{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T10:50:42Z","timestamp":1774263042266,"version":"3.50.1"},"reference-count":55,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2014,4,4]],"date-time":"2014-04-04T00:00:00Z","timestamp":1396569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper, we have presented a robust and an accurate activity recognition system called WS-HAR that consists of wavelet transform coupled with stepwise linear discriminant analysis (SWLDA) followed by hidden Markov model (HMM). Symlet wavelet has been employed in order to extract the features from the activity frames. The most prominent features were selected by proposing a robust technique called stepwise linear discriminant analysis (SWLDA) that focuses on selecting the localized features from the activity frames and discriminating their class based on regression values (i.e., partial F-test values). Finally, we applied a well-known sequential classifier called hidden Markov model (HMM) to give the appropriate labels to the activities. In order to validate the performance of the WS-HAR, we utilized two publicly available standard datasets under two different experimental settings, n\u2013fold cross validation scheme based on subjects; and a set of experiments was performed in order to show the effectiveness of each approach. The weighted average recognition rate for the WS-HAR was 97% across the two different datasets that is a significant improvement in classication accuracy compared to the existing well-known statistical and state-of-the-art methods.<\/jats:p>","DOI":"10.3390\/s140406370","type":"journal-article","created":{"date-parts":[[2014,4,4]],"date-time":"2014-04-04T11:11:12Z","timestamp":1396609872000},"page":"6370-6392","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis"],"prefix":"10.3390","volume":"14","author":[{"given":"Muhammad","family":"Siddiqi","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446\u2013701, Korea"}]},{"given":"Rahman","family":"Ali","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446\u2013701, Korea"}]},{"given":"Md.","family":"Rana","sequence":"additional","affiliation":[{"name":"Department of Electronics and Radio Engineering, Kyung Hee University, Suwon 446\u2013701, Korea"}]},{"given":"Een-Kee","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Electronics and Radio Engineering, Kyung Hee University, Suwon 446\u2013701, Korea"}]},{"given":"Eun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul 139\u2013701, Korea"}]},{"given":"Sungyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446\u2013701, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2014,4,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1109\/TIP.2005.852197","article-title":"Shape activity: A continuous-state HMM for moving\/deforming shapes with application to abnormal activity detection","volume":"14","author":"Vaswani","year":"2005","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","article-title":"A survey of advances in vision-based human motion capture and analysis","volume":"104","author":"Moeslund","year":"2006","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_3","unstructured":"Lee, J.T., Ryoo, M.S., Riley, M., and Aggarwal, J.K. (2007, January 5\u20137). Real-time detection of illegally parked vehicles using 1-D transformation. London, UK."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chang, S.F. (2002). The holy grail of content-based media analysis. IEEE Multimed., 6\u201310.","DOI":"10.1109\/93.998041"},{"key":"ref_5","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., and Basri, R. (2005, January 17\u201321). Actions as space-time shapes. Beijing, China."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., and Hebert, M. (2007, January 18\u201323). Spatio-temporal shape and flow correlation for action recognition. Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383512"},{"key":"ref_7","unstructured":"Doll\u00e1r, P., Rabaud, V., Cottrell, G., and Belongie, S. (2005, January 15\u201316). Behavior recognition via sparse spatio-temporal features. Beijing, China."},{"key":"ref_8","unstructured":"Shechtman, E., and Irani, M. (2005, January 20\u201326). Space-time behavior based correlation. San Diego, CA, USA."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"16:1","DOI":"10.1145\/1922649.1922653","article-title":"Human activity analysis: A review","volume":"43","author":"Aggarwal","year":"2011","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1177\/1420326X12469734","article-title":"An indoor human activity recognition system for smart home using local binary pattern features with hidden markov models","volume":"22","author":"Uddin","year":"2013","journal-title":"Indoor Built Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/TSMCB.2012.2199310","article-title":"Incremental learning for video-based gait recognition with LBP flow","volume":"43","author":"Hu","year":"2013","journal-title":"IEEE Trans. Cybern."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sanin, A., Sanderson, C., Harandi, M.T., and Lovell, B.C. (2013, January 17\u201318). Spatio-temporal covariance descriptors for action and gesture recognition. Tampa, FL, USA.","DOI":"10.1109\/WACV.2013.6475006"},{"key":"ref_13","unstructured":"Yeffet, L., and Wolf, L. (October, January 27). Local trinary patterns for human action recognition. Kyoto, Japan."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3844\/jcssp.2013.1.15","article-title":"Optimized local ternary pattern: A new texture model with set of optimal patterns for texture analysis","volume":"9","author":"Raja","year":"2013","journal-title":"J. Comput. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Foroughi, H., Naseri, A., Saberi, A., and Yazdi, H.S. (2008, January 26\u201329). An eigenspace-based approach for human fall detection using integrated time motion image and neural network. Beijing, China.","DOI":"10.1109\/ICOSP.2008.4697417"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Fiaz, M., and Ijaz, B. (2010, January 15\u201317). Vision based human activity tracking using artificial neural networks. Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICIAS.2010.5716186"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/34.824819","article-title":"Statistical pattern recognition: A review","volume":"22","author":"Jain","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Manosha Chathuramali, K., and Rodrigo, R. (2012, January 12\u201315). Faster human activity recognition with SVM. Colombo, Western, Sri Lanka.","DOI":"10.1109\/ICTer.2012.6421415"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Bengalur, M.D. (2013, January 22\u201325). Human activity recognition using body pose features and support vector machine. Mysore, India.","DOI":"10.1109\/ICACCI.2013.6637484"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kodagoda, S., and Piyathilaka, J. (2013, January 19\u201321). Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features. Melbourne, Australia.","DOI":"10.1109\/ICIEA.2013.6566433"},{"key":"ref_21","unstructured":"Lin, W., Sun, M.T., Poovandran, R., and Zhang, Z. (2008, January 18\u201321). Human activity recognition for video surveillance. Seattle, WA, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1109\/TASE.2013.2256349","article-title":"An unsupervised approach for automatic activity recognition based on hidden Markov model regression","volume":"10","author":"Trabelsi","year":"2013","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_23","first-page":"3659","article-title":"Hidden markov model-based human action recognition using mixed features","volume":"9","author":"Ji","year":"2013","journal-title":"J. Comput. Inf. Syst."},{"key":"ref_24","unstructured":"Thuc, H.L.U., Ke, S.R., Hwang, J.N., van Tuan, P., and Chau, T.N. (2012, January 10\u201312). Quasi-periodic action recognition from monocular videos via 3D human models and cyclic HMMs. Hanoi, Vietnam."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5460","DOI":"10.3390\/s130505460","article-title":"Activity recognition using hybrid generative\/discriminative models on home environments using binary sensors","volume":"13","author":"Sanchis","year":"2013","journal-title":"Sensors"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jneumeth.2007.07.017","article-title":"Toward enhanced P300 speller performance","volume":"167","author":"Krusienski","year":"2008","journal-title":"J. Neurosci. Methods"},{"key":"ref_27","unstructured":"Turunen, J. (2011). Wavelet-Based Method for Estimating Damping in Power Systems. [Ph.D. Thesis, Aalto University School of Electrical Engineering]."},{"key":"ref_28","unstructured":"Mika, S., Ratsch, G., Weston, J., Scholkopf, B., and Mullers, K. (1999, January 23\u201325). Fisher discriminant analysis with kernels. Madison, WI, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1162\/089976600300014980","article-title":"Generalized discriminant analysis using a kernel approach","volume":"12","author":"Baudat","year":"2000","journal-title":"Neural Comput."},{"key":"ref_30","unstructured":"Mika, S. (2002). Kernel Fisher Discriminants. [Ph.D. Thesis, Universit \u00e4tsbibliothek]."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1109\/34.598228","article-title":"Eigenfaces vs. fisherfaces: Recognition using class specific linear projection","volume":"19","author":"Belhumeur","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","first-page":"1","article-title":"An equality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes","volume":"3","author":"Baum","year":"1972","journal-title":"Inequalities"},{"key":"ref_33","unstructured":"Samaria, F.S. (1995). Face Recognition Using Hidden Markov Models. [Ph.D. Thesis, University of Cambridge]."},{"key":"ref_34","unstructured":"Schuldt, C., Laptev, I., and Caputo, B. (2004, January 23\u201326). Recognizing human actions: A local SVM approach. Cambridge, UK."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ni, B., Wang, G., and Moulin, P. (2013). Rgbd-hudaact: A color-depth video database for human daily activity recognition. Consumer Depth Cameras for Computer Vision, Springer.","DOI":"10.1007\/978-1-4471-4640-7_10"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., and Shah, M. (2009, January 20\u201325). Recognizing realistic actions from videos in the wild. Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., and Rozenfeld, B. (2008, January 24\u201326). Learning realistic human actions from movies. Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Stiefelhagen, R., and Serre, T. HMDB51: A large video database for human motion recognition. High Performance Computing in Science and Engineering' 12, Springer. May 27\u201330, 2013.","DOI":"10.1007\/978-3-642-33374-3_41"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1109\/TPAMI.2011.209","article-title":"The action similarity labeling challenge","volume":"34","author":"Hassner","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s10489-008-0159-2","article-title":"Independent shape component-based human activity recognition via Hidden Markov Model","volume":"33","author":"Uddin","year":"2010","journal-title":"Appl. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Roshtkhari, M.J., and Levine, M.D. (2012, January 28\u201330). A multi-scale hierarchical codebook method for human action recognition in videos using a single example. Toronto, ON, Canada.","DOI":"10.1109\/CRV.2012.32"},{"key":"ref_42","unstructured":"Ballan, L., Bertini, M., Del Bimbo, A., Seidenari, L., and Serra, G. (2009, January 12). Human action recognition and localization using spatio-temporal descriptors and tracking. Reggio Emilia, Italy."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3238","DOI":"10.1016\/j.patcog.2013.06.006","article-title":"Exploring trace transform for robust human action recognition","volume":"46","author":"Goudelis","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1016\/j.imavis.2013.08.005","article-title":"Human activity recognition in videos using a single example","volume":"31","author":"Levine","year":"2013","journal-title":"Image Vis. Comput."},{"key":"ref_45","first-page":"31","article-title":"Human activity recognition using gait pattern","volume":"5","author":"Gupta","year":"2013","journal-title":"Int. J. Comput. Vis. Image Process. (IJCVIP)"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Arunnehru, J., and Geetha, M.K. (2013, January 18\u201320). Motion intensity code for action recognition in video using PCA and SVM. Mining Intelligence and Knowledge Exploration, Tamil Nadu, India.","DOI":"10.1007\/978-3-319-03844-5_8"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Huang, C.P., Hsieh, C.H., Lai, K.T., and Huang, W.Y. (2011, January 21\u201323). Human action recognition using histogram of oriented gradient of motion history image. Beijing, China.","DOI":"10.1109\/IMCCC.2011.95"},{"key":"ref_48","first-page":"973","article-title":"Recognition of human actions using motion history information extracted from the compressed","volume":"3","author":"Takur","year":"2013","journal-title":"Int. J. Comput. Vis. Image Process. (IJCVIP)"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1861","DOI":"10.1109\/TIP.2014.2302677","article-title":"Evaluation of color spatio-temporal interest points for human action recognition","volume":"23","author":"Everts","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Wang, H., Klaser, A., Schmid, C., and Liu, C.L. (2011, January 20\u201325). Action recognition by dense trajectories. Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref_51","unstructured":"Liang, B., Zheng, L., Shah, S.A.A., Bennamoun, M., Boussaid, F., El-Sallam, A.A., Urschler, M., Bornik, A., Donoser, M., and Babahajiani, P. (2013, January 1\u20138). Three dimensional motion trail model for gesture recognition. Sydney, Australia."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.3390\/s130201635","article-title":"Exploring techniques for vision based human activity recognition: Methods, systems, and evaluation","volume":"13","author":"Xu","year":"2013","journal-title":"Sensors"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"88","DOI":"10.3390\/computers2020088","article-title":"A review on video-based human activity recognition","volume":"2","author":"Ke","year":"2013","journal-title":"Computers"},{"key":"ref_54","unstructured":"Odobez, J.M., Emonet, R., and Tavenard, R. (2013, January 27\u201330). Time-sensitive topic models for action recognition in videos. Paris, France."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Bettadapura, V., Schindler, G., Plotz, T., and Essa, I. (2013, January 23\u201328). Augmenting bag-of-words: Data-driven discovery of temporal and structural information for activity recognition. Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.338"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/4\/6370\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:09:58Z","timestamp":1760216998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/4\/6370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,4]]},"references-count":55,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2014,4]]}},"alternative-id":["s140406370"],"URL":"https:\/\/doi.org\/10.3390\/s140406370","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,4]]}}}