Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer
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 uns...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2012-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/12/10/13185 |
_version_ | 1798039526229147648 |
---|---|
author | M. Ejaz Ahmed Ju Bin Song |
author_facet | M. Ejaz Ahmed Ju Bin Song |
author_sort | M. Ejaz Ahmed |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-11T21:55:06Z |
format | Article |
id | doaj.art-b5fad9286195475fa44a4fe9f853b70c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T21:55:06Z |
publishDate | 2012-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b5fad9286195475fa44a4fe9f853b70c2022-12-22T04:01:08ZengMDPI AGSensors1424-82202012-09-011210131851321110.3390/s121013185Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial AccelerometerM. Ejaz AhmedJu Bin SongIn 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.http://www.mdpi.com/1424-8220/12/10/13185MEMS applicationhuman motion recognitionnon-parametric Bayesian inferenceinfinite Gaussian mixture modelGibbs sampler |
spellingShingle | M. Ejaz Ahmed Ju Bin Song Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer Sensors MEMS application human motion recognition non-parametric Bayesian inference infinite Gaussian mixture model Gibbs sampler |
title | Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer |
title_full | Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer |
title_fullStr | Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer |
title_full_unstemmed | Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer |
title_short | Non-Parametric Bayesian Human Motion Recognition Using a Single MEMS Tri-Axial Accelerometer |
title_sort | non parametric bayesian human motion recognition using a single mems tri axial accelerometer |
topic | MEMS application human motion recognition non-parametric Bayesian inference infinite Gaussian mixture model Gibbs sampler |
url | http://www.mdpi.com/1424-8220/12/10/13185 |
work_keys_str_mv | AT mejazahmed nonparametricbayesianhumanmotionrecognitionusingasinglememstriaxialaccelerometer AT jubinsong nonparametricbayesianhumanmotionrecognitionusingasinglememstriaxialaccelerometer |