Dissertations / Theses on the topic 'Genetic Expression Programming'

Genetic Programming (GP) is an Evolutionary Computation technique. Genetic Programming refers to a programming strategy where an artificial population of individuals represent solutions to a problem in the form of programs, and where an iterative process of selection and reproduction is used in order to evolve increasingly better solutions. This strategy is inspired by Charles Darwin's theory of evolution through the mechanism of natural selection. Genetic Programming makes use of computational procedures analogous to some of the same biological processes which occur in natural evolution, namely, crossover, mutation, selection, and reproduction. Cartesian Genetic Programming (CGP) is a form of Genetic Programming that uses directed graphs to represent programs. It is called 'Cartesian', because this representation uses a grid of nodes that are addressed using a Cartesian co-ordinate system. This stands in contrast to GP systems which typically use a tree-based system to represent programs. In this thesis, we will show how it is possible to enhance and extend Cartesian Genetic Programming in two ways. Firstly, we show how CGP can be made to evolve programs which make use of image manipulation functions in order to create image manipulation programs. These programs can then be applied to image classification tasks as well as other image manipulation tasks such as segmentation, the creation of image filters, and transforming an input image in to a target image. Secondly, we show how the efficiency - the time it takes to solve a problem - of a CGP program can sometimes be increased by reinterpreting the semantics of a CGP genome string. We do this by applying Multi-Expression Programming to CGP.

FIR filters are widely used nowadays, with applications from MP3 players, Hi-Fi systems, digital TVs, etc. to communication systems like wireless communication. They are implemented in DSPs and there are several trade-offs that make important to have an exact as possible estimation of the required filter order.

In order to find a better estimation of the filter order than the existing ones, genetic expression programming (GEP) is used. GEP is a Genetic Algorithm that can be used in function finding. It is implemented in a commercial application which, after the appropriate input file and settings have been provided, performs the evolution of the individuals in the input file so that a good solution is found. The thesis is the first one in this new research line.

The aim has been not only reaching the desired estimation but also pave the way for further investigations.

PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO
Esta Pesquisa tem por objetivo utilizar a Regressão Simbólica por Programação Genética para encontrar uma equação analítica para a fronteira de exercício ótima (ou curva de gatilho) de uma opção sobre um ativo do qual o preço tem um comportamento simulado pelo processo estocástico conhecido como processo de reversão à média (PRM). Para o cálculo do valor de uma opção desde de sua aquisição até sua maturação, normalmente faz-se o uso do cálculo da fronteira de exercício ótimo. Esta curva separa ao longo do tempo a decisão de exercer ou não a opção. Sabendo-se que já existem soluções analíticas para calcular a fronteira de exercício ótimo quando o preço do ativo segue um Movimento Geométrico Browniano, e que tal solução genérica ainda não foi encontrada para o PRM, neste trabalho, foi proposto o uso da Programação Genética (PG) para encontrar tal solução analítica. A Programação Genética utilizou um conjunto de amostras de curvas de exercício ótimo parametrizadas segundo a variação da volatilidade e da taxa de juros livre de risco, para encontrar uma função analítica para a fronteira de exercício ótima, obtendo-se resultados satisfatórios.
This research intends on to use the Symbolic Regression by Genetic Programming to find an analytical equation that represents an Optimal Exercise Boundary for an option of an asset having its price behavior simulated by a stochastic process known as Mean Reversion Process (MRP). To calculate an option value since its acquisition until its maturity, normally is used to calculate the Optimal Exercise Boundary. This frontier separates along the time the decision to exercise the option or not. Knowing there already are analytical solutions used to calculate the Optimal Exercise Boundary when the asset price follows the Geometric Brownian Motion, and such general solution was not found yet to MRP, in this work, it was proposed the use of Genetic Programming to find such analytical solution. The Genetic Programming used an amount of samples from optimal exercise curves parameterized according the change in the volatility and risk free interest rate, to find an analytical function that represents Optimal Exercise Boundary, achieving satisfactory results.

This thesis explores Web Information Extraction (WIE) and how it has been used in decision making and to support businesses in their daily operations. The research focuses on a WIE system based on Genetic Programming (GP) with an extensible model to enhance the automatic extractor. This uses a human as a teacher to identify and extract relevant information from the semi-structured HTML webpages. Regular expressions, which have been chosen as the pattern matching tool, are automatically generated based on the training data to provide an improved grammar and lexicon. This particularly benefits the GP system which may need to extend its lexicon in the presence of new tokens in the web pages. These tokens allow the GP method to produce new extraction patterns for new requirements.

Web Information Extraction (WIE) is the discipline dealing with the discovery, processing and extraction of specific pieces of information from semi-structured or unstructured web pages. The World Wide Web comprises billions of web pages and there is much need for systems that will locate, extract and integrate the acquired knowledge into organisations practices. There are some commercial, automated web extraction software packages, however their success comes from heavily involving their users in the process of finding the relevant web pages, preparing the system to recognise items of interest on these pages and manually dealing with the evaluation and storage of the extracted results. This research has explored WIE, specifically with regard to the automation of the extraction and validation of online training information. The work also includes research and development in the area of automated Web Information Retrieval (WIR), more specifically in Web Searching (or Crawling) and Web Classification. Different technologies were considered, however after much consideration, Naïve Bayes Networks were chosen as the most suitable for the development of the classification system. The extraction part of the system used Genetic Programming (GP) for the generation of web extraction solutions. Specifically, GP was used to evolve Regular Expressions, which were then used to extract specific training course information from the web such as: course names, prices, dates and locations. The experimental results indicate that all three aspects of this research perform very well, with the Web Crawler outperforming existing crawling systems, the Web Classifier performing with an accuracy of over 95% and a precision of over 98%, and the Web Extractor achieving an accuracy of over 94% for the extraction of course titles and an accuracy of just under 67% for the extraction of other course attributes such as dates, prices and locations. Furthermore, the overall work is of great significance to the sponsoring company, as it simplifies and improves the existing time-consuming, labour-intensive and error-prone manual techniques, as will be discussed in this thesis. The prototype developed in this research works in the background and requires very little, often no, human assistance.

Sabe-se que algumas alterações nutricionais maternas durante o período perinatal estão associadas com doenças metabólicas na vida adulta das proles, tais como diabetes melito tipo 2, resistência à insulina, obesidade e hipertensão arterial. O período da gestação em que estas alterações nutricionais influenciam a prole na idade adulta ainda não está elucidado. Modificações epigenéticas têm sido propostas como mecanismos responsáveis por estas desordens metabólicas. Ratas Wistar de doze semanas de idade foram alimentadas com dieta com conteúdo baixo (HO - 0,15% NaCl) ou normal (NR - 1,3% NaCl) de sódio desde o primeiro dia de gestação até o nascimento da prole ou HO durante a primeira (HO10) ou segunda (HO20) metade da gestação. O peso corpóreo e a ingestão de água e ração foram avaliados semanalmente durante a gestação. Teste de tolerância à insulina (ITT) e à glicose (GTT) e HOMA-IR foram realizados nas proles adultas. Expressão gênica por qRT-PCR e metilação do DNA na região promotora dos genes foram mapeadas utilizando tratamento com bissulfito de sódio e avaliadas por pirosequenciamento. O ganho de peso materno foi menor no HO e HO20 na terceira semana de gestação em comparação com NR e HO10. O peso ao nascimento da prole foi menor em machos e fêmeas dos grupos HO e HO20 em relação ao NR e HO10. O HOMA-IR foi maior nos machos com 12 semanas de idade do grupo HO em comparação com NR e com 20 semanas de idade do grupo HO10 em comparação com NR e HO20. Nas fêmeas com 12 semanas de idade o HOMA-IR foi maior no HO10 comparado com HO. Os níveis de insulina no soro foram maiores tanto nos machos com 20 semanas de idade do grupo HO10 comparado com NR quanto nas fêmeas com 12 semanas de idade do grupo HO10 comparado com HO. A área sob a curva do GTT indicou intolerância à glicose nos machos do grupo HO. A porcentagem de metilação das ilhas CpG no promotor dos genes de Igf1, Igf1r, Ins1, Ins2 e Insr no fígado de machos e fêmeas neonatais e no fígado, tecido adiposo branco e músculo em machos com 20 semanas de idade foi influenciada pela baixa ingestão de sal durante a gestação. Nenhuma destas alterações foi identificada nas fêmeas com 20 semanas de idade. Em conclusão, a baixa ingestão de sal na segunda metade da gestação é responsável pelo baixo peso ao nascimento em ambos os sexos. A intolerância à glicose observada na prole adulta ocorreu somente se a dieta hipossódica é dada durante a gestação inteira. Por outro lado, a resistência à insulina em resposta ao consumo de dieta hipossódica durante a gestação está relacionada com o momento em que ocorre este insulto e com o envelhecimento da prole. Também foi observado que alterações na metilação do promotor do gene Igf1 está correlacionado com o baixo peso ao nascimento em resposta a ingestão de dieta hipossódica durante a gestação
It is known that some maternal nutritional alterations during pregnancy are associated with metabolic disorders in adult offspring, such as insulin resistance, type 2 diabetes mellitus, obesity and arterial hypertension. The period of pregnancy in which these nutritional alterations influence adult offspring remains uncertain. Epigenetic changes are proposed to underlie these metabolic disorders. Twelve-week-old female Wistar rats were fed a low-salt (LS - 0.15% NaCl) or normal-salt (NS - 1.3% NaCl) diet since the first day of gestation until delivery or LS during the first (LS10) or second (LS20) half of gestation. Body weight, food and water intake were weekly evaluated during gestation. Blood glucose, insulin (ITT) and glucose (GTT) tolerance tests, HOMA-IR were performed in adult offspring. Gene expression and DNA methylation were mapped using bisulfite treatment evaluated by pyrosequencing in the male and female neonates and adult offspring. Weight gain was lower in LS and LS20 dams than in NS and LS10 dams in the third week of pregnancy. Birth weights were lower in male and female LS20 and LS rats compared with NS and LS10 neonates. HOMA-IR was higher in 12-week-old LS males compared with NS and in 20-week-old male LS10 rats compared with NS and LS20 rats. In 12-week-old LS10 females, HOMA-IR was higher than in LS. Serum insulin levels were higher in 20 week-old LS10 male compared with NS rats and in 12-week-old LS10 female compared to LS rats. The area under the curve of GTT indicated glucose intolerance in 12- and 20-week-old LS male. Methylation of CpG islands of the Insr, Igf1, Igf1r, Ins1 and Ins2 genes in liver in neonates male and female offspring and liver, white adipose tissue and muscle in 20-week-old male offspring were influenced by low-salt intake during pregnancy. None of these alterations was identified in 20-week-old females. In conclusion, low-salt diet consumption in the second half of pregnancy can result in low birth weights in the males and females offspring. Glucose intolerance observed in adult offspring occurred only if low salt intake was given throughout pregnancy. However, insulin resistance in response to low salt intake during pregnancy is related to the time at which this insult occurs and to the age of the offspring. Alterations in the DNA methylation of Igf1 were observed to be correlated with low birth weight in response to low salt feeding during pregnancy

碩士
元智大學
資訊管理學系
96
There have been many algorithm proposed to solve music classification problems. The composition of music context is complicated, and the music genre is defined by musical perception. Lacking of qualifications to determinate music genres makes music classification more difficult. In this paper, method based on genetic expression programming to classify Midi music files was proposed. This method uses statistical information of Midi file features to classify Midi music genres, and builds models and classification rules. The result can be use for music recommendation or classification systems.

碩士
國立高雄大學
電機工程學系碩士班
98
Global Positioning System (GPS) has been used extensively in various fields. One key to success of using GPS is the positioning accuracy. Geometric Dilution of Precision (GDOP) is an indicator showing how well the constellation of GPS satellites is organized geometrically. Traditional methods for the calculation of GDOP need to solve the measurement equations with complicated matrix transformation and inversion. GDOP can also be viewed as a regression problem from satellite signals. Previous study employs black-boxed machine learning methods for solving this problem. However, the structure of the regression models obtained from these methods is unknown so that they can not be analyzed extensively. This study employs the technique of genetic expression programming (GEP) for the regression of GPS GDOP. The regression models obtained from GEP have visible structures and can be modified in GPS application software. Several new input types for regression are defined. The experimental results show that GEP can generate precise models for GSP GDOP than other regression methods.

Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics
Alignment in the error space is a recent idea to exploit semantic awareness in genetic programming. In a previous contribution, the concepts of optimally aligned and optimally coplanar individuals were introduced, and it was shown that given optimally aligned, or optimally coplanar, individuals, it is possible to construct a globally optimal solution analytically. Consequently, genetic programming methods, aimed at searching for optimally aligned, or optimally coplanar, individuals were introduced. This paper critically discusses those methods, analyzing their major limitations and introduces a new genetic programming system aimed at overcoming those limitations. The presented experimental results, conducted on five real-life symbolic regression problems, show that the proposed algorithms’ outperform not only the existing methods based on the concept of alignment in the error space, but also geometric semantic genetic programming and standard genetic programming.

Finding an optimal solution for the logic circuit design problem is challenging and time-consuming especially for complex logic circuits. As the number of logic gates increases the task of designing optimal logic circuits extends beyond human capability. A number of evolutionary algorithms have been invented to tackle a range of optimisation problems, including logic circuit design. This dissertation explores two of these evolutionary algorithms i.e. Gene Expression Programming (GEP) and Multi Expression Programming (MEP) with the aim of integrating their strengths into a new Genetic Programming (GP) algorithm. GEP was invented by Candida Ferreira in 1999 and published in 2001 [8]. The GEP algorithm inherits the advantages of the Genetic Algorithm (GA) and GP, and it uses a simple encoding method to solve complex problems [6, 32]. While GEP emerged as powerful due to its simplicity in implementation and exibility in genetic operations, it is not without weaknesses. Some of these inherent weaknesses are discussed in [1, 6, 21]. Like GEP, MEP is a GP-variant that uses linear chromosomes of xed length [23]. A unique feature of MEP is its ability to store multiple solutions of a problem in a single chromosome. MEP also has an ability to implement code-reuse which is achieved through its representation which allow multiple references to a single sub-structure. This dissertation proposes a new GP algorithm, Improved Gene Expression Programming (IGEP) which im- proves the performance of the traditional GEP by combining the code-reuse capability and simplicity of gene encoding method from MEP and GEP, respectively. The results obtained using the IGEP and the traditional GEP show that the two algorithms are comparable in terms of the success rate when applied on simple problems such as basic logic functions. However, for complex problems such as one-bit Full Adder (FA) and AND-OR Arithmetic Logic Unit (ALU) the IGEP performs better than the traditional GEP due to the code-reuse in IGEP
Mathematical Sciences
M. Sc. (Applied Mathematics)

碩士
元智大學
資訊工程學系
97
Ethernet Passive Optical Networks (EPONs) are being designed to deliver multiple services and applications. To support these applications with their diverse requirements, EPONs require Quality-of-Service (QoS) mechanisms to build in. This study proposes an adaptive Interleaved Dynamic Bandwidth Allocation (IDBA) scheme incorporated with a Genetic Expression Programming (GEP) performance for traffic prediction mechanism in EPONs. Firstly, the IDBA can resolve the idle period problem in traditional Dynamic Bandwidth Allocation (DBA) mechanism to decrease bandwidth waste by interleaved transition. Secondly, the traffic characteristic in differentiated services is also considered in the proposed Interleaved Waited-Difference Bandwidth Allocation (IWDBA) and GEP prediction mechanism to provide more accurate prediction. Moreover, the remaining bandwidth will be collected and reallocate fairly in next group ONU. Simulation results show the preferable system performance for the proposed IDBA scheme in terms of packet delay, and the wasted bandwidth.

碩士
輔仁大學
資訊管理學系碩士在職專班
103
The securities market is the financial system in an important part, with the fast changing trends in the global financial system, while generating instability risks. And risk management in the financial system in a very important part, through corporate governance mechanisms, can operators make a monitoring and checks and balances to protect shareholders' equity, but how to choose investment targets and funds to make the appropriate configuration for investors even more important. In this study, the use of artificial intelligence in gene expression programming (Gene Expression Programming, GEP)to solve complex problems in a simple coding features, included in the basic analysis, indicators chips analysis and corporate governance, the establishment of stock gene, combined with genetic algorithm (Genetic Algorithm, GA)to establish the allocation of funds gene, with portfolio theory and investment analysis theory, GEP-GA model portfolios, expected to produce a portfolio balance model of corporate governance analysis and chips, improve ROI and risk management mechanisms, It can become investors (institutional investors)new portfolio system. According to experiments, we concluded three results. (1)Of this new combination of research methods of GEP and GA, to build a portfolio model with the allocation of funds to achieve the purpose of risk management, and to enhance the rate of return and reduce risk. (2)Basic analysis GEP design, analysis, and corporate governance picking chips gene added weight ratio, confirmed GEP picking genes affect the optimal portfolio investment decisions and rate of return, which significantly affect the basic analysis of indicators representing its investment combined with the rate of return. (3)The study GEP-GA model to buy stock held by investment performance than TAIEX weighted stock price index, Taiwan medium 100 index, mutual funds, and bank deposit rate of Taiwanese investment performance appraisal, there are a good performance, shows the research proposed GEP-GA system portfolio, the portfolio effect has to be acceptable.

碩士
國立高雄大學
電機工程學系碩士班
104
Path-following is an essential and important task in the applications of autonomous robots. Visual-based control is an emerging method due to its convenience and flexibility. However, the control flow is level-wise transforming from visual signals of tracks to the activation of the hardware actuators, with complicated calculations and inevitably error accumulation. This study presents a new method for the control of visual-based path-following of mobile robots. The control flow of visual-based path-following is rephrased as a regression problem which takes the visual positions of tracks as the input and produces direct control signals as output. To deal with the complex regression problem in this study, the technique of gene expression programming (GEP) is employed for discovering feasible control models. For any tracking paths, a control model can be obtained by collecting visual positions of tracks and the corresponding control signals by GEP. With the regression models, the control of path-following can be done with simpler control rules and less processing time. Our proposed method is implemented and integrated with a two-wheeled service robot carrying a simple CCD camera and is validated for visual path-following in real environments. The experimental results show that the proposed method is able to produce simple and precise control rules and improves the robot's performance for path-following.

碩士
國立交通大學
資訊科學與工程研究所
94
As the increase of knowledge of RNA functions, the research on RNA has recently attracted more attentions than ever. Like other biopolymers, the functions of RNA are dependent upon their structures. Since the effectiveness and efficiency of ab initio 3D structure determination Technologies are still limited, various computational approaches have been proposed. In this thesis, we are focused on RNA secondary structure prediction. Based on the number of RNA for which to predict the structures, computational methods can be classified as single-sequence prediction and multiple-sequence prediction. In general, single-sequence prediction is aimed to find the probable global secondary structures, and on the other hand, multiple-sequence prediction is aimed to identify the common local secondary structures in a given RNA family. Most of the current approaches to multiple-sequence prediction are limited to finding relatively short common structure elements. As a consequence, they fail to identify those longer common structures that may play important biological roles. We propose a multi-strategy method that combines the advantages of both single-sequence and multiple-sequence prediction. By using the prediction results of single-sequence predictors as the basis to form the graphical models of RNA secondary structures, we can improve the performance in multiple-sequence prediction. To demonstrate the efficiency and effectiveness, we tested our new approach on several real-world RNA families downloaded from Rfam. The experiments showed some promising results.