Abstract
Existing research on stress recognition focuses on the extraction of physiological features and uses a classifier that is based on global optimization. There are still challenges relating to the differences in individual physiological signals for stress recognition, including dispersed distribution and sample imbalance. In this work, we proposed a framework for real-time stress recognition using peripheral physiological signals, which aimed to reduce the errors caused by individual differences and to improve the regressive performance of stress recognition. The proposed framework was presented as a transductive model based on transductive learning, which considered local learning as a virtue of the neighborhood knowledge of training examples. The degree of dispersion of the continuous labels in the y space was also one of the influencing factors of the transductive model. For prediction, we selected the epsilon-support vector regression (e-SVR) to construct the transductive model. The non-linear real-time features were extracted using a combination of wavelet packet decomposition and bi-spectrum analysis. The performance of the proposed approach was evaluated using the DEAP dataset and Stroop training. The results indicated the effectiveness of the transductive model, which had a better prediction performance compared to traditional methods. Furthermore, the real-time interactive experiment was conducted in field studies to explore the usability of the proposed framework.
Highlights
As a psychological–physiological process, stress is the direct reflection of the conscious or unconscious human object or situation [1,2]
Theorists found that stress was a negative valence, which meant that the stress state was comparable to the valence with a certain degree
Peripheral physiological signals-based stress recognition can promote the achievement of real-time stress recording using non-invasive wearable devices
Summary
As a psychological–physiological process, stress is the direct reflection of the conscious or unconscious human object or situation [1,2]. Physiological signals can better reflect the real-time stress state compared to facial expressions [3]. Stress recognition based on physiological signals allows researchers to directly assess the user’s internal state, making it a key element of the human-to-computer interaction. State-of-the-art sensor technology makes it possible to monitor various physiological signals to analyze human behavior, cognitive science, social psychology, and group perception [4,5,6]. Wearable sensor technology to monitor a specific person’s stress recognition can serve medical and mental health purposes [7], as well as the accompanying care services. Some physiological signals derived from wearable non-invasive devices, such as the galvanic skin response (GSR), respiratory rate, electromyography, and blood volume pulse (BVP)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
