2018
Authors
Silva, W; Pinto, JR; Cardoso, JS;
Publication
2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
Abstract
Ordinal classification is a specific and demanding task, where the aim is not only to increase accuracy, but to also capture the natural order between the classes, and penalize incorrect predictions by how much they deviate from this ranking. If an ordinal classifier must be able to comply with all these requirements, a suitable ordinal metric must be able to accurately measure its degree of compliance. However, the current metrics are unable to completely capture these considerations when assessing classification performance. Moreover, most suffer from sensitivity to imbalanced classes, very common in ordinal classification. In this paper, we propose two variants of a novel performance index that accounts for both accuracy and ranking in the performance assessment of ordinal classification, and is robust against imbalanced classes. © 2018 IEEE.
2018
Authors
Couto, R; Campos, JC;
Publication
2018 1ST INTERNATIONAL CONFERENCE ON GRAPHICS AND INTERACTION (ICGI 2018)
Abstract
Alloy supports reasoning about software designs in early development stages. It is composed of a modelling language and a tool that is able to find valid instances of the model. Alloy is able to produce graphical representations of analysis results, which is essential for their interpretation. In previous work we have improved the representations with the usage of layout managers. Here, we further extend that work by presenting the improvements on the approach, and by introducing a new case study to analyse the contribution of layout managers, and to support validation trough a user study.
2018
Authors
Torgo, L; Matwin, S; Weiss, G; Moniz, N; Branco, P;
Publication
International Workshop on Cost-Sensitive Learning, COST@SDM 2018, San Diego, California, USA, May 5, 2018
Abstract
2018
Authors
Catalao, JPS; Siano, P; Li, F; Masoum, MAS; Aghaei, J;
Publication
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Abstract
2018
Authors
Fontes Filho, JR; Alves, CF;
Publication
Cadernos EBAPE.BR
Abstract
2018
Authors
Monteiro Pereira, RMM; Pereira, AJC; Ferreira, CM; Maciel Barbosa, FPM;
Publication
ENERGIES
Abstract
The energy sector is evolving rapidly, namely due to the increasing importance of renewable energy sources. The connection of large amounts of wind power generation poses new challenges for the dynamic voltage stability analysis of an electric power system, which has to be studied. In this paper, the traditional Doubly-Fed Induction Generator model is employed. Based on this model, a crowbar and chopper circuit is set up to protect the turbine during the short-circuit period. The EUROSTAG software package was used for the simulation studies of the system, and numerical results were obtained. Conclusions are drawn that provide a better understanding of the influence of crowbar and chopper protection on Doubly-Fed Induction Generators (DFIG), during low voltage ride through, in a system with wind power generation.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.