Forensic Chemistry ( IF 2.7 ) Pub Date : 2023-07-20 , DOI: 10.1016/j.forc.2023.100517 Frances A. Whitehead , Mary R. Williams , Michael E. Sigman
![]() |
The principles of subjective logic are applied to the competing propositions that ignitable liquid residue (ILR) is present, or is not present, in a fire debris sample. Analysts’ estimates of the strength of evidence coupled with their perceived levels of uncertainty combine to define a “fuzzy category” that is mapped to an opinion triangle. The opinion is expressed as a tuple consisting of the belief mass, disbelief mass, uncertainty and base rate. A workflow is introduced to guide the analyst through the fuzzy category formulation. Opinion tuples are also generated from a set of machine learning (ML) models trained on an ensemble of data sets. A set of 20 single-blind fire debris samples were analyzed by each of the authors, and by an ensemble of optimized support vector machine models. The opinions of each analyst and the ML ensemble were compared and combined to obtain an opinion representing a consensus of each analyst and the ML. The opinions of the analysts and ML were projected onto the zero-uncertainty axis and the projected opinion probabilities were used as scores to construct an receiver operating characteristic (ROC) curve. The area under the ROC curves for each analyst were greater than or equal to 0.90 and the area under the ML ROC curve was 0.96. The methodology is widely applicable to forensic problems that can be represented as a pair of mutually exclusive and exhaustive hypotheses.
中文翻译:
![](https://static.x-mol.com/jcss/images/paperTranslation.png)
火灾碎片分析中的分析师和机器学习意见
主观逻辑原理适用于火残骸样本中存在或不存在可燃液体残留物 (ILR) 的竞争命题。分析师对证据强度的估计加上他们感知的不确定性水平结合起来定义了映射到观点三角形的“模糊类别”。该意见被表达为由信念质量、不信念质量、不确定性和基准率组成的元组。引入了一个工作流程来指导分析人员完成模糊类别的制定。意见元组也是根据一组在数据集集合上训练的机器学习 (ML) 模型生成的。每位作者均通过一组优化的支持向量机模型对一组 20 个单盲火灾残骸样本进行了分析。对每位分析师和 ML 整体的意见进行比较和合并,以获得代表每位分析师和 ML 共识的意见。分析师和 ML 的意见被投影到零不确定性轴上,并且投影的意见概率被用作构建接收者操作特征 (ROC) 曲线的分数。每个分析师的 ROC 曲线下面积大于或等于 0.90,ML ROC 曲线下面积为 0.96。该方法广泛适用于可以表示为一对相互排斥且详尽的假设的法医问题。分析师和 ML 的意见被投影到零不确定性轴上,并且投影的意见概率被用作构建接收者操作特征 (ROC) 曲线的分数。每个分析师的 ROC 曲线下面积大于或等于 0.90,ML ROC 曲线下面积为 0.96。该方法广泛适用于可以表示为一对相互排斥且详尽的假设的法医问题。分析师和 ML 的意见被投影到零不确定性轴上,并且投影的意见概率被用作构建接收者操作特征 (ROC) 曲线的分数。每个分析师的 ROC 曲线下面积大于或等于 0.90,ML ROC 曲线下面积为 0.96。该方法广泛适用于可以表示为一对相互排斥且详尽的假设的法医问题。