Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system

Mehdi Khoury; Honghai Liu

doi:10.1109/FUZZY.2009.5277351

Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system

Mehdi Khoury^*
, Honghai Liu

^*Corresponding author for this work

University of Portsmouth

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

This paper continues to explore the potential of newly introduced Fuzzy Gaussian Inference (FGI) [1]. It aims at constructing fuzzy membership functions by modelling hidden probability distributions underlying human motions. A fuzzy rule-based system has been employed to assist boxing motion classification from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results indicate that adding a Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.

Original language	English
Title of host publication	2009 IEEE International Conference on Fuzzy Systems - Proceedings
Pages	842-847
Number of pages	6
DOIs	https://doi.org/10.1109/FUZZY.2009.5277351
State	Published - 2009
Externally published	Yes
Event	2009 IEEE International Conference on Fuzzy Systems - Jeju Island, Korea, Republic of Duration: 20 Aug 2009 → 24 Aug 2009

Publication series

Name	IEEE International Conference on Fuzzy Systems
ISSN (Print)	1098-7584

Conference

Conference	2009 IEEE International Conference on Fuzzy Systems
Country/Territory	Korea, Republic of
City	Jeju Island
Period	20/08/09 → 24/08/09

Access to Document

10.1109/FUZZY.2009.5277351

Cite this

@inproceedings{281544ef572f4d27a102e77b8524d790,

title = "Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system",

abstract = "This paper continues to explore the potential of newly introduced Fuzzy Gaussian Inference (FGI) [1]. It aims at constructing fuzzy membership functions by modelling hidden probability distributions underlying human motions. A fuzzy rule-based system has been employed to assist boxing motion classification from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results indicate that adding a Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.",

author = "Mehdi Khoury and Honghai Liu",

year = "2009",

doi = "10.1109/FUZZY.2009.5277351",

language = "英语",

isbn = "9781424435975",

series = "IEEE International Conference on Fuzzy Systems",

pages = "842--847",

booktitle = "2009 IEEE International Conference on Fuzzy Systems - Proceedings",

note = "2009 IEEE International Conference on Fuzzy Systems ; Conference date: 20-08-2009 Through 24-08-2009",

}

Khoury, M & Liu, H 2009, Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system. in 2009 IEEE International Conference on Fuzzy Systems - Proceedings., 5277351, IEEE International Conference on Fuzzy Systems, pp. 842-847, 2009 IEEE International Conference on Fuzzy Systems, Jeju Island, Korea, Republic of, 20/08/09. https://doi.org/10.1109/FUZZY.2009.5277351

Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system. / Khoury, Mehdi; Liu, Honghai.
2009 IEEE International Conference on Fuzzy Systems - Proceedings. 2009. p. 842-847 5277351 (IEEE International Conference on Fuzzy Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system

AU - Khoury, Mehdi

AU - Liu, Honghai

PY - 2009

Y1 - 2009

N2 - This paper continues to explore the potential of newly introduced Fuzzy Gaussian Inference (FGI) [1]. It aims at constructing fuzzy membership functions by modelling hidden probability distributions underlying human motions. A fuzzy rule-based system has been employed to assist boxing motion classification from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results indicate that adding a Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.

AB - This paper continues to explore the potential of newly introduced Fuzzy Gaussian Inference (FGI) [1]. It aims at constructing fuzzy membership functions by modelling hidden probability distributions underlying human motions. A fuzzy rule-based system has been employed to assist boxing motion classification from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results indicate that adding a Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.

UR - https://www.scopus.com/pages/publications/71249150056

U2 - 10.1109/FUZZY.2009.5277351

DO - 10.1109/FUZZY.2009.5277351

M3 - 会议稿件

AN - SCOPUS:71249150056

SN - 9781424435975

T3 - IEEE International Conference on Fuzzy Systems

SP - 842

EP - 847

BT - 2009 IEEE International Conference on Fuzzy Systems - Proceedings

T2 - 2009 IEEE International Conference on Fuzzy Systems

Y2 - 20 August 2009 through 24 August 2009

ER -

Boxing motions classification through combining fuzzy Gaussian inference with a context-aware rule-based system

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this