Diagnosis and biofeedback system for stress

Today everyday life for many people contain many situations that may trigger stress, or result in an individual living on an increased stress level under long duration. High level of stress over time may cause serious health problems. It is known that respiratory rate in terms of hyperventilation (defined as low pCO₂) is an important factor and can be used in the diagnosis of stress-related dysfunctions. It can also be used for biofeedback training but available measurement of respiratory rate and its metabolic consequences are not especially suitable for home and office use. The aim of this project is to develop a portable sensor system that can measure stress level during everyday situations e.g. at home or at work. The sensor explored here is a finger temperature (FT) sensor. FT reflects changes in sympathetic nervous system (SNS) and not hyperventilation, as SNS is an important marker of stress it is highly relevant. Clinical studies show that finger temperature, in general, decreases with stress however this changed pattern shows large individual variations. Consequently, diagnosis of stress from the FT measurements is difficult even for the clinical experts. Therefore, a computer-based stress diagnosis system is valuable. In this paper a case-based reasoning (CBR) stress management system is presented and evaluated. The results of the evaluation show a promising performance.