Motion-pattern recognition system using a wavelet-neural network

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a wavelet-neural network recognition system for personal fitness assistance and elderly daily activity monitoring applications. This discrete wavelet transform radial basis neural network (DWT-RBNN) analyzes vibration induced by human motions, and identifies motion status automatically. The 3-D vibration signals are measured by integrated accelerometer chip, and then DWT extracts vibration features. Local energy of extracted feature is calculated and used by RBNN. A multi-channel RBNN is designed and used for recognition. The computation burden is reduced because of the DWT pre-processing. From experiment results, RBNN shows successful recognition capability. This paper also presents flow diagram to determine engineering parameters for the present and future product developments.

Original languageEnglish
Article number8625510
Pages (from-to)170-178
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume65
Issue number2
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Pattern recognition systems
Neural networks
Discrete wavelet transforms
Accelerometers
Product development
Monitoring
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{3860757a31604fbabb431bac9cd86009,
title = "Motion-pattern recognition system using a wavelet-neural network",
abstract = "This paper presents a wavelet-neural network recognition system for personal fitness assistance and elderly daily activity monitoring applications. This discrete wavelet transform radial basis neural network (DWT-RBNN) analyzes vibration induced by human motions, and identifies motion status automatically. The 3-D vibration signals are measured by integrated accelerometer chip, and then DWT extracts vibration features. Local energy of extracted feature is calculated and used by RBNN. A multi-channel RBNN is designed and used for recognition. The computation burden is reduced because of the DWT pre-processing. From experiment results, RBNN shows successful recognition capability. This paper also presents flow diagram to determine engineering parameters for the present and future product developments.",
author = "Wen-Ren Yang and Chau-Shing Wang and Chen, {Chien Pu}",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/TCE.2019.2895050",
language = "English",
volume = "65",
pages = "170--178",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Motion-pattern recognition system using a wavelet-neural network. / Yang, Wen-Ren; Wang, Chau-Shing; Chen, Chien Pu.

In: IEEE Transactions on Consumer Electronics, Vol. 65, No. 2, 8625510, 01.05.2019, p. 170-178.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Motion-pattern recognition system using a wavelet-neural network

AU - Yang, Wen-Ren

AU - Wang, Chau-Shing

AU - Chen, Chien Pu

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This paper presents a wavelet-neural network recognition system for personal fitness assistance and elderly daily activity monitoring applications. This discrete wavelet transform radial basis neural network (DWT-RBNN) analyzes vibration induced by human motions, and identifies motion status automatically. The 3-D vibration signals are measured by integrated accelerometer chip, and then DWT extracts vibration features. Local energy of extracted feature is calculated and used by RBNN. A multi-channel RBNN is designed and used for recognition. The computation burden is reduced because of the DWT pre-processing. From experiment results, RBNN shows successful recognition capability. This paper also presents flow diagram to determine engineering parameters for the present and future product developments.

AB - This paper presents a wavelet-neural network recognition system for personal fitness assistance and elderly daily activity monitoring applications. This discrete wavelet transform radial basis neural network (DWT-RBNN) analyzes vibration induced by human motions, and identifies motion status automatically. The 3-D vibration signals are measured by integrated accelerometer chip, and then DWT extracts vibration features. Local energy of extracted feature is calculated and used by RBNN. A multi-channel RBNN is designed and used for recognition. The computation burden is reduced because of the DWT pre-processing. From experiment results, RBNN shows successful recognition capability. This paper also presents flow diagram to determine engineering parameters for the present and future product developments.

UR - http://www.scopus.com/inward/record.url?scp=85060449356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060449356&partnerID=8YFLogxK

U2 - 10.1109/TCE.2019.2895050

DO - 10.1109/TCE.2019.2895050

M3 - Article

AN - SCOPUS:85060449356

VL - 65

SP - 170

EP - 178

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 2

M1 - 8625510

ER -