Medical CT Images Classification Model Based on BBO-HS Algorithm Optimized SVM
Sun Rui · 2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · 2020
A medical CT image classification model with hybrid BBO (Biogeography Based Optimization) and HS (Harmony Search) algorithm is proposed to improve medical CT image classification accuracy and solve SVM parameter optimization problem in the classifier. Firstly, HS algorithm has strong search capabilities for global solutions, but poor local search abilities. It can be better to search global and local solutions by integrating migration operations of BBO algorithm into HS algorithm. Finally, the medical CT image classification model is established according to the optimal parameter and meanwhile the simulation test is also carried out to verify the performance of the model. The simulation result shows that relative to the comparison model, BBO-HS-SVM can not only improve medical CT image classification accuracy, but also accelerate the classification speed, thus being more suitable for the real-time classification requirements of medical CT images.