Psikhologicheskie Issledovaniya • ISSN 2075-7999
peer-reviewed • open access journal
      

 

Slavutskaya E.V., Slavutskii L.A. Using artificial neural networks for analysis of gender differences in younger teenagers

Full text in Russian: Славутская Е.В., Славутский Л.А. Использование искусственных нейронных сетей для анализа гендерных различий младших подростков
Chuvash State Pedagogical University, Cheboksary, Russia
Chuvash State University, Cheboksary, Russia

About authors
Suggested citation


Using of neural networks for psychodiagnostic data processing is proposed. The main features of the proposed algorithm are its visibility and highest definiteness in process of training and neural networks using. For this purpose, the structure of neural networks is rigidly connected with initial analyzed data, and training is achieved by their use. Thus a simple feedforward backpropagation network is built. The networks training and testing are carried out by the example of younger teenager's psychodiagnostic data (a total of 111 schoolchildren). It is shown that the proposed algorithm allows to identify psychological traits that are important to assess gender differences efficiently.

Keywords: neural network, psychodiagnostics, testing, gender differences

 




Fig. 1.
Example of data and the neural network structure.
Note. IQ – Intelligence quotient; Personality qualities by R.B. Cattell: A – gregariousness–isolation; B – abstract–concrete thinking; C – emotional stability – instability; D – excitement–balance; E – independence–obedience; F – carefree–concern; G – high–low discipline; H – boldness-shyness; I – softness–hardness; O – anxiety–calmness; Q3 – high–low self-control; Q4 – tension–relaxation.




Fig. 2. Training of the neural network, including IQ.
Note. The dependence of the errors Δ on the number of training cycles N: 1 – all children (670 cycles), 2 – K1 group (1147 cycles), 3 – E group (2109 cycles), 4 – K2 group (357 cycles).




Fig. 3. Training of the neural network, including IQ after the normalization of input data.
Note. The dependence of errors on the number of training cycles: 1 – all children (24 cycles), 2 – K1 group (22 cycles), 3 – E group (26 cycles), 4 – K2 group (23 cycles).




Fig. 4. The number of errors in determining of the gender of the subjects with sequential zeroing of input features.
Note. 1 – for all children, 2 – K1 group, 3 – E group, 4 – K2 group.


References
Cyrillic letters are transliterated according to BSI standards.

Arzamastsev A.A., Zenkova N.A. Modelirovanie v psikhologii na osnove iskusstvennykh neironnykh setei. Tambov: IMPI TSU, 2003. (in Russian)

Borovikov V.P. Neironnye seti. Moscow: Goryachaya linia – Telecom, 2008. (in Russian)

Baxt W.G. Complexity, chaos and human physiology: the justification for non-linear neural computational analysis. Cancer Letters, 1994, 2–3(77), 85–93.

Cattell R.B. Advanced in Cattelian personality theory. Handbook of personality. Theory and research. New York: The Guilford Press, 1990.

Dorrer M.G., Gorban A.N., Kopytov A.G. Zenkin V.I. Psychological intuition of neural networks. In: Proceedings of the World Congress on Neural Networks’95, Washington DC, 1995. pp. 193–196.

Grossberg S. Classical and instrumental learning by neural networks: Progress in theoretical biology. New York: Academic Press, 1974. Vol. 3, pp. 51–141.

Haykin S. Neural networks: A comprehensive foundation. New York: Prentice Hall, 1999.

Hebb D. Organization of behavior. New York: Science Edition, 1961.

Medvedev V.S. Neironnye seti. MATLAB 6. Moscow: Dialog-MIFI, 2002. (in Russian)

Polivanova K.N. Psikhologia vozrastnikh krizisov. Moscow: Academiya, 2000. (in Russian)

Rosenblatt R. Principles of neurodynamics. New York: Spartan Books, 1959.

Slavutskaya E.V. Psihologia obychenia, 2008, No. 12, 103–112. (in Russian)

Slavutskaya E.V. Vestnik Tomskogo gosudarstvennogo pedagogicheskogo universiteta, 2009, 9(87), 127–129. (in Russian)

Slavutskaya E.V. Izvestia Saratovskogo universiteta. Ser.: Filosofia. Pedagogica. Psihologia, 2011, 2(11), 76–81. (in Russian)

Velichkovskii B.M. Kognitivnaya nayka. Moscow: Academiya, 2006. (in Russian)

Received 5 October 2011. Date of publication: 29 June 2012.

About authors

Slavutskaya Elena V. Ph.D. (Psychology), Associated Professor, Chuvash State Pedagogical University, ul. K.Marksa, 38, 428000 Cheboksary, Russia.
E-mail: Этот адрес электронной почты защищен от спам-ботов. У вас должен быть включен JavaScript для просмотра.

Slavutskii Leonid A. Ph.D. (Physics and Mathematical Sciences), Professor, Chuvash State University, Moskovskii prospekt, 15, 428015 Cheboksary, Russia.
E-mail: Этот адрес электронной почты защищен от спам-ботов. У вас должен быть включен JavaScript для просмотра.

Suggested citation

Slavutskaya E.V., Slavutskiy L. A. Using artificial neural networks for analysis of gender differences in younger teenagers. Psikhologicheskie Issledovaniya, 2012, Vol. 5, No. 23, p. 4. http://psystudy.ru (in Russian, abstr. in English).

Permanent URL: http://psystudy.ru/index.php/eng/2012v5n23e/696-slavutskaya23e.html

Back to top >>

Related Articles