Year: 2024
Type: conference-paper
Abstract: The objective of this study is to integrate and classify electroencephalogram (EEG), electrocardiogram (ECG), and galvanic skin response (GSR) signals from a participant exposed to emotional stimuli—happiness, anger, fear, and sadness. We used the LazyPredict library to identify the most effective classification model, leveraging its simplified implementation and wide range of models and performance metrics. The signals were processed in Python following a detailed workflow: (1) normalization, (2) band-pass filtering, (3) epoch extraction and selection, and (4) relative energy extraction using Discrete Wavelet Transform (DWT). After preprocessing, the data were input into LazyPredict, where the Extra Trees model consistently demonstrated the best performance for binary emotion classification. Our experience with LazyPredict proved to be practical and efficient, facilitating the exploration of high-performing models for emotion classification.
Institution: Universidade Federal do Rio Grande do Norte
Language: English
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4404597688