Leveraging Tripartite Tier Convolutional Neural Network for Human Emotion Recognition: A Multimodal Data Approach

In the recent past, significant strides have been made in the field of deep learning and data fusion, enabling computers to comprehend, identify, and analyse human emotions with remarkable precision. However, reliance on external biological features for emotion recognition can be misleading, as individuals may consciously or unconsciously mask their true emotions. Consequently, an objective and reliable approach is sought, one that draws on physiological markers for emotion recognition. This paper introduces a novel model, the Tripartite Tier Convolutional Neural Network (TTCNN), specifically designed to leverage deep learning methods for the extraction and classification of significant features in multimodal emotion recognition. Amongst various physiological features, this study prioritizes eye movement and Electroencephalogram (EEG) data due to their robust potential to reflect emotional states. The multimodal data-based feature extraction facilitated by the TTCNN model yields a comprehensive set of features, enhancing the effectiveness of emotion classification into categories such as disgust, fear, sadness, happiness, and neutrality. This innovative cognitive approach has been evaluated using two established datasets, SEED and DEAP. The performance of the TTCNN model demonstrates its efficacy, achieving an impressive 95.84% classification accuracy on the SEED dataset and 87.01% on the DEAP dataset. These results significantly outperform existing state-of-the-art methods, underscoring the TTCNN model's potential as a robust tool for human emotion recognition. This research contributes to the advancement of computer-aided emotion analysis, presenting a significant step forward in the field and opening up potential applications in diverse areas such as psychology, healthcare, and human-computer interaction.