|Brown Brandl, Tami|
Submitted to: American Society of Agri Engineers Special Meetings and Conferences Papers
Publication Type: Other
Publication Acceptance Date: 6/30/2003
Publication Date: 7/28/2003
Citation: BROWN BRANDL, T.M., JONES, D.D., WOLDT, W.E. EVALUATING MODELING TECHNIQUES FOR LIVESTOCK STRESS PREDICTION. AMERICAN SOCIETY OF AGRI ENGINEERS SPECIAL MEETINGS AND CONFERENCES PAPERS. 2003. Paper #034009. Interpretive Summary: Extended periods of high temperature and relative humidity and low airflow can cause severe stress in feedlot cattle. Cattle producers must be made aware of these conditions to help deal with the problem. This study reports the efforts to predict stressful conditions using several mathematical methods. Measures to represent the environment include temperature, humidity, wind speed, and solar radiation. Breathing rate was used as the measure of stress on the cattle. Two types of "fuzzy" models were compared to traditional math models. Results showed that one "fuzzy" model gave better predictions than traditional models, but the second "fuzzy" model did poorly. Additional work is planned, because each model under-predicted the breathing rate at the most severe weather conditions.
Technical Abstract: Heat stress resulting from extreme heat events has caused large death losses in feedlot cattle. A method of predicting stressful situations would aid the producer in taking proactive measures. One-hundred and twenty-eight feedlot heifers of four differing genotypes (32 of each: Angus, MARC III crossbred, Charolais, and Gelbvieh) were penned according to genotype. Respiration rates (determined by counting flank movements) and surface temperatures were taken on a randomly selected subset of 10 animals/genotype twice daily on a predetermined schedule throughout the summer of 2002. Respiration rate was used as the indicator of stress. Weather parameters were collected using a weather station located at the feedlot of interest. Four modeling techniques were used to predict respiration rate (two multiple regression, and two fuzzy inference systems). Results showed that the Sugeno type fuzzy inference system had slightly better results than the two multiple regression models, while the Mamdani type fuzzy inference system was not able to perform at the level of the other three models. It appears that all models over estimate low respiration rates and under predict high respiration rates.