Genetic algorithms

Improving the quality of a product and manufacturing processes at a low cost is an economic and technological challenge which quality engineers and researches must contend with. In general, the quality of products and their cost are the main concerns for manufactures. This is because improving quality is very crucial for staying competitive and improving the organization's market position. However, some difficulty of finding where the standard of good quality is still remains. Customers' satisfaction is a key for setting up the quality target. One possible solution is to develop control limits, which are the limits for indicating the area of nonconforming product on the basis of minimizing the total cost or loss to the customer as well as to the manufacturer. Therefore, the goal of this dissertation is to develop an effective tool to improve a high quality of product while maintaining a minimum cost.

Effective and efficient supply chain management is essential for domestic and global organizations to compete successfully in the international market. Superior inventory control policies and product distribution strategies along with advanced information technology enable an organization to collaborate distribution and allocation of inventory to gain a competitive advantage in the world market. Our research establishes the strategic resource allocation model to capture and encapsulate the complexity of the modern global supply chain management problem. A mathematical model was constructed to depict the stochastic, multiple-period, two-echelon inventory with the many-to-many demand-supplier network problem. The model simultaneously constitutes the uncertainties of inventory control and transportation parameters as well as the varying price factors. A genetic algorithm (GA) was applied to derive optimal solutions through a two-stage optimization process. Practical examples and solutions from three sourcing strategies (single sourcing, multiple sourcing, and dedicated system) were included to illustrate the GA based solution procedure. Our model can be utilized as a collaborative supply chain strategic planning tool to efficiently determine the appropriate inventory allocation and a dynamic decision making process to effectively manage the distribution plan.

In this dissertation we will present a stochastic optimization algorithm and use it and other mathematical techniques to tackle problems arising in medicinal chemistry. In Chapter 1, we present some background about stochastic optimization and the Accelerated Random Search (ARS) algorithm. We then present a novel improvement of the ARS algorithm, DIrected Accelerated Random Search (DARS), motivated by some theoretical results, and demonstrate through numerical results that it improves upon ARS. In Chapter 2, we use DARS and other methods to address issues arising from the use of mixture-based combinatorial libraries in drug discovery. In particular, we look at models associated with the biological activity of these mixtures and use them to answer questions about sensitivity and robustness, and also present a novel method for determining the integrity of the synthesis. Finally, in Chapter 3 we present an in-depth analysis of some statistical and mathematical techniques in combinatorial chemistry, including a novel probabilistic approach to using structural similarity to predict the activity landscape.

During the Leukocytapheresis (LCAP) process used to treat patients suffering from acute Ulcerative Colitis, medical practitioners have to continuously monitor the Hematocrit (Ht) level in the blood to ensure it is within the acceptable range. The work done, as a part of this thesis, attempts to create an early warning system that can be used to predict if and when the Ht values will deviate from the acceptable range. To do this we have developed an algorithm based on the Group Method of Data Handling (GMDH) and compared it to other Neural Network algorithms, in particular the Multi Layer Perceptron (MLP). The standard GMDH algorithm captures the fluctuation very well but there is a time lag that produces larger errors when compared to MLP. To address this drawback we modified the GMDH algorithm to reduce the prediction error and produce more accurate results.

Design of intelligent systems that can learn from the environment and adapt to the change in the environment has been pursued by many researchers in this age of information technology. The Group Method of Data Handling (GMDH) algorithm to be implemented is a multilayered neural network. Neural network consists of neurons which use information acquired in training to deduce relationships in order to predict future responses. Most software tool during the simulation of the neural network based algorithms in a sequential, single processor machine like Pascal, C or C++ takes several hours or even days. But in this thesis, the GMDH algorithm was modified and implemented into a software tool written in Verilog HDL and tested with specific application (XOR) to make the simulation faster. The purpose of the development of this tool is also to keep it general enough so that it can have a wide range of uses, but robust enough that it can give accurate results for all of those uses. Most of the applications of neural networks are basically software simulations of the algorithms only but in this thesis the hardware design is also developed of the algorithm so that it can be easily implemented on hardware using Field Programmable Gate Array (FPGA) type devices. The design is small enough to require a minimum amount of memory, circuit space, and propagation delay.