Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV

Nor Aziyatul Izni Mohd Rosli, Mohd Azizi Abdul Rahman, Malarvili Balakrishnan, Takashi Komeda, Saiful Amri Mazlan, Hairi Zamzuri

Research output: Research - peer-reviewArticle

Abstract

Gender recognition is trivial for a physiotherapist, but it is considered a challenge for computers. The electromyography (EMG) and heart rate variability (HRV) were utilized in this work for gender recognition during exercise using a stepper. The relevant features were extracted and selected. The selected features were then fused to automatically predict gender recognition. However, the feature selection for gender classification became a challenge to ensure better accuracy. Thus, in this paper, a feature selection approach based on both the performance and the diversity between the two features from the rank-score characteristic (RSC) function in a combinatorial fusion approach (CFA) (Hsu et al.) was employed. Then, the features from the selected feature sets were fused using a CFA. The results were then compared with other fusion techniques such as naive bayes (NB), decision tree (J48), k-nearest neighbor (KNN) and support vector machine (SVM). Besides, the results were also compared with previous researches in gender recognition. The experimental results showed that the CFA was efficient and effective for feature selection. The fusion method was also able to improve the accuracy of the gender recognition rate. The CFA provides much better gender classification results which is 94.51% compared to Barani's work (90.34%), Nazarloo's work (92.50%), and other classifiers.

LanguageEnglish
Article number348
JournalApplied Sciences (Switzerland)
Volume7
Issue number4
DOIs
StatePublished - 2017 Mar 31

Fingerprint

Electromyography
Fusion reactions
Feature extraction
Decision trees
Support vector machines
Classifiers

Keywords

  • Data fusion
  • Electromyography (EMG)
  • Feature fusion
  • Feature selection
  • Gender recognition
  • Heart Rate Variability (HRV)
  • Sensor fusion
  • Signal processing
  • Stepper

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

Rosli, N. A. I. M., Rahman, M. A. A., Balakrishnan, M., Komeda, T., Mazlan, S. A., & Zamzuri, H. (2017). Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV. Applied Sciences (Switzerland), 7(4), [348]. DOI: 10.3390/app7040348

Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV. / Rosli, Nor Aziyatul Izni Mohd; Rahman, Mohd Azizi Abdul; Balakrishnan, Malarvili; Komeda, Takashi; Mazlan, Saiful Amri; Zamzuri, Hairi.

In: Applied Sciences (Switzerland), Vol. 7, No. 4, 348, 31.03.2017.

Research output: Research - peer-reviewArticle

Rosli NAIM, Rahman MAA, Balakrishnan M, Komeda T, Mazlan SA, Zamzuri H. Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV. Applied Sciences (Switzerland). 2017 Mar 31;7(4). 348. Available from, DOI: 10.3390/app7040348
Rosli, Nor Aziyatul Izni Mohd ; Rahman, Mohd Azizi Abdul ; Balakrishnan, Malarvili ; Komeda, Takashi ; Mazlan, Saiful Amri ; Zamzuri, Hairi. / Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV. In: Applied Sciences (Switzerland). 2017 ; Vol. 7, No. 4.
@article{41d20c45346148ca8c41fc966d1cf20d,
title = "Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV",
abstract = "Gender recognition is trivial for a physiotherapist, but it is considered a challenge for computers. The electromyography (EMG) and heart rate variability (HRV) were utilized in this work for gender recognition during exercise using a stepper. The relevant features were extracted and selected. The selected features were then fused to automatically predict gender recognition. However, the feature selection for gender classification became a challenge to ensure better accuracy. Thus, in this paper, a feature selection approach based on both the performance and the diversity between the two features from the rank-score characteristic (RSC) function in a combinatorial fusion approach (CFA) (Hsu et al.) was employed. Then, the features from the selected feature sets were fused using a CFA. The results were then compared with other fusion techniques such as naive bayes (NB), decision tree (J48), k-nearest neighbor (KNN) and support vector machine (SVM). Besides, the results were also compared with previous researches in gender recognition. The experimental results showed that the CFA was efficient and effective for feature selection. The fusion method was also able to improve the accuracy of the gender recognition rate. The CFA provides much better gender classification results which is 94.51% compared to Barani's work (90.34%), Nazarloo's work (92.50%), and other classifiers.",
keywords = "Data fusion, Electromyography (EMG), Feature fusion, Feature selection, Gender recognition, Heart Rate Variability (HRV), Sensor fusion, Signal processing, Stepper",
author = "Rosli, {Nor Aziyatul Izni Mohd} and Rahman, {Mohd Azizi Abdul} and Malarvili Balakrishnan and Takashi Komeda and Mazlan, {Saiful Amri} and Hairi Zamzuri",
year = "2017",
month = "3",
doi = "10.3390/app7040348",
volume = "7",
journal = "Applied Sciences",
issn = "1454-5101",
publisher = "Politechnica University of Bucharest",
number = "4",

}

TY - JOUR

T1 - Improved gender recognition during stepping activity for rehab application using the combinatorial fusion approach of EMG and HRV

AU - Rosli,Nor Aziyatul Izni Mohd

AU - Rahman,Mohd Azizi Abdul

AU - Balakrishnan,Malarvili

AU - Komeda,Takashi

AU - Mazlan,Saiful Amri

AU - Zamzuri,Hairi

PY - 2017/3/31

Y1 - 2017/3/31

N2 - Gender recognition is trivial for a physiotherapist, but it is considered a challenge for computers. The electromyography (EMG) and heart rate variability (HRV) were utilized in this work for gender recognition during exercise using a stepper. The relevant features were extracted and selected. The selected features were then fused to automatically predict gender recognition. However, the feature selection for gender classification became a challenge to ensure better accuracy. Thus, in this paper, a feature selection approach based on both the performance and the diversity between the two features from the rank-score characteristic (RSC) function in a combinatorial fusion approach (CFA) (Hsu et al.) was employed. Then, the features from the selected feature sets were fused using a CFA. The results were then compared with other fusion techniques such as naive bayes (NB), decision tree (J48), k-nearest neighbor (KNN) and support vector machine (SVM). Besides, the results were also compared with previous researches in gender recognition. The experimental results showed that the CFA was efficient and effective for feature selection. The fusion method was also able to improve the accuracy of the gender recognition rate. The CFA provides much better gender classification results which is 94.51% compared to Barani's work (90.34%), Nazarloo's work (92.50%), and other classifiers.

AB - Gender recognition is trivial for a physiotherapist, but it is considered a challenge for computers. The electromyography (EMG) and heart rate variability (HRV) were utilized in this work for gender recognition during exercise using a stepper. The relevant features were extracted and selected. The selected features were then fused to automatically predict gender recognition. However, the feature selection for gender classification became a challenge to ensure better accuracy. Thus, in this paper, a feature selection approach based on both the performance and the diversity between the two features from the rank-score characteristic (RSC) function in a combinatorial fusion approach (CFA) (Hsu et al.) was employed. Then, the features from the selected feature sets were fused using a CFA. The results were then compared with other fusion techniques such as naive bayes (NB), decision tree (J48), k-nearest neighbor (KNN) and support vector machine (SVM). Besides, the results were also compared with previous researches in gender recognition. The experimental results showed that the CFA was efficient and effective for feature selection. The fusion method was also able to improve the accuracy of the gender recognition rate. The CFA provides much better gender classification results which is 94.51% compared to Barani's work (90.34%), Nazarloo's work (92.50%), and other classifiers.

KW - Data fusion

KW - Electromyography (EMG)

KW - Feature fusion

KW - Feature selection

KW - Gender recognition

KW - Heart Rate Variability (HRV)

KW - Sensor fusion

KW - Signal processing

KW - Stepper

UR - http://www.scopus.com/inward/record.url?scp=85017346611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017346611&partnerID=8YFLogxK

U2 - 10.3390/app7040348

DO - 10.3390/app7040348

M3 - Article

VL - 7

JO - Applied Sciences

T2 - Applied Sciences

JF - Applied Sciences

SN - 1454-5101

IS - 4

M1 - 348

ER -