This paper describes the theory, implementation, and experimental evaluation of an Aggregation Cache Replacement ( ACR ) algorithm. By considering application background, carefully choosing weight values, using a sp...This paper describes the theory, implementation, and experimental evaluation of an Aggregation Cache Replacement ( ACR ) algorithm. By considering application background, carefully choosing weight values, using a special formula to calculate the similarity, and clustering ontologies by similarity for getting more embedded deep relations, ACR combines the ontology similarity with the value of object and decides which object is to be replaced. We demonstrate the usefulness of ACR through experiments. (a) It is found that the aggregation tree is created wholly differently according to the application cases. Therefore, clustering can direct the content adaptation more accurately according to the user perception and can satisfy the user with different preferences. (b) After comparing this new method with widely-used algorithm Last-Recently-Used (LRU) and First-in-First-out (FIFO) method, it is found that ACR outperforms the later two in accuracy and usability. (c) It has a better semantic explanation and makes adaptation more personalized and more precise.展开更多
Radiology doctors perform text-based image retrieval when they want to retrieve medical images.However,the accuracy and efficiency of such retrieval cannot keep up with the requirements.An innovative algorithm is bein...Radiology doctors perform text-based image retrieval when they want to retrieve medical images.However,the accuracy and efficiency of such retrieval cannot keep up with the requirements.An innovative algorithm is being proposed to retrieve similar medical images.First,we extract the professional terms from the ontology structure and use them to annotate the CT images.Second,the semantic similarity matrix of ontology terms is calculated according to the structure of the ontology.Lastly,the corresponding semantic distance is calculated according to the marked vector,which contains different annotations.We use 120 real liver CT images(divided into six categories)of a top three-hospital to run the algorithm of the program.Result shows that the retrieval index"Precision"is 80.81%,and the classification index"AUC(Area Under Curve)"under the"ROC curve"(Receiver Operating Characteristic)is 0.945.展开更多
基金Supported by the National Natural Science Foun-dation of China (60472050)
文摘This paper describes the theory, implementation, and experimental evaluation of an Aggregation Cache Replacement ( ACR ) algorithm. By considering application background, carefully choosing weight values, using a special formula to calculate the similarity, and clustering ontologies by similarity for getting more embedded deep relations, ACR combines the ontology similarity with the value of object and decides which object is to be replaced. We demonstrate the usefulness of ACR through experiments. (a) It is found that the aggregation tree is created wholly differently according to the application cases. Therefore, clustering can direct the content adaptation more accurately according to the user perception and can satisfy the user with different preferences. (b) After comparing this new method with widely-used algorithm Last-Recently-Used (LRU) and First-in-First-out (FIFO) method, it is found that ACR outperforms the later two in accuracy and usability. (c) It has a better semantic explanation and makes adaptation more personalized and more precise.
文摘Radiology doctors perform text-based image retrieval when they want to retrieve medical images.However,the accuracy and efficiency of such retrieval cannot keep up with the requirements.An innovative algorithm is being proposed to retrieve similar medical images.First,we extract the professional terms from the ontology structure and use them to annotate the CT images.Second,the semantic similarity matrix of ontology terms is calculated according to the structure of the ontology.Lastly,the corresponding semantic distance is calculated according to the marked vector,which contains different annotations.We use 120 real liver CT images(divided into six categories)of a top three-hospital to run the algorithm of the program.Result shows that the retrieval index"Precision"is 80.81%,and the classification index"AUC(Area Under Curve)"under the"ROC curve"(Receiver Operating Characteristic)is 0.945.