Inertial sensor-based human activity recognition (HAR) is the base of many human-centered mobile applications. Deep learning-based fine-grained HAR models enable accurate classification in various complex application scenarios. Nevertheless, the large storage and computational overhead of the existing fine-grained deep HAR models hinder their widespread deployment on resource-limited platforms. Inspired by the knowledge distillation's reasonable model compression and potential performance improvement capability, we design a multi-level HAR modeling pipeline called Stage-Logits-Memory Distillation (SMLDist) based on the widely-used MobileNet. By paying more attention to the frequency-related features during the distillation process, the SMLDist improves the HAR classification robustness of the students. We also propose an auto-search mechanism in the heterogeneous classifiers to improve classification performance. Extensive simulation results demonstrate that SMLDist outperforms various state-of-the-art HAR frameworks in accuracy and F1 macro score. The practical evaluation of the Jetson Xavier AGX platform shows that the SMLDist model is both energy-efficient and computation-efficient. These experiments validate the reasonable balance between the robustness and efficiency of the proposed model. The comparative experiments of knowledge distillation on six public datasets also demonstrate that the SMLDist outperforms other advanced knowledge distillation methods of students' performance, which verifies the good generalization of the SMLDist on other classification tasks, including but not limited to HAR.

翻译：基于惯性传感器的人体活动识别（HAR）是许多人本移动应用的基础。基于深度学习的细粒度HAR模型能够在各种复杂应用场景中实现精准分类。然而，现有细粒度深度HAR模型存在较大的存储和计算开销，阻碍其在资源受限平台上的广泛部署。受知识蒸馏的合理模型压缩及潜在性能提升能力的启发，我们基于广泛使用的MobileNet设计了一种名为SMLDist（Stage-Logits-Memory Distillation）的多级HAR建模流水线。通过在蒸馏过程中重点关注频率相关特征，SMLDist提升了学生模型的HAR分类鲁棒性。我们还提出了一种异构分类器中的自动搜索机制以改善分类性能。大量仿真结果表明，SMLDist在准确率和F1宏平均得分上优于多种最先进的HAR框架。在Jetson Xavier AGX平台上的实际评估显示，SMLDist模型兼具高能效和计算效率。这些实验验证了所提模型在鲁棒性与效率之间达到了合理平衡。在六个公开数据集上的知识蒸馏对比实验也表明，SMLDist在学生模型性能上优于其他先进知识蒸馏方法，这验证了SMLDist在包括但不限于HAR的其他分类任务上的良好泛化能力。