Stress Assessment Based on Decision Fusion of EEG and fNIRS Signals

• Main Authors: Al-Shargie, F., Tang, T.B., Kiguchi, M.
• Format: Article
• Published: Institute of Electrical and Electronics Engineers Inc. 2017
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85030634505&doi=10.1109%2fACCESS.2017.2754325&partnerID=40&md5=8f187f3d8b0e0df4305a465b1637a258; http://eprints.utp.edu.my/19358/

Fusion of electroencephalography (EEG) and functional near infrared spectroscopy (fNIRS) is an emerging approach in the field of psychological and neurological studies. We developed a decision fusion technique to combine the output probabilities of the EEG and fNIRS classifiers. The fusion explored support vector machine as classifier for each modality, and optimized the classifiers based on their receiver operating characteristic curve values. EEG and fNIRS signal were acquired simultaneously while performing mental arithmetic task under control and stress conditions. Experiment results from 20 subjects demonstrated significant improvement in the detection rate of mental stress by +7.76 ( p<0.001) and +10.57 ( p<0.0005), compared with sole modality of EEG and fNIRS, respectively. © 2013 IEEE.