151 resultados para Redes neurais ARTMAP nebulosa
Resumo:
This project aims to explore the many methods used for the development of recommendation systems to user ’ s items and apply the content - based recommendation method on a prototype system whose purpose is to recommend books to users. This paper exposes the most popular methods for creating systems capable of providing items (products) according to user preferences, such as collaborat ive filtering and content - based. It also point different techniques that can be applied to calculate the similarity between two entities, for items or users, as the Pearson ’s method, calculating the cosine of vectors and more recently, a proposal to use a Bayesian system under a Dirichlet distribution. In addition, this work has the purpose to go through various points on the design of an online application, or a website, dealing not only oriented algorithms issues, but also the definition of development to ols and techniques to improve the user’s experience. The tools used for the development of the page are listed, and a topic about web design is also discussed in order to emphasize the importance of the layout of the application. At the end, some examples of recommender systems are presented for curiosity , learning and research purposes
Resumo:
This work has as its theme the role of emotions and affectivity in learning, particularly in science learning, being developed from a literature review. We start from the idea that learning occurs through changes in the neural networks of each individual and that these changes are caused by a combination of genetic and biological factors also influenced by emotions and affectivity. We seek information on the functioning of the human brain, highlighting the neuroanatomy and neurocognition, to understand how the brain processes information, including the feelings and emotions experienced by the individual. Once we try to understand which roles are assigned to the feelings and emotions in different learning theories, emphasizing the cognitive and humanistic theories. Finally, we found some more recent contributions to the understanding of the learning process, to the field of neuroscience. We were led to conclude that there is great scope for research in applied neuroscience to education, since the work, especially in the national literature are still scarce
Resumo:
In this project the Pattern Recognition Problem is approached with the Support Vector Machines (SVM) technique, a binary method of classification that provides the best solution separating the data in the better way with a hiperplan and an extension of the input space dimension, as a Machine Learning solution. The system aims to classify two classes of pixels chosen by the user in the interface in the interest selection phase and in the background selection phase, generating all the data to be used in the LibSVM library, a library that implements the SVM, illustrating the library operation in a casual way. The data provided by the interface is organized in three types, RGB (Red, Green and Blue color system), texture (calculated) or RGB + texture. At last the project showed successful results, where the classification of the image pixels was showed as been from one of the two classes, from the interest selection area or from the background selection area. The simplest user view of results classification is the RGB type of data arrange, because it’s the most concrete way of data acquisition
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
The present paper aims at applying a model of bilingual onomasiological terminological dictionary, as proposed by Babini (2001b), for the development of an English-Portuguese and Portuguese-English electronic dictionary of the fundamental Artificial Neural Networks (ANN) terms. This subarea of Artificial Intelligence was chosen due to its use in several technological activities. The onomasiological dictionary is characterized by allowing searches of either lexical or terminological units from its semantic content. Our dictionary model allows two types of search: semasiological and onomasiological. The onomasiological search is made possible by a set of semes or semantic traits that make up the concept of each term in the dictionary.
Resumo:
The use of mobile robots in the agriculture turns out to be interesting in tasks of cultivation and application of pesticides in minute quantities to reduce environmental pollution. In this paper we present the development of a system to control an autonomous mobile robot navigation through tracks in plantations. Track images are used to control robot direction by preprocessing them to extract image features, and then submitting such characteristic features to a support vector machine to find out the most appropriate route. As the overall goal of the project to which this work is connected is the robot control in real time, the system will be embedded onto a hardware platform. However, in this paper we report the software implementation of a support vector machine, which so far presented around 93% accuracy in predicting the appropriate route.
Resumo:
Pós-graduação em Geologia Regional - IGCE
Resumo:
Pós-graduação em Engenharia Elétrica - FEIS
Resumo:
Pós-graduação em Geologia Regional - IGCE
Resumo:
Processos automatizados, como a furação, podem melhorar com o uso de métodos de controle e supervisão, com destaque para sensores e redes neurais artificiais. Neste estudo, foram utilizados diferentes sensores instalados em máquina-ferramenta para o registro dos sinais de força de avanço, potência elétrica, aceleração e sinal acústico, durante a furação de corpos de prova compostos por uma liga de titânio seguida de uma liga de alumínio. Os sinais e os diâmetros dos furos medidos na furação das amostras foram utilizados no treinamento da rede neural artificial. Os erros foram apresentados e analisados. Os resultados demonstraram alta capacidade da rede em estimar o diâmetro do furo nas diferentes condições de usinagem com erros baixos e até mesmo desprezíveis para a maior parte das aplicações industriais, mostrando assim eficiência do método proposto.
Resumo:
Indicadores de desempenho são importantes recursos para a gestão da qualidade no desenvolvimento de software. O volume de dados produzido por esses indicadores tende a aumentar significativamente com o tempo de monitoração, dificultando análises e tomadas de decisão. As bases históricas tornam-se complexas, considerando a quantidade de dados monitorados e a diversidade de indicadores (diferentes tipos, granularidade e frequência). Este trabalho propõe o uso de técnicas de aprendizagem de máquina para análise dessas bases, utilizando redes neurais artificiais combinadas com técnicas de visualização de informação. É utilizado um modelo de indicadores, com base nos processos do modelo de referência MPS para Software (MPS-SW), agrupados segundo as perspectivas estratégicas do Balanced Scorecard (BSC).
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Pós-graduação em Ciência da Computação - IBILCE