Analysis of York Pigs Feeding Behavior Using Stepwise Regression and Principal Component Regression

A statistical analysis was conducted on the feeding behavior of 106 York breeding pigs.Pearson correlation analysis,principal component correlation analysis and multiple stepwise regression equation methods were applied to establish regression equations of the York breeding pigs total feed intake per time and average feed intake per time with corrected fat thickness,feed conversion rate,and corrected daily gain.The results showed that:①there were three peak feed intake periods for the pigs,and the correlation coefficient between the feed intake and the corrected fat thickness of the pigs in the 24 h period was positive or negative,that is,increasing the number of feeding times and the feed intake was not necessarily conducive to the fat thickness accumulation,but the breeding goal of fat thickness could be achieved by controlling the feeding times and feed intake;②the average feed intake of pigs in the 60-90 kg body weight stage was 30%-50%higher than that of the 30-60 kg body weight stage,but the number of feeding times decreased,the peak feeding time was more concentrated,and the feeding duration per time was 3.0 min longer,indicating that as the weight of pigs increased,the feed intake increased significantly;and③the stepwise regression equations and the principal component equations showed that the feeding behavior of York pigs in the 30-90 kg growth stage was not only affected by the feeding time within 24 h,but also by environmental factors such as temperature and humidity.The feeding behavior of York pigs is a complex process of interaction between environmental factors and animal factors.

Study on the Accuracy of Different CASA Systems in the Quality Detection of Fresh Boar Semen

[Objectives]This study was conducted to compare and analyze the accuracy of computer-aided sperm analysis(CASA)and manual method for detecting the quality of fresh boar semen at room temperature.[Methods]Statistical methods such as analysis of variance,ZB score and Z score were used to compare the accuracy of five different brands of CASA systems and manual method to detect the vitality and density of fresh boar semen at room temperature.[Results]After setting the parameters of five CASA systems the same as follows:VCL(curvilinear velocity),VSL(straight-line velocity)≥5μm/s,STR(straightness)=VSL(straight-line velocity)/VAP(average path velocity)≥25%,the sperm motility of six parts of boar semen was tested at normal temperature using different brands of special fixed-volume slides with a uniform chamber height[(20±2)μm].There were no significant differences in sperm vitality detected by the five CASA systems(P>0.05).The ZB scores of the vitality obtained by observers or instrument engineers who did not have a job certificate from the quality inspection department showed that the results of three observers or instrument engineers were unsatisfactory(∣ZB∣>3),but there were no significant differences in vitality between the CASA systems and the inspector with a job certificate(P>0.05).Regarding sperm density detection,when the sperm density was less than 280×106/ml,there were no significant differences between the results displayed by the instruments and the results of the manual hemocytometer counting(P>0.05).[Conclusions]The accuracy of the CASA systems set to uniform parameters was consistent with the accuracy of the visual vitality obtained by an inspector with a job certificate.When the semen was diluted with 3%NaCl solution to a sperm density<280×10^6/ml,the sperm density detected by the CASA systems was consistent in reliability with that obtained by the hemocytometer detection.The CASA systems are faster and more efficient and objective than manual detection,and have the advantages of strong operability and easy promotion.

Process of Analyzing Pig Inbreeding Coefficient Using SAS Program

The paternity index is one of the important parameters which paternity determination depends on.Inbreeding is an indispensable and effective means to improve herds and breeds and breed new strains and breeds.It can fix good traits and improve herd genetic uniformity.The INBREED module of SAS statistical analysis software can be used to calculate the inbreeding coefficients of the offspring and their parents in the pig herd pedigree.In this study,we used actual data as an example to compile and operate an SAS program for calculating the inbreeding coefficients of a pig herd.Compared with the dedicated software for calculating inbreeding coefficients developed in recent years,such as BASIC+database dBASE,Visual Basic+database SQ L Serve method,DFREMLI,MTDF EMLI,VCE,ASREML,DMU,GBS and Herdsman,calculating inbreeding coefficients with SAS programs has the advantages of low cost,simple programming language,and easy operation.For livestock breeders who are not provided with special computing software,the use of SAS to calculate the inbreeding coefficients of pigs is of great significance to planned breed selection and assortative mating.

DNN-HMM based acoustic model for continuous pig cough sound recognition

To detect the respiratory disease through pig cough sound in the early stage,a novel method based on Deep Neural Networks-Hidden Markov Model(DNN-HMM)was proposed to construct an acoustic model for continuous pig cough sound recognition.Noises in the continuous pig sounds were eliminated by the Wiener algorithm based on wavelet thresholding the multitaper spectrum,and the experimental corpus was obtained from the denoised continuous pig sounds.The 39-dimensional Mel Frequency Cepstral Coefficients(MFCC)extracted from the corpus were considered as feature vectors.Sounds in pig farms were divided into pig coughs,non-pig coughs,and silence segments.In the HMM,the number of hidden states of pig cough,non-pig cough and silence segments were 5,5 and 3 respectively,and the observation states represented the feature vectors of the continuous pig sound signal.Based on experiments and empirical theory,the DNN model with 3 hidden layers and 100 nodes per layer was used to describe the correspondence between hidden states and observation serials.Through experiments,the context frames of DNN input were set to 5.Under the condition of optimal parameter setting,the traditional acoustic model Gaussian Mixture Model-Hidden Markov Model(GMM-HMM)was compared with DNN-HMM through a 5-fold cross-validation experiment.It was found that the Word Error Rate(WER)of each group in DNN-HMM was lower than that in GMM-HMM,and the average WER was 3.45%lower.At the same time,the best result of the DNN-HMM model was obtained with the lowest WER of 7.54%,and the average WER was 8.03%.The results showed that the method of DNN-HMM based acoustic model for continuous pig cough sound recognition was stable and reliable.