Deep Learning Techniques for Stress Detection
Keywords:
An electroencephalogram (EEG), , a galvanic skin response (GSR), a pulse of blood volume (BVP), etc.Abstract
The Convolutional neural network (CNN) approach is utilised to recognise stress in this paper. Biosignals in the body of the
person are used to identify stress in this case. Physionet's ("drivedb") database was used to create this model (www.
Physionet.org). In today's world, stress is a major factor in the development of a wide range of disorders. In this case, stress may
be recognised by analysing the body's biosignatures. Bio signals include EDA, sequential minimum optimization (SMO), heart rate
visibility (HRV), galvanic skin reaction, and so on. Generally, we use these bio signals. QT and RR intervals may be extracted
from the ECG database. Improved performance is achieved by using CNN, which uses biosignals to classify stress in the input
data.
