SciELO - Scientific Electronic Library Online

 
vol.15 issue1Data analysis techniques in observational studies in sport sciencesT-pattern analysis in soccer games: relationship between time and attack actions author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Cuadernos de Psicología del Deporte

On-line version ISSN 1989-5879Print version ISSN 1578-8423

Abstract

GONZALEZ-RUIZ, S.L.; GOMEZ-GALLEGO, I.; PASTRANA-BRINCONES, J.L.  and  HERNANDEZ-MENDO, A.. Classification algorithms and neural networks in automated observation records. CPD [online]. 2015, vol.15, n.1, pp.31-40. ISSN 1989-5879.  http://dx.doi.org/10.4321/S1578-84232015000100003.

The aim of this study is to analyse a set of data got through an on-line platform, using some ranking and knowledge oriented discovery rules techniques. Data mining techniques are applied to obtain a reliable relationship which can show the interest of the users in order to fill rigorously the on-line questionnaire attending to the way they do. Although there are programming techniques which allows us to observe the behaviour of users while filling the survey, current work uses artificial neural networks to predict their behaviour, based on variables obtained from the own survey. The sample is made up of 1,636 participants from different geographical areas and age ranges, obtained anonymously by answering the IPSETA questionnaire which is used for a psychological monitoring of sport talents. The results obtained using the analysis techniques show that females prefer to register on the platform to fill the survey, getting a high reliability (70%).

Keywords : data mining; artificial neural networks; WEKA, association rules; cluster analysis.

        · abstract in Spanish | Portuguese     · text in Spanish     · Spanish ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License