用多域雷达数据提升人体动作识别准确率，解决相似动作难区分问题。
PECL: A Heterogeneous Parallel Multi-Domain Network for Radar-Based Human Activity Recognition
- 设计并行多域网络，同时处理距离-时间、多普勒-时间、距离-多普勒三组信号
- 在相同数据集上达到96.16%准确率，优于现有方法至少4.78%
- 兼顾性能与效率，参数仅23.42M，适合实际医疗监控部署
雷达系统因其非侵入性、高隐私保护和对光照不敏感等优势，正被广泛应用于医疗监测。然而，现有研究多依赖单一域雷达信号，忽视人体动作序列中的时序依赖性，导致相似动作难以区分。为此，本文提出平行高效网络-注意力-长短期记忆（PECL）模型，联合处理距离-时间、多普勒-时间、距离-多普勒三个互补域的信号。该模型融合通道-空间注意力模块与时间单元，有效捕捉动作序列中的多维特征与动态依赖关系，显著提升分类精度与鲁棒性。实验表明，PECL在相同数据集上达到96.16%的准确率，较现有方法最高提升4.78%，尤其在易混淆动作区分上表现最优。尽管性能优异，其模型复杂度适中，仅含23.42M参数与1324.82M FLOPs，具备良好的参数效率，适用于实际医疗场景部署。
原文摘要 · Abstract (English)
Radar systems are increasingly favored for medical applications because they provide non-intrusive monitoring with high privacy and robustness to lighting conditions. However, existing research typically relies on single-domain radar signals and overlooks the temporal dependencies inherent in human activity, which complicates the classification of similar actions. To address this issue, we designed the Parallel-EfficientNet-CBAM-LSTM (PECL) network to process data in three complementary domains: Range-Time, Doppler-Time, and Range-Doppler. PECL combines a channel-spatial attention module and temporal units to capture more features and dynamic dependencies during action sequences, improving both accuracy and robustness. The experimental results show that PECL achieves an accuracy of 96.16% on the same dataset, outperforming existing methods by at least 4.78%. PECL also performs best in distinguishing between easily confused actions. Despite its strong performance, PECL maintains moderate model complexity, with 23.42M parameters and 1324.82M FLOPs. Its parameter-efficient design further reduces computational cost.
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。