Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Challenges in benchmarking stream learning algorithms with real-world data

Full text
Author(s):
Souza, Vinicius M. A. [1, 2] ; dos Reis, Denis M. [2] ; Maletzke, Andre G. [2] ; Batista, Gustavo E. A. P. A. [2, 3]
Total Authors: 4
Affiliation:
[1] Univ New Mexico, Albuquerque, NM 87131 - USA
[2] Univ Sao Paulo, Sao Carlos, SP - Brazil
[3] Univ New South Wales, Sydney, NSW - Australia
Total Affiliations: 3
Document type: Journal article
Source: DATA MINING AND KNOWLEDGE DISCOVERY; JUL 2020.
Web of Science Citations: 0
Abstract

Streaming data are increasingly present in real-world applications such as sensor measurements, satellite data feed, stock market, and financial data. The main characteristics of these applications are the online arrival of data observations at high speed and the susceptibility to changes in the data distributions due to the dynamic nature of real environments. The data stream mining community still faces some primary challenges and difficulties related to the comparison and evaluation of new proposals, mainly due to the lack of publicly available high quality non-stationary real-world datasets. The comparison of stream algorithms proposed in the literature is not an easy task, as authors do not always follow the same recommendations, experimental evaluation procedures, datasets, and assumptions. In this paper, we mitigate problems related to the choice of datasets in the experimental evaluation of stream classifiers and drift detectors. To that end, we propose a new public data repository for benchmarking stream algorithms with real-world data. This repository contains the most popular datasets from literature and new datasets related to a highly relevant public health problem that involves the recognition of disease vector insects using optical sensors. The main advantage of these new datasets is the prior knowledge of their characteristics and patterns of changes to adequately evaluate new adaptive algorithms. We also present an in-depth discussion about the characteristics, reasons, and issues that lead to different types of changes in data distribution, as well as a critical review of common problems concerning the current benchmark datasets available in the literature. (AU)

FAPESP's process: 16/04986-6 - Intelligent traps and sensors: an innovative approach to control insect pests and disease vectors
Grantee:Gustavo Enrique de Almeida Prado Alves Batista
Support type: Research Grants - eScience and Data Science Program - Regular Program Grants
FAPESP's process: 17/22896-7 - Unsupervised Context Detection of Streaming Data For Classification
Grantee:Denis Moreira dos Reis
Support type: Scholarships in Brazil - Doctorate
FAPESP's process: 18/05859-3 - Intelligent traps and sensors: an innovative approach to control insect pests and disease vectors
Grantee:Vinícius Mourão Alves de Souza
Support type: Scholarships in Brazil - Post-Doctorate