The purpose of this study was to develop a decision model for early-stage breast cancer patients. This model provides an opportunity for comparing two main treatment options, mastectomy and lumpectomy, with respect to quality of life by making use of Decision Theoretic Techniques. A Markov chain was constructed to project the clinical history of breast carcinoma following surgery. Then, health states used in the model were characterized by transition probabilities and utilities for quality of life. A Multi Attribute Utility Model was developed for outcome evaluation. This study was performed on the sample population of female university students, and utilities were elicited from these healthy volunteers. The results yielded by Multi Attribute Utility Model were validated by using Von Neumann-Morgenstern Standard Gamble technique. Finally, Monte Carlo Simulation was utilized in Treeage-Pro 2006 Suit software program in order to solve model and calculate expected utility value generated by each treatment option. The results showed that lumpectomy is more favorable for people who participated in this study. Sensitivity analysis on transition probabilities to local recurrence and salvaged states was performed and two threshold values were observed. Additionally, sensitivity analysis on utilities showed that the model was more sensitive to no evidence of disease state / however, was not sensitive to utilities of local recurrence and salvaged states.

In this thesis, an information system is designed and developed for engineer-to-order organizations to improve the traditional Bill-of-Material by handling variants of products and components efficiently. A database is developed to store the related information about inventories and configuration management in an effective way. The improved Bill-of-Material provides a common structure to access stored information for material management purposes. A model, based on network, is presented and included into the system for calculating time required to produce components and to make subassemblies or assemblies with the current inventory levels. The system is applied to T&Uuml / BiTAK-SAGE, which is an engineer-to-order organization carrying out Research and Development projects for Defense Industry.

In this study, a Lagrangean heuristic based on Lagrangean relaxation and subgradient optimization is proposed for the two-stage modular capacitated facility location problem. The objective is to minimize the cost of locating and operating plants and warehouses, plus the cost of transporting goods at both echelons to satisfy the demand of customers. The difference of our study from the two-stage capacitated facility location problem is the existence of multiple capacity levels as a candidate for each plant in the problem. Each capacity level has a minimum production capacity which has to be satisfied to open the relevant capacity level. Obviously, a single capacity level can be selected for an opened facility location. In the second echelon, the warehouses are capacitated and have unique fixed and variable costs for opening and operating. Multiple sourcing is allowed in both transportation echelons. Firstly, we develop a mixed integer linear programming model for the two-stage modular capacitated facility location problem. Then we develop a Lagrangean heuristic to solve the problem efficiently. Our Lagrangean heuristic consists of three main components: Lagrangean relaxation, subgradient optimization and a primal heuristic. Lagrangean relaxation is employed for obtaining the lower bound, subgradient optimization is used for updating the Lagrange multipliers at each iteration, and finally a three-stage primal heuristic is created for generating the upper bound solutions. At the first stage of the upper bound heuristic, global feasibility of the plants and warehouses is inspected and a greedy heuristic is executed, if there is a global infeasibility. At the next stage, an allocation heuristic is used to assign customers to warehouses and warehouses to plants sequentially. At the final stage of the upper bound heuristic, local feasibilities of the plants are investigated and infeasible capacity levels are adjusted if necessary. In order to show the efficiency of the developed heuristic, we have tested our heuristic on 280 problem instances generated randomly but systematically. The results of the experiments show that the developed heuristic is efficient and effective in terms of solution quality and computational effort especially for large instances.

In this thesis, we study both dynamic and distributed facility layout problems, where the demand for product mix changes over time. We propose a new simulated annealing algorithm, SALAB, for the dynamic facility layout problem. Four variants of SALAB find the best known solution for 20 of the 48 benchmark problems from the literature, improving upon the best known solutions of 18 problems. We modify SALAB to obtain DSALAB, solving the dynamic distributed facility layout problem with the objective of minimizing relocation cost and total (full and empty) travel cost of the material handling system. We simulate DSALAB solutions of randomly generated problems to study the tradeoff between total cost and congestion in the system. Our experimental results indicate that distributing the department duplicates throughout the facility reduces the total cost with diminishing returns and causes increasing congestion. Therefore, distribution beyond a certain level is not justified.

In this study, our aim is to determine the locations of bottle banks used in collecting recycled glass. The collection of recycled glass is done by a fleet of vehicles that visit some predetermined collection points, like restaurants and hospitals. The location of bottle banks depends on the closeness of the banks to the population zones where the recycled class is generated, and to the closeness of the banks to the predetermined collection points. A mathematical model, which combines the maximal covering problem in the presence of partial coverage and vehicle routing problem with profits, is presented. Heuristic procedures are proposed for the solution of the problem. Computational results based on generated test problems are provided. We also discuss a case study, where bottle banks are located in Yenimahalle, a district of Ankara

Returned products of many industries are transported backwards through supply chains for recovery, thus forming &ldquo / closed-loop supply chains&rdquo / . Benefits, forthcoming with more effective management of recovery of returns are gaining importance. However, some issues, such as lack of information required to assess the quality of the returned products, may translate into critical uncertainties in the product recovery decisions and prevent closed-loop supply chains from operating efficiently. Hence, it is envisaged that significant economies may be attained by increasing the quantity of information fed into the planning decisions related to returned products. Thus, the objective of this study is to test the hypothesis that ready availability of perfect quality grade information associated with returned products by means of &ldquo / embedded systems&rdquo / , may lead to improved over all performance of recovery operations. To this end, in this thesis, linear programming models of generic multistage recovery processes are built. It is demonstrated by computational studies that significant gains may be obtained especially in environments where the prices of recovered products are decreasing in time.

Quality has become a central concern as it has been observed that reducing defects will lower the cost of production. Hence, companies generate and store vast amounts of quality related data. Analysis of this data is critical in order to understand the quality problems and their causes, and to take preventive actions. In this thesis, we propose a methodology for this analysis based on one of the data mining techniques, association rules. The methodology is applied for quality related data of an electronics company. Apriori algorithm used in this application generates an excessively large number of rules most of which are redundant. Therefore we implement a three phase elimination process on the generated rules to come up with a reasonably small set of interesting rules. The approach is applied for two different data sets of the company, one for production defects and one for raw material non-conformities. We then validate the resultant rules using a test data set for each problem type and analyze the final set of rules.

In industrial quality improvement and design studies, an important aim is to improve the product or process quality by determining factor levels that would result in satisfactory quality results. In these studies, quality characteristics that are qualitative are often encountered. Although there are many effective methods proposed for parameter optimization (robust design) with continuous responses, the methods available for qualitative responses are limited. In this study, a parameter optimization method for solving binary response robust design problems is proposed. The proposed method uses Mahalanobis Taguchi System to form a classification model that provides a distance function to separate the two response classes. Then, it finds the product/process variable settings that minimize the distance from the desired response class using quadratic programming. The proposed method is applied on two cases previously studied using Logistic Regression. The classification models are formed and the parameter optimization is conducted using the formed MTS models. The results are compared with those of the Logistic Regression. Conclusions and suggestions for future work are given.

In this study, we propose a bi-objective facility location model that considers both partial coverage and service to uncovered demands. In this model, it is assumed that the demand nodes within the predefined distance of opened facilities are fully covered and after that distance the coverage level linearly decreases. The objectives are the maximization of the sum of full and partial coverage the minimization of the maximum distance between uncovered demand nodes and their closest opened facilities. We apply two existing Multi Objective Genetic Algorithms (MOGAs), NSGA-II and SPEA-II to the problem. We determine the drawbacks of these MOGAs and develop a new MOGA called modified SPEA-II (mSPEA-II) to avoid the drawbacks. In this method, the fitness function of SPEA-II is modified and the crowding distance calculation of NSGA-II is used. The performance of mSPEA-II is tested on randomly generated problems of different sizes. The results are compared with the solutions resulting from NSGA-II and SPEA-II. Our experiments show that mSPEA-II outperforms both NSGA-II and SPEA-II.

In this study we focus on two-sided mixed-model assembly line balancing type-I problem. There is a production target for a fixed time horizon and the objective is to produce this amount with the minimum level of workforce. A mathematical model is developed to solve this problem in an optimal manner. For large scale problems, the mathematical model fails to give the optimal solution within reasonable computational times. Thus, a heuristic approach based on threshold accepting algorithm is presented. Both the mathematical model and the heuristic approach are executed to solve several example problems from the literature and a case study problem which is derived from the refrigerator production. Computational experiments are carried out using both approaches. It is observed that the heuristic procedure finds good solutions within very reasonable computational times.