摘要
针对传统数据传输丢帧检测方法易受到外界的干扰,导致检测结果不够准确,无法对丢帧现象做出及时处理的问题,提出短距离无线通信CSD数据传输持续丢帧测试。分析短距离无线通信CSD数据传输中的持续丢帧现象特点并分析其产生的原因,在此基础上建立噪声模型,利用最小二乘法与平均斜率法分别去除数据中的噪声与趋势项,完成对CSD数据的处理,将预处理后的数据作为训练样本完全输入到BP神经网络分类器中,构建出增广模型从而对是否发生丢帧现象进行判断,完成丢帧测试。仿真结果表明,上述方法的检测精准度高,检测耗时短,有效提高了检测效率,在传输数据丢帧测试中可以广泛应用。
Traditional detection method is susceptible to external interference,resulting in inaccurate detection results.It is unable to deal with the frame drop in time.Therefore,a method of continuous frame loss test for CSD data transmission in short-range wireless communication was proposed.At first,the characteristics of continuous frame dropping in CSD data transmission of short-range wireless communication and its causes were analyzed.On this basis,a noise model was built.The least square method and the average slope method were used to remove the noise and trend terms in data,so that the processing of CSD data was completed.Moreover,the pre-processed data was completely input into BP neural network classifier as training samples,and thus to build the augmented model,which was used to judge whether a frame dropping phenomenon occurred.Finally,the frame drop test was completed.Simulation results show that the proposed method has high detection accuracy and short detection time,which effectively improves detection efficiency.This method can be widely applied in frame dropping test.
作者
陈贺婉
李虎
陆慧娟
CHEN He-wan;LI Hu;LU Hui-juan(President’s Office,China Jiliang University,Hangzhou Zhejiang 310018,China;College of Information Engineering,China Jiliang University,Hangzhou Zhejiang 310018,China)
出处
《计算机仿真》
北大核心
2020年第6期142-146,共5页
Computer Simulation
关键词
无线通信
数据传输
持续丢帧
神经网络
最小二乘法
Wireless communication
CSD data transmission
Continuous frame dropping
BP neural network
Least square method
