Kolmogorov-Arnold网络（KANs）作为基于IMU的人体活动识别特征提取器的初步研究
Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition
AI总结：
本研究探索将Kolmogorov-Arnold网络（KANs）作为基于IMU的人体活动识别特征提取器，实现四种架构变体并在四个公开数据集上验证，证实其性能优于CNN提取器且参数效率更高。
摘要：
在本研究中，我们探索了新型神经网络架构Kolmogorov-Arnold网络（KANs）作为基于传感器（具体为惯性测量单元IMU）的人体活动识别（HAR）特征提取器的应用。传统网络在每个节点对输入进行参数化加权求和，再将结果输入静态定义的非线性函数，而KAN在通往每个节点的边上执行由B样条（B-SPLINES）表示的非线性计算，随后仅在节点处对输入求和。该系统无需学习权重，而是学习样条参数。在原始研究中，这类网络已被证明能够更高效、更精确地学习复杂的实值函数，例如在回归或偏微分方程（PDE）求解场景中。我们假设这种能力对计算基于IMU的HAR的低层特征同样有利。为此，我们将KAN实现为基于IMU的人体活动识别任务的特征提取架构，包含四种架构变体。我们在四个公开HAR数据集上对KAN特征提取器进行了初步性能研究。结果表明，基于KAN的特征提取器在所有数据集上的表现均优于基于CNN的提取器，同时参数效率更高。
英文摘要：
In this work, we explore the use of a novel neural network architecture, the Kolmogorov-Arnold Networks (KANs) as feature extractors for sensor-based (specifically IMU) Human Activity Recognition (HAR). Where conventional networks perform a parameterized weighted sum of the inputs at each node and then feed the result into a statically defined nonlinearity, KANs perform non-linear computations represented by B-SPLINES on the edges leading to each node and then just sum up the inputs at the node. Instead of learning weights, the system learns the spline parameters. In the original work, such networks have been shown to be able to more efficiently and exactly learn sophisticated real valued functions e.g. in regression or PDE solution. We hypothesize that such an ability is also advantageous for computing low-level features for IMU-based HAR. To this end, we have implemented KAN as the feature extraction architecture for IMU-based human activity recognition tasks, including four architecture variations. We present an initial performance investigation of the KAN feature extractor on four public HAR datasets. It shows that the KAN-based feature extractor outperforms CNN-based extractors on all datasets while being more parameter efficient.
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。
