Ciência da Computação
URI permanente desta comunidadehttps://repositorio.fei.edu.br/handle/FEI/342
Navegar
3 resultados
Resultados da Pesquisa
- Comparison of Bio-Inspired Algorithms from the Point of View of Medical Image Segmentation(2018) Wachs Lopes G.A.; Beltrame F.S.; Santos R.M.; Rodrigues P.S.© 2018 IEEE.As new technological challenges depending on the computational performance of bio-inspired algorithms emerge, the demand for more efficient heuristic solutions grows up at same rate. Specifically, the medical field is one of the most challenging, due to the fact of the pre-processing steps, such as multilevel segmentation of color spaces, require greater precision. Thus, many algorithms inspired by natural behavior have emerged successfully aiming to find approximate solutions compatible with optimal ones, but with much higher performance in terms of computational time. Although they perform well, some of these newer algorithms have not yet been analyzed from their practical applicability in one or more medical databases. This paper presents a comparative study from a practical point of view of three of these new algorithms: Cuckoo Search (CS), KH (Krill Herd) and EHO (Elephant Herd Optimization). Our results suggest that these three algorithms are compatible in terms of performance in medical databases, but with EHO showing the best performance among all three.
- Parallel approach to the firefly algorithm(2018-10-05) LINHARES, G.; COSTA, G.; JACOBSON, L.; RODRIGUES, L.; BALLABENUTE, V.; Guilherme Lopes; RODRIGUES, P.© 2018 IEEE.Distributed computing is a computation approach in which many calculations are made at the same time in a distributed memory model, exploring the fact that big problems can sometimes be divided into little ones that can be solved at the same time. This paper uses the distributed computing concept to optimize the sequential version of the Firefly Algorithm (FA). Results show that the proposed distributed version is more efficient than the regular existing algorithm.
- A Bio-Inspired Methodology for Digital Imaging Forensic Detection(2019-09-05) SANTOS, G. L.; OLIVEIRA, G. R.; PRADO, F. F.; SERIKAKU, R.; SANTOS, R. M.; LOPES, G.; RODRIGUES, P. S.© 2019 IEEE.The increasing number of digital media users, as well as the development of multimedia platforms, such as smartphones and tablets, has also increased the number of users who professionally and fraudulently manipulate all types of digital media. This paper proposes a methodology based on an image processing pipeline to detect mainly copy-move type frauds, which are intended to hide or enlarge visual information. Our proposal has been tested in a Copy-Move Forgery database and the results were equal or better in performance than the state-of-art methods.