In modern animal husbandry, artificial intelligence helps accurately manage individual sheep. However, it is difficult to recognize the sheep’s facial features and capture the nuances. It is not easy to extract the fine-grained features of a sheep’s face because the traditional vision transformer cannot realize the effective embedding of the interaction scale. To address this problem, we propose a novel sheep Transformer tool called SheepFormer . This model comprises components such as the Interactive Scale Embedded Images Block ( ISEI ), Patch Short Long Distance Attention Module ( PSLDA ), Dynamic Relative Position Offset ( DRPO ), and Transformer Neck and Head ( TNH ). These components are designed to embed features at multiple scales, fuse long and short-distance self-attention, adaptively handle relative position offsets for various group sizes, and introduce a prediction head to detect fine-grained facial targets in sheep at different scales. SheepFormer integrates Residual Attention to seek dense facial features in sheep and utilizes a Transformer Head to replace the traditional head, exploring the predictive potential of self-attention mechanisms in sheep faces. Experimental results demonstrate a 7.1% improvement in average precision (AP) for sheep face detection compared to Collaborative DEtection TRansformer (CO-DETR) and an 11.12% enhancement in accurate classification of sheep identity document (ID) compared to Shifted Windows Transformer (Swin Transformer). This study demonstrates that SheepFormer can extract fine-grained facial features of sheep, which promotes the advancement of high-precision sheep individual recognition and provides a guide for recognizing kinship.

This article develops a new edge removal mechanism for the global stabilizability of Boolean networks (BNs). In order to achieve the edge removal control, several control variables are properly placed into the dynamics of BNs based on the fundamental logical operators. On the basis of the new edge removal mechanism, several necessary and sufficient conditions are obtained for the global stabilizability and set stabilizability of BNs. Furthermore, a kind of stable edge removal control is proposed and achieved via the -learning algorithm to optimize the edge removal mechanism. As an application, the edge removal control is used to verify whether or not the mammalian cortical area development model can be made stabilizable to the expected stable states.

Edge perturbations (EPs) are often induced by disease-causing mutations, which include edge removal and edge sign switch. This article explores the robust stability of Boolean networks (BNs) with these two kinds of EPs. At first, both edge removal perturbation and edge sign switch perturbation are converted to multibit function perturbations (FPs). After that, the parameterized reachability matrix is constructed to verify the robust stability of BNs with multibit FP. As applications, several new criteria are established for the robust stability of BNs subject to edge removal perturbation and edge sign switch perturbation. Finally, the results are demonstrated by the Boolean models of p53 pathways network and Toll pathway of Drosophila signaling pathway network.