Time filter

Source Type

Lapa J.,Polytechnic Institute of Porto | Bernardino J.,Polytechnic Institute of Coimbra | Almeida A.,Polytechnic Institute of Porto | Almeida A.,Knowledge Engineering and Decision Support Research Center
Advances in Intelligent Systems and Computing

Business Intelligence (BI) can be a powerful ally to organizations, in decision making processes. BI is not yet a reality in some companies in fact, it's even unknown in many of them. It is essential that the information and functionalities on BI suites come clearly to organizations. Only a correct choice will allow data to result in gains and business success. In this paper we present a comparative analysis of some BI tools capabilities, in order to aid organizations in the selection process of the most suitable BI platform. We also test the use of collaborative technologies to integrate data from social networks because it can be determinant in the design of future business strategies. © Springer International Publishing Switzerland 2015. Source

Pinto C.M.A.,Polytechnic Institute of Porto | Pinto C.M.A.,University of Porto | Pinto C.M.A.,Knowledge Engineering and Decision Support Research Center
International Journal of Bifurcation and Chaos

We study the peculiar dynamical features of a fractional derivative of complex-order network. The network is composed of two unidirectional rings of cells, coupled through a "buffer" cell. The network has a Z3 × Z5 cyclic symmetry group. The complex derivative Dα±jβ, with α,β ∈ R+ is a generalization of the concept of integer order derivative, where α = 1, β = 0. Each cell is modeled by the Chen oscillator. Numerical simulations of the coupled cell system associated with the network expose patterns such as equilibria, periodic orbits, relaxation oscillations, quasiperiodic motion, and chaos, in one or in two rings of cells. In addition, fixing β = 0.8, we perceive differences in the qualitative behavior of the system, as the parameter c ∈ [13, 24] of the Chen oscillator and/or the real part of the fractional derivative, α ∈ {0.5, 0.6, 0.7, 0.8, 0.9, 1.0}, are varied. Some patterns produced by the coupled system are constrained by the network architecture, but other features are only understood in the light of the internal dynamics of each cell, in this case, the Chen oscillator. What is more important, architecture and/or internal dynamics? © 2015 World Scientific Publishing Company. Source

Gomes E.F.,Knowledge Engineering and Decision Support Research Center | Gomes E.F.,Polytechnic Institute of Porto | Batista F.,Polytechnic Institute of Porto
International Journal of Software Engineering and its Applications

The automatic classification of urban sounds is important for environmental monitoring. In this work we employ SAX-based Multiresolution Motif Discovery to generate features for Urban Sound Classification. Our approach consists in the discovery of relevant frequent motifs in the audio signals and use the frequency of discovered motifs as characterizing attributes. We explore and evaluate different configurations of motif discovery for defining attributes. In the automatic classification step we use a decision tree based algorithm, random forests and SVM. Results obtained are compared with the ones using Mel-Frequency Cepstral Coefficients (MFCC) as features. MFCCs are commonly used in environmental sound analysis, as well as in other sound classification tasks. Experiments were performed on the Urban Sound dataset, which is publicly available. Our results indicate that we can separate difficult pairs of classes (where MFCC fails) using the motif approach for feature construction. © 2015 SERSC. Source

Sanches Fernandes L.F.,University of Tras os Montes e Alto Douro | Sanches Fernandes L.F.,Center for the Research and Technology of Agro Environmental and Biological science | Seixas F.J.,University of Tras os Montes e Alto Douro | Oliveira P.C.,University of Tras os Montes e Alto Douro | And 5 more authors.
Fresenius Environmental Bulletin

The Mike Basin - Water Quality modelling system was applied to the hydrographical basin of Sôrdo river located in the northeast of Portugal, in the region of Trásos-Montes and Alto Douro. This model allows the simulation of diffuse pollution caused by nitrate concentration in a small hydrographical basin (located in the demarcated region of the Port wine). The model allows the creation of a set of scenarios aiming at an effective planning of the basin under study. The available data for the drainages calculation were the monthly average effective rainfall between the years of 1960 and 2008. The Climate-change was predicted by the scenarios created in SIAM II and were simulated with the HadRM3 model. The limit quantities of nitrate present in the water should not contain over 25 mg/1; this is the maximum recommended value, and should not exceed 50 mg/1, this is the maximum allowable value by Portuguese law. We created simulation scenarios using the fertilizers produced by the bovine cattle and change of the agricultural uses or crops in this basin. For 2010 the fertilizers used were comprised between the recommended and the allowable maximum values. For 2071 the fertilizers were above the maximum allowable value. With these scenarios we found a 40% increase in nitrate levels due to climate change between the years 2010 and 2071. ©by PSP. Source

Grisi E.F.,University of Zaragoza | Yusta J.M.,University of Zaragoza | Khodr H.M.,Knowledge Engineering and Decision Support Research Center
Energy Conversion and Management

This work presents an analysis of the inherent potentialities and characteristics of the sugarcane industries that produce sugar, bioethanol, biogas and bioelectricity and that are being described as " Biorefineries". These Biorefineries are capable of producing bio-energy under diverse forms, intended for their own internal consumption and for external sales and marketing. A complex model and simulation are carried out of the processes of a sugarcane industry, with the data characteristic as well as the production costs, prices of products and considerations on the energy demand by basic processes. A Mixed-Integer Linear Programming (MILP) optimization problem formulation and an analysis of optimal solutions in short-term operation are described, taking into account the production cost functions of each commodity and the incomes obtained from selling electricity and other products. The objective is to maximize the hourly plant economic profit in the different scenarios considered in a real case study. Crown Copyright © 2010 Published by Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations