Enhanced emotion recognition in an IoMT platform: leveraging data augmentation and the random forest algorithm for ECG-based E-health

Advancement of technologies has enabled the creation of smart solutions to improve healthcare. The primary objective is to help healthcare practitioners make efficient and fast decisions and diagnoses. Vital signs provide meaningful information while monitoring patient health, which allows assessing patients’ emotional well-being and adjust therapy. This study introduces an AI-powered patient monitoring system and healthcare platform. The proposed healthcare platform uses Internet of Medical Things (IoMT) and machine learning to monitor and classify emotional states using ECG signals. Thus, a label transformation and Random Forest classifier are used to identify patient emotions as positive or negative based on selected features from Heart Rate Variability (HRV) provided by ECG sensor. Moreover, a data augmentation technique is used to expand the primary used dataset, DREAMER which is afterward integrated with SWELL and WESAD datasets to increase data variety. The model presents emotion identification on the platform with an accuracy of 99.89%, outperforming most existing related works.