Submitted in fulfilment of the requirements of the degree of Master of Engineering , Durban University of Technology, Durban, South Africa, 2016. / Reservoirs are designed to specific volume called the dead storage to be able to withstand the quantity of particles in the rivers flowing into it during its design period called its economic life. Therefore, accurate calculation of the quantities of sediment being transported is of great significance in environment engineering, hydroelectric equipment longevity, river aesthetics, pollution and channel navigability. In this study different input combination of monthly upstream suspended sediment concentration and upstream flow dataset for Inanda Dam for 15 years was used to develop a model for each month of the year. The predictive abilities of each of the developed model to predict the quantity of suspended sediment flowing into Inanda Dam were also compared with those of the corresponding developed Sediment Rating Curves using two evaluation criteria - Determination of Coefficient (R2) and Root-Mean-Square Error (RMSE). The results from this study show that a genetic programming approach can be used to accurately predict the relationship between the streamflow and the suspended sediment load flowing into Inanda Dam. The twelve developed monthly genetic programming (GP) models produced a significantly low difference when the observed suspended sediment load was compared with the predicted suspended sediment load. The average R2 values and RMS error for the twelve developed models were 0.9996 and 0.3566 respectively during the validation phase. The Genetic Programming models were also able to replicate extreme hydrological events like predicting low and high suspended sediment load flowing into the dam. Moreover, the study also produced accurate sediment rating curve models with low RMSE values of between 0.3971 and 11.8852 and high R2 values of between 0.9833 and 0.9962. This shows that sediment rating curves can be used to predict historical missing data of the quantity of suspended sediment flowing into Inanda Dam using existing streamflow datasets. The results from this study further show that the predictions from the Genetic Programming models are better than the predictions from the Sediment Raring Curve models, especially in predicting large quantities of suspended sediment load during high streamflow such as during flood events. This proves that Genetic Programming technique is a better predictive tool than Sediment Raring Curve technique. In conclusion, the results from this study are very promising and support the use of Genetic Programming in predicting the nonlinear and complex relationship between suspended sediment load and streamflow at the inlet of Inanda Dam in KwaZulu-Natal. This will help planners and managers of the dam to understand the system better in terms of its problems and to find alternative ways to address them.

This thesis presents Genetic Programming methodologies to find successful and understandable technical trading rules for financial markets. The methods when applied to the S&P500 consistently beat the buy-and-hold strategy over a 12-year period, even when considering transaction costs. Some of the methods described discover rules that beat the S&P500 with 99% significance. The work describes the use of a complexity-penalizing factor to avoid overfitting and improve comprehensibility of the rules produced by GPs. The effect of this factor on the returns for this domain area is studied and the results indicated that it increased the predictive ability of the rules. A restricted set of operators and domain knowledge were used to improve comprehensibility. In particular, arithmetic operators were eliminated and a number of technical indicators in addition to the widely used moving averages, such as trend lines and local maxima and minima were added. A new evaluation function that tests for consistency of returns in addition to total returns is introduced. Different cooperative coevolutionary genetic programming strategies for improving returns are studied and the results analyzed. We find that paired collaborator coevolution has the best results.

This research presents engineering tools that address an important area impacting many persons worldwide: epilepsy. Over 60 million people are affected by epilepsy, a neurological disorder characterized by recurrent seizures that occur suddenly. Surgery and anti-epileptic drugs (AED s) are common therapies for epilepsy patients. However, only persons with seizures that originate in an unambiguous, focal portion of the brain are candidates for surgery, while AED s can lead to very adverse side-effects. Although medical devices based upon focal cooling, drug infusion or electrical stimulation are viable alternatives for therapy, a reliable method to automatically pinpoint dysfunctional brain and direct these devices is needed. This research introduces a method to effectively localize epileptic networks, or connectivity between dysfunctional brain, to guide where to insert electrodes in the brain for therapeutic devices, surgery, or further investigation. The method uses an evolutionary algorithm (EA) and frequent itemset mining (FIM) to detect and cluster frequent concentrations of epileptic neuronal action potentials within human intracranial electroencephalogram (EEG) recordings. In an experiment applying the method to seven patients with neocortical epilepsy (a total of 35 seizures), the approach reliably identifies the seizure onset zone, in six of the subjects (a total of 31 seizures). Hopefully, this research will lead to a better control of seizures and an improved quality of life for the millions of persons affected by epilepsy.

This thesis was inspired by the difficulties of artificial evolutionary systems in finding elegant and well structured, regular solutions. That is that the solutions found are usually highly disorganized, poorly structured and exhibit limited re-use, resulting in bloat and other problems. This is also true of previous developmental evolutionary systems, where structural regularity emerges only by chance. We hypothesise that these problems might be ameliorated by incorporating repeated evaluations on increasingly difficult problems in the course of a developmental process. This thesis introduces a new technique for learning complex problems from a family of structured increasingly difficult problems, Evolutionary Developmental Evaluation (EDE). This approach appears to give more structured, scalable and regular solutions to such families of problems than previous methods. In addition, the thesis proposes some bio-inspired components that are required by developmental evolutionary systems to take full advantage of this approach. The key part of this is the developmental process, in combination with a varying fitness function evaluated at multiple stages of development, generates selective pressure toward generalisation. This also means that parsimony in structure is selected for without any direct parsimony pressure. As a result, the system encourages the emergence of modularity and structural regularity in solutions. In this thesis, a new genetic developmental system called Developmental Tree Adjoining Grammar Guided Genetic Programming (DTAG3P), is implemented, embodying the requirements above. It is tested on a range of benchmark problems. The results indicate that the method generates more regularly-structured solutions than the competing methods. As a result, the system is able to scale, at least on the problem classes tested, to very complex instances the system encourages the emergence of modularity and structural regularity in solutions. In this thesis, a new genetic developmental system called Developmental Tree Adjoining Grammar Guided Genetic Programming (DTAG3P), is implemented, embodying the requirements above. It is tested on a range of benchmark problems. The results indicate that the method generates more regularly-structured solutions than competing methods. As a result, the system is able to scale, at least on the problem classes tested, to very complex problem instances.

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-16T05:11:31Z (GMT). No. of bitstreams: 1 Faria_FabioAugusto_M.pdf: 2356744 bytes, checksum: cc78deb6dc272085fdf374d3a043ab77 (MD5) Previous issue date: 2010 / Resumo: Técnicas de aprendizagem vêm sendo empregadas em diversas áreas de aplicação (medicina, biologia, segurança, entre outras). Neste trabalho, buscou-se avaliar o uso da técnica de Programação Genética (PG) em tarefas de recuperação e classificação de imagens. PG busca soluções ótimas inspirada pela teoria de seleção natural das espécies. Indivíduos mais aptos (melhores soluções) tendem a evoluir e se reproduzir nas gerações futuras. As principais contribuições deste trabalho são: implementação de um classificador de imagens utilizando PG para combinar evidencias visuais (descritores de imagens) e assim, obter melhores resultados com relação à eficácia de classificação; Comparação de PG com outras técnicas de aprendizagem em tarefas de recuperação de imagens por conteúdo; Uso de regras de associação para recuperação de imagens / Abstract: Learning techniques have been used in several applications (medicine, biology, surveillance systems, e.g.) This work aims to evaluate the use of the Genetic Programming (GP) learning technique for image retrieval and classification tasks. This technique is a problem-solving system that follows principles of inheritance and evolution, inspired by the idea of Natural Selection. The space of all possible solutions is investigated using a set of optimization techniques that imitate the theory of evolution. The main contributions of this work are: proposal of classifier implementation using GP to combine visual evidences (image descriptors) to be used in image classification tasks; comparison of GP with other learning techniques in content-based image retrieval tasks / Mestrado / Recuperação de Informação / Mestre em Ciência da Computação

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-16T05:18:58Z (GMT). No. of bitstreams: 1 Calumby_RodrigoTripodi_M.pdf: 15749586 bytes, checksum: 2493b0b703adc1973eeabf7eb70ad21c (MD5) Previous issue date: 2010 / Resumo: Este trabalho apresenta uma abordagem para recuperação multimodal de imagens com realimentação de relevância baseada em programação genética. Supõe-se que cada imagem da coleção possui informação textual associada (metadado, descrição textual, etc.), além de ter suas propriedades visuais (por exemplo, cor e textura) codificadas em vetores de características. A partir da informação obtida ao longo das iterações de realimentação de relevância, programação genética é utilizada para a criação de funções de combinação de medidas de similaridades eficazes. Com essas novas funções, valores de similaridades diversos são combinados em uma única medida, que mais adequadamente reflete as necessidades do usuário. As principais contribuições deste trabalho consistem na proposta e implementação de dois arcabouços. O primeiro, RFCore, é um arcabouço genérico para atividades de realimentação de relevância para manipulação de objetos digitais. O segundo, MMRFGP, é um arcabouço para recuperação de objetos digitais com realimentação de relevância baseada em programação genética, construído sobre o RFCore. O método proposto de recuperação multimodal de imagens foi validado sobre duas coleções de imagens, uma desenvolvida pela Universidade de Washington e outra da ImageCLEF Photographic Retrieval Task. A abordagem proposta mostrou melhores resultados para recuperação multimodal frente a utilização das modalidades isoladas. Além disso, foram obtidos resultados para recuperação visual e multimodal melhores do que as melhores submissões para a ImageCLEF Photographic Retrieval Task 2008 / Abstract: This work presents an approach for multimodal content-based image retrieval with relevance feedback based on genetic programming. We assume that there is textual information (e.g., metadata, textual descriptions) associated with collection images. Furthermore, image content properties (e.g., color and texture) are characterized by image descriptores. Given the information obtained over the relevance feedback iterations, genetic programming is used to create effective combination functions that combine similarities associated with different features. Hence using these new functions the different similarities are combined into a unique measure that more properly meets the user needs. The main contribution of this work is the proposal and implementation of two frameworks. The first one, RFCore, is a generic framework for relevance feedback tasks over digital objects. The second one, MMRF-GP, is a framework for digital object retrieval with relevance feedback based on genetic programming and it was built on top of RFCore. We have validated the proposed multimodal image retrieval approach over 2 datasets, one from the University of Washington and another from the ImageCLEF Photographic Retrieval Task. Our approach has yielded the best results for multimodal image retrieval when compared with one-modality approaches. Furthermore, it has achieved better results for visual and multimodal image retrieval than the best submissions for ImageCLEF Photographic Retrieval Task 2008 / Mestrado / Sistemas de Recuperação da Informação / Mestre em Ciência da Computação

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-13T10:41:05Z (GMT). No. of bitstreams: 1 Santos_JeferssonAlexdos_M.pdf: 3412363 bytes, checksum: 9f3c3640964ef3c4b39b2ee532941a42 (MD5) Previous issue date: 2009 / Resumo: O uso de imagens de sensoriamento remoto (ISRs) como fonte de informação em aplicações voltadas para o agro-negócio e bastante comum. Nessas aplicações, saber como é a ocupação espacial é fundamental. Entretanto, reconhecer e diferenciar regiões de culturas agrícolas em ISRs ainda não é uma tarefa trivial. Embora existam métodos automáticos propostos para isso, os usuários preferem muitas vezes fazer o reconhecimento manualmente. Isso acontece porque tais métodos normalmente são feitos para resolver problemas específicos, ou quando são de propósito geral, não produzem resultados satisfatórios fazendo com que, invariavelmente, o usuário tenha que revisar os resultados manualmente. A pesquisa realizada objetivou a especificação e implementação parcial de um sistema para o reconhecimento semi-automático e vetorização de regiões em imagens de sensoriamento remoto. Para isso, foi usada uma estratégia interativa, chamada realimentação de relevância, que se baseia no fato de o sistema de classificação poder aprender quais são as regiões de interesse utilizando indicações de relevância feitas pelo usuário do sistema ao longo de iterações. A idéia é utilizar descritores de imagens para codificar informações espectrais e de textura de partições das imagens e utilizar realimentação de relevância com Programação Genética (PG) para combinar as características dos descritores. PG é uma técnica de aprendizado de máquina baseada na teoria da evolução. As principais contribuições deste trabalho são: estudo comparativo de técnicas de vetorização de imagens; adaptação do modelo de recuperação de imagens por conteúdo proposto recentemente para realização de realimentação de relevância usando regiões de imagem; adaptação do modelo de realimentação de relevância para o reconhecimento de regiões em ISRs; implementação parcial de um sistema de reconhecimento semi-automático e vetorização de regiões em ISRs; proposta de metodologia de validação do sistema desenvolvido. / Abstract: The use of remote sensing images as a source of information in agrobusiness applications is very common. In these applications, it is fundamental to know how the space occupation is. However, the identification and recognition of crop regions in remote sensing images are not trivial tasks yet. Although there are automatic methods proposed to that, users prefer sometimes to identify regions manually. That happens because these methods are usually developed to solve specific problems, or, when they have a general purpose, they do not yield satisfying results. This work presents a semi-automatic method to vectorize regions from remote sensing images using relevance feedback based on genetic programming (GP). Relevance feedback is a technique used in content-based image retrieval (CBIR). Its objective is to agregate user preferences to the search process. The proposed solution consists in using image descriptors to encode texture and spectral features from the images, applying relevance feedback based on GP to combine these features with information obtained from the users interactions and, finally, segment the image. Finally, segmented image (raster) is converted into a vector representation. The main contributions of this work are: comparative study of image vectorization techniques; extension of a recently proposed relevance feedback approach for dealing with image regions; extension of the relevance feedback model for region recognition in remote sensing images; parcial implementation of the semi-automatic and vectorization system of remote sensing images regions; proposal a validation methodology. / Mestrado / Mestre em Ciência da Computação

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-19T16:06:22Z (GMT). No. of bitstreams: 1 Armigliatto_GuilhermeMoraes_M.pdf: 5003825 bytes, checksum: b03061ff457c08c89d0e045840955929 (MD5) Previous issue date: 2011 / Resumo: Com os avanços tecnológicos, grandes coleções de imagens são geradas, manipuladas e armazenadas em bancos de dados. Dado o grande tamanho destes bancos, verifica-se a necessidade de se criar ferramentas para gerenciá-los de forma eficiente e eficaz. Uma das tarefas mais demandadas deste gerenciamento é a recuperação das imagens, e uma forma de fazê-la é baseada no uso de anotações textuais associadas às imagens (por exemplo, palavras-chave e categorias). Entretanto, a anotação manual de grandes coleções de imagens apresenta vários problemas, como o alto consumo de tempo e a não padronização dos termos utilizados. Desse modo, esta dissertação apresenta quatro novos métodos para anotação automática de imagens, que visam amenizar estes problemas. Estes métodos utilizam as abordagens de descritores de imagens, dicionários visuais, programação genética e regras de associação. Os descritores e os dicionários são utilizados para representar as propriedades visuais das imagens, a programação genética é usada para combinar estas características e as regras de associação são usadas para relacioná-las com anotações. A principal contribuição desta dissertação consiste na análise do comportamento das regras de associação utilizadas para anotação de imagens em um conjunto de experimentos. Resultados experimentais demonstraram que os métodos propostos apresentam desempenho comparável ou superior ao de técnicas tradicionais da literatura / Abstract: With technological advances, large collections of images are generated, handled and, stored in databases. Given the large size of these collections, there is a need for tools to manage efficiently and effectively these images. One of the most demanding tasks of this management is the retrieval of images from databases, usually based on the use of textual annotations associated with images (for example, keywords and categories). However, manual annotation of large images collections face a lot of problems related to the huge time required to annotate and the lack of standardization of used terms. This work presents four new methods for automatic image annotation. These methods rely on the use of image descriptors, visual dictionaries, genetic programming, and association rules. The descriptors and dictionaries are used to represent the visual properties of images, genetic programming is used to combine extracted visual features, and association rules are used to associate them with annotations. The main contribution of this work is views on the analyze the behavior of association rules used for annotating images on a set of experiments. Experimental results demonstrated that the proposed methods have performance comparable or superior to traditional techniques of literature / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

Orientador: Ricardo da Silva Torres, Hélio Pedrini / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-22T03:54:24Z (GMT). No. of bitstreams: 1 Andrade_FelipedosSantosPintode_M.pdf: 3172421 bytes, checksum: cf06d3683b1828f22508de3f77ed1c00 (MD5) Previous issue date: 2012 / Resumo: Recentemente, a fusão de descritores tem sido usada para melhorar o desempenho de sistemas de busca em tarefas de recuperação de imagens e vídeos. Descritores podem ser globais ou locais, dependendo de como analisam o conteúdo visual. A maioria dos trabalhos existentes tem se concentrado na fusão de um tipo de descritor. Este trabalho objetiva analisar o impacto da combinação de descritores locais e globais. Realiza-se um estudo comparativo de diferentes tipos de descritores e todas suas possíveis combinações. Além disso, investigam-se modelos para extração e a comparação das características globais e locais para recuperação de imagens e vídeos e estuda-se a utilização da técnica de programação genética para combinar esses descritores. Experimentos extensivos baseados em um projeto experimental rigoroso mostram que descritores locais e globais complementam-se quando combinados. Além disso, esta combinação produz resultados superiores aos observados para outras combinações e ao uso dos descritores individualmente / Abstract: Recently, fusion of descriptors has become a trend for improving the performance in image and video retrieval tasks. Descriptors can be global or local, depending on how they analyze visual content. Most of existing works have focused on the fusion of a single type of descriptor. Different from all of them, this work aims at analyzing the impact of combining global and local descriptors. Here, we perform a comparative study of different types of descriptors and all of their possible combinations. Furthermore, we investigate different models for extracting and comparing local and global features of images and videos, and evaluate the use of genetic programming as a suitable alternative for combining local and global descriptors. Extensive experiments following a rigorous experimental design show that global and local descriptors complement each other, such that, when combined, they outperform other combinations or single descriptors / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

The purpose of this project is to investigate the differences between psychoacoustic principles and genetic algorithms (GA0). These will be discussed separately. The review will also compare the compression ratio and the quality of the decompressed files decoded by these two methods.