سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / سومین کنفرانس بین المللی مهندسی و علوم کامپیوتر و اولین کنفرانس ملی سامانه های هوشمند، کلان داده و رایانش پیشرفته

PSO Fuzzy XGBoost Classifier Boosted with Neural Gas Features on EEG Signals in Emotion Recognition

نویسندگان :

S. Muhammad Hossein Mousavi¹

1- شرکت تحقیقات هوشمند کوروش

کلمات کلیدی :

EEG emotion recognition،Machine learning،XGBoost،Particle Swarm Optimization،Fuzzy logic،Neural Gas Network،Feature representation

چکیده :

Emotion recognition based on electroencephalogram (EEG) signals remains a challenging task due to the high dimensionality, nonlinearity, and uncertainty inherent in physiological data. To address these challenges, this paper proposes a hybrid machine learning framework that integrates Neural Gas Network (NGN)–based feature representation with an enhanced XGBoost classifier optimized using Particle Swarm Optimization (PSO) and fuzzy logic. NGN is employed to extract topology-preserving representations from EEG signals, while fuzzy logic enables soft decision boundaries to better handle ambiguity in emotional patterns. PSO is used to optimize key hyperparameters of the XGBoost model, improving classification performance. The proposed method is evaluated on a publicly available EEG emotion dataset and compared with several conventional classifiers and feature selection techniques. Experimental results demonstrate that the proposed PSO-Fuzzy-XGBoost model, combined with NGN features, achieves superior performance compared to baseline machine learning approaches and competitive results with respect to reported state-of-the-art methods. These findings highlight the effectiveness of combining feature representation, optimization, and fuzzy reasoning for EEG-based emotion recognition.