Validation of Practicality for CSI Sensing Utilizing Machine Learning
This work addresses the challenge of spatial generalization for CSI-based sensing in applications like activity monitoring, but it is incremental as it evaluates existing methods on new data without introducing novel techniques.
The study tackled the problem of using Channel State Information (CSI) from WLAN to recognize human postures with machine learning models, finding that while some models achieved over 85% accuracy in the original setting, their accuracy dropped to around 30% in a different environment.
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.