AI 中文总结
CADENCE提出一种CPU原生的双专家网络，通过卷积线性专家和分布区间专家结合元路由，在109个UCR数据集上以平均17.53秒达到0.8864准确率，接近HIVE-COTE 2.0但速度快得多。
AI 中文摘要
时间序列分类（TSC）在准确性和计算可扩展性之间表现出尖锐的权衡。诸如HIVE-COTE 2.0之类的元集成方法达到了最先进的准确性，但需要大量的计算，而超快速的随机卷积变换（例如MiniRocket、Hydra）在几秒钟内运行，但在处理相位无关分布、信号运动学以及大规模类别数下的决策树碎片化方面存在困难。在这项工作中，我们提出了CADENCE（用于时间序列分类卓越性的置信度自适应双专家网络），一种统一的、CPU原生的双专家架构。CADENCE将表示学习解耦为两条专门路径：（i）卷积线性专家，将10,000个确定性扩张特征与闭式L2正则化伍德伯里岭分类相结合，以及（ii）分布区间专家，将竞争性扩张核（Hydra）与跨信号运动学和FFT频谱带的二元Cornish-Fisher矩近似相结合，并使用ExtraTrees集成进行拟合。一个具有稀有类别保留的内部验证元路由器动态选择纯专家路由和置信度加权软混合，然后在100%的训练数据上进行完全重新拟合。在全部109个等长UCR档案数据集上，经过30次重采样（共3,270次运行）的评估，CADENCE实现了0.8864的总平均准确率。这在档案中排名第二，仅被HIVE-COTE 2.0（0.8895，p_Holm = 0.295，无统计学显著差异）超越，同时优于Hydra+MultiRocket（0.8818）、MultiRocket（0.8797）和HIVE-COTE 1.0（0.8786，p_Holm = 0.048）。CADENCE将与HIVE-COTE 2.0的差距缩小到0.31个百分点，同时在双核CPU上每个数据集平均仅需17.53秒。源代码和评估脚本：此https URL
英文摘要
Time series classification (TSC) exhibits a sharp trade-off between accuracy and computational scalability. Meta-ensembles like HIVE-COTE 2.0 reach state-of-the-art accuracy but require extensive compute, whereas ultra-fast random convolutional transforms (e.g., MiniRocket, Hydra) run in seconds but struggle with phase-independent distributions, signal kinematics, and decision tree fragmentation on large class counts. In this work, we present CADENCE (Confidence-Adaptive Dual-Expert Network for time series Classification Excellence), a unified, CPU-native dual-expert architecture. CADENCE decouples representation learning into two specialized pathways: (i) a Convolutional Linear Expert pairing 10,000 deterministic dilated features with closed-form L2-regularized Woodbury ridge classification, and (ii) a Distributional Interval Expert pairing competing dilated kernels (Hydra) with dyadic Cornish-Fisher moment approximations across signal kinematics and FFT spectral bands, fitted with an ExtraTrees ensemble. An internal validation meta-router with rare-class preservation dynamically selects between pure expert routing and confidence-weighted soft blending, followed by a full refit on 100% of training data. Evaluated across all 109 equal-length UCR Archive datasets over 30 resamples (3,270 total runs), CADENCE achieves a grand mean accuracy of 0.8864. This ranks #2 across the archive, surpassed only by HIVE-COTE 2.0 (0.8895, p_Holm = 0.295, no statistically significant difference), while outperforming Hydra+MultiRocket (0.8818), MultiRocket (0.8797), and HIVE-COTE 1.0 (0.8786, p_Holm = 0.048). CADENCE closes the gap to HIVE-COTE 2.0 to 0.31 percentage points while taking an average of only 17.53 seconds per dataset on a dual-core CPU. Source code and evaluation scripts: https://github.com/onisa-jr/CADENCE.git
Comments7 pages, 5 figures. Code and benchmark evaluation scripts available at https://github.com/onisa-jr/CADENCE.git
