ISSN: 0975-766X CODEN: IJPTFI Available Online through Research Article www.ijptonline.com EMOTIONAL STATE ASSESSMENT: VALENCE AND AROUSAL EVALUATION VIA EEG ANALYSIS M. Sundar Raj 1, K. Adalarasu* 2, M. Jagannath 3 and Vinodhini 1 1 Department of Biomedical Engineering, Bharath University, Chennai, Tamilnadu, India. 2 Department of ECE, PSNA College of Engineering & Technology, Dindigul, Tamilnadu, India. 3 School of Electronics Engineering, VIT University, Chennai, Tamilnadu, India. Email: adalarasu@psnacet.edu.in Received on 28-07-2016 Accepted on 01-09-2016 Abstract Emotions plays an important role in human beings day-to-day life. Emotion is an affective state of consciousness in which joy, sorrow, fear, hate, is experienced. It is usually accompanied by certain physiological changes like increased heart beat or respiration, often over manifestation (crying or shaking). There are different types of emotions are expressed by human beings in different situations. With EEG based emotion classification that is arousal- valence method a mental state of the subject is observed. By giving different mental and physical task to the person EEG is taken. The different emotional conditions are obtained by EEG waveform. EEG is taken by using RMS maximums 24 EEG machine. EEG acquire software is used to obtain the different waveforms. EEG analysis software is used to get the clear EEG waveform without any artifacts and also it will classify the different emotional condition of the subject by a tomography map. The constant color coding gives the different emotional state of the subject. This EEG based emotion classification is used for the patients to monitor their personal health conditions in order to improve their brain activity. Keywords: Emotions, arousal-valence model, RMS EEG machine, Tomography map. Introduction Stress and emotions are complex phenomena that play an important role in the quality of human life. Emotion plays a major role in motivation, cognition, creativity, attention, learning and decision making. Although several methods for the brain function analysis such as magneto encephalography (MEG), functional magnetic resonance imaging (FMRI) and positron emission tomography (PET) have been introduced, the EEG signal is still a valuable tool for monitoring the brain activity due to its relatively low cost and being convenient for the patient [1,11]. The brain is made up of 3 main parts: fore brain, mid brain and hind brain. There are about 150 million neurons are present in our IJPT Sep-2016 Vol. 8 Issue No.3 15712-15716 Page 15712
body. These neurons are responsible for the transmission of signals from one cell to another this is called as action potential. Through spinal cord the signals are transmitted. There are four different types of brain waves: alpha wave, beta wave, theta wave, delta wave. The normal range of brain waves is around 50 Hz. The cerebrum or cortex is the largest part of the human brain. It has four different lobes frontal, parietal, temporal, occipital. The electrodes are placed in these lobes for recording EEG waveforms. A. Emotional classification Emotion classifications are depends on how well the EEG features can be mapped onto chosen emotion representation. The emotion representation used is the two dimensional mapping with valence and arousal axes (Fig- 1). Valence: positive, happy emotions result in a higher frontal coherence in alpha, and higher right parietal beta power, compared to negative emotion. Arousal: excitation presented a higher beta power and coherence in the parietal lobe, plus lower alpha activity. Dominance: strength of an emotion, which is generally expressed in the EEG as an increase in the beta / alpha activity ratio in the frontal lobe, plus an increase in beta activity at the parietal lobe. Materials and Methods Fig 1- Arousal-Valence Model. Hardware: RMS maximums 24 EEG machine. Software: EEG acquiring and analysis software. A. RMS maximums 24 EEG machine: For data acquisition the RMS machine is used (Fig 2). The RMS EEG 24 channel 9 electrode EEG machine, provides a panel for connection of electrodes, all the electrodes are having individual wires which are metal plated which is to be placed on the scalp. Fig-2: RMS maximums machine. IJPT Sep-2016 Vol. 8 Issue No.3 15712-15716 Page 15713
b. Acquire software: K. Adalarasu*et al. /International Journal of Pharmacy & Technology The software is used to acquire the recordings of the subject, to start with the detail history of the concern subject is taken like name, gender, age, medical history if any, physically handicap and so on. Then impedance is checked, these shows the voltage of every electrode and whether it s placed on proper place. Then we start with proper EEG, the machine provides a record button which starts recording EEG, it also provides a stop button which can be used when the entire task are completed[8]. C. Analysis Software: The software only opens the file with EEG extension and which are saved in acquire software. There are different tools provided by the software like split screen, single map, tri map, frequency map, frequency spectrum, amplitude progressive, frequency progressive and frequency table, for frequency domain analysis the software provides 2 sec data, from which every frequency domain tool can be used, on the other hand the software gives a tool called Amplitude Progressive which provides 12 amplitude maps at consecutive time difference of 7.8125 ms, for this research work this tool have been taken into consideration[8]. Methodology For this project, the subjects were selected from the department of IBT, IT, and CSE, Bharath University, Chennai. For experimental purpose 10 samples (5 males and 5 females) were considered. The health conditions of the selected samples are healthy. We informed about the purpose of our project. The samples were selected from the group age of 18-22. On first, the EEG waveforms are obtained with a normal rest state of the subject. The subjects are asked to sit in their comfortable position. The electrodes are placed in the scalp region of the brain on the temporal and frontal region with the help of the 10-20 electrode gel. The other end of the electrodes are connected to the RMS machine in the following positions- M2, T7, C4, CZ, FZ, PZ, C3, T8, and M1 (P-parietal region, T-temporal region, C-central region, F-frontal region). Where M1 and M2 are reference electrodes (Fig-3). Fig 3- Electrode placement. IJPT Sep-2016 Vol. 8 Issue No.3 15712-15716 Page 15714
Using acquiring software the information of the sample is stored such as name, age, gender, medical history of any physically handicap and so on. At last the EEG waveform of the sample is obtained. Then by the use of analysis software the unwanted artifacts are removed also feature extraction preprocessing segmentation are done using analysis software. a. Tomography Map: The tomography map is useful to classify different emotional state of the subject. Since it play an important role in human beings. Each color denotes different emotional condition. The color coding is given below (Fig-4). Fig-4. Color coding for emotions. Result The emotional states of the subjects are obtained by using EEG analysis and acquire software along with RMS maximums machine. The emotional state of the subject is classified with the use tomography map (Fig-5). Fig-5. Tomography Map. By this tomography map emotional conditions are easily classified to the subjects. Conclusion Since emotion plays an important role in human beings our projects describes how the emotions are classified by the use of Arousal -Valence method. This method is very simple and emotions are easily classified. To get an EEG waveform accurately positioning of electrode is very much important. Since there is very high individual difference in representation of emotions, participants should be analyzed individually. We Conclude that future experiments with a large number of participants (e.g., N = 100) are needed to further understand the degree of individual IJPT Sep-2016 Vol. 8 Issue No.3 15712-15716 Page 15715
difference, seperability of emotion-classes and to finally understand the emotion specific EEG patterns that underlie the mental states. References 1. Xiao- Wei Wang, Emotional state classification from EEG data using machine learning approach, 96-104 (2014). 2. Bos., D.O.: EEG-based emotion recognition [online](2014) 3. Seyyed Abed Hosseini and Mohammad Bagher Naghibi-Sistani (2012). Classification of Emotional Stress Using Brain Activity, Applied Biomedical Engineering, Dr. Gaetano Gargiulo (Ed.), ISBN:978-953-307-256-2,InTech. 4. M. U. Ahmed and D.P. Mandic, Multivariate Multiscale Entropy Analysis, IEEE Signal Processing Letters, 19 (2012), 91-94. 5. Mauss, I.B., Robinson, M.D., Measures of emotion: A review. Cognition and Emotion, 23(2), 209 237 (2011). 6. M. U. Ahmed and D. P. Mandic, Multivariate multiscale entropy: A tool for complexity analysis of multichannel data, Physical Review, 84, (2011), 061918-1 061918-10. 7. S. Begum, M.U. Ahmed, P. Funk, N. Xiong, M. Folke, Case-Based Reasoning Systems in the Health Sciences: A Survey on Recent Trends and Developments, International journal of IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews, vol 41, Issue 4, (2011), pp 421-434. 8. N. Sulaiman, M.N. Taib, S. A. M. Aris, A.H.A. Hamid, S. Lias and Z.H. Murat, Stress features identification from EEG signals using EEG asymmetry and spectral centroids techniques. EMBS Conference on Biomedical Engineering and Sciences. (2010). 9. S. Ilan and Z. Inna, Multichannel analysis of EEG signal applied to sleep stage classification. Recent Advances in Biomedical Engineering, Intechopen, ISBN 978-953-307-004-9, October 1, (2009). 10. S. Begum, M.U. Ahmed, P. Funk, N. Xiong and B.V. Schéele, A case-based decision support system for individual stress diagnosis using fuzzy similarity matching, Computational Intelligence, Blackwell Publishing, Volume 25, Nr 3, pp 180-195, (2009). 11. Balasubramanian, V., Jagannath, M. and Adalarasu K., EEG based evaluation of viewer s response towards TV commercials, International Journal of Industrial and Systems Engineering, Vol. 13, No. 4, 2013, pp. 480 495. Corresponding Author: Dr. K. Adalarasu*, Email: adalarasu@psnacet.edu.in IJPT Sep-2016 Vol. 8 Issue No.3 15712-15716 Page 15716