Logistic regression model reveals major factors associated with total bacteria and somatic cell counts in goat bulk milk

Factors influencing somatic cell counts and bacterial contamination in unpasteurized milk obtained from water buffalo in Bangladesh

Little has been published on the factors influencing the safety and quality of milk derived from water buffalo in Bangladesh. This study aims to describe the milk hygiene parameters and milk chain characteristics of unpasteurized raw milk sold to consumers in order to improve milk hygiene. A quantitative study design evaluated somatic cell counts, total bacterial counts, and specific gram-negative (Enterobacteria) and gram-positive (staphylococci) pathogens in 377 aseptically collected milk samples. Samples were collected at multiple nodes along the buffalo milk value chain: 122 bulk tank milk samples were collected at the farm level, 109 milk samples at the middlemen level, and 111 milk samples at the milk collection centers. In addition, 35 samples were taken from various milk products at the retail level. It was found that progressively increasing somatic cell counts and bacterial counts, including potential pathogens, occurred along the milk chain. A seasonal increase in spring was found, varying based on the farming system (semi-intensive versus intensive). Other factors included water purity and cleanliness of containers, mixing buffalo and cow's milk, and the location of the water buffalo milk producer (coastal or river basin). This study demonstrated how improving udder health and milk hygiene along the water buffalo milk value chain would increase the safety and quality of water buffalo milk in the study area.

Recognition of bovine milk somatic cells based on multi-feature extraction and a GBDT-AdaBoost fusion model

Traditional laboratory microscopy for identifying bovine milk somatic cells is subjective, time-consuming, and labor-intensive. The accuracy of the recognition directly through a single classifier is low. In this paper, a novel algorithm that combined the feature extraction algorithm and fusion classification model was proposed to identify the somatic cells. First, 392 cell images from four types of bovine milk somatic cells dataset were trained and tested. Secondly, filtering and the K-means method were used to preprocess and segment the images. Thirdly, the color, morphological, and texture features of the four types of cells were extracted, totaling 100 features. Finally, the gradient boosting decision tree (GBDT)-AdaBoost fusion model was proposed. For the GBDT classifier, the light gradient boosting machine (LightGBM) was used as the weak classifier. The decision tree (DT) was used as the weak classifier of the AdaBoost classifier. The results showed that the average recognition accuracy of the GBDT-AdaBoost reached 98.0%. At the same time, that of random forest (RF), extremely randomized tree (ET), DT, and LightGBM was 79.9, 71.1, 67.3 and 77.2%, respectively. The recall rate of the GBDT-AdaBoost model was the best performance on all types of cells. The F1-Score of the GBDT-AdaBoost model was also better than the results of any single classifiers. The proposed algorithm can effectively recognize the image of bovine milk somatic cells. Moreover, it may provide a reference for recognizing bovine milk somatic cells with similar shape size characteristics and is difficult to distinguish.