scholarly journals Exploring the Unexplored: Identifying Implicit and Indirect Descriptions of Biomedical Terminologies Based on Multifaceted Weighting Combinations

2016 ◽  
Vol 2016 ◽  
pp. 1-11
Author(s):  
Sung-Pil Choi

In order to achieve relevant scholarly information from the biomedical databases, researchers generally use technical terms as queries such as proteins, genes, diseases, and other biomedical descriptors. However, the technical terms have limits as query terms because there are so many indirect and conceptual expressions denoting them in scientific literatures. Combinatorial weighting schemes are proposed as an initial approach to this problem, which utilize various indexing and weighting methods and their combinations. In the experiments based on the proposed system and previously constructed evaluation collection, this approach showed promising results in that one could continually locate new relevant expressions by combining the proposed weighting schemes. Furthermore, it could be ascertained that the most outperforming binary combinations of the weighting schemes, showing the inherent traits of the weighting schemes, could be complementary to each other and it is possible to find hidden relevant documents based on the proposed methods.

2019 ◽  
Vol 8 (2S3) ◽  
pp. 1145-1150

In today’s VLSI technology nodes, interconnect delay plays an important part in deciding the performance of the chip designs. Various methods are introduced at the level of placement and routing to address this problem. To address this problem at the level of global routing, net weighting methods are being explored in the industry and academia. We investigate four methods for weighting the critical nets during performance driven global routing. This paper presents a comparative study conducted on the four methods for net weighting proposed by us in our previous works


Term weighting is a preprocessing phase that has an important role in the text classification by giving the appropriate weight for each term in all documents. In previous research, many supervised term weighting methods have been introduced, but most of the supervised term weighting only considers the distribution of terms in the two classes so that it is not optimal for the multi-class classification. This paper introduces a new supervised weighting with association concept to optimize term weighting distributions in multi-class cases by considering terms that exist in each class and paying attention to the number of terms in the document belonging to the class, also considering the relationship pattern between one or more items with association concept in a dataset to measure the strength of terms in a class by using confidence values. The dataset used are the data twitter taken from the PR FM twitter account. The proposed supervised term weighting method implemented with SVM classifier can outperform unsupervised weighting schemes such as TF-IDF with the average accuracy 81.704%.


2003 ◽  
Vol 3 (3) ◽  
pp. 477-505 ◽  
Author(s):  
J LEIKIN ◽  
R MCFEE ◽  
F WALTER ◽  
R THOMAS ◽  
K EDSALL

2017 ◽  
Vol 102 (10) ◽  
pp. 1421-1434 ◽  
Author(s):  
Paul R. Sackett ◽  
Jeffrey A. Dahlke ◽  
Oren R. Shewach ◽  
Nathan R. Kuncel

Sign in / Sign up

Export Citation Format

Share Document