first-page":"797","article-title":"Personalization in Mobile Activity Recognition System Using K-Medoids Clustering Algorithm","volume":"9","author":"Viet","year":"2013","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_30","unstructured":"Zhao, Z., Chen, Y., Liu, J., Shen, Z., and Liu, M. (2011, January 19\u201322). Cross-people mobile-phone based activity recognition. Proceedings of the International Joint Conference on Artificial Intelligence, Barcelona, Spain."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2014.01.008","article-title":"Cross-person activity recognition using reduced kernel extreme learning machine","volume":"53","author":"Deng","year":"2014","journal-title":"Neural Netw."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.neucom.2016.08.077","article-title":"Sensor-based adaptive activity recognition with dynamically available sensors","volume":"218","author":"Wen","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Fallahzadeh, R., and Ghasemzadeh, H. (2017, January 18\u201320). Personalization without user interruption: Boosting activity recognition in new subjects using unlabeled data. Proceedings of the 8th International Conference on Cyber-Physical Systems, Pittsburgh, PA, USA.","DOI":"10.1145\/3055004.3055015"},{"key":"ref_34","unstructured":"Siirtola, P., Koskim\u00e4ki, H., and R\u00f6ning, J. (2018, January 25\u201327). Personalizing human activity recognition models using incremental learning. Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018), Brugge, Belgium."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2053","DOI":"10.1088\/0967-3334\/35\/10\/2053","article-title":"Classification of frailty and falls history using a combination of sensor-based mobility assessments","volume":"35","author":"Greene","year":"2014","journal-title":"Physiol. Meas."},{"key":"ref_36","unstructured":"Pereira, F. (February, January 31). Developments and trends on video coding: Is there a xVC virus?. Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication, Suwon, Korea."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.medengphy.2007.04.006","article-title":"Assessment of fall-risk by means of a neural network based on parameters assessed by a wearable device during posturography","volume":"30","author":"Giansanti","year":"2008","journal-title":"Med. Eng. Phys."},{"key":"ref_38","first-page":"1","article-title":"A real-time model-based human motion tracking and analysis for human-computer interface systems","volume":"2004","author":"Huang","year":"2004","journal-title":"Eurasip J. Adv. Sign. Proces."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1016\/j.patcog.2006.02.002","article-title":"Some refinements of rough K-Means","volume":"39","author":"Peters","year":"2006","journal-title":"Pattern Recognit."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., and Sander, J. (2000, January 15\u201318). Lof: Identifying density-based local outliers. Proceedings of the ACM SIGMOD International Conference on Management of Data, Dallas, TX, USA.","DOI":"10.1145\/342009.335388"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.medengphy.2016.10.014","article-title":"Review of fall detection techniques: A data availability perspective","volume":"39","author":"Khan","year":"2017","journal-title":"Med. Eng. Phys."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.gaitpost.2011.11.016","article-title":"Comparison of real-life accidental falls in older people with experimental falls in middle-aged test subjects","volume":"35","author":"Kangas","year":"2012","journal-title":"Gait Posture"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"De la Cal, E., Villar, J., Vergara, P., Sedano, J., and Herrero, A. (2017, January 6\u20138). A smote extension for balancing multivariate epilepsy-related time series datasets. Proceedings of the 12th International Conference on Soft Computing Models in Industrial and Environmental Applications, Le\u00f3n, Spain.","DOI":"10.1007\/978-3-319-67180-2_43"},{"key":"ref_45","unstructured":"(2017, September 10). Metabolic Equivalent Website. Available online: https:\/\/en.wikipedia.org\/wiki\/Metabolic_equivalent."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1109\/JBHI.2013.2287504","article-title":"Designing a robust activity recognition framework for health and exergaming using wearable sensors","volume":"18","author":"Alshurafa","year":"2014","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1111\/trf.14057","article-title":"Understanding tests of the association of categorical variables: The pearson chi-square test and fisher's exact test","volume":"57","author":"Hess","year":"2017","journal-title":"Transfusion"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"Libsvm: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intel. Syst. Technol."},{"key":"ref_49","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":"ACM SIGKDD Explor. Newsl."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.inffus.2016.09.005","article-title":"Multi-Sensor Fusion in Body Sensor Networks: \u2028State-of-the-art and research challenges","volume":"35","author":"Gravina","year":"2017","journal-title":"Inf. Fusion"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.inffus.2017.08.002","article-title":"Optimizing multi-sensor deployment via ensemble pruning for wearable activity recognition","volume":"41","author":"Cao","year":"2017","journal-title":"Inf. Fusion"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1850\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:07:33Z","timestamp":1760195253000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,6]]},"references-count":51,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2018,6]]}},"alternative-id":["s18061850"],"URL":"https:\/\/doi.org\/10.3390\/s18061850","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,6]]}}}