面向目标综合识别的证据关联挖掘方法

Evidence Association Mining Method for Integrated Target Identification

针对海量异构数据中难以得到目标综合识别结果问题,提出了一种证据关联挖掘方法。该方法将证据与待证事实进行关联性量化分析,提炼出反映目标综合识别信息不同侧面的证据。首先,建立了证据历史信息分类模型和证据相关强度矩阵;然后,根据新证据信息对模型进行迭代更新,从而将识别信息源包含的数据和信息有效运用于证据理论,并得出目标综合识别的正确结论;最后,仿真试验表明该方法的可行性和有效性,可为多源异类信息融合处理提供参考。

Aimed at the problem about obtaining the integrated target identification result diffi cultly from the massive heterogeneous data, an evidence association mining method is proposed. The quantitative correlation analysis between the evidence and the fact to be verified is carried out, and the evidences reflecting different aspects of the integrated target identification informa tion are extracted. Firstly, the classification model for the history evidence information and the related intensity matrix of the evidences are established. Then, the model is iteratively updated according to the new evidence information. The data and information contained in the identifica tion information sources are applied to the evidence theory, and a correct conclusion of the inte grated target identification is obtained. Finally, the simulation experiment shows its feasibility and validity. It can provide a reference to the multi source heterogeneous information fusion.