期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：4
页码：3294-3297
出版社：TechScience Publications
摘要：In today’s world data is rapidly and continuously growing and is not constant in nature. There is a problem to deal with such kind of evolving data, because it is impractical to store and process this streaming data. Also, in real world application, the stream of data coming is typically noisy, has some missing values, repeated features, and thus very large time is wasted to process that data. The time complexity can reduce by selecting only useful features to build model for classification. The proposed system takes into consideration the issue of adaptive preprocessing for streaming data. Here Genetic algorithm (GA) is used as a search method while selecting the features which will further use in learning model. GA alongwith selective windowing strategy is the proposed system. The proposed system is applied to different stream datasets and, also compared with existing preprocessing technique PCA, is showing significant improvement in classification accuracy.
