海上雷达通信数据特征实时监测算法研究
|
摘要
传统船载雷达通信数据检测算法存在小范围样本数据监测准确率低,究其根源在于算法对小样本数据特征计算能力不足,无法精准提取小样本特征。为此提出基于大数据分析的船载雷达通信数据特征实时监测算法,算法由2种计算子算法构成。首先,引入MIFS小样本特征滤除算法,对雷达数据内小样本周边数据进行滤除计算,提升小样本特征清晰度;其次,引入大数据IDWPA遗传编码特征算法,利用大数据分析能力对小样本数据进行遗传模型建力计算,准确抓取小样本特征,完成整套算法计算;最后,通过仿真实验证明提出算法能够有效解决传统算法特征计算力不足,监测准确率低的问题。
The traditional Ship-borne Radar communication data detection algorithm has low accuracy in monitoring small sample data. The reason is that the algorithm has insufficient computing power for small sample data features and can not accurately extract small sample features. For this reason, a real-time monitoring algorithm of Ship-borne Radar communication data characteristics based on large data analysis is proposed. The algorithm consists of two sub-algorithms. Firstly,MIFS small sample feature filtering algorithm is introduced to filter small sample data in radar data to improve the clarity of small sample feature. Secondly, large data IDWPA genetic coding feature algorithm is introduced to calculate the genetic model building power of small sample data by using large data analysis ability, accurately grasp small sample features, and complete the whole algorithm calculation. The simulation results show that the proposed algorithm can effectively solve the problem of insufficient computational power and low monitoring accuracy of traditional algorithms.
The traditional Ship-borne Radar communication data detection algorithm has low accuracy in monitoring small sample data. The reason is that the algorithm has insufficient computing power for small sample data features and can not accurately extract small sample features. For this reason, a real-time monitoring algorithm of Ship-borne Radar communication data characteristics based on large data analysis is proposed. The algorithm consists of two sub-algorithms. Firstly,MIFS small sample feature filtering algorithm is introduced to filter small sample data in radar data to improve the clarity of small sample feature. Secondly, large data IDWPA genetic coding feature algorithm is introduced to calculate the genetic model building power of small sample data by using large data analysis ability, accurately grasp small sample features, and complete the whole algorithm calculation. The simulation results show that the proposed algorithm can effectively solve the problem of insufficient computational power and low monitoring accuracy of traditional algorithms.
引文
[1]周国亮,朱永利,王桂兰,等.实时大数据处理技术在状态监测领域中的应用[J].电工技术学报,2014(s1):432-437.
[2]黄欣欣.大数据中用户特征信息优化定位检测仿真[J].计算机仿真,2017,34(10):357-360.
[3]王冠男.大数据环境下网络异常数据准确检测仿真[J].计算机仿真,2017,34(8):437-440.
[4]王小燕,张丽敏.基于大数据的数据挖掘引擎研究[J].电子设计工程,2017,25(15):31-34+38.
[2]黄欣欣.大数据中用户特征信息优化定位检测仿真[J].计算机仿真,2017,34(10):357-360.
[3]王冠男.大数据环境下网络异常数据准确检测仿真[J].计算机仿真,2017,34(8):437-440.
[4]王小燕,张丽敏.基于大数据的数据挖掘引擎研究[J].电子设计工程,2017,25(15):31-34+38.