Search

Body condition scoring is an objective scoring method used to evaluate the health of a cow by determining the amount of subcutaneous fat in a cow. Automated body condition scoring is becoming vital to large commercial dairy farms as it helps farmers score their cows more often and more consistently compared to manual scoring. A common approach to automated body condition scoring is to utilise a CNN-based model trained with data from a depth camera. The approaches presented in this paper make use of three depth cameras placed at different positions near the rear of a cow to train three independent CNNs. Ensemble modelling is used to combine the estimations of the three individual CNN models. The paper aims to test the performance impact of using ensemble modelling with the data from three separate depth cameras. The paper also looks at which of these three cameras and combinations thereof provide a good balance between computational cost and performance. The results of this study show that utilising the data from three depth cameras to train three separate models merged through ensemble modelling yields significantly improved automated body condition scoring accuracy compared to a single-depth camera and CNN model approach. This paper also explored the real-world performance of these models on embedded platforms by comparing the computational cost to the performance of the various models.

Single nucleotide polymorphism arrays have created new possibilities for performing genome-wide studies to detect genomic regions harboring sequence variants that affect complex traits. However, the majority of validated SNPs for which allele frequencies have been estimated are limited primarily to European breeds. The objective of this study was to perform SNP discovery in three South African indigenous breeds (Afrikaner, Drakensberger, and Nguni) using whole genome sequencing. DNA was extracted from blood and hair samples, quantified and prepared at 50 ng/μl concentration for sequencing at the Agricultural Research Council Biotechnology Platform using an Illumina HiSeq 2500. The fastq files were used to call the variants using the Genome Analysis Tool Kit. A total of 1,678,360 were identified as novel using Run 6 of 1000 Bull Genomes Project. Annotation of the identified variants classified them into functional categories. Within the coding regions, about 30% of the SNPs were non-synonymous substitutions that encode for alternate amino acids. The study of distribution of SNP across the genome identified regions showing notable differences in the densities of SNPs among the breeds and highlighted many regions of functional significance. Gene ontology terms identified genes such as MLANA , SYT10 , and CDC42EP5 that have been associated with coat color in mouse, and ADAMS3, DNAJC3 , and PAG5 genes have been associated with fertility in cattle. Further analysis of the variants detected 688 candidate selective sweeps (ZH p Z-scores ≤ -4) across all three breeds, of which 223 regions were assigned as being putative selective sweeps (ZH p scores ≤-5). We also identified 96 regions with extremely low ZH p Z-scores (≤-6) in Afrikaner and Nguni. Genes such as KIT and MITF that have been associated with skin pigmentation in cattle and CACNA1C , which has been associated with biopolar disorder in human, were identified in these regions. This study provides the first analysis of sequence data to discover SNPs in indigenous South African cattle breeds. The information will play an important role in our efforts to understand the genetic history of our cattle and in designing appropriate breed improvement programmes.

The majority of rural households in developing countries own village chickens that are reared under traditional scavenging systems with few inputs and exposure to various parasitic infestations. Understanding of the village chicken farming system and its influence on helminth infestation is a prerequisite for optimal prevention and control strategies. This study investigated the village chicken production system and associated gastrointestinal parasites in 87 households from Limpopo (n = 39) and KwaZulu-Natal (n = 48) provinces of South Africa. A total of 191 village chicken faecal samples and 145 intestines were collected to determine the prevalence of gastrointestinal parasites in villages of Limpopo and KwaZulu-Natal provinces, respectively. The faecal floatation analysis of samples from Limpopo and KwaZulu-Natal provinces indicated infestations by Ascaridia galli (18.77%), Heterakis gallinarum (15.56%) and Capillaria spp. (4.00%); tapeworms Choanotaenia infundibulum (2.10%) and Raillietina cesticillus (6.00%) and Eimeria spp. (29.46%). Mixed infestations were observed in five (4.90%) samples from Limpopo province and in only four (4.49%) from KwaZulu-Natal province, of which 1.12% were a mixture of C. infundibulum and Eimeria spp. and 3.37% a combination of H. gallinarum and Eimeria spp. In Limpopo, 2.94% of the chickens were positive for H. gallinarum and Eimeria spp., whilst 0.98% had A. galli and Capillaria spp. infestations. Further investigation is needed to understand the impact of gastrointestinal parasites on village chicken health and production and develop appropriate intervention and control strategies feasible for smallholder farmers.