An efficient model selection for linear discriminant function-based recursive feature elimination.

Model selection is an important issue in support vector machine-based recursive feature elimination (SVM-RFE). However, performing model selection on a linear SVM-RFE is difficult because the generalization error of SVM-RFE is hard to estimate. This paper proposes an approximation method to evaluate the generalization error of a linear SVM-RFE, and designs a new criterion to tune the penalty parameter C. As the computational cost of the proposed algorithm is expensive, several alpha seeding approaches are proposed to reduce the computational complexity. We show that the performance of the proposed algorithm exceeds that of the compared algorithms on bioinformatics datasets, and empirically demonstrate the computational time saving achieved by alpha seeding approaches.

Study on the Application Value of CT Thin-Layer Scan Data Assisted 3D Printing Technology in Hip and Knee Replacement.

To better study hip and knee replacement, 50 eligible hip and knee patients from March 2020 to April 2021 were selected. A 1 : 1 scale solid model was printed with CT thin-layer scanning data assisted by 3D printing technology to evaluate the ankle function of patients six months after surgery. The results showed that the 3D rapid prototyping time of the 1 : 1 fracture model in 50 patients was 3-4 hours. The operation time was 70-90 min, and the average operation time was 80 min. The actual application in operation was consistent with that in the simulation of the 3D printing model, after surgery, and there was no infection of incision soft tissue or loss of reduction in all 50 patients. CT thin-layer scan data aided 3D printing technology can help clinical hip and knee replacement simulation and planning, improving surgery's accuracy and safety.