Adaptive HCI Systems with GRU-Based User Emotion Recognition and Response Prediction

Human-Computer Interaction (HCI) has evolved to incorporate sophisticated systems capable of recognizing and responding to user emotions, enhancing the user experience by making interactions more intuitive and engaging. This paper explores the development of adaptive HCI systems utilizing Gated Recurrent Unit (GRU) neural networks for emotion recognition and response prediction. The core objective is to create interfaces that dynamically adjust based on the user's emotional state, thereby improving usability and satisfaction across various applications, including healthcare, education, and customer service. GRU-based models are particularly effective for this task due to their ability to handle sequential data and capture temporal dependencies inherent in emotional expressions. By processing multimodal inputs such as facial expressions, voice intonations, text, and physiological signals, these systems can accurately detect and predict emotions in real-time. The DEAP dataset, which includes EEG and other physiological recordings along with self-assessed emotional ratings, serves as a foundational resource for training and validating these models. The proposed approach involves pre-processing the physiological data using techniques like min-max normalization to ensure consistency and stability during model training. The GRU models then learn to map these inputs to corresponding emotional states, leveraging their memory capabilities to retain and interpret temporal patterns. The adaptive nature of these systems enables them to provide personalized responses, such as adjusting the interface layout or offering support when negative emotions are detected. The implementation of GRU-based emotion recognition and response prediction in HCI systems holds significant potential for enhancing user interactions by making them more responsive and emotionally intelligent. This paper demonstrates the effectiveness of GRU models in real-time emotion monitoring and highlights their applications in creating more adaptive and empathetic technology interfaces. The proposed model is implemented in Python and has an accuracy of about 99.12% which is higher than other existing methods. Keywords: Human-Computer Interaction (HCI), Gated Recurrent Unit (GRU), Neural Networks, Emotional Detection.