Page - 160 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

In addition, it is necessary to consider the individual difference in the electroencephalogram. Even if the subjects are the same person, the data that can be acquired changes due to the good contacts when attaching the EEG and the large number of gels. In order to solve these problems, it is considered necessary to convert to absorb problems such as individual differences before analyzing data. Even after feature quantity creation, it is necessary to group feature quantities for each electrode site and investigate the contribution to depression. As a problem in this research, for each objective variable called D, each feature quantity is treated as an independent explanatory variable without grouping for each electrode site. There is also a method by which explanatory variables are grouped like Group Lasso and variables can be selected. In the future, we would like to take into account the use of a method of checking the contribution degree to the objective variables collectively for each electrode site. In order to confirm the relationship, we want to conduct experiments on the assumption that the number of electrodes is 6 or more. We also want to compare the results of random feature selection. In the multiple regression analysis used in the evaluation, there is a problem that as the explanatory variable increases, the multiple correlation coefficient and the determination coefficient become larger. Further, similar signals are acquired from the electrode portions of the electroencephalogram data. It is necessary to be aware that if there is a high correlation between explanatory variables, the multiple collinearity problem may cause correct results in multiple regression analysis. References [1] Haviland JM, Lelwica M, “The induced affect response: 10-week-old infants’ responses to three emotion expressions”, Developmental Psychology, vol. 23, issue 1, 1987, pp. 97-104. [2] Caron AJ, Caron RF, MacLean DJ, “Infant discrimination of naturalistic emotional expressions: the role of face and voice”, Society for Research in Child Development, vol. 59, issue 3, Jun 1988, pp. 604-616. [3] Berkman LF, Berkman CS, Kasl S, Freeman DH Jr, Leo L, Ostfeld AM, Cornoni-Huntley J, Brody JA, “Depressive symptoms in relation to physical health and functioning in the elderly”, American Journal of Epidemiology, vol. 124, issue 3, Sep 1986, pp. 372–388. [4] Peter Salmon, “Effects of physical exercise on anxiety, depression, and sensitivity to stress: A unifying theory”, Clinical Psychology Review, vol. 21, issue 1, Feb 2001, pp. 33-61. [5] Daniela Girardi, Filippo Lanubile, Nicole Novielli, “Emotion Detection Using Noninvasive Low Cost Sensors”, 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII). [6] Justin Dauwels, F Vialatte, Andrzej Cichocki, “Diagnosis of Alzheimer's disease from EEG signals: where are we standing?”, Current Alzheimer research, vol. 7, issue 6, Sep 2010. [7] U. RajendraAcharya, H.Fujita, Vidya K.Sudarshan, ShreyaBhat, Joel E.W.Koh, “Application of entropies for automated diagnosis of epilepsy using EEG signals: A review”, Knowledge-Based Systems, vol. 88, Nov 2015, pp. 85-96. Y.Tsurugasaki etal. / IdentificationofEffectiveEEGElectrodes forDepressionSensing160