Joint segmentation of multivariate time series with hidden process regression for human activity recognition

• Published in: Neurocomputing (Amsterdam) Vol. 120; no. 120; pp. 633 - 644
• Main Authors: Chamroukhi, F., Mohammed, S., Trabelsi, D., Oukhellou, L., Amirat, Y.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 23.11.2013; Elsevier
• Subjects: Acceleration; Acceleration data; Applied sciences; Artificial intelligence; Computer Science; Computer science; control theory; systems; Computer Vision and Pattern Recognition; Data processing. List processing. Character string processing; Exact sciences and technology; Expectation–maximization algorithm; Hidden process regression; Human activity recognition; Human motion; Information retrieval. Graph; Mathematical models; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Recognition; Regression; Robotics; Segmentation; Sequences; Software; Theoretical computing; Time series; Times series segmentation; Unsupervised learning; Human activity recognition; Expectation–maximization algorithm; Hidden process regression; Unsupervised learning; Acceleration data; Times series segmentation; Expectation-maximization algorithm; Segmentation; Variability; Modeling; Time variation; Human factor; Prospective; Static model; Dynamic model; Pattern extraction; Monitoring; Multimodel; Multivariate process; Computer vision; Statistical analysis; Time series; Human activity; Scene analysis; regime switching model; Hidden Markov model; Observation data; Automatic recognition; EM algorithm; RECONNAISSANCE
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2013.04.003

The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the variability of the human activities over time (dynamic models) rather than static ones which can have some limitations in such a dynamic context. In this paper, the problem of activity recognition is analyzed through the segmentation of the multidimensional time series of the acceleration data measured in the 3-d space using body-worn accelerometers. The proposed model for automatic temporal segmentation is a specific statistical latent process model which assumes that the observed acceleration sequence is governed by sequence of hidden (unobserved) activities. More specifically, the proposed approach is based on a specific multiple regression model incorporating a hidden discrete logistic process which governs the switching from one activity to another over time. The model is learned in an unsupervised context by maximizing the observed-data log-likelihood via a dedicated expectation–maximization (EM) algorithm. We applied it on a real-world automatic human activity recognition problem and its performance was assessed by performing comparisons with alternative approaches, including well-known supervised static classifiers and the standard hidden Markov model (HMM). The obtained results are very encouraging and show that the proposed approach is quite competitive even it works in an entirely unsupervised way and does not requires a feature extraction preprocessing step. •We present a novel way for automatic human activity recognition from acceleration data.•It is based on a well-established statistical latent data model.•It works in an entirely unsupervised way and does not require feature extraction preprocessing.•It is assessed on a real-world automatic human activity recognition problem.