2012- 21st Annual NC State Undergraduate Research Symposium

Session Time : 4/10/12 12:15 PM - 4/10/12 1:30 PM

Content Area : Animal Science

Poster Appointment: , -

Student Presenters :
Catherine Grace McVey Animal Science

Mentors and/or Co-Authors :
Daniel Egger Duke Center for Quantitative Modeling

Abstract Title : Equine QFBR: A Computational Approach to Equine Temperament Anaylsis

Abstract :
Within the equestrian community there is a great deal of antiquated knowledge relating anatomical features of the equine face to aspects of personality/temperament. This noninvasive behavioral evaluation technique offers equine professionals a distinct advantage in identifying horses cognitively suited for success in today’s competitive equestrian discipline, yet most methods for applying these techniques have traditionally been guarded as training secrets, and as a result remain highly subjective, inaccessible, and scientifically unexplored. The purpose of this project was to bring objectivity and accessibility to this facial evaluation technique via a user-friendly and statistically validated computational approach. A test-retest methodology was first employed in a bias-controlled setting to evaluate the objectivity of facial classifications. All facial regions rejected the null hypothesis at the 2 % significance level, and the facial characteristics themselves were concluded to be both objective and quantifiable. A total of 26 trigonometric measures were then derived to quantitatively describe this confirmed variation within the relevant structures of the equine face. These measure next were coded into MATLAB, and, using the program’s interactive image-analysis interface, applied to a sample of 81 national-caliber Arabian show horses. The computed measurements were subsequently used to develop a trinomial categorization model capable of predicting riding discipline with 79% accuracy (using only four facial measures) and three separate multiple linear regression models capable of predicting the win percentiles of individual horses within each riding discipline with statistically significant degrees of correlation.