Browsing by Author "Li, Han-Lin"

Now showing 1 - 20 of 28

A DIAMOND Method for Classifying Biological Data
(2010)
Li, Han-Lin
;
Huang, Yao-Huei
;
Chen, Ming-Hsien
;
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 study proposes an effective method called DIAMOND to classify biological and medical data. Given a set of objects with some classes, DIAMOND separates the objects into different cubes, where each cube is assigned to a class. Via the union of these cubes, we utilize mixed integer programs to induce classification rules with better rates of accuracy, support and compactness. Two practical data sets, one of HSV patient results and the other of Iris flower, are tested to illustrate the advantages of DIAMOND over some current methods.
A DIAMOND method of inducing classification rules for biological data
(2011-08-01)
Li, Han-Lin
;
Huang, Yao-Huei
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Identifying the classification rules for patients, based on a given dataset, is an important role in medical tasks. For example, the rules for estimating the likelihood of survival for patients undergoing breast cancer surgery are critical in treatment planning. Many well-known classification methods (as decision tree methods and hyper-plane methods) assume that classes can be separated by a linear function. However, these methods suffer when the boundaries between the classes are non-linear. This study presents a novel method, called DIAMOND, to induce classification rules from datasets containing non-linear interactions between the input data and the classes to be predicted. Given a set of objects with some classes, DIAMOND separates the objects into different cubes, and assigns each cube to a class. Via the unions of these cubes, DIAMOND uses mixed-integer programs to induce classification rules with better rates of accuracy, support and compact. This study uses three practical datasets (Iris flower, HSV patients, and breast cancer patients) to illustrate the advantages of DIAMOND over some current methods. (C) 2011 Published by Elsevier Ltd.
A distributed computation algorithm for solving portfolio problems with integer variables
(2008-04-16)
Li, Han-Lin
;
Tsai, Jung-Fa
;
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 portfolio problem with integer variables can facilitate the use of complex models, including models containing discrete asset values, transaction costs, and logical constraints. This study proposes a distributed algorithm for solving a portfolio program to obtain a global optimum. For a portfolio problem with n integer variables, the objective function first is converted into an ellipse function containing n separated quadratic terms. Next, the problem is decomposed into m equal-size separable programming problems solvable by a distributed computation system composed of rn personal computers linked via the Internet. The numerical examples illustrate that the proposed method can obtain the global optimum effectively for large scale portfolio problems involving integral variables. (c) 2007 Elsevier B.V. All rights reserved.
A fuzzy ranking method with range reduction techniques
(2008-02-01)
Ma, Li-Ching
;
Li, Han-Lin
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
For ranking alternatives based on pairwise comparisons, current analytic hierarchy process (AHP) methods are difficult to use to generate useful information to assist decision makers in specifying their preferences. This study proposes a novel method incorporating fuzzy preferences and range reduction techniques. Modified from the concept of data envelopment analysis (DEA), the proposed approach is not only capable of treating incomplete preference matrices but also provides reasonable ranges to help decision makers to rank decision alternatives confidently. (C) 2007 Elsevier B.V. All rights reserved.
A Logarithmic Method for Reducing Binary Variables and Inequality Constraints in Solving Task Assignment Problems
(2013-09-01)
Li, Han-Lin
;
Huang, Yao-Huei
;
Fang, Shu-Cherng
;
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 studies the classical task assignment problem (TAP) in which M unbreakable tasks are assigned to N agents with the objective to minimize the communication and process costs subject to each agent's capacity constraint. Because a large-size TAP involves many binary variables, most, if not all, traditional methods experience the difficulty in solving the problem within a reasonable time period. Recent works present a logarithmic approach to reduce the number of binary variables in problems with mixed-integer variables. This study proposes a new logarithmic method that significantly reduces the numbers of binary variables and inequality constraints in solving task assignment problems. Our numerical experiments demonstrate that the proposed method is superior to other known methods of this kind for solving large-size TAPs.
A new hybrid MCDM model combining DANP with VIKOR to improve e-store business
(2013-01-01)
Chiu, Wan-Yu
;
Tzeng, Gwo-Hshiung
;
Li, Han-Lin
;
科技管理研究所
;
資訊管理與財務金融系註：原資管所+財金所
Many consumers today buy products and services from e-stores. Because e-store managers are responsible for allocating different resources, it is essential that they understand consumers' shopping behaviour to provide the best possible value for visitors to their websites. Therefore, the purpose of this article is to focus on assessing and improving strategies to reduce the gaps in customer satisfaction caused by interdependence and feedback problems among dimensions and criteria to achieve the aspiration level. We propose a new hybrid Multiple Attribute Decision Making (MADM) model, combining the Decision Making Trial and Evaluation Laboratory (DEMATEL), DEMATEL-based Analytic Network Process (DANP), and Vlsekriterijumsko KOmpromisno Rangiranje (VIKOR) methods to solve these problems. Then, three real cases are used to illustrate how the proposed new hybrid Multiple Criteria Decision-Making (MCDM) model improves e-store business. These results can provide e-store managers with a knowledge-based understanding of how to create marketing strategies that reduce the performance gaps of dimensions and criteria to satisfy consumers' needs and encourage customers to purchase more. Crown Copyright (C) 2012 Published by Elsevier B.V. All rights reserved.
A new hybrid MCDM model combining DANP with VIKOR to improve e-store business
(2013-01-01)
Chiu, Wan-Yu
;
Tzeng, Gwo-Hshiung
;
Li, Han-Lin
;
科技管理研究所
;
資訊管理與財務金融系註：原資管所+財金所
Many consumers today buy products and services from e-stores. Because e-store managers are responsible for allocating different resources, it is essential that they understand consumers' shopping behaviour to provide the best possible value for visitors to their websites. Therefore, the purpose of this article is to focus on assessing and improving strategies to reduce the gaps in customer satisfaction caused by interdependence and feedback problems among dimensions and criteria to achieve the aspiration level. We propose a new hybrid Multiple Attribute Decision Making (MADM) model, combining the Decision Making Trial and Evaluation Laboratory (DEMATEL), DEMATEL-based Analytic Network Process (DANP), and Vlsekriterijumsko KOmpromisno Rangiranje (VIKOR) methods to solve these problems. Then, three real cases are used to illustrate how the proposed new hybrid Multiple Criteria Decision-Making (MCDM) model improves e-store business. These results can provide e-store managers with a knowledge-based understanding of how to create marketing strategies that reduce the performance gaps of dimensions and criteria to satisfy consumers' needs and encourage customers to purchase more. Crown Copyright (C) 2012 Published by Elsevier B.V. All rights reserved.
A Superior Representation Method for Piecewise Linear Functions
(2009-03-01)
Li, Han-Lin
;
Lu, Hao-Chun
;
Huang, Chia-Hui
;
Hu, Nian-Ze
;
資訊管理與財務金融系註：原資管所+財金所
Many nonlinear programs can be piecewisely linearized by adding extra binary variables. For the last four decades, several techniques of formulating a piecewise linear function have been developed. By expressing a piecewise linear function with m+1 break points, the current method requires us to use m additional binary variables and 4m constraints, which causes heavy computation when m is large. This study proposes a superior way of expressing the same piecewise linear function, where only [log(2)m] binary variables and 8+8 [log(2)m] additive constraints are used. Various numerical experiments demonstrate that the proposed method is more computationally efficient than current methods.
Adjusting ordinal and cardinal inconsistencies in decision preferences based on gower plots
(2006-09-01)
Li, Han-Lin
;
Ma, Li-Ching
;
交大名義發表
;
National Chiao Tung University
Gower plots provide a powerful graphical tool to detect cardinal and ordinal inconsistencies in a pairwise preference matrix. However, there is no systematical way to help a decision maker to reduce these inconsistencies. This paper develops a model that can assist in making a consistent decision. Gower plots are used to detect major inconsistencies. A multi-objective program is then formulated to adjust both the cardinal inconsistencies and the preference changes subjected to the constraints of ordinal consistency.
An enhanced logarithmic method for signomial programming with discrete variables
(2016-12-16)
Li, Han-Lin
;
Fang, Shu-Cherng
;
Huang, Yao-Huei
;
Nie, Tiantian
;
資訊管理與財務金融系註：原資管所+財金所
Signomial programming problems with discrete variables (SPD) appear widely in real-life applications, but they are hard to solve. This paper proposes an enhanced logarithmic method to reformulate the SPD problem as a mixed 0-1 linear program (MILP) with a minimum number of binary variables and inequality constraints. Both of the theoretical analysis and numerical results strongly support its superior performance to other state-of-the-art linearization methods. We also extend the proposed method to linearize some more complicated problems involving product and fractional terms in discrete and continuous variables. (C) 2016 Elsevier B.V. All rights reserved.
Convex relaxation for solving posynomial programs
(2010-01-01)
Lu, Hao-Chun
;
Li, Han-Lin
;
Gounaris, Chrysanthos E.
;
Floudas, Christodoulos A.
;
資訊管理與財務金融系註：原資管所+財金所
Convex underestimation techniques for nonlinear functions are an essential part of global optimization. These techniques usually involve the addition of new variables and constraints. In the case of posynomial functions x(1)(alpha 1)x(2)(alpha 2) ... x(n)(alpha n), logarithmic transformations (Maranas and Floudas, Comput. Chem. Eng. 21: 351-370, 1997) are typically used. This study develops an effective method for finding a tight relaxation of a posynomial function by introducing variables y(j) and positive parameters beta(j), for all alpha(j) > 0, such that y(j) = x(j)(-beta j). By specifying beta(j) carefully, we can find a tighter underestimation than the current methods.
Convex underestimation for posynomial functions of positive variables
(2008-06-01)
Li, Han-Lin
;
Tsai, Jung-Fa
;
Floudas, Christodoulos A.
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
The approximation of the convex envelope of nonconvex functions is an essential part in deterministic global optimization techniques (Floudas in Deterministic Global Optimization: Theory, Methods and Application, 2000). Current convex underestimation algorithms for multilinear terms, based on arithmetic intervals or recursive arithmetic intervals (Hamed in Calculation of bounds on variables and underestimating convex functions for nonconvex functions, 1991; Maranas and Floudas in J Global Optim 7: 143-182, (1995); Ryoo and Sahinidis in J Global Optim 19: 403-424, (2001)), introduce a large number of linear cuts. Meyer and Floudas (Trilinear monomials with positive or negative domains: Facets of convex and concave envelopes, pp. 327-352, (2003); J Global Optim 29: 125-155, (2004)), introduced the complete set of explicit facets for the convex and concave envelopes of trilinear monomials with general bounds. This study proposes a novel method to underestimate posynomial functions of strictly positive variables.
Decision on enterprise computing solutions for an international tourism
(2007-12-01)
Huang, Chia-Hui
;
Kao, Han-Ying
;
Li, Han-Lin
;
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 study proposes a multi-objective decision approach for evaluating the enterprise computing solutions in international tourism. We first analyze one tour operator in Thailand as well as its specific requirements for enterprise computations. In the decision processes for enterprise computation, several experts are invited to evaluate the alternatives based on a multi-tier electronic business architecture. This study designs two models for evaluating the information systems investments in international tourism. The first model maximizes the overall utility for each criterion, and the other model maximizes the utility for every expert. Because each alternative for enterprise computation involves approximate costs and efforts, we represent the cost data with fuzzy sets and possibility distributions.
Deducing the classification rules for thermal comfort controls using optimal method
(2016-03)
Hu, Chih-Chien
;
Li, Han-Lin
;
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 study investigates the feasibility of using a rule set of human thermal sensation index to control a heating ventilation and air conditioning (HVAC) system in order to achieve a desired thermal comfort level and energy savings. A novel approach based on an optimization method is developed to deduce the rules of learning human thermal comfort. In contrast to conventional thermal comfort levels, the proposed approach explains the linguistic rules in an "If ... Then" form, in which proposed thermal comfort levels do not require an iterative solution and can be easily adjusted, depending on the specific thermal sensation of occupants. Results of this study demonstrate that the proposed thermal comfort control mechanism can also be implemented to achieve thermal comfort, energy savings, and reduce computational costs. (C) 2016 Elsevier Ltd. All rights reserved.
Detecting and adjusting ordinal and cardinal inconsistencies through a graphical and optimal approach in AHP models
(2007-03-01)
Li, Han-Lin
;
Ma, Li-Ching
;
交大名義發表
;
National Chiao Tung University
An AHP model suffering from significant cardinal or/and ordinal inconsistencies in its preference matrix is difficult to rank rationally the alternatives. This study proposes an iterative method to assist a decision maker to detect/adjust inconsistencies and to represent his/her judgments properly. A Gower plot is first used to detect ordinal and cardinal inconsistencies. Two optimization models are then constructed to provide suggeted adjustments upon the request of the decision maker. By examining the Gower plots and numerical suggestions, the decision maker may revise iteratively the preference ratios to improve inconsistencies until all alternatives are ranked. (c) 2005 Elsevier Ltd. All rights reserved.
Developing, navigation graphs for TED talks
(2017-01)
Hu, Chih-Chien
;
Li, Han-Lin
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
TED Talks is one of the most well-known online video providers. However, current TED displaying system is not efficient in helping users to "navigate" among videos. This study utilizes optimization techniques to help users to develop their navigation graphs thus to find TED Talks videos effectively. The synthesized graph representation encodes the visual metaphors among these videos and keywords to enable visual navigation onto a global overview. Such a navigation graph not only allows users to explore the entire collection of videos and keywords, but also supports seeing sailing selecting processes for understanding and intuitive guidance for navigation. Our experimental evaluations explicate that the proposed system is more effective and faster than other presentation structures in helping users to explore their preferred materials. (C) 2016 Elsevier Ltd. All rights reserved.
Forming a TED talks sphere for convenient search
(2020-04-29)
Shih, Chia-Hui
;
Li, Han-Lin
;
Hu, Chih-Chien
;
Lin, Bertrand M. .
;
資訊管理與財務金融系註：原資管所+財金所
Purpose TED (Technology, Entertainment, Design, ) Talks has been one of the most popular video systems. However, the current TED Talks system expressed its inquired videos as in a two-dimensional (2D) table, which is inconvenient for searching the relationships among videos and tags. This study converts the TED Talks table into a sphere by using optimization techniques to help users search for preferred videos. Design/methodology/approach There are five phases in this study as follows. Phase 1: Reorganize data of 36 tags and 108 videos; Phase 2: Allocate tags on the TED sphere; Phase 3: Allocate videos on the TED sphere; Phase 4: Develop an online interactive TED retrieval system; and Phase 5: Perform survey and evaluation. Findings One survey demonstrated that the TED Talks sphere is more convenient for searching videos, as it is more user-friendly because of its graphical user interface, more convenient to use, more useful for retrieving information and can facilitate a more responsive search for users' preferred videos. Research limitations/implications The numbers of tags and videos able to be displayed on a sphere is limited by the capacity of an optimization software and hardware. Practical implications The proposed sphere system can be used by a large number of users of TED Talks groups. Social implications This sphere systems can also be applied to other fields which use 2D forms to display the relationships among objects. Originality/value This study uses an optimization method to convert a 2D form into a 3D sphere to highlight the relationships among numerous objects.
Global Optimization for Generalized Geometric Programs with Mixed Free-Sign Variables
(2009-05-01)
Li, Han-Lin
;
Lu, Hao-Chun
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Many optimization problems are formulated as generalized geometric programming (GGP) containing signomial terms f(X) . g(Y), where X and Y are continuous and discrete free-sign vectors, respectively. By effectively convexifying f(X) and linearizing g(Y), this study globally solves a GGP with a lower number of binary variables than are used in current GGP methods. Numerical experiments demonstrate the computational efficiency of the proposed method.
Improving the E-Store Business Model for Satisfying Customers' Needs Using a Hybrid MCDM Combined DANP with Grey Relational Model
(2010)
Chiu, Wan-Yu
;
Tzeng, Gwo-Hshiung
;
Li, Han-Lin
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
The current paper aims to qualitatively and quantitatively measure and evaluate e-store index criteria used to achieve the aspired levels for satisfying customers' needs. Such research should help e-store managers understand customers' feelings and requirements for improving the e-store business. Therefore, in the current approach, we use a hybrid MCDM model to address the dependent relational problems among the criteria. Specifically, we combine DANP (DEMATEL-based ANP) and grey relation analysis (GRA) methods to calculate the relative importance weights and relation of the criteria between interdependence and feedback. We also propose a strategy to improve the criteria gap for closing to the aspired levels of human life and convenient service. As such, this research can provide e-store managers with an understanding of how to improve business models in order to achieve consumers' needs and promote more repurchases and enable them to devise the best marketing strategies to provide the most effective and efficient service for their customers.
Indoor thermal comfort controls optimized by deducing rules
(2016)
Hu, Chih-Chien
;
Li, Han-Lin
;
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 novel approach based on an optimization method is developed to deduce the rules of learning human thermal comfort states. In order to achieve a desired thermal comfort level and energy savings, the study constructs a mechanism with varied control strategies by using the deduced rule set. The proposed method is superior to other indoor thermal comfort based controls in that it produces interpretable rules and generates appropriate set-points for control systems. Analytical results of this study demonstrate that the proposed thermal comfort control mechanism can also be implemented with wireless sensor network (WSN) to achieve thermal comfort and energy savings with limited computational resources. In other words, the solution enables the ubiquitous control of indoor thermal comfort.