Deep Attention SMOTE:面向不平衡燃气轮机异常检测的可学习插值数据增强
在工业装备健康监测领域,针对多维时间序列的类不平衡与类别重叠问题,近期发表于 Computers in Industry 的论文 “Deep attention SMOTE: Data augmentation with a learnable interpolation factor for imbalanced anomaly detection of gas turbines”…
2026/9/29 11:07:08