Emotion recognition to improve e-healthcare systems in smart cities

Abstract

The ability to detect and control patients’ pain is a fundamental objective within any medical service. Nowadays, the evaluation of pain in patients depends mainly on the continuous monitoring of the medical staff and, where applicable, on people from the immediate environment of the patient. However, the detection of pain becomes a priority situation when the patient is unable to express verbally his/her experience of pain, as is the case of patients under sedation or babies, among others. Therefore, it is necessary to provide alternative methods for its evaluation and detection. As a result, the implementation of a system capable of determining whether a person suffers pain at any level would mean an increase in the quality of life of patients, enabling a more personalized adaptation of palliative treatments. Among other elements, it is possible to consider facial expressions as a valid indicator of a person’s degree of pain. Consequently, this paper presents the design of a remote patient monitoring system that uses an automatic emotion detection system by means of image analysis. For this purpose, a system based on texture descriptors is used together with Support Vector Machines (SVM) for their classification. The results obtained with different databases provide accuracies around 90%, which proves the validity of our proposal. In this way, the e-health systems of a Smart City will be improved by introducing a system as the one proposed here.