Page - 160 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments
Image of the Page - 160 -
Text of the Page - 160 -
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, âThe induced affect response: 10-week-old infantsâ
responses to three emotion expressionsâ, Developmental Psychology, vol. 23,
issue 1, 1987, pp. 97-104.
[2] Caron AJ, Caron RF, MacLean DJ, âInfant discrimination of naturalistic
emotional expressions: the role of face and voiceâ, 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, âDepressive symptoms in relation to physical
health and functioning in the elderlyâ, American Journal of Epidemiology, vol.
124, issue 3, Sep 1986, pp. 372â388.
[4] Peter Salmon, âEffects of physical exercise on anxiety, depression, and
sensitivity to stress: A unifying theoryâ, Clinical Psychology Review, vol. 21,
issue 1, Feb 2001, pp. 33-61.
[5] Daniela Girardi, Filippo Lanubile, Nicole Novielli, âEmotion Detection Using
Noninvasive Low Cost Sensorsâ, 2017 Seventh International Conference on
Affective Computing and Intelligent Interaction (ACII).
[6] Justin Dauwels, F Vialatte, Andrzej Cichocki, âDiagnosis of Alzheimer's
disease from EEG signals: where are we standing?â, Current Alzheimer
research, vol. 7, issue 6, Sep 2010.
[7] U. RajendraAcharya, H.Fujita, Vidya K.Sudarshan, ShreyaBhat, Joel
E.W.Koh, âApplication of entropies for automated diagnosis of epilepsy using
EEG signals: A reviewâ, Knowledge-Based Systems, vol. 88, Nov 2015, pp.
85-96.
Y.Tsurugasaki etal. / IdentiïŹcationofEffectiveEEGElectrodes
forDepressionSensing160
Intelligent Environments 2019
Workshop Proceedings of the 15th International Conference on Intelligent Environments
- Title
- Intelligent Environments 2019
- Subtitle
- Workshop Proceedings of the 15th International Conference on Intelligent Environments
- Authors
- Andrés Muñoz
- Sofia Ouhbi
- Wolfgang Minker
- Loubna Echabbi
- Miguel Navarro-CĂa
- Publisher
- IOS Press BV
- Date
- 2019
- Language
- German
- License
- CC BY-NC 4.0
- ISBN
- 978-1-61499-983-6
- Size
- 16.0 x 24.0 cm
- Pages
- 416
- Category
- TagungsbÀnde