Sensor-based human activity recognition (HAR) aims to recognize a human's physical actions by using sensors attached to different body parts. As a user-specific application, HAR often suffers poor generalization from training on an individual to testing on another individual, or from one body part to another body part. To tackle this cross-domain HAR problem, this article proposes a domain adaptation (DA) method called local domain adaptation (LDA), whose core is to align cluster-to-cluster distributions between the source domain and the target domain. On the one hand, LDA differs from existing set-to-set alignment by reducing the distribution discrepancy at a finer granularity. On the other hand, LDA is superior to the class-to-class alignment because it can provide more accurate soft labels for the target domain. Specifically, LDA contains three main steps: 1) groups the activity class into several high-level abstract clusters; 2) maps the original data of each cluster in both domains into the same low-dimension subspace to align the intracluster data distribution; 3) predicts the class labels for target domain in the low-dimension subspace. Experimental results on two public HAR benchmark datasets show that LDA outperforms state-of-the-art DA methods for the cross-domain HAR.

中文翻译：

---

跨域活动识别的本地域适配

基于传感器的人类活动识别 (HAR) 旨在通过使用连接到不同身体部位的传感器来识别人类的身体动作。作为特定于用户的应用程序，HAR 从一个人的训练到另一个人的测试，或从一个身体部位到另一个身体部位的泛化能力通常很差。为了解决这个跨域 HAR 问题，本文提出了一种称为本地域自适应 (LDA) 的域自适应 (DA) 方法，其核心是对齐源域和目标域之间的集群到集群分布。一方面，LDA 与现有的 set-to-set 对齐不同，它以更细的粒度减少分布差异。另一方面，LDA 优于类到类对齐，因为它可以为目标域提供更准确的软标签。具体来说，LDA 包含三个主要步骤：1) 将活动类分组为几个高级抽象集群；2）将两个域中每个簇的原始数据映射到同一个低维子空间，对齐簇内数据分布；3) 在低维子空间中预测目标域的类标签。在两个公共 HAR 基准数据集上的实验结果表明，对于跨域 HAR，LDA 的性能优于最先进的 DA 方法。