Channel Selection of EEG Emotion Recognition using Stepwise Discriminant Analysis

Pane, Evi Septiana; Wibawa, Adhi Dharma; Pumomo, Mauridhi Hery

doi:10.1109/cenim.2018.8711196

Cited by 19 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Genetic algorithms allow the dimensionality of the feature vector to be reduced using evolutionary methods, leaving only more informative feature [ 2 , 86 , 97 ]. Stepwise discriminant analysis SDA [ 74 ]. SDA is the extension of the statistical tool for discriminant analysis that includes the stepwise technique.…”

Section: Eeg-based Bci Systems For Emotion Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

EEG-Based BCI Emotion Recognition: A Survey

Torres

Hernández-Álvarez

et al. 2020

Sensors

183

View full text Add to dashboard Cite

Affecting computing is an artificial intelligence area of study that recognizes, interprets, processes, and simulates human affects. The user’s emotional states can be sensed through electroencephalography (EEG)-based Brain Computer Interfaces (BCI) devices. Research in emotion recognition using these tools is a rapidly growing field with multiple inter-disciplinary applications. This article performs a survey of the pertinent scientific literature from 2015 to 2020. It presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective. Our survey gives an overview of datasets, emotion elicitation methods, feature extraction and selection, classification algorithms, and performance evaluation. Lastly, we provide insights for future developments.

show abstract

Section: Eeg-based Bci Systems For Emotion Recognitionmentioning

confidence: 99%

“…Stepwise discriminant analysis SDA [ 74 ]. SDA is the extension of the statistical tool for discriminant analysis that includes the stepwise technique.…”

Section: Eeg-based Bci Systems For Emotion Recognitionmentioning

confidence: 99%

EEG-Based BCI Emotion Recognition: A Survey

Torres

Hernández-Álvarez

et al. 2020

Sensors

183

View full text Add to dashboard Cite

show abstract

“…Several factors are taken into consideration in generating the EEG dataset for emotion recognition, including [11]: a) Stimulus media: The literature studies showed several categories of stimuli to evoke emotions such as audio [16], [17], visual, and audio-visual media [14] as well as others including the ambient assisted living (AAL) technology [18], a combination of music, video, and game stimuli [19], mobile learning application [20], augmented reality (AR) [21], virtual reality (VR) [22], [23], and tactile enhanced multimedia (TEM) [24]. b) Proper stimuli presentation setup [11].…”

Section: Rq 1: What Factors Need To Be Considered To Generate and Distribute Eeg Data To Represent Emotional Reactions?mentioning

confidence: 99%

“…b) Frequency domain feature. This is based on the frequency domain of a signal, and several features have been reviewed in previous studies such as power spectral density (PSD) [62], band power using wavelet transform [59], [63], mel-frequency cepstral coefficients (MFCCs) technique [64], and differential entropy (DE) [14], [15], [40], [65], [66]. c) Time-frequency domain feature.…”

Section: Feature Extractionmentioning

confidence: 99%

“…There has been rapid development of research on EEG signals-based recognition over the past five years in terms of data acquisition, data preprocessing, feature extraction, feature representation, and classification process [2], [7]- [11]. The success of this study, however, is strongly influenced by: i) distribution of the data used [9], ii) consider of differences in participant characteristics, such as personality traits, intellectual abilities, and gender in emotion reaction [12], [13], and iii) consider the characteristics of the EEG signals such as having a low frequency and containing spatial information on emotion recognition [14], [15]. In response to these issues, the research presented here will examine three important points that affect the success of emotion recognition packaged in several research questions: i) what factors need to be considered to generate and distribute EEG data to represent emotional reactions?, ii) how can EEG signals be generated with consideration of differences in participant characteristics?, and iii) how do EEG signals with characteristics exist among its features for emotion recognition?…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The challenges of emotion recognition methods based on electroencephalogram signals: a literature review

Wirawan

Wardoyo

Lelono

2022

IJECE

View full text Add to dashboard Cite

Electroencephalogram (EEG) signals in recognizing emotions have several advantages. Still, the success of this study, however, is strongly influenced by: i) the distribution of the data used, ii) consider of differences in participant characteristics, and iii) consider the characteristics of the EEG signals. In response to these issues, this study will examine three important points that affect the success of emotion recognition packaged in several research questions: i) What factors need to be considered to generate and distribute EEG data?, ii) How can EEG signals be generated with consideration of differences in participant characteristics?, and iii) How do EEG signals with characteristics exist among its features for emotion recognition? The results, therefore, indicate some important challenges to be studied further in EEG signals-based emotion recognition research. These include i) determine robust methods for imbalanced EEG signals data, ii) determine the appropriate smoothing method to eliminate disturbances on the baseline signals, iii) determine the best baseline reduction methods to reduce the differences in the characteristics of the participants on the EEG signals, iv) determine the robust architecture of the capsule network method to overcome the loss of knowledge information and apply it in more diverse data set.

show abstract