The performance of similarity search in the unstructured databases largely depends on the employed similarity model. The properties of metric space model enable indexing the data with metric access methods efficiently. But for unconstrained or nonmetric similarity models typical for multimedia, medical, or scientific databases, in which metric postulates do not hold, there exists no general solution so far. Motivated by the successful application of Ptolemaic indexing to the image retrieval, we introduce SIMDEX Framework which is a universal framework that is capable of revealing alternative indexing methods that will serve for efficient yet effective similarity searching for any similarity model. It explores the axiom space in order to discover novel techniques suitable for database indexing. We review all existing variants (simple I-SIMDEX; GP-SIMDEX and PGP-SIMDEX which both use genetic programming) and we outline how the different groups of domain researchers can benefit from them. We also describe a real application of SIMDEX Framework to practice while building the Smart Pivot Table indexing method together with advanced Triangle+ filtering for metric spaces empowered by LowerBound Tightening technique. At all cases, we provide extensive experimental evaluations of mentioned techniques. Powered by...

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2018-01-12T11:44:53Z No. of bitstreams: 1 douglasdeoliveiramatosbraga.pdf: 1221207 bytes, checksum: 2e8c8b8de9aa188f87fe5670354d478c (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2018-01-23T13:56:44Z (GMT) No. of bitstreams: 1 douglasdeoliveiramatosbraga.pdf: 1221207 bytes, checksum: 2e8c8b8de9aa188f87fe5670354d478c (MD5) / Made available in DSpace on 2018-01-23T13:56:44Z (GMT). No. of bitstreams: 1 douglasdeoliveiramatosbraga.pdf: 1221207 bytes, checksum: 2e8c8b8de9aa188f87fe5670354d478c (MD5) Previous issue date: 2017-08-31 / O planejamento energético é base para as tomadas de decisões nas companhias de energia elétrica e, para isto, depende fortemente da disponibilidade de previsões acuradas para as cargas. Devido á inviabilidade de armazenamentos em larga-escala e o custo elevado de compras de energia a curto prazo, além da possibilidade de multas e sanções de órgãos governamentais, previsões em curto prazo são importantes para a otimização da alocação de recursos e da geração de energia. Neste trabalho utilizamos nove métodos univariados de séries temporais para a previsão de cargas a curto prazo, com horizontes de 1 a 24 horas a frente. Buscando melhorar a acurácia das previsões, propomos um método de combinação de previsões através de Regressão Simbólica, que combina de forma não-linear as previsões obtidas pelos nove métodos de séries temporais utilizados. Diferente de outros métodos não-lineares de regressão, a Regressão Simbólica não precisa de uma especificação previa da forma funcional. O método proposto é aplicado em uma série real da cidade do Rio de Janeiro (RJ), que contém cargas horárias de 104 semanas dos anos de 1996 e 1997. Comparamos, através de critérios indicados na literatura, os resultados obtidos pelo método proposto com os resultados obtidos por métodos tradicionais de combinação de previsões e ao resultado de simulações de redes neurais artificiais aplicados ao mesmo conjunto de dados. O método proposto obteve melhores resultados, que indicam que a não-linearidade pode ser aspecto importante para combinação de previsões no problema de previsão de carga a curto prazo / Decision-making in energy companies relies heavily on the availability of accurate load forecasts. Because storing electricity on a large scale is not viable, the cost of short-term energy purchasing is high, and there are government fines and sanctions for failing to supply energy on demand, short-term load forecasts are important for the optimization of resource allocation and energy production. In this work we used nine univariate time series methods for short-term load forecasts, with forecast horizons ranging from 1 to 24 hours ahead. In order to improve the accuracy of forecasts, we propose a method of combining forecasts through Symbolic Regression, which combines in a non-linear way the forecasts obtained by the nine methods of the time series used. Unlike other non-linear regression methods, Symbolic Regression does not need a previous specification of the function structure. We applied the proposed method to a real time series of the city of Rio de Janeiro (RJ), which contains data on hourly loads of 104 weeks in the years 1996 and 1997. We compare, through the criteria indicated in the literature, the results obtained by the proposed method with the results obtained by traditional methods of forecasts combination and the result obtained by artificial neural networks applied to the same dataset. The method has yielded better results, indicating that non-linearity may be important in combining predictions in short term load forecasts.

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 is focused on finding procedures that would accelerate symbolic regressions in Cartesian Genetic Programming. It describes Cartesian Genetic Programming and its use in the task of symbolic regression. It deals with the SIMD architecture and the SSE and AVX instruction set. Several optimizations that lead to a significant acceleration of evolution in Cartesian Genetic Programming are presented. A method of a bit-level parallel simulation that uses AVX2 vectors allows to process 256 input combinations of a logic circuit in paralell. Similarly it is possible to use a byte-level parallel simulation and work with 32 bytes when evolving an image filter. A new method of batch mutation can accelerate the evolution of combinational logic circuits thousand times depending on the problem size. For example, using a combination of these and other methods the evolution of 5 x 5b multipliers took 5.8 seconds on average on an Intel Core i5-4590 processor.

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.

[pt] 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. / [en] 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.

In den letzten Jahren hat sich maschinelles Lernen als hilfreiches Werkzeug zur Vorhersage von simulierten Materialeigenschaften erwiesen. Somit können aufwendige Berechnungen mittels Dichtefunktionaltheorie umgangen werden und bereits bekannte Materialien besser verstanden oder sogar neuartige entdeckt werden. Eine zentrale Rolle spielt dabei der Deskriptor, ein möglichst interpretierbarer Satz von Materialkenngrößen. Diese Arbeit präsentiert einen Ansatz zur Auffindung von Deskriptoren für periodische Multikomponentensysteme, deren Eigenschaften durch die genaue atomare Anordnung mitbeinflusst wird. Primäre Features von Einzel-, Paar- und Tetraederclustern werden über die Superzelle gemittelt und weiter algebraisch kombiniert. Aus den so erzeugten Kandidaten wird mittels Dimensionalitätsreduktion ein geeigneter Deskriptor identifiziert. Zudem stellt diese Arbeit Strategien vor bei der Modellfindung Kreuzvalidierung einzusetzen, sodass stabilere und idealerweise besser generalisierbare Deskriptoren gefunden werden. Es werden außerdem mehrere Fehlermaße untersucht, die die Qualität der Deskriptoren bezüglich Genauigkeit, Komplexität der Formeln und Berücksichtung der atomaren Anordnung charakterisieren. Die allgemeine Methodik wurde in einer teilweise parallelisierten Python-Software implementiert. Als konkrete Problemstellungen werden Modelle für die Gitterkonstante und die Mischenergie von ternären Gruppe-IV Zinkblende-Legierungen "gelernt", mit einer Genauigkeit von 0.02 Å bzw. 0.02 eV. Datenbeschaffung, -analyse, und -bereinigung werden im Hinblick auf die Zielgrößen als auch auf die primären Features erläutert, sodass umfassende Analysen und die Parametrisierung der Methodik an diesem Testdatensatz durchgeführt werden können. Als weitere Anwendung werden Gitterkonstante und Bandlücken von binären Oktett-Verbindungen vorhergesagt. Die präsentierten Deskriptoren werden mit den Fehlermaßen evaluiert und ihre physikalische Relevanz wird abschließend disktutiert. / In the last years, machine learning methods have proven as a useful tool for the prediction of simulated material properties. They may replace effortful calculations based on density functional theory, provide a better understanding of known materials or even help to discover new materials. Here, an essential role is played by the descriptor, a desirably interpretable set of material parameters. This PhD thesis presents an approach to find descriptors for periodic multi-component systems where also the exact atomic configuration influences the physical characteristics. We process primary features of one-atom, two-atom and tetrahedron clusters by an averaging scheme and combine them further by simple algebraic operations. Compressed sensing is used to identify an appropriate descriptor out from all candidate features. Furthermore, we develop elaborate cross-validation based model selection strategies that may lead to more robust and ideally better generalizing descriptors. Additionally, we study several error measures which estimate the quality of the descriptors with respect to accuracy, complexity of their formulas and the capturing of configuration effects. These generally formulated methods were implemented in a partially parallelized Python program. Actual learning tasks were studied on the problem of finding models for the lattice constant and the energy of mixing of group-IV ternary compounds in zincblende structure where an accuracy of 0.02 Å and 0.02 eV is reached, respectively. We explain the practical preparation steps of data acquisition, analysis and cleaning for the target properties and the primary features, and continue with extensive analyses and the parametrization of the developed methodology on this test case. As an additional application we predict lattice constants and band gaps of octet binary compounds. The presented descriptors are assessed quantitatively by the error measures and, finally, their physical meaning is discussed.

This master's thesis offers a brief introduction to evolutionary computation. It describes and compares the genetic programming and grammar based genetic programming and their potential use in automatic software repair. It studies possible applications of grammar based genetic programming on automatic software repair. Grammar based genetic programming is then used in design and implementation of a new method for automatic software repair. Experimental evaluation of the implemented automatic repair was performed on set of test programs.

This diploma thesis deals with the cryptanalysis of symmetric encryption algorithms. The aim of this thesis is to show different point of view on this issues. The dissimilar way, compared to the recent methods, lies in the use of the power of evolutionary principles which are in the cryptanalytic system applied with help of genetic programming. In the theoretical part the cryptography, cryptanalysis of symmetric encryption algorithms and genetic programming are described. On the ground of the obtained information a project of cryptanalytic system which uses evolutionary principles is represented. Practical part deals with implementation of symmetric encrypting algorithm, linear cryptanalysis and simulation instrument of genetic programming. The end of the thesis represents experiments together with projected cryptanalytic system which uses genetic programming and evaluates reached results.