白骨化尸体死亡时间的推断

本文分析了15具白骨化尸体标本的股骨汞(Hg),铅(Pb),镉(Cd)元素含量数据,在三年的时间内采集了3次,一共收集到45个数据。首先将这组数据看着纵向数据,利用线性随机效应混合模型、Cox随机混合效应模型进行分析,结果显示,如果对每个白骨化尸体标本建立线性模型,可以精确预测出死亡时间,而且不需要采集铅元素含量数据。混合效应模型的预测效果也很好,最大误差不会超过1个月。其次我们对数据不作任何假设,利用机器学习中随机森林方法分析数据,并利用5折交叉验证方法来判断结果的可靠性,训练集和测试集的NMSE分别为0.1205944,0.5604286,因此可以用训练出的模型来预测死亡时间。

Estimating of Postmortem Interval of Skeletonization of Body

Based on 45 observations,including Hg,Pb and Cd element contents of femur of skeletonization of body,which had been collected in continuous three years since 2012.Firstly,we deal with the sample through the linear mixed-effects models and Cox random mixed model.The results show that the postmortem interval is estimated accurately.It is important that the Pb element is not necessary.Secondly,the method of random forest is used to analysize the data.And five-fold cross-validation proved that NMSE of training set and validation set are 0.1205944 and 0.5604286,individually.Therefore,postmortem interval of skeletonization of body can be predicted by some models.