Unsupervised Discretization of Continuous Variables in a Chicken Egg Quality Traits Dataset

Zeynel Cebeci, Figen Yıldız

Abstract


Discretization is a data pre-processing task transforming continuous variables into discrete ones in order to apply some data mining algorithms such as association rules extraction and classification trees. In this study we empirically compared the performances of equal width intervals (EWI), equal frequency intervals (EFI) and K-means clustering (KMC) methods to discretize 14 continuous variables in a chicken egg quality traits dataset. We revealed that these unsupervised discretization methods can decrease the training error rates and increase the test accuracies of the classification tree models. By comparing the training errors and test accuracies of the model applied with C5.0 classification tree algorithm we also found that EWI, EFI and KMC methods produced the more or less similar results. Among the rules used for estimating the number of intervals, the Rice rule gave the best result with EWI but not with EFI. It was also found that Freedman-Diaconis rule with EFI and Doane rule with EFI and EWI slightly performed better than the other rules.

Keywords


Data preprocessing; Discretization; Unsupervised discretization; Egg quality traits

Full Text:

PDF


DOI: https://doi.org/10.24925/turjaf.v5i4.315-320.1056

 Creative Commons License
This work is licensed under Creative Commons Attribution 4.0 International License

ISSN: 2148-127X

Turkish JAF Sci.Tech.

Turkish Journal of Agriculture - Food Science and Technology (TURJAF) is indexed by the following national and international scientific indexing services:



 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 





Our Journals

Turkish Journal of Agriculture - Food Science and Technology

International Journal of Poultry - Ornamental Birds Science and Technology

Turkish Research Journal of Academic Social Science

Turkish Research Journal of Academic Technical Science

Turkish Research Journal of Academic Health and Medical Sciences

Our congresses

International Anatolian Agriculture, Food, Environment and Biology Congress (TARGID)

International Congress of the Turkish Journal of Agriculture - Food Science and Technology (TURJAF)

Our Youtube Channel

TURAS TV

Our Books

Our Scientific Books

About Us

The Turkish Science and Technology Publishing (TURSTEP) is an online and open-access platform to publish recent research and articles of scholars worldwide. Founded in 2013 and based in Turkey, the TURSTEP as a platform for academics, educators, scholars, and students from Turkey and around the world, to connect with one another. The TURSTEP disseminates research that is proven or predicted to be of significant influence for the general public.

       

Contact Us

Please send all inquiries to the email:

teditor@agrifoodscience.com

Business Adress

Eğriköprü Mh. 75-28. Sk. 11/10 58050 Merkaz/Sivas, Turkey