嵌入式实时系统中劣质数据动态检测方法研究

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。

Bad data dynamic detection method in embedded real-time system research

In embedded real-time system, data is prone to loss in the transmission process, vulnerable to outside attacks into bad data in the collection process, threatening the safety of the whole system, the bad data detection method is realized by the clustering method, not only the communication overhead, and the detection performance is low. To this end, a new method of dynamic detection of bad data in embedded real-time system is put forward. This paper introduces the construction method of autoregressive model, the variation of quality data to construct the autoregressive model, in order to make the autoregressive error as much as possible close to 0, in the face of the dynamic changes of the embedded real-time system to adjust the model, by adjusting the model after detection of bad data in embedded real time system the detection process is given. The experimental results show that the proposed method is used to detect the low quality data, the detection accuracy and efficiency are high, the communication cost is low, and the overall performance is excellent.