基於上下文區分對比學習的時間序列異常檢測（英文版）

英文标题：Time-series Anomaly Detection via Contextual Discriminative Contrastive Learning中文摘要：针对时间数据中的异常检测问题，提出了一种新的方法，借鉴了 DeepSVDD 的损失函数，结合了 Neutral AD 的确定性对比损失，提高了在实际工业数据集中的性能表现。英文摘要：Detecting anomalies in temporal data is challenging due to anomalies beingdependent on temporal dynamics. One-class classification methods are commonlyused for anomaly detection tasks, but they have limitations when applied totemporal data. In particular, mapping all normal instances into a singlehypersphere to captu