A voting ensemble classifier for stress detection
Sami Hadhri, Mondher Hadiji, Walid Labidi
Abstract
This paper presents a Machine Learning and IoT-based intelligent medical system for the detection and monitoring of patient stress. This system is made up of a medical kit measuring the oxygen saturation, the heart rate and the galvanic skin response thanks to sensors attached at the top of the patient’s hand which send the measured physiological values to the Firebase server. A voting classifier, combining five Machine Learning algorithms (Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree and Random Forest) using holdout and K-fold cross-validation, was implemented on a Raspberry board installed in the doctor’s office. The proposed system can make predictions with the Soft Voting classifier with an accuracy that reaches 78%.