摘要
Unrepresentative data samples are likely to reduce the utility of data classifiers in practical application. This study presents a multi-approaches-guided preprocess algorithm in the design of an effective chance discovery model, which bases on data crystallization, clustering and neural network techniques. We used data crystallization to discover unobservable events of the input samples with the objective of indicating unrepresentative samples, used clustering techniques to process the samples into isolated and inconsistent clusters, and neural networks to construct the chance discovery data set model. The aim of this paper is to develop a combined method for data preprocess by using different methods to preprocess different data features in order for exerting their unique characteristics. The results show its effect to industrial decision making.
- 出版日期2008
- 单位哈尔滨工程大学