基于ORCA风格动态归纳偏差自适应的多模态可穿戴时间序列智能体异常检测
Agentic Anomaly Detection with ORCA-Style Dynamic Inductive Bias Adaptation in Multimodal Wearable Time Series Data
- BITS Pilani（皮尔尼理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对资源受限的非平稳生理时间序列异常检测问题，提出ORCA框架，通过监督控制器动态调整时间感受野，在WBAN和MIMIC-IV数据集上实现稳健性能，无需预调时间范围。
AI中文摘要：
无线体域网（WBAN）生成的多变量生理时间序列具有高度非平稳性，且常需在严格的计算和内存约束下处理。该场景中一个关键却未被充分探索的挑战是选择合适的时间感受野，其为异常检测模型提供强归纳偏差。现有方法通常依赖固定时间上下文，在异构信号 regime 中表现不稳定，且需针对特定数据集调优。我们提出ORCA，一种智能体控制的异常检测框架，可在推理时基于轻量信号统计量动态调整时间感受野。ORCA不引入额外可训练参数或学习策略，而是采用监督控制器自主在离散时间上下文间选择，实现无需重训练的状态依赖归纳偏差自适应。在定制WBAN数据集上，ORCA取得与最强固定上下文基线相当的性能（AUROC=0.99），同时消除了提前调优时间范围的需求。我们进一步在MIMIC-IV这一具有挑战性的分布外基准上评估ORCA，观察到其在异构临床条件下表现出保守泛化行为且无性能崩溃。这些结果表明，自适应时间归纳偏差控制是资源受限、非平稳生理时间序列异常检测的实用且稳健设计原则。
英文摘要：
Wireless Body Area Networks (WBANs) generate multivariate physiological time series that are highly nonstationary and must often be processed under strict computational and memory constraints. A critical yet underexplored challenge in this setting is selecting an appropriate temporal receptive field, which serves as a strong inductive bias for anomaly detection models. Existing approaches typically rely on fixed temporal contexts, which can perform inconsistently across heterogeneous signal regimes and require dataset-specific tuning. We propose ORCA, an agentically controlled anomaly detection framework that dynamically adapts the temporal receptive field at inference time based on lightweight signal statistics. Rather than introducing additional trainable parameters or learned policies, ORCA employs a supervisory controller that autonomously selects among discrete temporal contexts, enabling state-dependent inductive bias adaptation without retraining. Across a custom WBAN dataset, ORCA achieves performance comparable to the strongest fixed-context baselines (AUROC = 0.99) while eliminating the need to tune temporal horizons in advance. We further evaluate ORCA on MIMIC-IV as a challenging out-of-distribution benchmark, observing conservative generalization behavior without performance collapse under heterogeneous clinical conditions. These results highlight adaptive temporal inductive bias control as a practical and robust design principle for anomaly detection in resource-constrained, nonstationary physiological time series.
