Emotional states detection approaches based on physiological signals for healthcare applications: A review

Mood disorders, anxiety, depression, and stress affect people’s quality of life and increase the vulnerability to diseases and infections. Depression, e.g., can carry undesirable consequences such as death. Hence, emotional states detection approaches using wearable technology are gaining interest in the last few years. Emerging wearable devices allow monitoring different physiological signals in order to extract useful information about people’s health status and provide feedback about their health condition. Wearable applications include e.g., patient monitoring, stress detection, fitness monitoring, wellness monitoring, and assisted living for elderly people, to name a few. This increased interests in wearable applications have allowed the development of new approaches to assist people in everyday activities and emergencies that can be incorporated into the smart city concept. Accurate emotional state detection approaches will allow an effective assistance, thus improving people’s quality of life and well-being. With these issues in mind, this chapter discusses existing emotional states’ approaches using machine and/or deep learning techniques, the most commonly used physiological signals in these approaches, existing physiological databases for emotion recognition, and highlights challenges and future research directions in this field. © Springer Nature Switzerland AG 2020.

• Fecha de publicación: 2019
• Institución: Universidad de Medellín
• Repositorio: Repositorio UDEM
• Idioma: eng
• OAI Identifier: oai:repository.udem.edu.co:11407/6071
• Acceso en línea: http://hdl.handle.net/11407/6071
• Palabra clave: Affective recognition; Deep learning; Emotional states; Emotions; Machine learning; Physiological signals; Quality of life; Smart city; Well-being
• License: http://purl.org/coar/access_right/c_16ec