面向不平衡时间序列量化的类条件高斯混合建模
Class-Conditioned Gaussian Mixture Modeling for Imbalanced Time Series Quantification
浏览论文内容
中文总结 AI 辅助
本文针对不平衡时间序列量化问题，提出类条件高斯混合量化器 CC-GMNet-TS，结合 Transformer 特征提取器与类专属混合模型，在三个基准上取得优于传统方法的低误差。
中文摘要 AI 辅助
量化是指在未标记实例包中估计类别 prevalence（ prevalence 在此指类别占比），这一任务在汇总统计比单个实例标签更重要的领域（如生物信号监测、跌倒检测和活动识别）中至关重要。本文针对具有挑战性的不平衡时间序列数据场景研究该问题，开发了 CC-GMNet-TS，这是一种类条件高斯混合量化器，结合了基于 Transformer 的特征提取器与每类潜在混合模型。与以往所有类别共享单个高斯混合的混合基量化器不同，CC-GMNet-TS 在有界潜在空间中为每个类别分配自身的紧凑混合模型，并针对这些类特定组件对片段嵌入进行评分，以创建强调稀有但具信息性模式的包级表示。包通过人工 prevalence 协议（APP）和先验偏移包采样（PShift）从标记池中构建，以覆盖广泛的类别 prevalence 场景，模型采用面向量化的损失函数进行端到端训练。在三个基准数据集（手势肌电数据 EMG Data、SmartFallMM 和 UCI-HAR）上的实验表明，与传统聚合器和近期深度量化器相比，CC-GMNet-TS 在这三个基准上实现了更低的误差； ablation 实验则证实了 Transformer 骨干网络和类条件混合模型在 PShift 过程中的贡献。
英文摘要
Quantification, estimating class prevalences in bags of unlabeled instances is vital in domains where aggregate statistics are more important than individual instance labels, such as biosignal monitoring, fall detection, and activity recognition. We investigate this issue in the challenging setting of imbalanced time series data and develop CC-GMNet-TS, a class-conditioned Gaussian mixture quantifier that combines a Transformer-based feature extractor with per-class latent mixtures. Unlike previous mixture-based quantifiers, which use a single Gaussian mixture shared by all classes, CC-GMNet-TS assigns each class its own compact mixture in a bounded latent space and scores segment embeddings against these class-specific components to create bag-level representations that emphasize rare but informative patterns. Bags are constructed from labeled pools using the Artificial Prevalence Protocol (APP) and prior shift bag sampling (PShift) to cover a wide range of class prevalence scenarios, and the model is trained end-to-end with a quantification-oriented loss. Experiments on three benchmarks: EMG Data for Gestures, SmartFallMM, and UCI-HAR show that CC-GMNet-TS achieves lower error across the three benchmarks compared to traditional aggregators and recent deep quantifiers, while ablations confirm the contributions of both the Transformer backbone and class-conditioned mixtures during PShift.
发表机构
- Texas State University（德克萨斯州立大学）
机构由 AI 辅助整理，请以论文原文为准。
