对比两种模型在WiFi信号上识别人体动作，发现数据集决定最佳模型。
Evaluating BiLSTM and CNN+GRU Approaches for Human Activity Recognition Using WiFi CSI Data
- 用CNN+GRU提取空间特征，用BiLSTM捕捉长期时序依赖。
- 在UT-HAR数据集上准确率达95.20%，在NTU-Fi HAR上达92.05%。
- 适合医疗监护与智能家居等无感监测场景。
本文比较了BiLSTM与CNN+GRU两种深度学习模型在两个基于WiFi信道状态信息（CSI）的人体动作识别（HAR）数据集——UT-HAR与NTU-Fi HAR上的表现。结果表明，CNN+GRU在UT-HAR数据集上准确率达95.20%，得益于其提取空间特征的能力；而BiLSTM在高分辨率的NTU-Fi HAR数据集上表现更优，准确率为92.05%，因其能更有效地捕捉长期时序依赖。研究强调了数据集特性与预处理技术对模型性能的关键影响。同时展示了此类模型在医疗健康与智能家居等实际应用中的可行性，凸显其在无感动作识别方面的潜力。
原文摘要 · Abstract (English)
This paper compares the performance of BiLSTM and CNN+GRU deep learning models for Human Activity Recognition (HAR) on two WiFi-based Channel State Information (CSI) datasets: UT-HAR and NTU-Fi HAR. The findings indicate that the CNN+GRU model has a higher accuracy on the UT-HAR dataset (95.20%) thanks to its ability to extract spatial features. In contrast, the BiLSTM model performs better on the high-resolution NTU-Fi HAR dataset (92.05%) by extracting long-term temporal dependencies more effectively. The findings strongly emphasize the critical role of dataset characteristics and preprocessing techniques in model performance improvement. We also show the real-world applicability of such models in applications like healthcare and intelligent home systems, highlighting their potential for unobtrusive activity recognition.
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。