In this thesis, we propose a model which applies the genetic programming (GP) to train the profitable and stable trading strategy in the training period, and then the strategy is applied to trade stocks in the testing period. The variables for GP in our models include 6 basic information and 25 technical indicators. We perform our models on Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) from 2000/9/14 to 2010/5/21, approximately ten years. We conduct five experiments. In these experiments, we find that the trading strategies generated by GP with two arithmetic trees have more stable returns. In addition, if we obtain the trading strategies in three historical periods which are the most similar to the current training period, we earn higher return in the testing periods. In each experiment, 24 cases are considered, with training periods of 90, 180, 270, 365, 455, 545, 635 and 730 days, and testing periods of 90, 180 and 365 days, respectively. The testing period is rolling updated until the end of the experiment period. The best cumulative return 165.30\% occurs when 730-day training period pairs with 365-day testing period, which is much higher than the return of the buy-and-hold strategy 1.19\%.

No description available.

Thesis (Ph. D.)--Missouri University of Science and Technology, 2009. / Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed January 5, 2010) Includes bibliographical references (p. 152-159).

The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file. Title from PDF of title page (University of Missouri--Columbia, viewed on January 19, 2010). Thesis advisor: Dr. Tina Smilkstein. Includes bibliographical references.

This research addresses the design and development of a decision support tool to provide healthcare policy makers with insights and feedback when evaluating proposed patient flow and infection mitigation and control strategies in the emergency department (ED). An agent-based modeling (ABM) approach was used to simulate EDs, designed to be tuneable to specific parameters related to specification of topography, agent characteristics and behaviours, and the application in question. In this way, it allows for the user to simulate various ‘what-if’ scenarios related to infection spread and patient flow, where such policy questions may otherwise be left “best intent open loop” in practice. Infection spread modeling and patient flow modeling have been addressed by mathematical and queueing models in the past; however, the application of an ABM approach at the level of an institution is novel. A conjecture of this thesis is that such a tool should be augmented with Machine Learning (ML) technology to assist in performing optimization or search in which patient flow and infection spread are signals or variables of interest. Therefore this work seeks to design and demonstrate a decision support tool with ML capability for optimizing ED processes. The primary contribution of this thesis is the development of a novel, flexible, and tuneable framework for spatial, human-scale ABM in the context of a decision support tool for healthcare policy relating to infection spread and patient flow within EDs . The secondary contribution is the demonstration of the utility of ML for automatic policy generation with respect to the ABM tool. The application of ML to automatically generate healthcare policy in concert with an ABM is believed to be novel and of emerging practical importance. The tertiary contribution is the development and testing of a novel heuristic specific to the ML paradigm used: Genetic Programming (GP). This heuristic aids learning tasks performed in conjunction with ABMs for healthcare policy. The primary contribution is clearly demonstrated within this thesis. The others are of a more difficult nature; the groundwork has been laid for further work in these areas that are likely to remain open for the foreseeable future.

This research addresses the design and development of a decision support tool to provide healthcare policy makers with insights and feedback when evaluating proposed patient flow and infection mitigation and control strategies in the emergency department (ED). An agent-based modeling (ABM) approach was used to simulate EDs, designed to be tuneable to specific parameters related to specification of topography, agent characteristics and behaviours, and the application in question. In this way, it allows for the user to simulate various ‘what-if’ scenarios related to infection spread and patient flow, where such policy questions may otherwise be left “best intent open loop” in practice. Infection spread modeling and patient flow modeling have been addressed by mathematical and queueing models in the past; however, the application of an ABM approach at the level of an institution is novel. A conjecture of this thesis is that such a tool should be augmented with Machine Learning (ML) technology to assist in performing optimization or search in which patient flow and infection spread are signals or variables of interest. Therefore this work seeks to design and demonstrate a decision support tool with ML capability for optimizing ED processes. The primary contribution of this thesis is the development of a novel, flexible, and tuneable framework for spatial, human-scale ABM in the context of a decision support tool for healthcare policy relating to infection spread and patient flow within EDs . The secondary contribution is the demonstration of the utility of ML for automatic policy generation with respect to the ABM tool. The application of ML to automatically generate healthcare policy in concert with an ABM is believed to be novel and of emerging practical importance. The tertiary contribution is the development and testing of a novel heuristic specific to the ML paradigm used: Genetic Programming (GP). This heuristic aids learning tasks performed in conjunction with ABMs for healthcare policy. The primary contribution is clearly demonstrated within this thesis. The others are of a more difficult nature; the groundwork has been laid for further work in these areas that are likely to remain open for the foreseeable future.

本文以2003至2009年的資料為研究區間，採用基本面分析指標、技術面分析指標及基因規畫法對倫敦黃金午後定盤價每季帄均塑造金價預測模型，同時歸納以基因規畫法塑造金價預測模型時，應使用何種投入指標與相關基因規畫法參數設定，較有機會獲得較佳預測力的金價預測模型。 最後發現對於黃金價格而言，各國股市大盤及黃金供需相關因素為使用基因規畫法塑造金價預測模型時較重要的指標種類，而於經濟狀況有劇烈變動時，加入技術分析指標將會改善模型的表現。而比較指標與基因規畫設定參數(如挑選函式、運算子集合、演化代數、染色體群大小)對模型預測力之影響，發現指標對模型預測力的影響遠大於基因規畫設定參數。 / The research uses the data between 2003 to 2009 to discuss the gold price forecastting model. Using fundamental analysis indices, technical analysis indices and Genetic Programming(GP) to modeling the gold price forecastting model. This paper also summarized that what kind of indexes and GP parameters should be set for getting better performance? Finally found that ,using the stock indices of important market and gold supply/demand factors to modeling usually get better performance. If there are drastic changes in economic conditions, using the technical analysis indices can improve the performance of model. The comparison of influence on model performance between indexes and GP parameters(ex. selecetio function, operator set, reproducting times, population size) show that, the indices have more influence to model performance than GP parameters.

Evolvable Hardware is a technique derived from evolutionary computation applied to a hardware design. The term evolutionary computation involves similar steps as involved in the human evolution. It has been given names in accordance with the electronic technology like, Genetic Algorithm (GA), Evolutionary Strategy (ES) and Genetic Programming (GP). In evolutionary computing, a configured bit is considered as a human chromosome for a genetic algorithm, which has to be downloaded into hardware. Early evolvable hardware experiments were conducted in simulation and the only elite chromosome was downloaded to the hardware, which was labelled as Extrinsic Hardware. With the invent of Field Programmable Gate Arrays (FPGAs) and Reconfigurable Processing Units (RPUs), it is now possible for the implementation solutions to be fast enough to evaluate a real hardware circuit within an evolutionary computation framework; this is called an Intrinsic Evolvable Hardware. This research has been taken in continuation with project 'Evolvable Hardware' done at Manukau Institute of Technology (MIT). The project was able to manually evolve two simple electronic circuits of NAND and NOR gates in simulation. In relation to the project done at MIT this research focuses on the following: To automate the simulation by using In Circuit Debugging Emulators (IDEs), and to develop a strategy of configuring hardware like an FPGA without the use of their company supplied in circuit debugging emulators, so that the evolution of an intrinsic evolvable hardware could be controlled, and is hardware independent. As mentioned, the research conducted here was able to develop an evolvable hardware friendly Generic Structure which could be used for the development of evolvable hardware. The structure developed was hardware independent and was able to run on various FPGA hardware’s for the purpose of intrinsic evolution. The structure developed used few configuration bits as compared to current evolvable hardware designs.

Thesis (Ph.D.)--Auburn University, 2007. / Abstract. Includes bibliographic references (ℓ. 167-176)

Thesis (Ph. D.)--Electrical and Computer Engineering, Georgia Institute of Technology, 2007. / Committee Chair: Vachtsevanos, George J.; Committee Co-Chair: Litt, Brian; Committee Member: Butera, Robert J.; Committee Member: Echauz, Javier; Committee Member: Howard, Ayanna M.; Committee Member: Williams, Douglas B.