用测试噪声模拟训练，四传感器模型融合提升活动识别鲁棒性。
Sensor-Specific Transformer (PatchTST) Ensembles with Test-Matched Augmentation
- 针对每个传感器位置独立训练PatchTST模型，使用匹配测试噪声的增强数据
- 在私有榜单上宏平均F1显著高于基线，验证方法有效性
- 适合应对真实场景中传感器噪声干扰的活动识别任务
我们提出一种噪声感知、传感器特定的集成方法，用于在第二届WEAR数据集挑战赛中实现鲁棒的人体活动识别。该方法基于PatchTST Transformer架构，在篡改后的训练集上训练四个独立模型，每个模型对应一个惯性传感器位置。训练时将1秒滑动窗口进行增强，以模拟测试阶段的噪声。通过匹配训练与测试数据的模式（JSON编码的50样本窗口），并应用随机抖动、缩放、旋转和通道丢弃，使各模型学会泛化至真实世界中的传感器扰动。推理阶段，对Kaggle测试集上所有四个传感器模型的softmax概率取平均，生成最终标签。在私有排行榜上，该流程实现了显著优于基线的宏平均F1，表明测试匹配增强与Transformer集成相结合是应对噪声条件下鲁棒HAR的有效策略。
原文摘要 · Abstract (English)
We present a noise-aware, sensor-specific ensemble approach for robust human activity recognition on the 2nd WEAR Dataset Challenge. Our method leverages the PatchTST transformer architecture, training four independent models-one per inertial sensor location-on a tampered training set whose 1-second sliding windows are augmented to mimic the test-time noise. By aligning the train and test data schemas (JSON-encoded 50-sample windows) and applying randomized jitter, scaling, rotation, and channel dropout, each PatchTST model learns to generalize across real-world sensor perturbations. At inference, we compute softmax probabilities from all four sensor models on the Kaggle test set and average them to produce final labels. On the private leaderboard, this pipeline achieves a macro-F1 substantially above the baseline, demonstrating that test-matched augmentation combined with transformer-based ensembling is an effective strategy for robust HAR under noisy conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。