Anzeige
Erschienen in:
2022 | OriginalPaper | Buchkapitel
Feature Extraction and Classification for Emotion Recognition Using Discrete Cosine Transform
verfasst von : Garima, Nidhi Goel, Neeru Rathee
Erschienen in: Artificial Intelligence and Speech Technology
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
In recent years, the rigorous development in tools and techniques for biomedical signal acquisition and processing has drawn interest of researchers towards EEG signal processing. Human emotion recognition using Electroencephalography (EEG) signals has proved to be a viable alternative as it cannot be easily imitated like the facial expressions or speech signals. In this research, authors have explored EEG signals for behavior analysis using Discrete Cosine Transform and classifying the signals using K-Nearest Neighbors. The algorithm is then evaluated on publically available DEAP Dataset. Experimental results are expressed in terms of F1 score, accuracy, precision and recall. The performance metrics evaluation for the classification of the emotional labels of DEAP dataset has further confirmed the effectiveness of the research. Comparison evaluation with the recent state-of-the-art methods further confirms the efficacy of the proposed work.