用无线信号检测人体姿态，发现模型在不同环境下表现差异大。
Validation of Practicality for CSI Sensing Utilizing Machine Learning
- 用无线信道状态信息训练五类机器学习模型识别姿势
- 深度学习与朴素贝叶斯支持向量机在原环境准确率达85%以上
- 换环境后准确率骤降至约30%，泛化能力差
本研究利用无线局域网中常见的信道状态信息（CSI）作为训练数据，构建并评估了五种不同的机器学习模型以识别人体姿势（站立、坐姿、躺卧）。所用模型包括：(i) 线性判别分析，(ii) 朴素贝叶斯-支持向量机，(iii) 核函数支持向量机，(iv) 随机森林，以及 (v) 深度学习。我们系统分析了不同训练数据量对模型精度的影响，并在不同于数据采集环境的场景中测试了模型的空间泛化能力。实验结果表明，尽管两种模型——(ii) 朴素贝叶斯-支持向量机和 (v) 深度学习——在原始环境中准确率可达85%以上，但在新环境中准确率下降至约30%。这说明基于CSI的机器学习模型虽在一致空间结构下表现良好，但其性能随空间条件变化显著降低，凸显其泛化能力的重大挑战。
原文摘要 · Abstract (English)
In this study, we leveraged Channel State Information (CSI), commonly utilized in WLAN communication, as training data to develop and evaluate five distinct machine learning models for recognizing human postures: standing, sitting, and lying down. The models we employed were: (i) Linear Discriminant Analysis, (ii) Naive Bayes-Support Vector Machine, (iii) Kernel-Support Vector Machine, (iv) Random Forest, and (v) Deep Learning. We systematically analyzed how the accuracy of these models varied with different amounts of training data. Additionally, to assess their spatial generalization capabilities, we evaluated the models' performance in a setting distinct from the one used for data collection. The experimental findings indicated that while two models -- (ii) Naive Bayes-Support Vector Machine and (v) Deep Learning -- achieved 85% or more accuracy in the original setting, their accuracy dropped to approximately 30% when applied in a different environment. These results underscore that although CSI-based machine learning models can attain high accuracy within a consistent spatial structure, their performance diminishes considerably with changes in spatial conditions, highlighting a significant challenge in their generalization capabilities.
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。