V
Victor L. F. Souza
Researcher at Federal University of Pernambuco
Publications - 21
Citations - 557
Victor L. F. Souza is an academic researcher from Federal University of Pernambuco. The author has contributed to research in topics: Context (language use) & Overfitting. The author has an hindex of 6, co-authored 19 publications receiving 378 citations. Previous affiliations of Victor L. F. Souza include Instituto Nacional de Matemática Pura e Aplicada & Universidade de Pernambuco.
Papers
More filters
Journal ArticleDOI
Computational Intelligence and Financial Markets
Rodolfo C. Cavalcante,Rodrigo C. Brasileiro,Victor L. F. Souza,Jarley P. Nobrega,Adriano L. I. Oliveira +4 more
TL;DR: An overview of the most important primary studies published from 2009 to 2015, which cover techniques for preprocessing and clustering of financial data, for forecasting future market movements, for mining financial text information, among others, are given.
Proceedings ArticleDOI
A Writer-Independent Approach for Offline Signature Verification using Deep Convolutional Neural Networks Features
TL;DR: The experiments performed show that the proposed approach outperformed other WI-HSV methods from the literature, and was able to outperform the writer-dependent method with CNN features in the Brazilian dataset.
Proceedings ArticleDOI
Automatic method for stock trading combining technical analysis and the Artificial Bee Colony Algorithm
TL;DR: The proposed intelligent system based on historical closing prices that uses technical analysis, the Artificial Bee Colony Algorithm (ABC), a selection of past values (lags), nearest neighbor classification (k-NN) and its variation, the Adaptative Classification and Nearest Neighbor (A- k-NN).
Journal ArticleDOI
A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification
TL;DR: A white-box analysis of the writer-independent framework highlights how it handles the challenges, the dynamic selection of references through fusion function, and its application for transfer learning, and the experimental results show that “good” and “bad” quality skilled forgeries are characterized using the instance hardness measure.
Posted Content
A writer-independent approach for offline signature verification using deep convolutional neural networks features
TL;DR: The use of features extracted using a deep convolutional neural network (CNN) combined with a writer-dependent SVM classifier resulted in significant improvement in performance of handwritten signature verification (HSV) when compared to the previous state-of-the-art methods as discussed by the authors.