Encontrados 10 documentos, a visualizar página 1 de 1
Customized crowds and active learning to improve classification
Costa, Joana; Silva, Catarina; Antunes, Mário; Ribeiro, BernardeteTraditional classification algorithms can be limited in their performance when a specific user is targeted. User preferences, e.g. in recommendation systems, constitute a challenge for learning algorithms. Additionally, in recent years user’s interaction through crowdsourcing has drawn significant interest, although its use in learning settings is still underused. In this work we focus on an active strategy th...
Programa, Conteúdos e Métodos de Ensino Teórico e Prático : Técnicas de Reconhe...
Ribeiro, Bernardete MartinsRelatório de unidade curricular, apresentado para provas de agregação em Engenharia Informática, da Faculdade de Ciências e Tecnologia da Universidade de Coimbra
Computational Intelligence: Neural Networks and Kernel Methods
Ribeiro, Bernardete MartinsSumário do seminário apresentado para provas de agregação em Engenharia Informática da Faculdade de Ciências e Tecnologia da Universidade de Coimbra
Feature selection for bankruptcy prediction : a multi-objective optimization ap...
Mendes, F.; Duarte, J.; Vieira, Armando; Gaspar-Cunha, A.; Ribeiro, Bernardete; Ribeiro, André M. S.; Neves, João CarvalhoIn this work a Multi-Objective Evolutionary Algorithm (MOEA) was applied for feature selection in the problem of bankruptcy prediction. The aim is to maximize the accuracy of the classifier while keeping the number of features low. A two-objective problem - minimization of the number of features and accuracy maximization – is fully analyzed using two classifiers: Support Vector Machines and Logistic Function. A...
Financial distress model prediction using SVM +
Ribeiro, Bernardete; Silva, C.; Vieira, Armando; Gaspar-Cunha, A.; Neves, JoãoFinancial distress prediction is of great importance to all stakeholders in order to enable better decision-making in evaluating firms. In recent years, the rate of bankruptcy has risen and it is becoming harder to estimate as companies become more complex and the asymmetric information between banks and firms increases. Although a great variety of techniques have been applied along the years, no comprehensive ...
Multi-objective evolutionary algorithms for feature selection : application in ...
Gaspar-Cunha, A.; Mendes, F.; Duarte, J.; Vieira, Armando; Ribeiro, Bernardete; Ribeiro, André M. S.; Neves, João CarvalhoA Multi-Objective Evolutionary Algorithm (MOEA) was adapted in order to deal with problems of feature selection in datamining. The aim is to maximize the accuracy of the classifier and/or to minimize the errors produced while minimizing the number of features necessary. A Support Vector Machines (SVM) classifier was adopted. Simultaneously, the parameters required by the classifier were also optimized. The vali...
Image complexity and feature mining for steganalysis of least significant bit m...
Liu, Qingzhong; Sung, Andrew H.; Ribeiro, Bernardete; Wei, Mingzhen; Chen, Zhongxue; Xu, JianyunThe information-hiding ratio is a well-known metric for evaluating steganalysis performance. In this paper, we introduce a new metric of image complexity to enhance the evaluation of steganalysis performance. In addition, we also present a scheme of steganalysis of least significant bit (LSB) matching steganography, based on feature mining and pattern recognition techniques. Compared to other well-known methods...
On Text-based Mining with Active Learning and Background Knowledge Using SVM
Silva, Catarina; Ribeiro, BernardeteAbstract Text mining, intelligent text analysis, text data mining and knowledge-discovery in text are generally used aliases to the process of extracting relevant and non-trivial information from text. Some crucial issues arise when trying to solve this problem, such as document representation and deficit of labeled data. This paper addresses these problems by introducing information from unlabeled documents i...
Support vector machines for quality monitoring in a plastic injection molding p...
Ribeiro, BernardeteSupport vector machines (SVMs) are receiving increased attention in different application domains for which neural networks (NNs) have had a prominent role. However, in quality monitoring little attention has been given to this more recent development encompassing a technique with foundations in statistic learning theory. In this paper, we compare C-SVM and ν-SVM classifiers with radial basis function (RBF) NNs...
Convex hull calculations: a Matlab implementation and correctness proofs for th...
Kovacec, Alexander; Ribeiro, BernardeteThis paper provides full Matlab -code and informal correctness proofs for the lexicographic reverse search algorithm for convex hull calculations. The implementation was tested on a 1993 486-PC for various small and some larger, partially highly degenerate combinatorial polytopes, one of which (a certain 13- dimensional 24 vertex polyhedron) occurs naturally in the study of a well known problem posed by Profess...
| Financiadores do RCAAP | |||||||
|
|
|
|
|
|
||