V
Vinicius M. A. Souza
Researcher at University of São Paulo
Publications - 40
Citations - 1177
Vinicius M. A. Souza is an academic researcher from University of São Paulo. The author has contributed to research in topics: Data stream mining & Time series. The author has an hindex of 15, co-authored 38 publications receiving 846 citations. Previous affiliations of Vinicius M. A. Souza include Universidade Estadual de Maringá & University of New Mexico.
Papers
More filters
Journal ArticleDOI
CID: an efficient complexity-invariant distance for time series
TL;DR: The first complexity-invariant distance measure for time series is introduced, and it is shown that this improvement does not compromise efficiency, since it can be lower bound and use a modification of triangular inequality, thus making use of most existing indexing and data mining algorithms.
Journal ArticleDOI
Evaluation of statistical and machine learning models for time series prediction: identifying the state-of-the-art and the best conditions for the use of each model
TL;DR: One of the most extensive, impartial and comprehensible experimental evaluations ever done in the time series prediction field is presented, showing that SARIMA is the only statistical method able to outperform, but without a statistical difference, the following machine learning algorithms: ANN, SVM, and kNN-TSPI.
Proceedings ArticleDOI
Data stream classification guided by clustering on nonstationary environments and extreme verification latency
TL;DR: Sao Paulo Research Foundation (FAPESP) (grant numbers 2011/17698-5, 2012/50714-7, 2013/26151-5)
Proceedings ArticleDOI
Time Series Classification Using Compression Distance of Recurrence Plots
TL;DR: Although recurrence plots cannot provide the best accuracy rates for all data sets, it is demonstrated that it can be predicted ahead of time that the method will outperform the time representation with Euclidean and Dynamic Time Warping distances.
Journal ArticleDOI
Exploring Low Cost Laser Sensors to Identify Flying Insect Species
Diego Furtado Silva,Vinicius M. A. Souza,Daniel P. W. Ellis,Eamonn Keogh,Gustavo E. A. P. A. Batista +4 more
TL;DR: The solution to the most important challenge to make this sensor practical: the creation of an accurate classification system is presented and it is shown that the correct combination of feature extraction and machine learning techniques can achieve an accuracy of almost 90 % in the task of identifying the correct insect species among nine species.