Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals

Electromyography (EMG) signals are one of the most studied inputs for driver drowsiness detection systems. As the number of EMG features available can be daunting, finding the most significant and minimal subset features is desirable. Hence, a simplified feature selection method is necessary. This w...

Full description

Bibliographic Details
Main Authors: Faradila, Naim, Mahfuzah, Mustafa, Norizam, Sulaiman, Zarith Liyana, Zahari
Format: Article
Language:English
Published: International Information and Engineering Technology Association 2022
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/42665/
_version_ 1848827307409539072
author Faradila, Naim
Mahfuzah, Mustafa
Norizam, Sulaiman
Zarith Liyana, Zahari
author_facet Faradila, Naim
Mahfuzah, Mustafa
Norizam, Sulaiman
Zarith Liyana, Zahari
author_sort Faradila, Naim
building UMP Institutional Repository
collection Online Access
description Electromyography (EMG) signals are one of the most studied inputs for driver drowsiness detection systems. As the number of EMG features available can be daunting, finding the most significant and minimal subset features is desirable. Hence, a simplified feature selection method is necessary. This work proposed a dual-layer ranking feature selection algorithm based on statistical formula f EMG signals for driver fatigue detection. In the beginning, in the first layer, 21 filter algorithms were calculated to rank 47 sets of EMG features (25 time-domain and 9 frequency-domain) and applied to six classifiers. Then, in the second layer, all the ranks were re-ranked based on the statistical formula (average, median, mode and variance). The classification performance of all rankings was compared along with the number of features. The highest classification accuracy achieved was 95% for 12 features using the Average Statistical Rank (ASR) and LDA classifier. It is conclusive that a combination of features from the time domain and frequency domain can deliver better performance compared to a single domain feature. Concurrently, the statistical rank ASR performed better than the single filter rank by reducing the number of features. The proposed model can be a benchmark for the enhanced feature selection method for EMG driver fatigue signal.
first_indexed 2025-11-15T03:48:33Z
format Article
id ump-42665
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:58:38Z
publishDate 2022
publisher International Information and Engineering Technology Association
recordtype eprints
repository_type Digital Repository
spelling ump-426652025-09-03T00:28:05Z https://umpir.ump.edu.my/id/eprint/42665/ Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals Faradila, Naim Mahfuzah, Mustafa Norizam, Sulaiman Zarith Liyana, Zahari T Technology (General) TK Electrical engineering. Electronics Nuclear engineering Electromyography (EMG) signals are one of the most studied inputs for driver drowsiness detection systems. As the number of EMG features available can be daunting, finding the most significant and minimal subset features is desirable. Hence, a simplified feature selection method is necessary. This work proposed a dual-layer ranking feature selection algorithm based on statistical formula f EMG signals for driver fatigue detection. In the beginning, in the first layer, 21 filter algorithms were calculated to rank 47 sets of EMG features (25 time-domain and 9 frequency-domain) and applied to six classifiers. Then, in the second layer, all the ranks were re-ranked based on the statistical formula (average, median, mode and variance). The classification performance of all rankings was compared along with the number of features. The highest classification accuracy achieved was 95% for 12 features using the Average Statistical Rank (ASR) and LDA classifier. It is conclusive that a combination of features from the time domain and frequency domain can deliver better performance compared to a single domain feature. Concurrently, the statistical rank ASR performed better than the single filter rank by reducing the number of features. The proposed model can be a benchmark for the enhanced feature selection method for EMG driver fatigue signal. International Information and Engineering Technology Association 2022-06 Article PeerReviewed pdf en cc_by_4 https://umpir.ump.edu.my/id/eprint/42665/1/Dual-layer%20ranking%20feature%20selection%20method%20based%20on%20statistical%20formula.pdf Faradila, Naim and Mahfuzah, Mustafa and Norizam, Sulaiman and Zarith Liyana, Zahari (2022) Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals. Traitement du Signal, 39 (3). pp. 1079-1088. ISSN 0765-0019. (Published) https://doi.org/10.18280/ts.390335 https://doi.org/10.18280/ts.390335 https://doi.org/10.18280/ts.390335
spellingShingle T Technology (General)
TK Electrical engineering. Electronics Nuclear engineering
Faradila, Naim
Mahfuzah, Mustafa
Norizam, Sulaiman
Zarith Liyana, Zahari
Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title_full Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title_fullStr Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title_full_unstemmed Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title_short Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals
title_sort dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of emg signals
topic T Technology (General)
TK Electrical engineering. Electronics Nuclear engineering
url https://umpir.ump.edu.my/id/eprint/42665/
https://umpir.ump.edu.my/id/eprint/42665/
https://umpir.ump.edu.my/id/eprint/42665/