Integrated Analysis of Machine Learning and Deep Learning in Silkworm Pupae (Bombyx mori) Species and Sex Identification

Abstract

Hybrid pairing of the corresponding silkworm species is a pivotal link in sericulture, ensuring egg quality and directly influencing silk quantity and quality. Considering the potential of image recognition and the impact of varying pupal postures, this study used machine learning and deep learning for global modeling to identify pupae species and sex separately or simultaneously. The performance of traditional feature-based approaches, deep learning feature-based approaches, and their fusion approaches were compared. First, 3600 images of the back, abdomen, and side postures of 5 species of male and female pupae were captured. Next, six traditional descriptors, including the histogram of oriented gradients (HOG), and six deep learning descriptors, including ConvNeXt-S, were utilized to extract significant species and sex features. Finally, classification models were constructed using the multilayer perceptron (MLP), support vector machine, and random forest. The results indicate that the {HOG + ConvNeXt-S + MLP} model excelled, achieving 99.09% accuracy for separate species and sex recognition and 98.40% for simultaneous recognition, with precision–recall and receiver operating characteristic curves ranging from 0.984 to 1.0 and 0.996 to 1.0, respectively. In conclusion, it can capture subtle distinctions between pupal species and sexes and shows promise for extensive application in sericulture.

Intelligent Animal Husbandry: Present and Future

“…The paper by He et al [14] offers an economical and intelligent solution for sericulture breeding based on validation of the effectiveness of machine learning and deep learning in recognizing the species and sexes of pupae through image analysis. Additionally, this research has a future perspective in the development of a finer-grained neural network for improving the detection of subtle variations across species and sexes using datasets from diverse breeding batches [14]. The other problem of animal husbandry, requiring intelligent approaches for recognition and prediction, is animal behavior.…”

“…This Special Issue presents experimental and review material for discussing a wide spectrum of questions related to “Intelligent Animal Husbandry”, from the use of modern technologies for genetic progress in animals, to the application of information and communications technologies (ICT) to control the behavior and breeding conditions of animals, to intelligent waste management in animal husbandry ( Figure 1 ). The publications included in the collection reflect an opportunity for intelligent approaches and smart solutions for raising different species of farm animals: dairy animals, such as cows and buffaloes [ 6 , 12 ]; pigs [ 4 , 13 ]; silkworms [ 14 ]; rabbits [ 8 ]; and chickens [ 11 ].…”

“…Accurate identification of the species and sex of pupae is also essential for silkworm sericulture, particularly for silk quality. The paper by He et al [ 14 ] offers an economical and intelligent solution for sericulture breeding based on validation of the effectiveness of machine learning and deep learning in recognizing the species and sexes of pupae through image analysis. Additionally, this research has a future perspective in the development of a finer-grained neural network for improving the detection of subtle variations across species and sexes using datasets from diverse breeding batches [ 14 ].…”