iKAN：基于 KAN 的异构数据集人类活动识别全局增量学习
iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets
AI总结：
提出用于可穿戴传感器人类活动识别的增量学习框架 iKAN，利用 Kolmogorov-Arnold Networks 替代多层感知机并扩展特征分支以同时解决灾难性遗忘和非均匀输入问题，在六个公共数据集上显著优于 EWC 和经验回放方法。
摘要：
本工作提出了一个用于可穿戴传感器人类活动识别（HAR）的增量学习（IL）框架，同时解决两个挑战：灾难性遗忘和非均匀输入。该可扩展框架 iKAN 率先将 Kolmogorov-Arnold Networks (KAN) 用于 IL，以替代多层感知机作为分类器，利用样条的局部可塑性和全局稳定性。为了使 KAN 适应 HAR，iKAN 使用特定任务特征分支和特征重分布层。与主要调整输出维度或分类器节点数量以适应新任务的现有 IL 方法不同，iKAN 专注于扩展特征提取分支，以适应来自不同传感器模态的新输入，同时保持分类器输出的一致维度和数量。跨六个公共 HAR 数据集的持续学习证明了 iKAN 框架的增量学习性能，最终性能为 84.9%（加权 F1 分数），平均增量性能为 81.34%，显著优于两种现有的增量学习方法，如 EWC（51.42%）和经验回放（59.92%）。
英文摘要：
This work proposes an incremental learning (IL) framework for wearable sensor human activity recognition (HAR) that tackles two challenges simultaneously: catastrophic forgetting and non-uniform inputs. The scalable framework, iKAN, pioneers IL with Kolmogorov-Arnold Networks (KAN) to replace multi-layer perceptrons as the classifier that leverages the local plasticity and global stability of splines. To adapt KAN for HAR, iKAN uses task-specific feature branches and a feature redistribution layer. Unlike existing IL methods that primarily adjust the output dimension or the number of classifier nodes to adapt to new tasks, iKAN focuses on expanding the feature extraction branches to accommodate new inputs from different sensor modalities while maintaining consistent dimensions and the number of classifier outputs. Continual learning across six public HAR datasets demonstrated the iKAN framework's incremental learning performance, with a last performance of 84.9\% (weighted F1 score) and an average incremental performance of 81.34\%, which significantly outperforms the two existing incremental learning methods, such as EWC (51.42\%) and experience replay (59.92\%).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
