Data mining to estimate broiler mortality when exposed to heat wave

Abstract

Heat waves usually result in losses of animal production since they are exposed to thermal stress inducing an increase in mortality and consequent economical losses. Animal science and meteorological databases from the last years contain enough data in the poultry production business to allow the modeling of mortality losses due to heat wave incidence. This research analyzes a database of broiler production associated to climatic data, using data mining techniques such as attribute selection and data classification (decision tree) to model the impact of heat wave incidence on broiler mortality. The temperature and humidity index (THI) was used for screening environmental data. The data mining techniques allowed the development of three comprehensible models for estimating specifically high mortality during broiler production. Two models yielded a classification accuracy of 89.3% by using Principal Component Analysis (PCA) and Wrapper feature selection approaches. Both models obtained a class precision of 0.83 for classifying high mortality. When the feature selection was made by the domain experts, the model accuracy reached 85.7%, while the class precision of high mortality was 0.76. Meteorological data and the calculated THI from meteorological stations were helpful to select the range of harmful environmental conditions for broilers 29 and 42 days old. The data mining techniques were useful for building animal production models.

Quantitative histo-morphometric analysis of heat-stress-related damage in the small intestines of broiler chickens

“…The absence of mortality and no effect on body weight was unexpected, as on chicken farms birds seem to be more sensitive to heat stress, with even fatal outcomes under comparable climatic conditions in some cases (McDougald & McQuistion, 1980;Vale et al, 2008). The most likely reason for this discrepancy is the fact that, in this study, the birds were kept in an experimental unit with more than sufficient space, under perfect hygienic conditions and free of any Figure 1.…”

Performance of Laying Hens and Economic Viability of Different Climatization Systems

“…According to Jácome et al (2007), temperature range for laying hens may vary between 15ºC and 28ºC, whereas relative air humidity may vary between 40% and 80%. Vale et al (2008) reported that local wind speed above 1.4 m s -1 and dry bulb temperature above 24ºC would cause high mortality rates in meat chickens. Figure 1 shows that the sheds' external environment was within the literature-established thermo-neutrality zone during most of the time.…”

Técnica de mineração de dados: uma revisão da literatura

“…There are several methods, but the aim is not to exhaust the subject but to identify the most used. The main technologies are: Neural Networks, Decision Tree, Genetic Algorithms (AGs), Fuzzy logic and Statistics (1,5,18,(29)(30) .…”

“…The Decision Tree is a model graphically represented by branches, similar to a tree, but in the inverted sense; they are also called classification or regression trees, in case the dependent variable be respectively categorical or numeric (2,29,30,34) .…”

“…These two purposes do not eliminate each other, and can appear together in the same study (29,31,34) . Some recent researches have used the induction of a Decision Tree to predict and obtain knowledge (29)(30) .…”