In order to solve the problem of information retrieval on the semantic web, a new semantic information retrieval （SIR） model for searching ontologies on the semantic web is proposed. First, SIR transformed domain on...In order to solve the problem of information retrieval on the semantic web, a new semantic information retrieval （SIR） model for searching ontologies on the semantic web is proposed. First, SIR transformed domain ontologies into global ontologies. Then semantic index terms were extracted from these global ontologies. Based on semantic index terms, logical inferences can be performed and the logical views of the concept can be obtained. These logical views represent the expanded meaning of the concept. Using logical views, SIR can perform the information retrieval and inferences based on the semantic relationships in the documents, not only on the syntactic analysis of the documents. SIR can significantly enhance the recall and precision of the information retrieval by the semantic inference. Finally, the practicability of the SIR model is analyzed.展开更多
The Web comprises of voluminous rich learning content. The volume of ever growing learning resources however leads to the problem of information overload. A large number of irrelevant search results generated from sea...The Web comprises of voluminous rich learning content. The volume of ever growing learning resources however leads to the problem of information overload. A large number of irrelevant search results generated from search engines based on keyword matching techniques further augment the problem. A learner in such a scenario needs semantically matched learning resources as the search results. Keeping in view the volume of content and significance of semantic knowledge, our paper proposes a multi-threaded semantic focused crawler （SFC） specially designed and implemented to crawl on the WWW for educational learning content. The proposed SFC utilizes domain ontology to expand a topic term and a set of seed URLs to initiate the crawl. The results obtained by multiple iterations of the crawl on various topics are shown and compared with the results obtained by executing an open source crawler on the similar dataset. The results are evaluated using Semantic Similarity, a vector space model based metric, and the harvest ratio.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The National Natural Science Foundation of China (No.60273072),the National High Technology Research and Development Program of China (863Program)(No.2002AA423450).
文摘In order to solve the problem of information retrieval on the semantic web, a new semantic information retrieval （SIR） model for searching ontologies on the semantic web is proposed. First, SIR transformed domain ontologies into global ontologies. Then semantic index terms were extracted from these global ontologies. Based on semantic index terms, logical inferences can be performed and the logical views of the concept can be obtained. These logical views represent the expanded meaning of the concept. Using logical views, SIR can perform the information retrieval and inferences based on the semantic relationships in the documents, not only on the syntactic analysis of the documents. SIR can significantly enhance the recall and precision of the information retrieval by the semantic inference. Finally, the practicability of the SIR model is analyzed.
文摘The Web comprises of voluminous rich learning content. The volume of ever growing learning resources however leads to the problem of information overload. A large number of irrelevant search results generated from search engines based on keyword matching techniques further augment the problem. A learner in such a scenario needs semantically matched learning resources as the search results. Keeping in view the volume of content and significance of semantic knowledge, our paper proposes a multi-threaded semantic focused crawler （SFC） specially designed and implemented to crawl on the WWW for educational learning content. The proposed SFC utilizes domain ontology to expand a topic term and a set of seed URLs to initiate the crawl. The results obtained by multiple iterations of the crawl on various topics are shown and compared with the results obtained by executing an open source crawler on the similar dataset. The results are evaluated using Semantic Similarity, a vector space model based metric, and the harvest ratio.
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.
