在微控制器上实现高精度实时人体活动识别，兼顾低内存占用与可解释性。
Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusion
- 分层结构动态选择识别模块，融合多谱图特征提升效率
- 仅用22.3 KiB RAM和439.5 KiB ROM即达96.70%准确率
- 支持可解释预测，适合穿戴、工业及智能家居场景
边缘应用对高精度本地模式识别的需求日益增长，但现有方法难以兼顾准确性与计算约束。为此，提出一种资源感知的分层网络HPPI-Net，基于多谱图融合与可解释模块，实现微控制器上的实时人体活动识别（HAR）。部署于ARM Cortex-M4微控制器，优化后仅需22.3 KiB RAM和439.5 KiB ROM，达到96.70%准确率。该网络采用两层架构：第一层利用快速傅里叶变换（FFT）谱图提取初步特征；第二层根据状态动态激活静止活动专用模块或并行的LSTM-MobileNet网络（PLMN）。PLMN通过三个并行的LSTM编码器融合FFT、小波与Gabor谱图，使用高效通道注意力（ECA）和深度可分离卷积（DSC）优化特征，实现通道级可解释性并显著降低乘加操作。相比MobileNetV3，HPPI-Net准确率提升1.22%，RAM减少71.2%，ROM减少42.1%。结果表明，该模型在精度与效率间取得良好平衡，提供可解释预测，为内存受限的边缘平台上的可穿戴、工业及智能家居应用提供实用方案。
原文摘要 · Abstract (English)
The demand for accurate on-device pattern recognition in edge applications is intensifying, yet existing approaches struggle to reconcile accuracy with computational constraints. To address this challenge, a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules, namely the Hierarchical Parallel Pseudo-image Enhancement Fusion Network (HPPI-Net), is proposed for real-time, on-device Human Activity Recognition (HAR). Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy while utilizing only 22.3 KiB of RAM and 439.5 KiB of ROM after optimization. HPPI-Net employs a two-layer architecture. The first layer extracts preliminary features using Fast Fourier Transform (FFT) spectrograms, while the second layer selectively activates either a dedicated module for stationary activity recognition or a parallel LSTM-MobileNet network (PLMN) for dynamic states. PLMN fuses FFT, Wavelet, and Gabor spectrograms through three parallel LSTM encoders and refines the concatenated features using Efficient Channel Attention (ECA) and Depthwise Separable Convolution (DSC), thereby offering channel-level interpretability while substantially reducing multiply-accumulate operations. Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%. These results demonstrate that HPPI-Net achieves a favorable accuracy-efficiency trade-off and provides explainable predictions, establishing a practical solution for wearable, industrial, and smart home HAR on memory-constrained edge platforms.
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。