3results about How to "Excellent sensitivity" patented technology

This invention relates to the field of intelligent brain disease diagnosis technology, specifically providing an auxiliary diagnostic method and system based on multimodal decoupled dynamic graph learning. The method includes: acquiring and preprocessing multimodal data (such as neuroimaging, genetic markers, etc.) of the subject; extracting common pathological information and modality-specific features through a shared encoder and modality-specific encoders respectively, and optimizing the separation process using a decoupling loss function; furthermore, fusing all modality embeddings using a multi-head self-attention mechanism with a masked matrix to generate initial node representations, where the mask is used to suppress modality self-attention; subsequently, performing hierarchical dynamic graph convolution based on the node representations: in each layer, dynamically updating the graph adjacency matrix by combining the current node representation with the original features, and iteratively optimizing the node representations through message passing; finally, inputting the optimized representations into a classifier to obtain disease prediction results. This invention improves the automation performance and reliability of diagnosis.

The application discloses a ship bow shaking chaos phenomenon nested iteration sliding mode control method, through the established ship straight sailing chaos model; the nested iteration sliding mode controller is constructed, the dynamic surface technology is combined to simplify the design process, the heading stability and the rudder angle response optimization are realized; the model perturbation and the sea wave disturbance are effectively coped with, and the bow shaking chaos control precision and the robustness are obviously improved. Compared with the traditional method, the application is better in the heading convergence speed, the steady-state error suppression and the rudder angle regulation sensitivity, effectively solves the problems that the traditional sliding mode control has large chattering, slow response and poor adaptability under complex disturbance, and has important engineering value for guaranteeing the ship heading stability and the steering safety under complex sea conditions.

This invention discloses a liquid-phase probe-targeted capture library construction method and kit for enteroviruses, belonging to the field of virus detection technology. This invention combines targeted enrichment with high-throughput sequencing, featuring broad coverage, high flexibility, high sensitivity, and high specificity, enabling multi-dimensional information output including quantitative, qualitative, and in-depth analysis. Through the probe-targeted capture "enrichment-screening" mechanism, this invention reduces probe redundancy design, minimizes background nucleic acid interference from intestinal flora, exhibits excellent adaptability to complex samples, and eliminates the need for complex sample pretreatment, making it suitable for large-scale epidemiological detection.