摘要
针对实物保护系统(Physical Protection System,PPSY)中单一传感器报警准确率较低的问题,提出了一种基于改进ID3的CAC-ID3(Confidence And Correlation-ID3)算法在多传感器实物保护系统中数据融合的新方法。与传统的单一传感器数据信息处理相比,多传感器数据融合能够更加准确、全面的得到被测对象的数据信息,有效地利用多传感器资源。CAC-ID3算法首先在ID3的基础上引入属性置信度重新计算期望熵,解决属性和价值不对等的问题,克服多传感器数据分类时多值偏向的缺点,其值由经验和相关领域知识决定。然后通过引入属性间的相关度来调整信息增益值,提高分类精度。实验结果表明:基于CAC-ID3的决策树算法的多传感器PPSY能有效提高报警准确率和可靠性,防止敌对分子入侵,提高传感器对PPSY的检测的效能,且该算法的分类精度高于ID3算法。
Aiming at the low alarm accuracy of a single sensor in the Physical Protection System(PPSY),a new data fusion method based on improved ID3 Confidence And Correlation-ID3(CAC-ID3)algorithm was proposed in the multi-sensor Physical Protection System.Compared with the traditional single sensor data processing,the multisensor data fusion system can obtain more accurate and comprehensive data information of the tested objects and make effective use of multi-sensor resources.CAC-ID3 algorithm firstly introduces attribute confidence to recalculate expected entropy on the basis of ID3 to solve the problem of mismatch between attributes and values and overcome the shortcoming of multi-value bias in multi-sensor data classification,whose value is determined by experience and relevant domain knowledge.Then the information gain is adjusted by introducing the relevancy between attributes to improve the classification accuracy.The experimental results show that the multi-sensor PPSY based on CAC-ID3 decision tree algorithm can effectively improve alarm accuracy and reliability,prevent the invasion of hostile molecules,and improve the sensor's detection efficiency of PPSY;The classification accuracy of this algorithm is higher than that of ID3 algorithm.
作者
李爱国
苏越
雷鲁飞
陈博
LI Ai-guo;SU Yue;LU Fei-lei;CHEN Bo(School of Computer Science and Technology,Xi'an University of Science and Technology,Xi'an Shanxi 710054,China)
出处
《计算机仿真》
2024年第1期355-359,424,共6页
Computer Simulation