Master thesis deals with possibilities of predicting traffic situation on the macroscopic level using data, that were recorded using traffic sensors. This sensors could be loop detectors, radar detectors or cameras. The main problem discussed in this thesis is the travel time of cars. A method for travel time prediction was designed and implemented as a part of this thesis. Data from real traffic were used to test the designed method. The first objective of this thesis is to become familiar with the prediction methods that will be used. The main objective is to use the acquired knowledge to design and to implement an aplication that will predict required traffic variables.

Genetic programming is a nature-inspired method of programming that allows an automated creation and adaptation of programs. For nearly two decades, this method has been able to provide human-comparable results across many fields. This work gives an introduction to the problems of evolutionary algorithms, genetic programming and the way they can be used to improve already existing software. This work then proposes a program able to use these methods to improve an implementation of cartesian genetic programming (CGP). This program is then tested on a CGP implementation created specifically for this project, and its functionality is then verified on other already existing implementations of CGP.

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 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.

[pt] As técnicas de programação genética permitem flexibilidade no processo de otimização, possibilitando sua aplicação em diferentes áreas do conhecimento e fornecendo novas maneiras para que especialistas avancem em suas áreas com mais rapidez. Parameter mapping approach é um método de otimização numérica que utiliza a programação genética para mapear valores iniciais em parâmetros ótimos para um sistema. Embora esta abordagem produza bons resultados para problemas com soluções triviais, o uso de grandes equações/árvores pode ser necessário para tornar este mapeamento apropriado em sistemas mais complexos.A fim de aumentar a flexibilidade e aplicabilidade do método a sistemas de diferentes níveis de complexidade, este trabalho introduz uma generalização utilizando a programação genética multigênica, para realizar um mapeamento multivariado, evitando grandes estruturas complexas. Foram considerados três conjuntos de funções de benchmark, variando em complexidade e dimensionalidade. Análises estatísticas foram realizadas, sugerindo que este novo método é mais flexível e mais eficiente (em média), considerando funções de benchmark complexas e de grande dimensionalidade. Esta tese também apresenta uma abordagem do novo algoritmo para otimização numérica multimodal.Este segundo algoritmo utiliza algumas técnicas de niching, baseadas no procedimento chamado de clearing, para manter a diversidade da população. Um conjunto benchmark de funções multimodais, com diferentes características e níveis de dificuldade,foi utilizado para avaliar esse novo algoritmo. A análise estatística sugeriu que esse novo método multimodal, que também utiliza programação genética multigênica,pode ser aplicado para problemas que requerem mais do que uma única solução. Como forma de testar esses métodos em problemas do mundo real, uma aplicação em nanotecnologia é proposta nesta tese: ao timização estrutural de fotodetectores de infravermelho de poços quânticos a partir de uma energia desejada. Os resultados apresentam novas estruturas melhores do que as conhecidas na literatura (melhoria de 59,09 por cento). / [en] Genetic programming techniques allow flexibility in the optimization process, making it possible to use them in different areas of knowledge and providing new ways for specialists to advance in their areas more quickly and more accurately.Parameter mapping approach is a numerical optimization method that uses genetic programming to find an appropriate mapping scheme among initial guesses to optimal parameters for a system. Although this approach yields good results for problems with trivial solutions, the use of large equations/trees may be required to make this mapping appropriate for more complex systems.In order to increase the flexibility and applicability of the method to systems of different levels of complexity, this thesis introduces a generalization by thus using multi-gene genetic programming to perform a multivariate mapping, avoiding large complex structures.Three sets of benchmark functions, varying in complexity and dimensionality, were considered. Statistical analyses carried out suggest that this new method is more flexible and performs better on average, considering challenging benchmark functions of increasing dimensionality.This thesis also presents an improvement of this new method for multimodal numerical optimization.This second algorithm uses some niching techniques based on the clearing procedure to maintain the population diversity. A multimodal benchmark set with different characteristics and difficulty levels to evaluate this new algorithm is used. Statistical analysis suggested that this new multimodal method using multi-gene genetic programming can be used for problems that requires more than a single solution. As a way of testing real-world problems for these methods, one application in nanotechnology is proposed in this thesis: the structural optimization of quantum well infrared photodetector from a desired energy.The results present new structures better than those known in the literature with improvement of 59.09 percent.

This thesis examines a conversion of a solution produced by geometric semantic genetic programming (GSGP) to an instantion of cartesian genetic programming (CGP). GSGP has proven its quality to create complex mathematical models; however, the size of these models can get problematically large. CGP, on the other hand, is able to reduce the size of given models. This thesis combinated these methods to create a subtree CGP (SCGP). The SCGP uses an output of GSGP as an input and the evolution is performed using the CGP. Experiments performed on four pharmacokinetic tasks have shown that the SCGP is able to reduce the solution size in every case. Overfitting was detected in one out of four test problems.

This thesis deals with image classification based on genetic programming and coevolution. Genetic programming algorithms make generating executable structures possible, which allows us to design solutions in form of programs. Using coevolution with the fitness prediction lowers the amount of time consumed by fitness evaluation and, therefore, also the execution time. The thesis describes a theoretical background of evolutionary algorithms and, in particular, cartesian genetic programming. We also describe coevolutionary algorithms properties and especially the proposed method for the image classifier evolution using coevolution of fitness predictors, where the objective is to find a good compromise between the classification accuracy, design time and classifier complexity. A part of the thesis is implementation of the proposed method, conducting the experiments and comparison of obtained results with other methods.

The aim of this work is to design and implement a method for the evolutionary design of neural networks with generative encoding. The proposed method is based on J. F. Miller's approach and uses a brain model that is gradually developed and which allows extraction of traditional neural networks. The development of the brain is controlled by programs created using cartesian genetic programming. The project was implemented in Python with the use of Numpy library. Experiments have shown that the proposed method is able to construct neural networks that achieve over 90 % accuracy on smaller datasets. The method is also able to develop neural networks capable of solving multiple problems at once while slightly reducing accuracy.

The main goal of the master's thesis is to compose a study on cartesian genetic programming with focus on evolution of circuits and to design a concept for visualisation of this evolution. Another goal is to create a program to visualise the circuit evolution in cartesian genetic programming, its generations and chromosomes. The program is capable of visualising the changes between generations and chromosomes and comparing more chromosomes at once. Several user cases had been prepared for the resulting program.

Symbolic regression is the problem of identifying the mathematic description of a hidden system from experimental data. Symbolic regression is closely related to general machine learning. This work deals with symbolic regression and its solution based on the principle of genetic programming and coevolution. Genetic programming is the evolution based machine learning method, which automaticaly generates whole programs in the given programming language. Coevolution of fitness predictors is the optimalization method of the fitness modelling that reduces the fitness evaluation cost and frequency, while maintainig evolutionary progress. This work deals with concept and implementation of the solution of symbolic regression using coevolution of fitness predictors, and its comparison to a solution without coevolution. Experiments were performed using cartesian genetic programming.