An IoT-based Smart Emotion Recognition Using Internal Body Parameters

Emotion recognition using physiological signals has gained significant attention in recent years due to its potential applications in mental health monitoring, human-computer interaction, and stress management. This study focuses on recognizing six emotional states—neutral, happy, sad, fear, anger, and surprise—using internal body parameters such as blood pressure, oxygen saturation, blood glucose, heart rate, and body temperature. Leveraging an Internet of Things (IoT)-enabled framework, real-time data was collected from participants. The collected data underwent preprocessing, including data selection, data cleaning, normalization, and feature extraction, to enhance its quality and reliability. Various machine learning classifiers, including Decision Tree, Random Forest, Gradient Boost, Support Vector Machine, Multi-layer perceptron, and Logistic regression, were employed to classify emotions based on physiological features. Experimental results revealed that the Random Forest model achieved the highest accuracy (96.5%), outperforming other classifiers, followed by Decision Tree (94.2%). The IoT system was tested for real-time performance, achieving robust classification accuracy under varying network conditions. The findings indicate that physiological signals, combined with IoT and machine learning, provide an effective framework for emotion recognition. This research contributes to the development of real-time, non-invasive emotion recognition systems, with promising applications in healthcare, wearable devices, and personalized user experiences. Future work will explore the integration of additional physiological parameters and advanced deep-learning models for enhanced accuracy and scalability, and usage in advanced technology.