并非所有合成数据都同等重要：面向自动驾驶系统不平衡碰撞伤害严重性预测的专家委员会审计筛选
Not All Synthetic Data Are Equal: Expert-Committee Audit Screening for Imbalanced Crash-Injury-Severity Prediction in Automated Driving Systems
另 1 家 · 查看机构详情
- Ningbo University（宁波大学）
- Imperial College London（帝国理工学院）
- The University of Hong Kong（香港大学）
- University College London（伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对自动驾驶碰撞伤害严重性预测中数据不平衡与合成样本可信度不足的问题，提出专家委员会审计筛选（ECAS）框架，通过多维审计与帕累托筛选提升少数类样本质量，显著改善预测性能。
中文摘要 AI 辅助
自动驾驶系统（ADS）日益在公共道路上运行，引发了安全担忧，然而由于碰撞报告有限、严重后果罕见且伤害类别高度不平衡，可靠的碰撞伤害严重性预测仍然困难。现有的增强方法主要增加少数类样本数量，但很少评估生成的样本对于安全关键预测是否可信。本研究提出了专家委员会审计筛选（ECAS），一种面向数据不平衡下ADS碰撞伤害严重性预测的可信度感知样本接受框架。利用来自国家公路交通安全管理局常设通用命令记录的1,477起事件级ADS碰撞，ECAS通过一个仅使用真实数据的专家委员会，基于标签支持、边界分离、委员会一致性和局部合理性来审计生成的少数类样本。类内百分位数归一化和帕累托非支配排序选择被接受的样本，无需手动分配证据权重。在结合归一化流增强和表格先验数据拟合网络（TabPFN）分类器的固定骨干下，最佳ECAS配置在所有证据配置中实现了最高的平衡准确率、宏F1和轻伤召回率。局部邻域分析表明，与未经筛选的保留样本相比，ECAS接受的样本得到附近真实少数类碰撞的更好支持。Shapley加法解释和部分依赖图进一步表明，较低伤害严重性类别主要与碰撞对方和碰撞前运动相关，而中度以上伤害对公布的速度限制和运行环境更为敏感。这些发现支持从数量导向的增强转向可信度感知的样本接受，用于ADS安全预测和风险治理。
英文摘要
Automated driving systems (ADSs) are increasingly operating on public roads, raising safety concerns, yet reliable prediction of crash injury severity remains difficult because crash reports are limited, severe outcomes are rare, and injury classes are highly imbalanced. Existing augmentation methods mainly increase minority-class sample size but rarely assess whether generated samples are credible for safety-critical prediction. This study proposes Expert-Committee Audit Screening (ECAS), a credibility-aware sample acceptance framework for ADS crash injury severity prediction under data imbalance. Using 1,477 incident-level ADS crashes from the National Highway Traffic Safety Administration Standing General Order records, ECAS audits generated minority samples through a real-data-only expert committee based on label support, boundary separation, committee agreement, and local plausibility. Within-class percentile normalization and Pareto non-dominated sorting select accepted samples without manually assigned evidence weights. With a fixed backbone combining normalizing flow augmentation and a Tabular Prior-data Fitted Network (TabPFN) classifier, the best ECAS configuration achieved the highest balanced accuracy, macro-F1, and minor-injury recall among all evidence configurations. Local neighborhood analysis showed that ECAS-accepted samples were better supported by nearby real minority crashes than unscreened retained samples. Shapley additive explanations and partial dependence plots further indicated that lower injury severity classes were mainly associated with crash counterpart and pre-crash movement, whereas moderate-plus injuries were more sensitive to posted speed limit and operating context. These findings support a shift from quantity-oriented augmentation to credibility-aware sample acceptance for ADS safety prediction and risk governance.
