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\%).

本研究提出了一种对可穿戴传感器人体活动识别（HAR）进行增量学习的框架，该框架同时解决了两个挑战：灾难性遗忘和非均匀输入。该框架（称为 iKAN）使用 Kolmogorov-Arnold 网络（KAN）作为分类器，利用样条函数的局部可塑性和全局稳定性，通过适应任务特定的特征分支和特征重新分配层来将 KAN 调整为适用于 HAR。与现有的主要调整输出维度或分类器节点数量以适应新任务的增量学习方法不同，iKAN 着重扩展特征提取分支以适应来自不同传感器模态的新输入，同时保持一致的维度和分类器输出数量。该研究通过在六个公共 HAR 数据集上持续学习，展示了 iKAN 框架的增量学习性能，其最终性能为 84.9％（加权 F1 分数），平均增量性能为 81.34％，明显优于两种现有的增量学习方法 EWC（51.42％）和经验重播（59.92％）。