Keywords:image processing, gussian mixture models, expectation maximization, human daily activities
In recently, automatic detection of human activities has gained importance in a research topic due to the individual nature of the activities. Ability to monitor of human daily activities will enhance the capabilities of an application in computer vision. Combination of visual keyword embedding models and a statistical semantic prior model have been recently proposed in the task of mapping images to their contents. Many techniques were proposed to identify activities with supervised dictionary creation methods based on both supervised information with scene description, advantages and limits the discriminative power of the resulting visual words. However, it is a very challenging issue and none of the existing methods provides robust results. In this paper, we propose to classify a human daily activities supervised by learning algorithm based on a Gaussian Mixture model (GM) optimizing with an Expectation-Maximization-based (EM) approach. The approach is composed of four main phases: (1) data preprocessing (2) constructing the modeling with Gaussian distribution (3) Expectation-Maximization (4) measurement and evaluation. We test our model in a publicly available data-set that classify into twelve different daily activities performed by different environment background. This proved to be the case as GMEM with 150 keywords reached average accuracy of » 84.6%. The experimental results indicate that our proposed approach offers significant performance improvements in the classification of human daily activities.
Ranasinghe DC, Torres RLS, Wickramasinghe A. Automated activity recognition and monitoring of elderly using wireless sensors: Research challenges. 5th IEEE International Workshop on Advances in Sensors and Interfaces; 2013. p. 224-7.
Ann OC, Theng LB. Human activity recognition: A Review. 2014 IEEE International Conference on Control System, Computing and Engineering; 2014. p. 389-93.
Kay W, et al. The kinetics human action video dataset. Computer Vision and Pattern Recognition. 2017.
Zainudin MNS, Sulaiman MN, Mustapha N, Perumal T. Activity recognition based on accelerometer sensor using combinational classifiers. 2015 IEEE Conference on Open Systems (ICOS); 2016. p. 68-73.
Bulling A, Blanke U, Schiele B. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR) 2014;46(3):1-33.
Yang JB, Nguyen MN, San PP, Li XL, Krishnaswamy S. Deep convolutional neural networks on multichannel time series for human activity recognition. Proceedings of the 24th International Conference on Artificial Intelligence. AAAI Press; 2015. p. 3995-4001.
Chinpanthana N, Phiasai T. Deep textual Searching for Visual Semantics of Personal Photo Collections with a Hybrid Similarity Measure. International Symposium on Computer Science and Intelligent Controls; 2017. p. 124-28.
Fine S, Singer Y, Tishby N. The hierarchical hidden Markov model: analysis and applications. Machine Learning 1998;32:41-62.
Natarajan P, Nevatia R. Coupled hidden semi Markov models for activity recognition. 2007 IEEE Workshop on Motion and Video Computing; 2007.
Jindong W, Yiqiang C, Shuji H, Xiaohui P, Lisha H. Deep Learning for Sensor-based Activity Recognition: A Survey Pattern Recognition Letters. 2019;119: 3-11.
Catal C,Tufekci S, Pirmit E, Kocabag G. On the use of ensemble of classifiers for accelerometer-based activity recognition. Applied Soft Computing 2015;37:1018-22.
Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. International Workshop of Ambient Assisted Living (IWAAL 2012); 2012. p. 216-23
Lopes N, Ribeiro B. Deep belief networks (DBNs). Machine Learning for Adaptive Many-Core Machines - A Practical Approach. Springer International Publishing; 2015. p. 155-86.
Chen Y, Xue Y. A deep learning approach to human activity recognition based on single accelerometer. 2015 IEEE International Conference on Systems, Man, and Cybernetics; 2015. p. 1488-92.
Zeng M, Nguyen LT, Yu B, Mengshoel OJ, Zhu J, Wu P, et al. Convolutional Neural Networks for human activity recognition using mobile sensors. 6th International Conference on Mobile Computing, Applications and Services; 2014. p. 197-205.
Alsheikh MA, Selim A, Niyato D, Doyle L, Lin S, Tan HP. Deep activity recognition models with triaxial accelerometers. AAAI workshop; 2016.
Ordonez FJ, Toledo P, Sanchis A. Sensor-based bayesian detection of anomalous living patterns in a home setting. Personal Ubiquitous Comput 2015;19(2):259-70.
Jennifer RK, Gary MW, Samuel AM. Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 2011;12(2):74-82.
Reyes-Ortiz JL, Oneto L, Samà A, Parra X, Anguita D. Transition-aware human activity recognition using smartphones. Neurocomputing 2016;171:754-67.
Everingham M, Gool L, Williams CK, Winn J, Zisserman A. The PASCAL visual object classes (VOC) challenge. International Journal of Computer Vision 2010;88:303-38.
Caesar H, Uijlings J, Ferrari V. COCO-Stuff: Thing and stuff classes in context. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2018. p. 1209-18.
Lin T, Maire M, Belongie SJ, Hays J, Perona P, Ramanan D, et al. Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, editors. Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham. p. 740-55.
Dhillon IS, Guan Y, Kulis B. Kernel K-means: spectral clustering and normalized cuts. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2004. p. 551-6.
Frey PW, Slate DJ. Letter recognition using Holland-style adaptive classifiers. Machine Learning.1991;6:161-82.
Bishop CM. Pattern recognition and machine learning. New York: Springer; 2006.
Banfield JD, Raftery AE. Model-based Gaussian and non-Gaussian clustering. Biometrics 1993;49:803-21.
Chen M. EM algorithm for Gaussian mixture model (EM GMM) [Internet]. MATLAB Central File Exchange; 2021 [cited 2021 January 8]. Available from: https://www.mathworks.com/ matlabcentral/fileexchange/26184-em-algorithm-for-gaussian-mixture-model-em-gmm
Drumm-Boyd C. Activities & instrumental activities of daily living - definitions, importance and assessments [Internet]. 2020. Available from: https://www.payingforseniorcare.com/ activities-of-daily-living.
Costenoble A, Knoop V, Vermeiren S, Vella RA, Debain A, Rossi G, et al. A comprehensive overview of activities of daily living in existing frailty instruments: a systematic literature search. The Gerontologist; 2019.
Lian X, Li Z, Wang C, Lu B, Zhang L. Probabilistic models for supervised dictionary learning. Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition; 2010. p. 2305-12.
Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A. (2008). Discriminative learned dictionaries for local image analysis. IEEE Conference on Computer Vision and Pattern Recognition; 2008.
The article has been published in Kasem Bundit Engineering Journal (KBEJ) is the copyright of the Kasem Bundit University. Do not bring all of the messages or republished except permission from the university.
If the article is published as an article that infringes the copyright or has the wrong content the author of article must be responsible.