Classifying Uncertain and Evolving Data Streams with Distributed Extreme Learning Machine

• Published in: Journal of computer science and technology Vol. 30; no. 4; pp. 874 - 887
• Main Author: 韩东红 张昕 王国仁
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2015; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Alliances; Artificial Intelligence; Artificial neural networks; Classification; Classifiers; Computer Science; Data Structures and Information Theory; Data transmission; Datasets; Decision trees; Distributed processing; Drift; Global positioning systems; GPS; Information management; Information Systems Applications (incl.Internet); Learning; Machine learning; Model accuracy; Neural networks; Probability; Regular Paper; Science; Software Engineering; Studies; Theory of Computation; 不确定性; 分布式; 分类算法; 大数据集; 学习机; 概率模型; 流分类; 矩阵运算; United States > US; concept drift; classification; extreme learning machine; distributed computing; uncertain data stream
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-015-1566-6

Conventional classification algorithms are not well suited for the inherent uncertainty, potential concept drift, volume, and velocity of streaming data. Specialized algorithms are needed to obtain efficient and accurate classifiers for uncertain data streams. In this paper, we first introduce Distributed Extreme Learning Machine （DELM）, an optimization of ELM for large matrix operations over large datasets. We then present Weighted Ensemble Classifier Based on Distributed ELM （WE-DELM）, an online and one-pass algorithm for efficiently classifying uncertain streaming data with concept drift. A probability world model is built to transform uncertain streaming data into certain streaming data. Base classifiers are learned using DELM. The weights of the base classifiers are updated dynamically according to classification results. WE-DELM improves both the efficiency in learning the model and the accuracy in performing classification. Experimental results show that WE-DELM achieves better performance on different evaluation criteria, including efficiency, accuracy, and speedup.