Browsing by Author "Lai, Shih-Chung"

Now showing 1 - 2 of 2

Predicting Television Ratings and Its Application to Taiwan Cable TV Channels
(2013)
Huang, Hui-Ling
;
Lee, Hua-Chin
;
Shu, Li-Sun
;
Lai, Shih-Chung
;
Tsai, Tse-Ming
Using forecast television network ratings, television executives estimate a price to sell time to advertisers. TV rating is an important feedback mechanism because its results greatly affect the immense profits of TV companies, advertisers, and program producers. Therefore, how to select the samples for TV rating investigation plays an important role in predicting program ratings. How to design an accurate predicting model for program rating also is an important investigation. The predicting problem is essentially a bi-objective optimization problem which minimizes the number of samples and maximizes the predicting accuracy of program rating. In this study, we propose an evolutionary approach to designing a rating model (ERM) by simultaneous optimization of sampling sub-area selection and parameter tuning using an intelligent genetic algorithm (IGA). In this study, the ERM is applied to Taiwan Cable TV Channels in Taipei and Taiwan. The experiments show that TV rating prediction of the proposed ERM is efficient smaller than that of using the same number of sub-areas with the largest TV ratings and an optimal prediction program rating by using the selected sub-areas.
SCMHBP: prediction and analysis of heme binding proteins using propensity scores of dipeptides
(2014-12-08)
Liou, Yi-Fan
;
Charoenkwan, Phasit
;
Srinivasulu, Yerukala Sathipati
;
Vasylenko, Tamara
;
Lai, Shih-Chung
Background: Heme binding proteins (HBPs) are metalloproteins that contain a heme ligand (an iron-porphyrin complex) as the prosthetic group. Several computational methods have been proposed to predict heme binding residues and thereby to understand the interactions between heme and its host proteins. However, few in silico methods for identifying HBPs have been proposed. Results: This work proposes a scoring card method (SCM) based method (named SCMHBP) for predicting and analyzing HBPs from sequences. A balanced dataset of 747 HBPs (selected using a Gene Ontology term GO: 0020037) and 747 non-HBPs (selected from 91,414 putative non-HBPs) with an identity of 25% was firstly established. Consequently, a set of scores that quantified the propensity of amino acids and dipeptides to be HBPs is estimated using SCM to maximize the predictive accuracy of SCMHBP. Finally, the informative physicochemical properties of 20 amino acids are identified by utilizing the estimated propensity scores to be used to categorize HBPs. The training and mean test accuracies of SCMHBP applied to three independent test datasets are 85.90% and 71.57%, respectively. SCMHBP performs well relative to comparison with such methods as support vector machine (SVM), decision tree J48, and Bayes classifiers. The putative non-HBPs with high sequence propensity scores are potential HBPs, which can be further validated by experimental confirmation. The propensity scores of individual amino acids and dipeptides are examined to elucidate the interactions between heme and its host proteins. The following characteristics of HBPs are derived from the propensity scores: 1) aromatic side chains are important to the effectiveness of specific HBP functions; 2) a hydrophobic environment is important in the interaction between heme and binding sites; and 3) the whole HBP has low flexibility whereas the heme binding residues are relatively flexible. Conclusions: SCMHBP yields knowledge that improves our understanding of HBPs rather than merely improves the prediction accuracy in predicting HBPs.