Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer
| Autor: | Ju Bin Song, M. Ejaz Ahmed |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2012 |
| Předmět: |
Engineering
infinite Gaussian mixture model Walking Accelerometer lcsh:Chemical technology Biochemistry Fuzzy logic Article Analytical Chemistry Pattern Recognition Automated Running symbols.namesake Motion MEMS application Accelerometry Gibbs sampler Humans Computer vision lcsh:TP1-1185 Electrical and Electronic Engineering Cluster analysis Instrumentation non-parametric Bayesian inference Parametric statistics human motion recognition business.industry Nonparametric statistics Bayes Theorem Equipment Design Micro-Electrical-Mechanical Systems Mixture model Atomic and Molecular Physics and Optics ComputingMethodologies_PATTERNRECOGNITION symbols A priori and a posteriori Artificial intelligence business Algorithms Gibbs sampling |
| Zdroj: | Sensors; Volume 12; Issue 10; Pages: 13185-13211 Sensors (Basel, Switzerland) Sensors, Vol 12, Iss 10, Pp 13185-13211 (2012) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s121013185 |
| Popis: | In this paper, we propose a non-parametric clustering method to recognize the number of human motions using features which are obtained from a single microelectromechanical system (MEMS) accelerometer. Since the number of human motions under consideration is not known a priori and because of the unsupervised nature of the proposed technique, there is no need to collect training data for the human motions. The infinite Gaussian mixture model (IGMM) and collapsed Gibbs sampler are adopted to cluster the human motions using extracted features. From the experimental results, we show that the unanticipated human motions are detected and recognized with significant accuracy, as compared with the parametric Fuzzy C-Mean (FCM) technique, the unsupervised K-means algorithm, and the non-parametric mean-shift method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|