用轻量级网络实现高效人体动作识别，降低能耗与计算开销。
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition
- 基于回声状态网络构建轻量级分类器，引入分块标记化提取特征。
- 在多个数据集上准确率超80%，计算量仅为DeepConvLSTM的1/6。
- 适合边缘计算场景，特别适用于低功耗实时动作识别任务。
本文旨在通过引入一种名为PatchEchoClassifier的新模型，开发针对时序数据的节能分类器。该模型基于回声状态网络（ESN）机制，专为使用一维传感器信号的人体活动识别（HAR）设计，并采用分块标记化方法提取局部特征表示。为高效训练，提出了一种知识蒸馏框架，将高容量的MLP-Mixer教师模型的知识迁移到轻量级的水库学生模型中。在多个HAR数据集上的实验表明，该模型在保持超过80%准确率的同时，显著降低了计算成本；其浮点运算量（FLOPS）仅约为广泛使用的卷积基线DeepConvLSTM的六分之一。结果表明，PatchEchoClassifier是边缘计算环境中实现实时、节能人体活动识别的有前景方案。
原文摘要 · Abstract (English)
This paper aims to develop an energy-efficient classifier for time-series data by introducing PatchEchoClassifier, a novel model that leverages a reservoir-based mechanism known as the Echo State Network (ESN). The model is designed for human activity recognition (HAR) using one-dimensional sensor signals and incorporates a tokenizer to extract patch-level representations. To train the model efficiently, we propose a knowledge distillation framework that transfers knowledge from a high-capacity MLP-Mixer teacher to the lightweight reservoir-based student model. Experimental evaluations on multiple HAR datasets demonstrate that our model achieves over 80 percent accuracy while significantly reducing computational cost. Notably, PatchEchoClassifier requires only about one-sixth of the floating point operations (FLOPS) compared to DeepConvLSTM, a widely used convolutional baseline. These results suggest that PatchEchoClassifier is a promising solution for real-time and energy-efficient human activity recognition in edge computing environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。