Differential evolution algorithm as a tool for optimal feature subset selection in motor imagery EEG

Baig, Muhammad Zeeshan; Aslam, Nauman; Shum, Hubert P. H.; Zhang, Li

doi:10.1016/j.eswa.2017.07.033

Cited by 137 publications

(97 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During an experiment that involved walking, the EEG can be considered as only a raw estimate of arousal level, but new advancements have the ability to change this concept [56]. The EEG signal analysis becomes complex with the high dimensional data and the best option is to use a feature selection algorithm to select the optimal feature set for the analysis [57]. A critical review on the use of EEG in HCI was presented by Spapé et al which discusses the shortcomings and contribution of EEG signals in HCI [58].…”

Section: Electroencephalographymentioning

confidence: 99%

A Survey on Psycho-Physiological Analysis & Measurement Methods in Multimodal Systems

Baig¹,

Kavakli²

2019

MTI

Self Cite

View full text Add to dashboard Cite

Psycho-physiological analysis has gained greater attention in the last few decades in various fields including multimodal systems. Researchers use psychophysiological feedback devices such as skin conductance (SC), Electroencephalography (EEG) and Electrocardiography (ECG) to detect the affective states of the users during task performance. Psycho-physiological feedback has been successful in detection of the cognitive states of users in human-computer interaction (HCI). Recently, in game studies, psycho-physiological feedback has been used to capture the user experience and the effect of interaction on human psychology. This paper reviews several psycho-physiological, cognitive, and affective assessment studies and focuses on the use of psychophysiological signals in estimating the user's cognitive and emotional states in multimodal systems. In this paper, we review the measurement techniques and methods that have been used to record psycho-physiological signals as well as the cognitive and emotional states in a variety of conditions. The aim of this review is to conduct a detailed study to identify, describe and analyze the key psycho-physiological parameters that relate to different mental and emotional states in order to provide an insight into key approaches. Furthermore, the advantages and limitations of these approaches are also highlighted in this paper. The findings state that the classification accuracy of >90% has been achieved in classifying emotions with EEG signals. A strong correlation between self-reported data, HCI experience, and psychophysiological data has been observed in a wide range of domains including games, human-robot interaction, mobile interaction, and simulations. An increase in β and γ-band activity have been observed in high intense games and simulations.

show abstract

Section: Electroencephalographymentioning

confidence: 99%

A Survey on Psycho-Physiological Analysis & Measurement Methods in Multimodal Systems

Baig¹,

Kavakli²

2019

MTI

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [19], they utilized a differential evolution (DE) based technique to select most relevant features in EEG based MI and CSP as feature extractor (CSP+DE-FS). They achieved excellent accuracy and small standard deviation with 96.02% and 3.77% respectively.…”

Section: Related Workmentioning

confidence: 99%

“…As initial step, original dataset which contains EEG signal is filtered using 4 th order Butterworth band-pass filter as commonly used in EEG signal processing [14], [25], [26]. EEG signal were filtered in frequency range 8-30 Hz as same range with [19], [27]- [30]. After filtered, a time slot or window between 0.5 -2 seconds is chosen for further process.…”

Section: B Narrow Window Feature Extractionmentioning

confidence: 99%

“…After filtered, a time slot or window between 0.5 -2 seconds is chosen for further process. This time slot is narrower window than some prior researches, such as: 0.5 -3.5 seconds [14], 0 -3.5 seconds [6], [19] and 0.5 -2.5 seconds [21]. The selected time slot, which is range about 1.5 seconds, consists of 150 data points because 100 Hz down-sampled data is used in this study.…”

Section: B Narrow Window Feature Extractionmentioning

confidence: 99%

“…In spatial domain, Common Spatial Pattern (CSP) is one of most popular technique in EEG based MI classification. Therefore, many studies have been used and improve CSP such as: CSP with sparse time-frequency segment common spatial pattern [18], CSP combined with Differential Evolution as feature selection [19], CSP combined with symmetrical feature [20] and Filter Bank Regularized Common Spatial Pattern [21]. Another approach based on time-frequency signal processing technique by employing three popular wavelet technique has been conducted by [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Narrow Window Feature Extraction for EEG-Motor Imagery Classification using k-NN and Voting Scheme

Wijaya¹,

Adji²,

Setiawan³

2018

EECSI

View full text Add to dashboard Cite

Achieving consistent accuracy still big challenge in EEG based Motor Imagery classification since the nature of EEG signal is non-stationary, intra-subject and inter-subject dependent. To address this problems, we propose the feature extraction scheme employing statistical measurements in narrow window with channel instantiation approach. In this study, k-Nearest Neighbor is used and a voting scheme as final decision where the most detection in certain class will be a winner. In this channel instantiation scheme, where EEG channel become instance or record, seventeen EEG channels with motor related activity is used to reduce from 118 channels. We investigate five narrow windows combination in the proposed methods, i.e.: one, two, three, four and five windows. BCI competition III Dataset IVa is used to evaluate our proposed methods. Experimental results show that one window with all channel and a combination of five windows with reduced channel outperform all prior research with highest accuracy and lowest standard deviation. This results indicate that our proposed methods achieve consistent accuracy and promising for reliable BCI systems.

show abstract

Efficient feature subset selection and classification using levy flight‐based cuckoo search optimization with parallel support vector machine for the breast cancer data

S¹,

Amali²

2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The complexity of breast cancer classification is a drastic concern for a long time. Therefore, different algorithms for data mining have been developed and used to effectively classify the dataset of breast cancer. But, due to inefficient subset choice of this operation, these algorithms have problems in accuracy of classification. In this article, levy flight–based cuckoo search optimization (LFCSO) with parallel support vector machine (PSVM) is proposed for enhancing the classification accuracy of breast cancer. The proposed LFCSO‐PSVM technique includes three key steps: (i) preprocessing, (ii) feature selecting subset, and (iii) classification. Preprocessing is carried out using k‐means clustering that is required to eliminate the values. To acquire maximum detailed feature, these attributes are transmitted to the process the feature selecting subset, which is executed by LFCSO algorithm, and the aspiration function is used to determine the essential feature on the basis of proper fitness values. Then, the PSVM algorithm is implemented to classify the model for training and testing. This is used to increase the accuracy of the classification for the breast cancer dataset. The experimental outcomes demonstrate that the proposed LFCSO‐PSVM algorithm provides higher efficiency of classification than the existing algorithms in terms of precision, recall, f‐measurement, and reliability.

show abstract

Differential evolution algorithm as a tool for optimal feature subset selection in motor imagery EEG

Cited by 137 publications

References 41 publications

A Survey on Psycho-Physiological Analysis & Measurement Methods in Multimodal Systems

A Survey on Psycho-Physiological Analysis & Measurement Methods in Multimodal Systems

Narrow Window Feature Extraction for EEG-Motor Imagery Classification using k-NN and Voting Scheme

Efficient feature subset selection and classification using levy flight‐based cuckoo search optimization with parallel support vector machine for the breast cancer data

Contact Info

Product

Resources

About