论文部分内容阅读
针对分布式光纤周界安防系统易受外界各种干扰导致误报率高的问题,本文根据不同干扰源引起的系统输出信号在时频分布上的差异,基于小波分析方法建立小波能量熵(WEG)测度将这种差异表现为信号分解尺度上能量分布的差异进行定量描述,实现对系统输出信号进行特征提取和分类,可以有效区分外界轻微扰动、风雨等环境因素与蓄意入侵所引起的信号之间的差别,提高系统的准确性和实时性。实验结果表明:本文方法可以有效排除非人为入侵的干扰,正确识别率高于93%,实验较低的误报率。
According to the difference of time-frequency distribution of system output signal caused by different sources of interference, a wavelet energy entropy (WEG) method is established based on the wavelet analysis method to solve the problem of distributed perimeter security system vulnerable to various false alarms. ) Measurements show the difference as a quantitative description of the differences in energy distribution at the signal decomposition scale, and can extract and classify the features of the output signals of the system so as to effectively distinguish external disturbances, wind and rain and other environmental factors from signals caused by intentional invasion Between the differences, improve system accuracy and real-time. The experimental results show that this method can effectively eliminate the interference of non-human intrusion, correct recognition rate is higher than 93%, lower false positive rate of experiment.