基于自适应分段聚合的云模型序列相似度评价方法

SIMILARITY EVALUATION METHOD OF CLOUD MODEL SERIES BASED ON SELF-ADAPTION PIECEWISE AGGREGATE

为了更好地对时间序列连续型指标数据进行评价,最大限度提取局部数据特征值,提出一种自适应分段聚合云模型评价方法。依据云模型的熵判断分段聚合数据的稳定性,对稳定性极差的分段聚合数据重新进行分段聚合,自适应地形成稳定性较好的云模型数据序列。同时,综合考虑云模型的距离和形状,提出一种通过超熵值进行修正的云模型相似度评价方法,并对云模型数据序列进行评价。通过实验验证,对突发性较强的时间序列进行大幅度压缩时,该方法能够保证评价结果的准确性,评价结果符合预期。

In order to better evaluate the time series continuous index data and extract local data eigenvalues to the maximum extent,this paper proposes a self-adaption piecewise aggregate evaluation of cloud model.According to the entropy of cloud model,the stability of piecewise aggregate data was judged.The piecewise aggregate data with poor stability were divided to form the cloud model data sequence with good stability adaptively.Considering the distance and shape of the cloud model,a cloud model similarity evaluation method modified by the hyperentropy value was proposed,and the cloud model data sequence was evaluated.The experimental results show that the method can ensure the accuracy of the evaluation results when the sudden strong time series are compressed to a large extent,and the evaluation results are in line with the expectation.