期刊论文

Anomaly Event Detection for Farmland Information Monitoring Based on Improved CoSaMP

中文

农业机械学报

1000-1298

2019

50

10

230-235

10.6041/j.issn.1000-1298.2019.10.026

14C0404:湖南省教育厅科学研究项目 18C1383:湖南省教育厅科学研究项目 2019JJ40136:湖南省自然科学基金

本校为第一机构

针对农田监测区域大、监测节点能量有限以及异常事件具有偶发性等特点,提出了一种基于改进压缩采样匹配追踪的农田信息异常事件检测算法(DP-CoSaMP)。针对传统压缩采样匹配追踪(Compressive sampling matching pursuit,Co Sa MP)算法中相似原子选择和稀疏度要求已知问题,引进Dice系数有效区分原子相关性,保证选择最优原子;利用峰值信噪比(Peak signal to noise ratio,PSNR)与匹配信号残差具有相似变化趋势,动态调整算法迭代次数,避免稀疏度获取困难问题。仿真实验结果表明,本文算法异常事件检测成功率较现有算法提高了20%,网络能耗降低了15%,平均检测时间减少了50%。

The wireless sensor network technology provides efficient and reliable technical means for farmland information monitoring in recent years. WSN is a self-organizing network composed of a large number of sensor nodes with sensing and computing capabilities. WSN can detect abnormal events in farmland information, such as fire, environmental pollution, etc. Considering the characteristics of the large monitoring area, limited energy of monitoring nodes and occasional abnormal events, an anomaly event detection for farmland information monitoring b...