Abstract
Cattle productivity in Japan has been declining though livestock farmers and breeders tried to use artificial insemination regularly. The reason behind this declining productivity is the poor evaluation of the applicability of artificial insemination. To address this issue, this research proposes an objective evaluation method to estimate the applicability of programmed Artificial Insemination (pAI). The objective evaluation method tries to estimate the applicability of pAI based on the analysis of various indices from dairy and beef cattle using Bayesian Network Model (BNM). The estimation of the pAI applicability considers 14 and 17 physiological indices for diary and beef cattle respectively. These indices include the basic information (days after childbirth, parity, etc.), diagnosis of appearance, diagnosis of genital organ and the veterinarians' judgments. The overall success rate in estimating the applicability is 89.8% for 1051 records of dairy cattle and 95.6% for 1128 records of beef cattle. The proposed method avoids the subjective error in estimating the applicability of pAI. In addition, the experiment revealed that the applicability of pAI can be evaluated even though the number of measure indices is few.