基于特征选择的战场数据处理技术研究  

A Battlefield Data Processing Method Based on Feature Selection

作　　者：王冬海[1] 戴磊[1] 

机构地区：[1]中国电子科学研究院,北京100041

出　　处：《中国电子科学研究院学报》2012年第3期298-301,共4页Journal of China Academy of Electronics and Information Technology

摘　　要：面向现代战场中各类感知设备产生海量实时数据,消除冗余及无关数据是提升信息质量,降低军事信息系统资源开销的关键技术。提出了一种基于特征选择的数据降维方法,实验结果表明该方法能够大幅消减噪音数据,有效提升信息质量,降低系统开销,适用于现代战争环境。Toward the vast and real-time data generated by all kinds of sensors in modern battlefield, re- duction of redundant and unrelated data is essential technology for military information system. A data di- mension reduction method based on feature selection technology is proposed. Experiments results demon- strate that the proposed method is efficiency in reducing noisy data to be treat of and suitable for modern battlefield environment.

关 键 词：网络中心战 特征选择 信息增益 

分 类 号：TN919[电子电信—通信与信息系统]