Irrespective of internal or external factors when a person feels excessive pressure it reflects in his facial expression, speech and physiological behaviour signals. Instead of traditional questioner method of stress evaluation, researchers now a day’s take various audiovisual and bio-signals, like heartbeat rate, muscle activity, blood pressure (BP) and skin conductivity. Electroencephalogram (EEG), Electrocardiogram (ECG), Electromyogram (EMG), Respiration (RSP) and Skin Conductivity (SC) are highly used bio-sensors for capturing bio signals. ECG signal gives heart-beat rate, inter-beat interval, and heart rate variability (HRV). EMG sensor when fit at upper trapezius gives the reading of muscle contraction which may be correlated with emotional state. SC sensors provide conductance and resistance of the skin which can also be used as a feature of importance. A wide range of physiological features from various analysis domains, including time/frequency, entropy, geometric analysis, sub-band spectra, multi-scale entropy, etc. along with audiovisual feature, got research attention in the process to find the best stress-relevant features and to correlate them with stress level. This article makes a detailed discussion of effectiveness of various bio signals for stress level and emotional state detection.

Bio signals, cognitive computing, automated emotion detection

[1]. R. Dhatchayini and K. Mohamed Amanullah, “Brain Tumor Detection Using Clustering Method”, International Journal of Computer Sciences and Engineering, september 2018.
[2]. M.U Nagaral1 and T. H. Reddy, “Predicting the Characteristics of a Human from Facial Features by Using SURF”, International Journal of Computer Sciences and Engineering, September 2018.
[3]. R. Zimmermann, L.M.Crespo, J.Edelmann, O. Lambercy, M.C. Fluet, R. Riener, M.Wolf and R.Gassert, “Detection of motor execution using a hybrid fNIRS-biosignal BCI: a feasibility study”, Journal of NeuroEngineering and Rehabilitation, vol: 10(4), 2013.
[4]. J.A. Healey and R.W. Picard, “Detecting Stress during Real-World Driving Tasks using Physiological Sensors”, IEEE Transactions on Intelligent Transportation Systems, 2005.
[5]. S. Sager, D. Borth, B. Elizalde, C. Schulze, B. Raj, and I.Lane, and A. Dengel, “AudioSentibank: Large-scale Semantic Ontology of Acoustic Concepts for Audio Content Analysis”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, July 2016.
[6]. F. Al-Shargie, M. Kiguchi,N. Badruddin, S.C. Dass,A.F. M.Hani and T. B. Tang, “Mental stress assessment using simultaneous measurement of EEG and fNIRS”, Biomedical Optics Express, October 2016 .
[7]. J. Chu, I.Moon, and M.Mun, “A Real-Time EMG Pattern Recognition System Based on Linear-Nonlinear Feature Projection for a Multifunction Myoelectric Hand”, IEEE Transactions on Biomedical Engineering, Nov ember 2006.
[8]. J. Kim and E. Andre, “Emotion Recognition Based on Physiological Changes in Music Listening”, IEEE Transactions On Pattern Analysis and Machine Intelligence, December 2008.
[9]. K.ConnWelch,U. Lahiri, Z.Warren and N. Sarkar, “An Approach to the Design of Socially Acceptable Robots for Children with Autism Spectrum Disorders”, INT J SOC ROBOT ,2010.
[10]. A. Dutta, U. Lahiri , A.Das, M.A. Nitsche and D.Guiraud, “Post-stroke balance rehabilitation under multi-levelelectro therapy: a conceptual review”, Frontiers in neuroscience , December 2014.
[11]. A. Panat and A.Patil, “Analysis of emotion disorders based on EEG signals of Human Brain”, International Journal of Computer Science, Engineering and Applications, August 2012.
[12]. R. Agarwal and J.Gotman, “Computer-Assisted Sleep Staging”, IEEE Transactions on Biomedical Engineering, December 2001.