Intelligent System for Topic Survey in MEDLINE by Keyword Recommendation and Learning Text Characteristics

 

 

 

 

Mar. 2th, 2004

 

 

 

 

Pei-Yi, Huang

 

 

 

 

 

Abstract

 

 

 

 

Selecting MEDLINE records by keywords and combinations sometimes does not achieve efficient and high quality results as people interested. This intelligent system had implemented for assisting experts in selecting MEDLINE records for database construction purposes with two features: a learning mechanism extract patterns of interests abstracts of MEDLINE records. And keyword recommendation system which assists experts’ knowledge in unexpected cases.

 

 

 

 

 

Source

 

 

 

 

Intelligent System for Topic Survey in MEDLINE by Keyword Recommendation and Learning Text Characteristics
Miyako,T., Sanae,N., Hiroshi,M., Hideki,T., Yasuhiko,K. and Satoru,M., in Genome Informatics, Vol. 11, Page: 73-82, 2000

 

 

 

 

 

 

 

 

 

 

Reference

 

 

 

 

1.          Shimozono, S., Shinohara, A., Shinohara, T., Miyano, S., Kuhara, S., and Arikawa,S., Knoledge acquisition from amino acid sequence by machine learning system BONSAI, Trans. IPS Japan, 35(10):2009-2018, 1994.

2.          Stapley, B.J. and Benoit, G., Biobibliometrics: Information retrieval and visualization from co-occurrences of gene names in Medline abstracts, Proc. Pacific Symp. Biocomputing 2000, World Scientific, 529-540, 2000

3.          Hideo, B., Yoshinori, T., Osamu, M., Kenta, N., and Satoru, Miyano., Extensive feature detection of N-terminal protein sorting signals. Bioinformatics, Vol.18, No.2, pp.298-305, 2002.

4.          Quinlan, J.: Induction of decision trees, Machine Learning, Vol. 1, pp.81-106, 1986.