Principal component analysis-based frequent pattern evaluation on the object-relational data model of a cricket match database
Frequent pattern evaluation is imperative for cricket match data to develop more proficient coaching strategies and progress the performance of individual players. The rapid growth in size of the match database far exceeds the human ability to analyse, thus creating an opportunity to extract knowledge from this database. Very few research efforts have been carried out on sports data (especially on cricket) and none of them focused on play patterns. Our work emphasises play patterns to discover interesting patterns from cricket matches and evaluate those patterns to turn them into knowledge that can further be used to modify the coaching process and play styles. Since real-time cricket data are too complex, an object-relational model is used here. In this work, Principal Component Analysis (PCA) is used to reduce high dimensional match data set into lower dimensional data set in order to improve predictive performance and to detect frequently occurring play patterns.
Volume (Year): 1 (2009)
Issue (Month): 4 ()
|Contact details of provider:|| Web page: http://www.inderscience.com/browse/index.php?journalID=282|
When requesting a correction, please mention this item's handle: RePEc:ids:injdan:v:1:y:2009:i:4:p:364-384. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Graham Langley)
If references are entirely missing, you can add them using this form.