Real-Time Classification of Anxiety in Virtual Reality Therapy Using Biosensors and a Convolutional Neural Network

Abstract

Virtual Reality Exposure Therapy is a method of cognitive behavioural therapy that aids in the treatment of anxiety disorders by making therapy practical and cost-efficient. It also allows for the seamless tailoring of the therapy by using objective, continuous feedback. This feedback can be obtained using biosensors to collect physiological information such as heart rate, electrodermal activity and frontal brain activity. As part of developing our objective feedback framework, we developed a Virtual Reality adaptation of the well-established emotional Stroop Colour–Word Task. We used this adaptation to differentiate three distinct levels of anxiety: no anxiety, mild anxiety and severe anxiety. We tested our environment on twenty-nine participants between the ages of eighteen and sixty-five. After analysing and validating this environment, we used it to create a dataset for further machine-learning classification of the assigned anxiety levels. To apply this information in real-time, all of our information was processed within Virtual Reality. Our Convolutional Neural Network was able to differentiate the anxiety levels with a 75% accuracy using leave-one-out cross-validation. This shows that our system can accurately differentiate between different anxiety levels.