Browsing by Author "Yu, CS"

Now showing 1 - 9 of 9

A fuzzy multiobjective program with quasiconcave membership functions and fuzzy coefficients
(2000-01-01)
Li, HL
;
Yu, CS
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
A method is proposed for solving a fuzzy multi-objective linear programming problem (FMP) with quasiconcave membership functions and fuzzy coefficients. The proposed method first expresses a piecewise function as the summation of absolute terms. Then we search for the interval where the optimal solution is allocated by finding the corresponding points with same value of membership functions. After that, the problem is solved by goal programming techniques. Comparing with other FMP methods, the proposed method does not need to add extra zero-one variables, to divide the original problem into several sub-problems, or transforming all original quasiconcave functions into concave functions. In addition, the proposed method could solve a FMP problem with fuzzy coefficients;to obtain a solution closing to a global optimum. (C) 2000 Elsevier Science B.V. All rights reserved.
A global optimization method for nonconvex separable programming problems
(1999-09-01)
Li, HL
;
Yu, CS
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Conventional methods of solving nonconvex separable programming (NSP) problems by mixed integer programming methods requires adding numerous 0-1 variables. In this work, we present a new method of deriving the global optimum of a NSP program using less number of 0-1 variables. A separable function is initially expressed by a piecewise linear function with summation of absolute terms. Linearizing these absolute terms allows us to convert a NSP problem into a linearly mixed 0-1 program solvable for reaching a solution which is extremely close to the global optimum. (C) 1999 Elsevier Science B.V. All rights reserved.
An algorithm for generalized fuzzy binary linear programming problems
(2001-09-16)
Yu, CS
;
Li, HL
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Fuzzy binary linear programming (FBLP) problems are very essential in many fields such as assignment and assembly line balancing problems in operational research, multiple projects, locations, and candidates selection cases in management science, as well as representing and reasoning with prepositional knowledge in artificial intelligence. Although FBLP problems play a significant role in human decision environment, not very much research has focused on FBLP problems. This work first proposes a simple means of expressing a triangular fuzzy number as a linear function with an absolute term. A method of linearizing absolute terms is also presented. The developed goal programming (GP) model weighted by decision-makers' (DMs) preference aims to optimize the expected objective function and minimize the sum of possible membership functions' deviations. After presented a novel way of linearizing product terms, the solution algorithm is proposed to generate a crisp trade-off promising solution that is also an optimal solution in a certain sense. Three examples, equipment purchasing choice, investment project selection, and assigning clients to project leaders, illustrate that the proposed algorithm can effectively solve generalized FBLP problems. (C) 2001 Elsevier Science B.V. All rights reserved.
Comments on "Fuzzy programming with nonlinear membership functions..."
(1999-01-01)
Li, HL
;
Yu, CS
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Yang ct al., in their paper "Fuzzy programming with nonlinear membership functions...", published in Fuzzy Sets and Systems 41 (1991), declared that their model can solve a fuzzy program with an S-shaped membership function by adding only one 0-1 variable. This paper indicates that their declaration is correct only for a specific type of S-shape membership functions. We propose another model to treat the fuzzy programs which cannot be solved effectively by Yang et al. (C) 1999 Elsevier Science B.V. All rights reserved.
Comments on "Fuzzy programming with nonlinear membership functions..."
(1999-01-01)
Li, HL
;
Yu, CS
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Yang ct al., in their paper "Fuzzy programming with nonlinear membership functions...", published in Fuzzy Sets and Systems 41 (1991), declared that their model can solve a fuzzy program with an S-shaped membership function by adding only one 0-1 variable. This paper indicates that their declaration is correct only for a specific type of S-shape membership functions. We propose another model to treat the fuzzy programs which cannot be solved effectively by Yang et al. (C) 1999 Elsevier Science B.V. All rights reserved.
Fine-grained protein fold assignment by support vector machines using generalized npeptide coding schemes and jury voting from multiple-parameter sets
(2003-03-01)
Yu, CS
;
Wang, JY
;
Yang, JM
;
Lyu, PC
;
Lin, CJ
In the coarse-grained fold assignment of major protein classes, such as all-alpha, all-beta, alpha + beta, alpha/beta proteins, one can easily achieve high prediction accuracy from primary amino acid sequences. However, the fine-grained assignment of folds, such as those defined in the Structural Classification of Proteins (SCOP) database, presents a challenge due to the larger amount of folds available. Recent study yielded reasonable prediction accuracy of 56.0% on an independent set of 27 most populated folds. In this communication, we apply the support vector machine (SVM) method, using a combination of protein descriptors based on the properties derived from the composition of n-peptide and jury voting, to the fine-grained fold prediction, and are able to achieve an overall prediction accuracy of 69.6% on the same independent set-significantly higher than the previous results. On 10-fold cross-validation, we obtained a prediction accuracy of 65.3%. Our results show that SVM coupled with suitable global sequence-coding schemes can significantly improve the fine-grained fold prediction. Our approach should be useful in structure prediction and modeling. (C) 2003 Wiley-Liss, Inc.
Method for solving quasi-concave and non-concave fuzzy multi-objective programming problems
(2001-09-01)
Yu, CS
;
Li, HL
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
This paper proposes a method based on linear programming techniques to treat quasi-concave and non-concave fuzzy multi-objective programming (FMOP) problems. The proposed method initially presents a piecewise linear expression to interpreting a quasi-concave membership function. Then we find the convex-type break points acid transform all quasi-concave membership functions into concave functions. After that, the converted program is solved by linear programming techniques to obtain a global optimum. Tn addition to not containing any of the zero-one variables, the proposed method does not require dividing the quasi-concave FMOP problem into large sub-problems as in conventional methods. The extension of the proposed method can treat general non-concave FMOP problems by merely adding less number of zero-one variables. (C) 2001 Elsevier Science B.V. All rights reserved.
Predicting subcellular localization of proteins for Gram-negative bacteria by support vector machines based on n-peptide compositions
(2004-05-01)
Yu, CS
;
Lin, CJ
;
Hwang, JK
;
生物科技學系
;
生物資訊及系統生物研究所
Gram-negative bacteria have five major subcellular localization sites: the cytoplasm, the periplasm, the inner membrane, the outer membrane, and the extracellular space. The subcellular location of a protein can provide valuable information about its function. With the rapid increase of sequenced genomic data, the need for an automated and accurate to predict subcellular localization becomes increasingly important. We present an approach to predict subcellular localization for Gram-negative bacteria. This method uses the support vector machines trained by multiple feature vectors based on n-peptide compositions. For a standard data set comprising 1443 proteins, the overall prediction accuracy reaches 89%, which, to the best of our knowledge, is the highest prediction rate ever reported. Our prediction is 14% higher than that of the recently developed multimodular PSORT-B. Because of its simplicity, this approach can be easily extended to other organisms and should be a useful tool for the high-throughput and large-scale analysis of proteomic and genomic data.
The fragment transformation method to detect the protein structural motifs
(2006-05-15)
Lu, CH
;
Lin, YS
;
Chen, YC
;
Yu, CS
;
Chang, SY
To identify functional structural motifs from protein structures of unknown function becomes increasingly important in recent years due to the progress of the structural genomics initiatives. Although certain structural patterns such as the Asp-His-Ser catalytic triad are easy to detect because of their conserved residues and stringently constrained geometry, it is usually more challenging to detect a general structural motifs like, for example, the beta beta alpha-metal binding motif, which has a much more variable conformation and sequence. At present, the identification of these motifs usually relies on manual procedures based on different structure and sequence analysis tools. In this study, we develop a structural alignment algorithm combining both structural and sequence information to identify the local structure motifs. We applied our method to the following examples: the beta beta alpha-metal binding motif and the treble clef motif. The beta beta alpha-metal binding motif plays an important role in nonspecific DNA interactions and cleavage in host defense and apoptosis. The treble clef motif is a zinc-binding motif adaptable to diverse functions such as the binding of nucleic acid and hydrolysis of phosphodiester bonds. Our results are encouraging, indicating that we can effectively identify these structural motifs in an automatic fashion. Our method may provide a useful means for automatic functional annotation through detecting structural motifs associated with particular functions.