Table of Content

25 December 2011, Volume 20 Issue 6

Previous Issue    Next Issue

Theory Analysis and Methodology Study

Study on Hybrid Heuristics Algorithm for Optimal Loading Problem of Multi-model and Multi-cargo

WANG Xiao-bo, LI Yi-jun

2011, 20(6):  1-8. 

Asbtract ( )  

References | Related Articles | Metrics

In order to satisfy the individual and various demands of customers, we establish a multi-model and multi-cargo loading problem model. Hybrid heuristic algorithm is used to get the optimization solution. Firstly,we use sequence of real numbers coding so as to simplify the problem. On the basis of cubage-weight balance algorithm, we construct an initial solution to improve the feasibility. Through adopting strategy combining sorting options with the best reserved, we ensure the diversity of population. We adopt the improved non-uniform mutation so as to enhance local search ability of chromosomes. Secondly, the elite population genetic algorithm seeks taboo search, to improve the search efficiency. Finally, an example is given to illustrate the effectiveness of the models and methods and it can offer an thought to settle the practical problem on a large scale.

A Method for Solving the Minimum Cost Transportation Problem with Time Limited

LI Zhen-ping, XU Qing-yun, LI Na, MA Yuan-yuan

2011, 20(6):  9-14. 

Asbtract ( )  

References | Related Articles | Metrics

The minimum cost transportation problem with time limited is investigated in this paper. Firstly, the relationship between the transportation time and the transportation qualitity is analyzed, then the transportation time is divided into two parts: one part has no relationship with the transportation qualitity; the other part is a function of the transportation qualitity. Furthermore, according to the relationship between the transportation time ond the transportation qualitity, the minimum cost transportation problem is reformulated into a transportation problem with upper bound of variables. An effect solving method is proposed, and some numercial examples are used for simulation. The results show that the method of this paper is effrcient for solving this kind of problem.

Heuristic Method For Component Assignment Problem in System Reliability Optimization

LIU Qin, SUN Lin-yan

2011, 20(6):  15-18. 

Asbtract ( )  

References | Related Articles | Metrics

This paper reviews the literature about component assignment problem in system reliability optimization. Based on the characteristic of the problem, a new heuristic is proposed. The heuristic is designed with the reliability importance. A numerical example is given in the paper. Existing heuristic is compared with our method. The new heuristic is simple and efficient. It can obtain satisfactory solution in very short time, which is appropriate for large-scale problem.

Integrated Optimization of Three-level Supply Chain under Different Risk Attitude

GUAN Zhi-min, ZHOU Bao-gang, YANG Xi-huai

2011, 20(6):  19-24. 

Asbtract ( )  

References | Related Articles | Metrics

This paper researches integrated optimization problem of three-level supply chain consisting of suppliers, distributor and retailers under decision makers’ different risk attitude. Considering risk factors for price, quality, delivery, demand and supply as fuzzy variables, we model fuzzy chance constrained programming credibility theory. Confidence level of credibility measure represents the degree of decision makers’ risk preference. The optimistic value and the pessimistic value of fuzzy variables are used to convert chance constrained into crisp equivalents. Finally, a numerical example is given to analyze the impact of decision makers’ risk attitude toward integrated supply chain.

Reformation in Coping with Demand Disruption under Supply Chain Network Competition

TENG Chun-xian, ZHANG Chao, CHENG Zhao-bo

2011, 20(6):  25-32. 

Asbtract ( )  

References | Related Articles | Metrics

Using supply chain network(SCN)in which producing, and selling homogeneous products as study object, and manufacturers as the core of the SCN, this paper constructs a SCN equilibrium model for the two stages before and after demand disruption under the economic background of SCN VS SCN competition by variational inequality theory and Nash Game theory. Then it compares the effectiveness of different types of reformation in coping with demand disruption.

Supply Chain Coordination Model with Advance Booking Discounts Program

ZHONG Yuan-guang, ZHOU Yong-wu, GUO Jin-sen

2011, 20(6):  33-38. 

Asbtract ( )  

References | Related Articles | Metrics

We consider a supply chain that consists of a supplier and a retailer, selling a single product to the customers over a short selling season. In this paper, we mainly research how the retailer uses the ABD program to entice customers to pre-commit their orders and how the supplier designs the payment plan so as to maximize his/her own expected profit. Under the supplier-Stackelberg game, the paper gets the decision models based on the object of expected profit. Solving the models, we have got the optimal solutions and obtained some effective theorems. Finally, we provide a detailed numerical example to illustrate the model and the theoretical analysis.

Two-stage Component Commonality Inventory Model with Guaranteed Delivery Time

CHEN Ke-jia, LIN Lin

2011, 20(6):  39-44. 

Asbtract ( )  

References | Related Articles | Metrics

In a two-stage production system, for the case of single component commonality in the second stage, the guaranteed delivery time is considered and the first-stage non-component, single-component, double-component commonality inventory models are established. The impact of guaranteed delivery time on the total costs is studied. The optimal inventory levels of the three models are analyzed. Numerical examples suggest that when the unit purchase costs of common components and non-common components are equal, the more use of component commonality can not generate the lower total costs.

Robust Optimization Model of Eco-industrial Symbiotic Network

LI Chun-fa, HAO Lin-na, LIU Li, WANG Lan-ying

2011, 20(6):  45-50. 

Asbtract ( )  

References | Related Articles | Metrics

Stable and sustainable operation of EISN is basic guarantee for the enterprises in eco-industrial park to achieve maximum economic and environmental benefits. This paper develops a framework for the optimization model and analysis of EISN profit maximization with government incentives, which includes n-producer enterprises and m-decomposer enterprises. Moreover, for a more reflection of operation of EISN and taking into account the uncertainty sub-unit cost and conversion of secondary raw materials that the decomposition enterprises use, robust discrete optimization model of the profit maximization problem of EISN has been constructed. Meanwhile, it employs the minimum cost flow method based on network-based model to solve the model. Finally, it proves the existence of the Solutions of the model and the corresponding case.

Model and Algorithm of FIP Location with Multi-type Demand Flows

ZHANG Xi, YANG Chao, HUANG Song

2011, 20(6):  51-58. 

Asbtract ( )  

References | Related Articles | Metrics

We consider the location problem of different type demand flow on the origin and destination(O-D)pairs of network. Based on the basic flow interception problem(FIP)model, we give the multi-objective FIP location model with multi-type demand flows. The model is transformed into multi-objective fuzzy programming problem, and the hybrid genetic algorithm is introduced to solve the model. The computational experiments demonstrate the efficiency of our HGA.

Retailer’s Optimal Pricing and Ordering Policy under Permissible Delay in Payments

LI Ming-fang, WANG Dao-ping

2011, 20(6):  59-65. 

Asbtract ( )  

References | Related Articles | Metrics

The main purpose of this paper is to develop an inventory model under permissible delay in payments, in which the supplier provides not only a permissible delay but also a cash discount to the retailer, where the demand rate is considered to be a function of the retail price. This model further expands the classical economic production quantity(EPQ)model. We do this in order to reflect the real-life business situations. Mathematical models have derived for obtaining the optimal pricing, optimal cycle time and optimal payment time for items. Finally, a numerical example is given to illustrate the results developed in this paper.

Univariate Time Series Clustering Method Based on Principal Component Analysis

SU Mu-ya, GUO Chong-hui

2011, 20(6):  66-72. 

Asbtract ( )  

References | Related Articles | Metrics

For the high dimensionality of time series, based on theoretical analysis, a new method is proposed to reduce the dimension of univariate time series via principal component analysis, thus univariate time series clustering method based on principal component analysis is presented. The main idea is that, similarities among the univariate time series are reflected by similarities among the corresponding coefficients under the same basic vectors of linear space. In the process of theoretical analysis, we firstly do the principal component analysis on univariate time series data sets and then analyze the relationship among univariate time series, eigenvectors of sample covariance matrix and principal components. Moreover, we prove that the vectors composed of principal components are linear independent. In order to further verify the correctness of theoretical analysis results and the performance of the proposed algorithm, simulation data and real stock data are used to do the numerical experiments finally.

Optimal Matching for Multi-attribute Exchanges With Fuzzy Information in E-brokerage

SHENG Ying, JIANG Zhong-zhong, FAN Zhi-ping

2011, 20(6):  73-81. 

Asbtract ( )  

References | Related Articles | Metrics

This paper investigates an optimal matching approach for the multi-attribute exchanges with fuzzy information which trade a single unit of the same commodity. First, we propose a new calculation method of matching degree, based on the improved fuzzy information axiom from both buyers’and sellers’points of view. Since the satisfactions of buyers and sellers are considered, this method can obtain more reasonable and realistic matching degree. Second, a mathematic model is built to maximize the matching degree of buyers and sellers in multiple attributes. By solving the model, the trade matching results can be achieved. Finally, a numerical example is given to illustrate the feasibility and practicality of the proposed matching approach.

Application Research

Online Strategy on Hydropower

XU Yin-feng, CAO Yong-feng, ZHENG Fei-feng

2011, 20(6):  82-87. 

Asbtract ( )  

References | Related Articles | Metrics

This paper considers the problem of single reservoir hydropower scheduling in multiple time periods, and the target is to maximize the general power generation in the whole schedule term. Without the information of the following incoming water when making decisions, the paper builds the hydropower scheduling model based on the on-line algorithm. Without the current period incoming water information, it designs an online hydropower scheduling strategy with a competitive ratio of 2/(2-β(1-Ф)).When the current period information is available, it designs an online strategy and proves its competitive ratio 1+(1-Ф)/(1+Ф).

Combined DEA and Neural Network for Predicting Investment Validity of Infrastructure on China

LI Yu-long, LI Zhong-fu

2011, 20(6):  88-98. 

Asbtract ( )  

References | Related Articles | Metrics

Combined model of data envelopment analysis(DEA)and neural network for predicting investment validity of infrastructure on China is proposed in this paper. Firstly, investment efficiency on infrastructure based on DEA method from 1993 to 2007 is evaluated to obtain the basic data to predict investment validity. And then, according to the classifying samples which is established based on the evaluated results with DEA method, the scale validity and technical validity of infrastructure is separately predicted with the multi-layer perceptron neural network (MLP-NN). The results show that the prediction of investment validity on infrastructure is feasible, and the response rate and the recall have an obvious advantage by comparing with RBF neural network approach and C-SVM method and logistic regression. DEA-MLP-NN method is more effective.

Gaussian Method in Case-Based Reasoning and Applications

ZHENG Kang-ning, LI Xiang-yang, YANG Kai

2011, 20(6):  99-105. 

Asbtract ( )  

References | Related Articles | Metrics

To resolve the problem of the limitation of low accuracy and reliability in Case-based Reasoning(CBR), Gaussian Case-based Reasoning(GCBR)is proposed. In this research, based on the research on similarity measure on the basis of Euclidean metric, a new means of dealing with similarity measure by employing Gaussian transformations in place of the Euclidean metric is proposed. The concept of distance proportion is introduced to make a transformation that can transfer distances between a pair of cases on each feature into Gaussian indicators, and similarity between two cases will be derived. On that basis, the nearest-neighbor is applied to retrieve case similarity, and the predictive value will be generated by modifying cases. Taking the prediction for the risks of logistics outsourcing enterprise for example, compared with classical CBR model on the basis of Euclidean metric and the Grey CBR, GCBR model statistically and significantly performs better on predictive accuracy, which illustrates the feasibility of applying GCBR model to predict the risks of logistics outsourcing enterprise.

Research on Airline Crew Scheduling

ZHAO Zheng-jia

2011, 20(6):  106-113. 

Asbtract ( )  

References | Related Articles | Metrics

Giving an example of Beijing-Chengdu flights of Air China, the paper presents a new method to solve the problem of crew scheduling. In the new method, crews are not assigned jobs according to flight pairings directly. At first, ‘crew pairings’ are generated with Hungary algorithms to minimize crews’ staying time. Then, the least crews are deduced with the method of worker-scheduling for production management. At last, the specific crews’ scheduling is obtained in which the crews can take rest on successive two days in one week. By the method, the scheduling enables an airline corporation to fulfill its flights with least crews and crews to stay at staying-airports with least time.

Coordination Mechanism of Quality Safety Activities of High Quality Pork Supply Chain Basing on Evolutionary Game

PENG Yu-shan, SUN Shi-min, Zhou Xia

2011, 20(6):  114-119. 

Asbtract ( )  

References | Related Articles | Metrics

In this paper, the conception of the quality safety activities coordination of the high quality pork supply chain partner is presented. We study the game evolutionary processes of the quality safety activities coordination of the high quality pork supply chain partner and the related influence factors using the dual population evolutionary game theory of evolutionary game theory. The results show that the cooperation evolution direction is affected by the cooperation cost, cooperation income, coefficient of income distribution (loss apportion coefficient), probability of being punished, potential loss, management scale, and coefficients of either encouragement or punishment. It will promote the realization of coordination of the quality safety activities of the high quality pork supply chain partner by reducing the coordination cost, improving coordination earnings, and building a fair interest distribution(loss apportion)mechanism, strengthening external supervision and punishment.

Risk Measurement and Selection Optimization of Project Portfolio Based on the Interaction Effect

ZHAO Jing, GUO Peng, PAN Nv-zhao

2011, 20(6):  120-126. 

Asbtract ( )  

References | Related Articles | Metrics

The risk measurement and selection optimization of project portfolio is studied based on the asymmetric interaction effects. The project portfolio interaction effects is described from three aspects of resource, outcome and technology, an risk measurement method for project portfolio with risk interaction effects is put forward based on the niche theory and the niche overlap theory and then the selecting optimization model for profit maximum and risk minimization of the project portfolio is established. According to the model, the method is designed and an example is given. The result shows that interaction effects have significant effects on portfolio risk measurement and project selection, which also provide a new perspective and ideas for the research into project portfolio.

Pricing of Collateralized Debt Obligation Based on Copula

WU Heng-yu, LI Bing, YAN Wu, LV Jiang-lin

2011, 20(6):  127-136. 

Asbtract ( )  

References | Related Articles | Metrics

Collateralized debt obligation played an important role in US subprime financial crisis. So theorists pay more attention to acurate pricing of it. The paper uses KMV model to assess default probability of every obligor and their correlation coefficient between them with three Copulas and simulate default time,and then price every tranches of collateralized debt obligation.It is found that the fair premium based on Student-t Copula is higher than Gaussion Copula and Clayton Copula, and the higher the fair premium of every tranch is, the longer CDO time and recovery rate are.

The Market Price of Risk in RMB Interest Rate Swaps

CHEN-Ke , REN Zhao-zhang

2011, 20(6):  137-146. 

Asbtract ( )  

References | Related Articles | Metrics

This paper studies the market prices for the liquidity and default risks incorporated into RMB interest rate swap spreads. We apply three-factor generalized Gaussian affine model, and jointly model the RMB Treasury, repo and swap term structures. The parameters are estimated using maximum likelihood method. The result shows that in the current pricing process on RMB interest rate swaps, the liquidity factors are relatively more important than the default factors, and the market gives the liquidity risks significant risk premia. RMB interest rate swaps can be priced with Repo rates as their benchmark plus credit risk premia when applying swap spread method to them.

Bayesian Filtering Method for Stock Index Dynamic Characteristics with Regime-Switching

HAO Li-ya, ZHU Hui-ming, YU Ke-ming

2011, 20(6):  147-156. 

Asbtract ( )  

References | Related Articles | Metrics

To demystify the regime-switching information hidden in the stock index, a kind of non-Gauss nonlinear state space model is brought forward to allow for fat-tails in the mean equation innovation to capture the changes in volatility caused by economic forces and for Markov switching process in the latent volatility equation. In the sequential Bayesian perspective we provide a Bayesian filtering algorithm for parameter learning and state filtering of the model. In empirical study, the regime-switching information based on the stochastic volatility model is demystified by using this algorithm on CSI300 index spots open price futures. In the applications, we compare the algorithm with MCMC method in both efficiency and accuracy. We find that the Bayesian filtering algorithm outperforms existing MCMC.

Abnormal Media Information May Have No Benefit for Stock Returns

WANG Su-sheng, LIU Yan

2011, 20(6):  157-164. 

Asbtract ( )  

References | Related Articles | Metrics

This paper applies the residual attention model to test the relationship between abnormal media information and stock returns with a special sample, in order to provide investors with some guides to make decisions. We find that relative to stocks with low abnormal media information, those stocks with high abnormal media information will have lower returns in the next month. The “media effect” exists in Chinese stock market. A long-short equity strategy can earn excess returns even after controlling well-known risk factors. The result is robust. Furthermore, our findings suggest that the excess return from “media effect” is due to the significantly low returns of high abnormal media information stocks. We believe that the explanation of this asymmetry phenomenon is possibly the stock price’s overreaction to media coverage caused by investor sentiment, which yields lower expected returns.

Management Science

Research on Individual Advantage Identification and Evaluation of Organizational Learning Capacity

JIA Jian-feng, ZHAO Xi-nan, SUN Shi-min

2011, 20(6):  165-171. 

Asbtract ( )  

References | Related Articles | Metrics

Organizational learning capacity is a multidimensional concept. It is conducive to the promotion of organizational performance improvement to identify individual advantage and evaluate the situation of organizational learning capacity. In accordance with the idea of goal programming and q-norm distance, an individual advantage identification method of organizational learning capacity is put forward. The method identifies individual advantage from the view of respecting each evaluator, and on this basis, comprehensive evaluation conclusion is given. Taking 20 divisions of a large domestic software enterprise as a study sample, an empirical study is made, in which organizational learning capacity is composed of discovering capacity, innovating capacity, selecting capacity, executing capacity, transferring capacity, reflecting capacity, capacity of acquiring knowledge from environment, capacity of contributing knowledge to environment, and capacity of building organizational memory. the research result shows that evaluation method of organizational learning capacity based on individual advantage is in line with “people-oriented management” thinking, easy to be accepted by evaluators, and has the characteristics of objectivity and benchmarking effects.

Study on Process Planning of Data Entering Outsourcing Based on Cost Object

WU Feng, LIU Ming

2011, 20(6):  172-181. 

Asbtract ( )  

References | Related Articles | Metrics

The key factors in volved inprocess programming of data entering in BPO are analyzed,which include requirements of task,process method, schedule and equipment. The programming method is used to build the maths model, and the Genetic algorithm(GA)is selected to solve the optimization model in view of its easy encoding easy, fast search and robustness compared to other methods. According to the characteristics of the model, the normal GA is used for single-objective optimization. A case study is conducted and solved by MATLAB,and it shows this method is effective.

Research into Objective Self-Determined Evaluation Based on Two-Dimension IOWA Operator

YI Ping-tao, LI Wei-wei, GUO Ya-jun

2011, 20(6):  182-187. 

Asbtract ( )  

References | Related Articles | Metrics

This paper does research on objective self-determineed evaluation question, in which every evaluation object is viewed as an independent agent. First, each evaluation agent’s competitive view is defined, and then the notion of attributes absolute and relative advantage degrees is given independently according to the attributes values distribution. Based on this, the attribute absolute and relative advantage degrees are viewed as induced component in order to reorder the attributes. And then the reordered attributes poison weighting vector is determined under the hypothesis of weights non-dictatorship. At last, an application is given to illustrate the using of this method, and the application results show that this method can not only improve every evaluation object’s competition advantage, but also increase the result acceptability. So this method is valid.

A Method for Estimating Risks Considering the Interrelationships Among Risks

ZHANG Lei, FAN Zhi-ping, YUE Qi

2011, 20(6):  188-195. 

Asbtract ( )  

References | Related Articles | Metrics

In this paper, with respect to the risk estimation problem considering the interrelationships among risks, a method for estimating risks is proposed. Firstly, according to the evaluation information provided by a panel of experts, the interrelationships among risks are identified by constructing an integration interaction matrix, and a hierarchical structure of risks is determined. Then, according to the divided or undivided hierarchical structure of risks and information on risk probabilities and risk losses provided by the experts, each risk value is calculated using the related knowledge of probability theory. Finally, an example is given to illustrate the feasibility and availability of the proposed method.

Evaluation on the Efficiency of the Input and Output of Science and Technology Based on Composite DEA and Malmquist Index

CHEN Yan-wu

2011, 20(6):  196-204. 

Asbtract ( )  

References | Related Articles | Metrics

This paper applies nonparametric DEA method to the evaluation of the efficiency of science and technology of nine cities of Fujian Province during 2004 and 2008, and uses compound DEA method and Malmquist index to analyze the forming reasons and dynamic productivity variation of non-DEA efficiency regions of the efficiency of science and technology of Fujian Province. Positive results show that the efficiency of science and technology of cities of Fujian Province generally shows an upward tendency, yet there exist relatively great disparities in the scope and efficiency of the science and technology input and output between different regions. And the increase of productivity is mainly contributed by the technical efficiency, while the technology progress fluctuates. The pull of technology progress to the productivity needs further strengthening and consolidation. And R&D input should be improved and introduction and innovation of science should be strengthened,and assimilation innovation should be emphasized.

Research on the Optimization Problem of Production Process Based on Time Constraint

WU Ying-feng, LI Hong-lou, WANG Da-wei

2011, 20(6):  205-209. 

Asbtract ( )  

References | Related Articles | Metrics

This paper proposes a real life problem of optimization of production process: optimization of production process based on Time constraint. According to custom’s demand, it needs to complete the productive task of designated work pieces in a strict time window. The real life problem is originated form the produce demand. The objective is to minimize the total cost of production process, satisfying the time constraint. In this paper, the real life problem is formulated as an integer programming model. As a case study, a software package(Cplex 9.0)is applied for the production process of slave cylinder in some manufactory.

Research on Construction Safety Supervision Based on Evolutionary Game Theory

CHENG Min, CHEN Hui

2011, 20(6):  210-215. 

Asbtract ( )  

References | Related Articles | Metrics

Based on the assumption that both the construction enterprise and supervision department have bounded rationality, the interaction mechanism and stable state between the safety production strategy of construction enterprise and the supervision strategy of supervision department is analyzed with evolutionary game theory in this paper. A numerical example is given for construction enterprise and the strategy that enterprise and supervision department will chose is discussed. The results demonstrate that the stable state of construction safety supervision is related to certain key factors including cost of regulatory procedures, probability of accidents, loss of construction enterprises resulted from accidents, cost of safety supervision and penalty strength. Based on the analysis, several effective measures for construction safety supervision are presented.

Study on Differential Pricing Decisions for the Product with Multiple Warranty under Pro-rata Warranty Policy

LU Zhen, WANG Li-ying

2011, 20(6):  216-221. 

Asbtract ( )  

References | Related Articles | Metrics

Warranty service is a contract between manufacture and consumer, which is usually applied to sales promotion. The price is related to warranty length of product. Considering the reality, based on the consumer utility theory, assuming pro-rata warranty policy and the product failure with Index distribution function, in order to maximum manufacture’s revenue, It studies the differential pricing issues for the product with multiple warranty. It analyzes the optimal combinational strategy with pricing and warranty, and employs optimization theory and method to derive the optimal pricing policy, and verifies the validity of the model through the numerical analysis and analyzes the difference between differential pricing and single pricing. Then it analyzes the impact of the consumer shift flexibility to the benefits of manufacturers.

Empirical Analysis on Influencing Factors of Anhui Private-owned Tech Enterprises’ Salary Incentive

LENG Hui, LIU Xiao-feng

2011, 20(6):  222-225. 

Asbtract ( )  

References | Related Articles | Metrics

Based on the research hypothesis about the influencing factors of Anhui private-owned tech enterprises’ salary incentive, this paper mainly tests the improvement space of private-owned tech enterprises in the status and effect of salary incentive by the data statistics and empirical analysis of choosing valid samples and variables. Finally from the status of Anhui private-owned tech enterprises’ salary incentive, this paper analyzes the goal,the level and the structure of salary incentive based on strategic and system aspect, and put forward relevant policies and proposals.

A Credit Rating Model for Enterprises Based on Projection Pursuit and Optimal Partition

ZHANG Mu, ZHOU Zong-fang

2011, 20(6):  226-231. 

Asbtract ( )  

References | Related Articles | Metrics

A new credit rating model for enterprises based on projection pursuit and optimal partition is presented in this paper. Using projection pursuit, the comprehensive credit score of each sample is obtained. After sorting the comprehensive credit score descending, the ordered sample series is generated. A clustering analysis of the ordered samples is carried out with the optimal partition method, so the clustering results are obtained definitely. And then, each optimal partition point is regarded as the threshold to divide the credit grades. Finally, the credit rating for enterprises is achieved. Through a specific example, it is proved that the model proposed by this paper is feasible and effective.