A identificação de formas apresenta inúmeras aplicações na área de visão computacional, pois representa uma poderosa ferramenta para analisar as características de um objeto. Dentre as aplicações, podemos citar como exemplos a interação entre humanos e robôs, com a identificação de ações e comandos, e a análise de comportamento para vigilância com a biometria não invasiva. Em nosso trabalho nós desenvolvemos um novo descritor de formas 2D baseado na utilização de redes complexas e teoria espectral de grafos. O contorno da forma de um objeto é representado por uma rede complexa, onde cada ponto pertencente a forma será representado por um vértice da rede. Utilizando uma dinâmica gerada artificialmente na rede complexa, podemos definir uma série de matrizes de adjacência que refletem a dinâmica estrutural da forma do objeto. Cada matriz tem seu espectro calculado, e os principais autovalores são utilizados na construção de um vetor de características. Esse vetor, após aplicar as operações de módulo e normalização, torna-se nossa assinatura espectral de forma. Os principais autovalores de um grafo estão relacionados com propriedades topológicas do mesmo, o que permite sua utilização na descrição da forma de um objeto. Para validar nosso método, nós realizamos testes quanto ao seu comportamento frente a transformações de rotação e escala e estudamos seu comportamento quanto à contaminação das formas por ruído Gaussiano e quanto ao efeito de oclusões parciais. Utilizamos diversas bases de dados comumente utilizadas na literatura de análise de formas para averiguar a eficiência de nosso método em tarefas de recuperação de informação. Concluímos o trabalho com a análise qualitativa do comportamento de nosso método frente a diferentes curvas e estudando uma aplicação na análise de sequências de caminhada. Os resultados obtidos em comparação aos outros métodos mostram que nossa assinatura espectral de forma apresenta bom resultados na precisão de recuperação de informação, boa tolerância a contaminação das formas por ruído e oclusões parciais, e capacidade de distinguir ações humanas e identificar os ciclos de uma sequência de caminhada. / The shape is a powerful feature to characterize an object and the shape analysis has several applications in computer vision area. We can cite the interaction between human and robots, surveillance, non-invasive biometry and human actions identifications among other applications. In our work we have developed a new 2d shape descriptor based on complex network and spectral graph theory. The contour shape of an object is represented by a complex network, where each point belonging shape is represented by a vertex of the network. A set of adjacencies matrices is generated using an artificial dynamics in the complex network. We calculate the spectrum of each adjacency matrix and the most important eigenvalues are used in a feature vector. This vector, after applying module and normalization operations, becomes our spectral shape signature. The principal eigenvalues of a graph are related to its topological properties. This allows us use eigenvalues to describe the shape of an object. We have used shape benchmarks to measure the information retrieve precision of our method. Besides that, we have analyzed the response of the spectral shape signature under noise, rotation and occlusions situations. A qualitative study of the method behavior has been done using curves and a walk sequence. The achieved comparative results to other methods found in the literature show that our spectral shape signature presents good results in information retrieval tasks, good tolerance under noise and partial occlusions situation. We present that our method is able to distinguish human actions and identify the cycles of a walk sequence.

The study of complex brain networks, where the brain can be viewed as a system with various interacting regions that produce complex behaviors, has grown tremendously over the past decade. With both an increase in longitudinal study designs, as well as an increased interest in the neurological network changes that occur during the progression of a disease, sophisticated methods for dynamic brain network analysis are needed. We first propose a paradigm for longitudinal brain network analysis over patient cohorts where we adapt the Stochastic Actor Oriented Model (SAOM) framework and model a subject's network over time as observations of a continuous time Markov chain. Network dynamics are represented as being driven by various factors, both endogenous (i.e., network effects) and exogenous, where the latter include mechanisms and relationships conjectured in the literature. We outline an application to the resting-state fMRI network setting, where we draw conclusions at the subject level and then perform a meta-analysis on the model output. As an extension of the models, we next propose an approach based on Hidden Markov Models to incorporate and estimate type I and type II error (i.e., of edge status) in our observed networks. Our model consists of two components: 1) the latent model, which assumes that the true networks evolve according to a Markov process as they did in the original SAOM framework; and 2) the measurement model, which describes the conditional distribution of the observed networks given the true networks. An expectation-maximization algorithm is developed for estimation. Lastly, we focus on the study of percolation - the sudden emergence of a giant connected component in a network. This has become an active area of research, with relevance in clinical neuroscience, and it is of interest to distinguish between different percolation regimes in practice. We propose a method for estimating a percolation model from a given sequence of observed networks with single edge transitions. We outline a Hidden Markov Model approach and EM algorithm for the estimation of the birth and death rates for the edges, as well as the type I and type II error rates. / 2018-07-25T00:00:00Z

abstract: Complex dynamical systems consisting interacting dynamical units are ubiquitous in nature and society. Predicting and reconstructing nonlinear dynamics of units and the complex interacting networks among them serves the base for the understanding of a variety of collective dynamical phenomena. I present a general method to address the two outstanding problems as a whole based solely on time-series measurements. The method is implemented by incorporating compressive sensing approach that enables an accurate reconstruction of complex dynamical systems in terms of both nodal equations that determines the self-dynamics of units and detailed coupling patterns among units. The representative advantages of the approach are (i) the sparse data requirement which allows for a successful reconstruction from limited measurements, and (ii) general applicability to identical and nonidentical nodal dynamics, and to networks with arbitrary interacting structure, strength and sizes. Another two challenging problem of significant interest in nonlinear dynamics: (i) predicting catastrophes in nonlinear dynamical systems in advance of their occurrences and (ii) predicting the future state for time-varying nonlinear dynamical systems, can be formulated and solved in the framework of compressive sensing using only limited measurements. Once the network structure can be inferred, the dynamics behavior on them can be investigated, for example optimize information spreading dynamics, suppress cascading dynamics and traffic congestion, enhance synchronization, game dynamics, etc. The results can yield insights to control strategies design in the real-world social and natural systems. Since 2004, there has been a tremendous amount of interest in graphene. The most amazing feature of graphene is that there exists linear energy-momentum relationship when energy is low. The quasi-particles inside the system can be treated as chiral, massless Dirac fermions obeying relativistic quantum mechanics. Therefore, the graphene provides one perfect test bed to investigate relativistic quantum phenomena, such as relativistic quantum chaotic scattering and abnormal electron paths induced by klein tunneling. This phenomenon has profound implications to the development of graphene based devices that require stable electronic properties. / Dissertation/Thesis / Ph.D. Electrical Engineering 2012

BRILHANTE, Igo Ramalho. Mobility Data under Analysis a Complex Network Perspective from Interactions Among Trajectories to Movements among Points Interest. 2012. 104 f. Dissertação (Mestrado em ciência da computação)- Universidade Federal do Ceará, Fortaleza-CE, 2012. / Submitted by Elineudson Ribeiro (elineudsonr@gmail.com) on 2016-07-28T19:53:04Z No. of bitstreams: 1 2012_dis_irbrilhante.pdf: 13581729 bytes, checksum: 9b1d7b6164309bf59f7d6ba1370cd90e (MD5) / Approved for entry into archive by José Jairo Viana de Sousa (jairo@ufc.br) on 2016-08-02T14:18:14Z (GMT) No. of bitstreams: 1 2012_dis_irbrilhante.pdf: 13581729 bytes, checksum: 9b1d7b6164309bf59f7d6ba1370cd90e (MD5) / Made available in DSpace on 2016-08-02T14:18:14Z (GMT). No. of bitstreams: 1 2012_dis_irbrilhante.pdf: 13581729 bytes, checksum: 9b1d7b6164309bf59f7d6ba1370cd90e (MD5) Previous issue date: 2012 / The explosion of personal positioning devices like GPS-enabled smartphones has enabled the collection and storage of a huge amount of positioning data in the form of trajectories. Thereby, trajectory data have brought many research challenges in the process of recovery, storage and knowledge discovery in mobility as well as new applications to support our society in mobility terms. Other research area that has been receiving great attention nowadays is the area of complex network or science of networks. Complex network is the first approach to model complex system that are present in the real world, such as economic markets, the Internet, World Wide Web and disease spreading to name a few. It has been applied in different field, like Computer Science, Biology and Physics. Therefore, complex networks have demonstrated a great potential to investigate the behavior of complex systems through their entities and the relationships that exist among them. The present dissertation, therefore, aims at exploiting approaches to analyze mobility data using a perspective of complex networks. The first exploited approach stands for the trajectories as the main entities of the networks connecting each other through a similarity function. The second, in turn, focuses on points of interest that are visited by people, which perform some activities in these points. In addition, this dissertation also exploits the proposed methodologies in order to develop a software tool to support users in mobility analysis using complex network techniques. / The explosion of personal positioning devices like GPS-enabled smartphones has enabled the collection and storage of a huge amount of positioning data in the form of trajectories. Thereby, trajectory data have brought many research challenges in the process of recovery, storage and knowledge discovery in mobility as well as new applications to support our society in mobility terms. Other research area that has been receiving great attention nowadays is the area of complex network or science of networks. Complex network is the first approach to model complex system that are present in the real world, such as economic markets, the Internet, World Wide Web and disease spreading to name a few. It has been applied in different field, like Computer Science, Biology and Physics. Therefore, complex networks have demonstrated a great potential to investigate the behavior of complex systems through their entities and the relationships that exist among them. The present dissertation, therefore, aims at exploiting approaches to analyze mobility data using a perspective of complex networks. The first exploited approach stands for the trajectories as the main entities of the networks connecting each other through a similarity function. The second, in turn, focuses on points of interest that are visited by people, which perform some activities in these points. In addition, this dissertation also exploits the proposed methodologies in order to develop a software tool to support users in mobility analysis using complex network techniques.

A identificação de formas apresenta inúmeras aplicações na área de visão computacional, pois representa uma poderosa ferramenta para analisar as características de um objeto. Dentre as aplicações, podemos citar como exemplos a interação entre humanos e robôs, com a identificação de ações e comandos, e a análise de comportamento para vigilância com a biometria não invasiva. Em nosso trabalho nós desenvolvemos um novo descritor de formas 2D baseado na utilização de redes complexas e teoria espectral de grafos. O contorno da forma de um objeto é representado por uma rede complexa, onde cada ponto pertencente a forma será representado por um vértice da rede. Utilizando uma dinâmica gerada artificialmente na rede complexa, podemos definir uma série de matrizes de adjacência que refletem a dinâmica estrutural da forma do objeto. Cada matriz tem seu espectro calculado, e os principais autovalores são utilizados na construção de um vetor de características. Esse vetor, após aplicar as operações de módulo e normalização, torna-se nossa assinatura espectral de forma. Os principais autovalores de um grafo estão relacionados com propriedades topológicas do mesmo, o que permite sua utilização na descrição da forma de um objeto. Para validar nosso método, nós realizamos testes quanto ao seu comportamento frente a transformações de rotação e escala e estudamos seu comportamento quanto à contaminação das formas por ruído Gaussiano e quanto ao efeito de oclusões parciais. Utilizamos diversas bases de dados comumente utilizadas na literatura de análise de formas para averiguar a eficiência de nosso método em tarefas de recuperação de informação. Concluímos o trabalho com a análise qualitativa do comportamento de nosso método frente a diferentes curvas e estudando uma aplicação na análise de sequências de caminhada. Os resultados obtidos em comparação aos outros métodos mostram que nossa assinatura espectral de forma apresenta bom resultados na precisão de recuperação de informação, boa tolerância a contaminação das formas por ruído e oclusões parciais, e capacidade de distinguir ações humanas e identificar os ciclos de uma sequência de caminhada. / The shape is a powerful feature to characterize an object and the shape analysis has several applications in computer vision area. We can cite the interaction between human and robots, surveillance, non-invasive biometry and human actions identifications among other applications. In our work we have developed a new 2d shape descriptor based on complex network and spectral graph theory. The contour shape of an object is represented by a complex network, where each point belonging shape is represented by a vertex of the network. A set of adjacencies matrices is generated using an artificial dynamics in the complex network. We calculate the spectrum of each adjacency matrix and the most important eigenvalues are used in a feature vector. This vector, after applying module and normalization operations, becomes our spectral shape signature. The principal eigenvalues of a graph are related to its topological properties. This allows us use eigenvalues to describe the shape of an object. We have used shape benchmarks to measure the information retrieve precision of our method. Besides that, we have analyzed the response of the spectral shape signature under noise, rotation and occlusions situations. A qualitative study of the method behavior has been done using curves and a walk sequence. The achieved comparative results to other methods found in the literature show that our spectral shape signature presents good results in information retrieval tasks, good tolerance under noise and partial occlusions situation. We present that our method is able to distinguish human actions and identify the cycles of a walk sequence.

abstract: The research on the topology and dynamics of complex networks is one of the most focused area in complex system science. The goals are to structure our understanding of the real-world social, economical, technological, and biological systems in the aspect of networks consisting a large number of interacting units and to develop corresponding detection, prediction, and control strategies. In this highly interdisciplinary field, my research mainly concentrates on universal estimation schemes, physical controllability, as well as mechanisms behind extreme events and cascading failure for complex networked systems. Revealing the underlying structure and dynamics of complex networked systems from observed data without of any specific prior information is of fundamental importance to science, engineering, and society. We articulate a Markov network based model, the sparse dynamical Boltzmann machine (SDBM), as a universal network structural estimator and dynamics approximator based on techniques including compressive sensing and K-means algorithm. It recovers the network structure of the original system and predicts its short-term or even long-term dynamical behavior for a large variety of representative dynamical processes on model and real-world complex networks. One of the most challenging problems in complex dynamical systems is to control complex networks. Upon finding that the energy required to approach a target state with reasonable precision is often unbearably large, and the energy of controlling a set of networks with similar structural properties follows a fat-tail distribution, we identify fundamental structural ``short boards'' that play a dominant role in the enormous energy and offer a theoretical interpretation for the fat-tail distribution and simple strategies to significantly reduce the energy. Extreme events and cascading failure, a type of collective behavior in complex networked systems, often have catastrophic consequences. Utilizing transportation and evolutionary game dynamics as prototypical settings, we investigate the emergence of extreme events in simplex complex networks, mobile ad-hoc networks and multi-layer interdependent networks. A striking resonance-like phenomenon and the emergence of global-scale cascading breakdown are discovered. We derive analytic theories to understand the mechanism of control at a quantitative level and articulate cost-effective control schemes to significantly suppress extreme events and the cascading process. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2016

A identificação de formas apresenta inúmeras aplicações na área de visão computacional, pois representa uma poderosa ferramenta para analisar as características de um objeto. Dentre as aplicações, podemos citar como exemplos a interação entre humanos e robôs, com a identificação de ações e comandos, e a análise de comportamento para vigilância com a biometria não invasiva. Em nosso trabalho nós desenvolvemos um novo descritor de formas 2D baseado na utilização de redes complexas e teoria espectral de grafos. O contorno da forma de um objeto é representado por uma rede complexa, onde cada ponto pertencente a forma será representado por um vértice da rede. Utilizando uma dinâmica gerada artificialmente na rede complexa, podemos definir uma série de matrizes de adjacência que refletem a dinâmica estrutural da forma do objeto. Cada matriz tem seu espectro calculado, e os principais autovalores são utilizados na construção de um vetor de características. Esse vetor, após aplicar as operações de módulo e normalização, torna-se nossa assinatura espectral de forma. Os principais autovalores de um grafo estão relacionados com propriedades topológicas do mesmo, o que permite sua utilização na descrição da forma de um objeto. Para validar nosso método, nós realizamos testes quanto ao seu comportamento frente a transformações de rotação e escala e estudamos seu comportamento quanto à contaminação das formas por ruído Gaussiano e quanto ao efeito de oclusões parciais. Utilizamos diversas bases de dados comumente utilizadas na literatura de análise de formas para averiguar a eficiência de nosso método em tarefas de recuperação de informação. Concluímos o trabalho com a análise qualitativa do comportamento de nosso método frente a diferentes curvas e estudando uma aplicação na análise de sequências de caminhada. Os resultados obtidos em comparação aos outros métodos mostram que nossa assinatura espectral de forma apresenta bom resultados na precisão de recuperação de informação, boa tolerância a contaminação das formas por ruído e oclusões parciais, e capacidade de distinguir ações humanas e identificar os ciclos de uma sequência de caminhada. / The shape is a powerful feature to characterize an object and the shape analysis has several applications in computer vision area. We can cite the interaction between human and robots, surveillance, non-invasive biometry and human actions identifications among other applications. In our work we have developed a new 2d shape descriptor based on complex network and spectral graph theory. The contour shape of an object is represented by a complex network, where each point belonging shape is represented by a vertex of the network. A set of adjacencies matrices is generated using an artificial dynamics in the complex network. We calculate the spectrum of each adjacency matrix and the most important eigenvalues are used in a feature vector. This vector, after applying module and normalization operations, becomes our spectral shape signature. The principal eigenvalues of a graph are related to its topological properties. This allows us use eigenvalues to describe the shape of an object. We have used shape benchmarks to measure the information retrieve precision of our method. Besides that, we have analyzed the response of the spectral shape signature under noise, rotation and occlusions situations. A qualitative study of the method behavior has been done using curves and a walk sequence. The achieved comparative results to other methods found in the literature show that our spectral shape signature presents good results in information retrieval tasks, good tolerance under noise and partial occlusions situation. We present that our method is able to distinguish human actions and identify the cycles of a walk sequence.

Redes complexas é uma área de estudo relativamente recente, que tem chamado a atenção da comunidade científica e vem sendo aplicada com êxito em diferentes áreas de atuação tais como redes de computadores, sociologia, medicina, física, matemática entre outras. Entretanto a literatura demonstra que poucos são os trabalhos que empregam redes complexas na extração de características de imagens para posterior analise ou classificação. Dada uma imagem é possível modela-la como uma rede, extrair características topológicas e, utilizando-se dessas medidas, construir o classificador desejado. Esse trabalho objetiva, portanto, investigar mais a fundo esse tipo de aplicação, analisando novas formas de modelar uma imagem como uma rede complexa e investigar diferentes características topológicas na caracterização de imagens. Como forma de analisar o potencial das técnicas desenvolvidas, selecionamos um grande desafio na área de visão computacional: identificação vegetal por meio de análise foliar. A identificação vegetal é uma importante tarefa em vários campos de pesquisa como biodiversidade, ecologia, botânica, farmacologia entre outros. / Complex networks is a relatively recent field of study, that has called the attention of the scientific community and has been successfully applied in different areas such as computer networking, sociology, medicine, physics, mathematics and others. However the literature shows that there are few works that employ complex networks in feature extraction of images for later analysis or classification. Given an image, it can be modeled as a network, extract topological features and, using these measures, build the classifier desired. This work aims, therefore, investigate this type of application, analyzing new forms of modeling an image as a complex network and investigate some topological features to characterize images. In order to analyze the potential of the techniques developed, we selected a major challenge in the field of computer vision: plant identification by leaf analysis. The plant identification is an important task in many research fields such as biodiversity, ecology, botany, pharmacology and others.

Imagens multiespectrais estão presentes na grande maioria de dispositivos de imageamento atuais, desde câmeras pessoais até microscópios, telescópios e satélites. No entanto, grande parte dos trabalhos em análise de texturas e afins propõem abordagens monocromáticas, que muitas vezes consideram apenas níveis de cinza. Nesse contexto e considerando o aumento da capacidade dos computadores atuais, o uso da informação espectral deve ser considerada na construção de modelos melhores. Ultimamente redes neurais convolucionais profundas pré-treinadas tem sido usadas em imagens coloridas de 3 canais, porém são limitadas a apenas esse formato e computam muitas convoluções, o que demanda por hardware específico (GPU). Esses fatos motivaram esse trabalho, que propõem técnicas para a modelagem e caracterização de imagens multiespectrais baseadas em redes complexas, que tem se mostrado uma ferramenta eficiente em trabalhos anteriores e possui complexidade computacional similar à métodos tradicionais. São introduzidas duas abordagens para aplicação em imagens coloridas de três canais, denominadas Rede Multicamada (RM) e Rede Multicamada Direcionada (RMD). Esses métodos modelam todos os canais da imagem de forma conjunta, onde as redes possuem conexões intra e entre canais, de forma parecida ao processamento oponente de cor do sistema visual humano. Experimentos em cinco bases de textura colorida mostram a proposta RMD supera vários métodos da literatura no geral, incluindo redes convolucionais e métodos tradicionais integrativos. Além disso, as propostas demonstraram alta robustez a diferentes espaços de cor (RGB, LAB, HSV e I1I2I3), enquanto que outros métodos oscilam de base para base. Também é proposto um método para caracterizar imagens multiespectrais de muitos canais, denominado Rede Direcionada de Similaridade Angular (RDSA). Nessa proposta, cada pixel multiespectral é considerado como um vetor de dimensão equivalente à quantidade de canais da imagem e o peso das arestas representa sua similaridade do cosseno, apontando para o pixel de maior valor absoluto. Esse método é aplicado em um conjunto de imagens de microscopia por fluorescência de 32 canais, em um experimento para identificar variações na estrutura foliar do espécime Jacaranda Caroba submetidos à diferentes condições. O método RDSA obtém as maiores taxas de acerto de classificação nesse conjunto de dados, com 91, 9% usando o esquema de validação cruzada Leave-one-out e 90, 5(±1, 1)% com 10-pastas, contra 81, 8% e 84, 7(±2, 2) da rede convolucional VGG16. / Multispectral images are present in the vast majority of current imaging devices, from personal cameras to microscopes, telescopes and satellites. However, much of the work in texture analysis and the like proposes monochromatic approaches, which often consider only gray levels. In this context and considering the performance increase of current computers, the use of the spectral information must be considered in the construction of better models. Lately, pre-trained deep convolutional neural networks have been used in 3-channel color images, however they are limited to just this format and compute many convolutions, which demands specific hardware (GPU). These facts motivated this work, which propose techniques for the modeling and characterization of multispectral images based on complex networks, which has proved to be an efficient tool in previous works and has computational complexity similar to traditional methods. Two approaches are introduced for application in 3-channel color images, called Multilayer Network (RM) and Directed Multilayer Network (RMD). These methods model all channels of the image together, where the networks have intra- and inter-channel connections, similar to the opponent color processing of the human visual system. Experiments in five color texture datasets shows that the RMD proposal overcomes several methods of the literature in general, including convolutional networks and traditional integrative methods. In addition, the proposals have demonstrated high robustness to different color spaces (RGB, LAB, HSV and I1I2I3), while other methods oscillate from dataset to dataset. Moreover it is proposed a new method to characterize multispectral images of many channels, called Directed Network of Angular Similarity (RDSA). In this proposal, each multispectral pixel is considered as a vector of dimensions equivalent to the number of channels of the image and the weight of the edges represents its cosine similarity, pointing to the pixel of greatest absolute value. This method is applied to a set of fluorescence microscopy images of 32 channels in an experiment to identify variations in the leaf structure of the Jacaranda Caroba specimen under different conditions. The RDSA method obtains the highest classification rates in this dataset, with 91.9% with the Leave-one-out cross-validation scheme and 90.5(±1.1)% with 10-folds, against 81.8% and 84.7(±2.2) of the convolutional network VGG16.

Um dos padrões mais importantes que ocorrem em ecossistemas é a relação espécie-área, que relaciona o número de espécies em um ecossistema com a sua área disponível. O estudo dessa relação é fundamental para entender-se a biodiversidade e o impacto de políticas ambientais de preservação de espécies, de modo que é possível analisar desde os tamanhos das reservas necessários para a conservação das espécies e até verificar o impacto da intervenção humana em habitats naturais. Assim sendo, várias estratégias matemáticas e computacionais foram desenvolvidas para prever e entender esse padrão ecológico em modelos ecológicos. Todavia, muitas abordagens são simuladas em ambientes homogêneos e regulares, porém, sabe-se que, em cada ecossistema, há regiões com acidentes geográficos, variações de altitudes, vegetação e clima. Dessa forma, nesse trabalho, estamos interessados em estudar a influência de diferentes ambientes no processo de evolução das espécies. Para isso, consideramos modelos ecológicos que utilizam características geográficas para colonização e, comportamentos individuais como dispersão, mutação, acasalamento. Com isso, foi possível simular a propagação das espécies em diferentes topologias e analisar como ocorreu a dinâmica em cada uma delas. Assim, verificamos que a topologia regular e a dispersão homogênea dos indivíduos são duas características que maximizam a diversidade de espécies. E por outro lado, a formação de regiões mais densas e interações heterogêneas, contribuem para a diminuição da quantidade de espécies, apesar de em alguns casos, ajudarem na velocidade de propagação e colonização. / One of the most important patterns that occur in ecosystems is the species-area relationship, which says that the number of species increases with the sampled area. There is a great interest among ecologists about this pattern, since it is possible to verify the human impact on the environment and the area of reserves necessary to maintain species. Thus, motivated by the explanation of such behavior, some mathematical and computational strategies have been developed over the years. However, most approaches are simulated in homogeneous and regular scenarios, however, in the ecosystem, there are regions with landforms, different climates and vegetation. Thus, in this work, we are interested in studying the influence of different environments in the evolution process of the species. We consider ecological models that use geographical characteristics for colonization and individual behaviors such as dispersion, mutation, and mating. Thereby, it was possible to simulate the propagation of the species in different topologies and to analyze how the dynamics occurred in each case. Therefore, we verified that the regular topology and the homogeneous dispersion of the individuals are two characteristics that maximize the diversity of species. On the other hand, denser regions and heterogeneous interactions, contribute to the decrease the number of species, even when in some cases, they help in the speed of propagation and colonization.