Study On Medical Image Segmentation And Malicious Sample Classification

This paper is divided into two parts:First,in order to realize fast segmentation of mass medical images,This paper proposes a method based on Spark-YARN distributed processing of medical images.First,a medical image segmentation model based on improved combination of fuzzy kernel clustering and CV model is established,and then we used Spark distributed software and Yarn resource management platform to do batch processing of medical images.Finally,we carried out simulation experiments,and the results showed that the proposed method achieved efficient and accurate segmentation.The realization of mass accurate medical image segmentation is of great significance to the medical diagnosis of large data and the study of pathology.Two.For the classification of malicious samples,a new and effective malicious sample classification feature is proposed.On this basis,a new malware classification model is established,which is characterized by extracting the function 16 byte code in the malicious sample file.The classification model is established by using the maximum common subsequence and the maximum group algorithm,and the better classification results are obtained.Because the research of malicious code generation is in the continuous update stage,and continuously generate various new malicious codes that can surpass traditional detection technology barriers,which makes the task of anti malware become very arduous.Therefore,fast and accurate classification of malicious code has become an important means of anti malicious code.It can lay a good technical foundation for tracing,controlling and deleting malicious code.Therefore,how to effectively classify malicious code has become one of the most important issues in the field of information security.Experiments show that the new malicious code classification method and the malicious code classification model built on this basis achieve a better classification.