Recognition of two emotional states of joy and sadness using phase lag index and SVM classifier

Tabanfar, Zahra; Yousefipoor, Farzaneh; Firoozabadi, Mohammad; Khodakarami, Zeynab; Shankayi, Zeinab

doi:10.1109/icbme.2016.7890981

Cited by 4 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The brain contains specific areas that are linked to emotional activity [ 13 ], and EEG-based connectivity analysis has allowed researchers to better understand how the human brain processes emotions. Additionally, it is believed that functional brain networks represent the intrinsic activity of the brain, which may provide important details regarding the communication between various brain areas [ 14 , 15 , 16 , 17 ]. Different emotional states may correspond to different networks created from the EEG signals gathered during emotion evocation, which is useful for researchers to study the information exchange mechanisms of the brain during the processing of emotional activities and the variations in brain interaction patterns under different emotions.…”

Section: Introductionmentioning

confidence: 99%

Emotional Brain Network Community Division Study Based on an Improved Immunogenetic Algorithm

et al. 2022

View full text Add to dashboard Cite

Emotion analysis has emerged as one of the most prominent study areas in the field of Brain Computer Interface (BCI) due to the critical role that the human brain plays in the creation of human emotions. In this study, a Multi-objective Immunogenetic Community Division Algorithm Based on Memetic Framework (MFMICD) was suggested to study different emotions from the perspective of brain networks. To improve convergence and accuracy, MFMICD incorporates the unique immunity operator based on the traditional genetic algorithm and combines it with the taboo search algorithm. Based on this approach, we examined how the structure of people’s brain networks alters in response to different emotions using the electroencephalographic emotion database. The findings revealed that, in positive emotional states, more brain regions are engaged in emotion dominance, the information exchange between local modules is more frequent, and various emotions cause more varied patterns of brain area interactions than in negative brain states. A brief analysis of the connections between different emotions and brain regions shows that MFMICD is reliable in dividing emotional brain functional networks into communities.

show abstract

Section: Introductionmentioning

confidence: 99%

Emotional Brain Network Community Division Study Based on an Improved Immunogenetic Algorithm

et al. 2022

View full text Add to dashboard Cite

show abstract

A Survey on Feature Extraction Methods for EEG Based Emotion Recognition

Phadikar

Sinha

Ghosh

2020

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

Analysis of EEG Fluctuation Patterns Using Nonlinear Phase-Based Functional Connectivity Measures for Emotion Recognition

Kumar,

Ganapathy,

D. Puthankattil

et al. 2024

Fluct. Noise Lett.

View full text Add to dashboard Cite

Automated emotion recognition is crucial in identifying and monitoring psychological disorders. Although several electroencephalography (EEG)-based methods have been explored for emotion recognition, capturing the subtle oscillations within EEG signals associated with distinct emotional states remains a persistent challenge. Nonlinear phase-based functional connectivity (FC) can capture the intricate time-varying patterns of brain activity during the processing of emotions. In this work, an attempt has been made to characterize the EEG-based emotional states using nonlinear phase-based FC techniques. For this, the EEG signals are obtained from the publicly available DEAP database and decomposed into four frequency bands: Theta (4–7[Formula: see text]Hz), alpha (8–12[Formula: see text]Hz), beta (13–30[Formula: see text]Hz) and gamma (30–45[Formula: see text]Hz). Three nonlinear phase-based FC measures, namely phase lag index (PLI), phase locking value (PLV) and Rho index, are extracted from individual frequency bands. Two types of features, namely network features and FC indices, are fed to three classifiers, namely random forest (RF), extreme gradient boosting (XGB) and K-Nearest Neighbors (KNN). The results reveal that the proposed approach can capture EEG dynamics to characterize emotional states. The gamma band-based Rho index demonstrated prominence in discriminating arousal and valence emotional states. The utilization of the Rho index-based FC feature effectively reveals interactions among cortical brain regions in response to audio-visual stimuli. Thus, the proposed approach could be extended to classifying various emotional states in clinical settings.

show abstract

Recognition of two emotional states of joy and sadness using phase lag index and SVM classifier

Cited by 4 publications

References 10 publications

Emotional Brain Network Community Division Study Based on an Improved Immunogenetic Algorithm

Emotional Brain Network Community Division Study Based on an Improved Immunogenetic Algorithm

A Survey on Feature Extraction Methods for EEG Based Emotion Recognition

Analysis of EEG Fluctuation Patterns Using Nonlinear Phase-Based Functional Connectivity Measures for Emotion Recognition

Contact Info

Product

Resources

About