嵌入式实时系统中劣质数据动态检测方法研究

发布时间：2018-05-30 05:27

本文选题：嵌入式实时系统 + 劣质数据　；参考：《科学技术与工程》2017年17期

【摘要】：在嵌入式实时系统中,数据在采集过程中容易出现丢失现象、在传输过程中容易受到外界攻击变成劣质数据,威胁整个系统的安全。当前劣质数据检测方法通过聚类法实现,不仅通信开销大,而且检测性能低下。为此,提出一种新的嵌入式实时系统中劣质数据动态检测方法,建立嵌入式实时系统。介绍自回归模型的构建方法,通过优质数据的变化规律构建自回归模型。为了使构建的自回归模型的误差尽可能地接近0,面对嵌入式实时系统的动态变化对构建的模型进行自适应调整。通过调整后的模型对嵌入式实时系统中劣质数据进行检测,给出检测过程。实验结果表明,采用所提方法对劣质数据进行动态检测,检测精度和效率较高,通信开销较低,整体性能优异。
[Abstract]:In the embedded real-time system, the data is easy to be lost in the process of acquisition, and it is easy to be attacked by the outside world and become inferior data during the transmission process, which threatens the security of the whole system. The current poor data detection method is realized by clustering method, which not only has high communication overhead, but also has low detection performance. Therefore, a new method for dynamic detection of poor quality data in embedded real-time system is proposed, and the embedded real-time system is established. The construction method of autoregressive model is introduced, and the autoregressive model is constructed by changing law of high quality data. In order to make the error of the constructed autoregressive model as close to zero as possible, the constructed model is adaptively adjusted in the face of the dynamic changes of the embedded real-time system. The poor data in embedded real-time system are detected by the adjusted model, and the detection process is given. The experimental results show that the proposed method for dynamic detection of inferior data has high detection accuracy and efficiency, low communication cost and excellent overall performance.
【作者单位】：郑州大学西亚斯国际学院电子信息工程学院;
【分类号】：O212.1

【相似文献】