Title page for ETD etd-461113689652491

Type of Document

Master's Thesis

Author

Wilson II, Lawriston A

URN

etd-461113689652491

Title

Prediction of Fertility of Virginia Beef Heifers Using Expert Systems Technology

Degree

Master of Science

Department

Animal and Poultry Sciences

Advisory Committee

Advisor Name	Title
William D. Hohenboken	Committee Chair
Conrad D. Heatwole	none
W. E. Beal	none

Keywords

artificial intelligence
beef cattle
biological type
reproduction

Date of Defense

1996-08-16

Availability

unrestricted

Abstract

An expert system to predict the fertility of beef heifers was developed using the A.I. Toolkit KAPPA-PC

2.33. The knowledge base was developed from scientific literature and from a beef cattle reproduction

expert. The expert system computes an evaluation age, age both at the start and end of the breeding season,

and weight per day of age to classify a heifer as having either a 3LOW2, 3GOOD2, or 3EXCELLENT2

likelihood of conception. The expert system summarizes the information that is entered into the computer and

creates a text file of the summary. It also gives explanations for every prediction to help identify and alleviate

any problem areas that may affect a heifer1s ability to reproduce. The program requires an IBM compatible

computer installed with Windows 3.13 or greater. From simulated data for purebred or crossbred British

cattle, there was 72% prediction agreement between the expert system and the expert. From analysis of

historical data of Hereford-Angus crossbred cattle, heifers categorized as 3LOW2 and 3GOOD2 had

significantly higher observed pregnancy rates than expected for each category. There was no significant

difference between observed and expected pregnancy rates for heifers in the 3EXCELLENT2 category.

Pregnancy rates for post-weaning and pre-breeding evaluations for the 3LOW2 heifers were found to be

lower from the combined 3GOOD2 and 3EXCELLENT2 heifers at P=.03 and P=.06 respectively. Observed

successful calving rates for heifers categorized as 3LOW2, 3GOOD2, and 3EXCELLENT2 did not differ

significantly from the expected calving rates for each category.

Files

Filename		Size	Approximate Download Time (Hours:Minutes:Seconds)
Filename		Size	28.8 Modem	56K Modem	ISDN (64 Kb)	ISDN (128 Kb)	Higher-speed Access
	etd.pdf	244.72 Kb	00:01:07	00:00:34	00:00:30	00:00:15	00:00:01