Although many deep learning (DL) algorithms have been proposed for the IMU-based HAR domain, traditional machine learning that utilizes handcrafted time series features (TSFs) still often performs well. It is not rare that combinations among DL and TSFs show better accuracy than DL-only approaches. However, there is a problem with time series features in IMU-based HAR. The amount of derived features can vary greatly depending on the method used to select the 3D basis. Fortunately, DL's strengths include capturing the features of input data and adaptively deriving parameters. Thus, as a new DNN model for IMU-based human activity recognition (HAR), this paper proposes rTsfNet, a DNN model with Multi-head 3D Rotation and Time Series Feature Extraction. rTsfNet automatically selects 3D bases from which features should be derived by extracting 3D rotation parameters within the DNN. Then, time series features (TSFs), based on many researchers' wisdom, are derived to achieve HAR using MLP. Although rTsfNet is a model that does not use CNN, it achieved higher accuracy than existing models under well-managed benchmark conditions and multiple datasets: UCI HAR, PAMAP2, Daphnet, and OPPORTUNITY, all of which target different activities.

翻译：尽管已有许多深度学习（DL）算法被提出用于基于IMU的人体活动识别（HAR）领域，但利用手工设计时间序列特征（TSFs）的传统机器学习方法仍常表现良好。深度学习方法与时间序列特征的结合往往比纯深度学习方法具有更高的准确率，这并不罕见。然而，基于IMU的人体活动识别中的时间序列特征存在一个问题：根据三维坐标系选择方法的不同，推导出的特征数量可能差异巨大。幸运的是，深度学习的优势之一在于能够捕捉输入数据的特征并自适应地推导参数。为此，本文提出一种新的面向IMU人体活动识别（HAR）的DNN模型——rTsfNet，该模型采用多头三维旋转与时间序列特征提取方法。rTsfNet通过提取DNN内部的三维旋转参数，自动选择应从中推导特征的三维坐标系。随后，基于众多研究者的智慧，推导出时间序列特征（TSFs），并利用MLP实现人体活动识别。尽管rTsfNet不采用CNN，但在良好控制的基准条件下和多个数据集（UCI HAR、PAMAP2、Daphnet和OPPORTUNITY，这些数据集涵盖不同活动类型）中，其准确率均优于现有模型。