Effectiveness of Statistical Features for Human Emotions Classification using  EEG Biosensors

Chai, Tong-Yuen; San, Woo San; Ho, Jee-Hou; Rizon, M.

doi:10.19026/rjaset.5.4401

Cited by 12 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the capability of the brain to perform sophisticated emotional tasks and to investigate the complex dynamic information that is reflected from the brain cortex, several researchers have used non-linear methods for automatic detection of emotions through EEG signals [57]. Previous emotion studies have used a small number of features, mostly relative powers [3], Hurst [15], Hjorth parameters [58], Fractal Dimension (FD) [59], and statistical features [60,61]. Moreover, entropy has been considered as the most prevalent methods to evaluate the presence or absence of long-range dependence on physiological signal analysis including approximate entropy (ApEn), sample entropy (SampEn) and permutation entropy (PerEn) which are relatively robust to noise and powerful enough to quantify the complexity of a time series [62].…”

Section: Introductionmentioning

confidence: 99%

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Al-Qazzaz

Sabir

Ali

et al. 2019

Sensors

View full text Add to dashboard Cite

Identifying emotions has become essential for comprehending varied human behavior during our daily lives. The electroencephalogram (EEG) has been adopted for eliciting information in terms of waveform distribution over the scalp. The rationale behind this work is twofold. First, it aims to propose spectral, entropy and temporal biomarkers for emotion identification. Second, it aims to integrate the spectral, entropy and temporal biomarkers as a means of developing spectro-spatial ( S S ) , entropy-spatial ( E S ) and temporo-spatial ( T S ) emotional profiles over the brain regions. The EEGs of 40 healthy volunteer students from the University of Vienna were recorded while they viewed seven brief emotional video clips. Features using spectral analysis, entropy method and temporal feature were computed. Three stages of two-way analysis of variance (ANOVA) were undertaken so as to identify the emotional biomarkers and Pearson’s correlations were employed to determine the optimal explanatory profiles for emotional detection. The results evidence that the combination of applied spectral, entropy and temporal sets of features may provide and convey reliable biomarkers for identifying S S , E S and T S profiles relating to different emotional states over the brain areas. EEG biomarkers and profiles enable more comprehensive insights into various human behavior effects as an intervention on the brain.

show abstract

Section: Introductionmentioning

confidence: 99%

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Al-Qazzaz

Sabir

Ali

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Although various techniques have been implemented to extract features from EEG signals for emotion classification, including statistical features [1,2], Mel-frequency Cepstral coefficients [3,12], Kerneldensity Estimation [4], Gabor visual features [5] and CMAC-based Model of Affects [6], power spectral density [29] being the most fundamental technique for extracting features is still used [7][8][9][10][11].…”

Section: Related Workmentioning

confidence: 99%

“…Consequently, features as the input for the classification through supervised machine learning are extracted from the filtered signals. Different set of features has been experimented including statistical features [1,2], Mel-frequency Cepstral coefficients [3], Kerneldensity Estimation [4], Gabor visual features [5] and CMAC-based model of the effects [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Emotional profiling through supervised machine learning of interrupted EEG interpolation

Yaacob¹,

Omar²,

Handayani³

et al. 2019

IJACR

View full text Add to dashboard Cite

It has been reported that the construction of emotion profiling models using supervised machine learning involves data acquisition, signal pre-processing, feature extraction and classification. However, almost all papers do not address the issue of profiling emotion using supervised machine learning on the interrupted encephalogram (EEG) signals. Based on a preliminary study, emotion profiling on interrupted EEG signals produces low classification accuracy, using multilayer perceptron (MLP). Furthermore, lower emotion classification accuracy is produced from interrupted EEG signals with higher number of segments. Thus, the objective of this paper is to propose a technique and present the outcomes of handling interrupted EEG signals for emotion profiling. This is done by the suppression and interpolation of originally interrupted EEG signals at pre-process stage. As a result, emotion classification using MLP on interpolated data improves from 80.1% to 95%.

show abstract

“…Extensive research in the field of affective brain mapping has been published on characterising EEG variations during distinct emotion elicitations using Power Spectral Density (PSD) (Kawasaki et al, 2009;Chanel et al, 2011;Gandhi et al, 2011;Wang et al, 2011;Jatupaiboon et al, 2013), Common Spatial Patterns (CSP) (Li and Lu, 2009;Fattahi et al, 2013), Fast Fourier Transform (FFT) analysis (Yoon and Chung, 2013), entropy analysis (Hosseini, 2011;Khalilzadeh et al, 2010;Srinivasan et al, 2007), Higher Order Crossing (HOC) analysis (Petrantonakis and Hadjileontiadis, 2010a; Petrantonakis and Hadjileontiadis, 2010b), third-order spectral analysis (Hosseini et al, 2010;Hosseini, 2012) and statistical analysis (Takahashi and Tsukaguchi, 2004;Yuen et al, 2013) techniques. Current research findings reveal that PSD is an established technique for EEG signal analysis in the frequency domain (Dressler et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

Depression diagnosis and management using EEG-based affective brain mapping in real time

Mahajan

Bansal

2015

IJBET

View full text Add to dashboard Cite

Development of affective Brain-Computer Interfaces (BCIs) via Electroencephalogram (EEG) has emerged as a cynosure of research in early diagnosis and effective management of depression. However, conventional BCIs are still lacking in terms of high computational complexity, less accuracy due to Fourier phase suppression and lack of substantial conclusion for depression diagnosis. An automated, EEG-based depression diagnostic and management tool is proposed to overcome these limitations. Channel eventrelated potentials, cross-coherence and power spectra plots in MATLAB are quantified and studied as an outcome to map real-time, emotion-specific multichannel EEG data set into distinct emotional states. A fast and stable fourth-order statistics-based independent component analysis is incorporated to reject temporal/spatial artefacts. Increases in frontal alpha (8-13 Hz) and delta (0.5-4 Hz) power/coherence are during depressed and normal/relaxed states, respectively. Devotional music (relaxed state) is found to facilitate depression elimination. Results are found to be statistically significant across all subjects with minimal p-values. Hence, it has been inferred that the proposed model has the potential to aid early and accurate depression diagnostic and management process.

show abstract

Effectiveness of Statistical Features for Human Emotions Classification using EEG Biosensors

Cited by 12 publications

References 28 publications

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Emotional profiling through supervised machine learning of interrupted EEG interpolation

Depression diagnosis and management using EEG-based affective brain mapping in real time

Contact Info

Product

Resources

About