Cross-Domain Transfer Learning Method for Thermal Adaptive Behavior Recognition with WiFi

TL;DR

This paper introduces a cross-domain transfer learning approach using WiFi signals and hybrid deep learning models to accurately recognize dressing behaviors, enhancing thermal comfort prediction while addressing privacy and cost issues.

Contribution

It proposes a novel transfer learning method combining WiFi signal analysis with a hybrid CNN-SVM model for adaptive behavior recognition.

Findings

Achieved 96.9% accuracy in one scenario.

Achieved 94.9% accuracy in another scenario.

Enhanced robustness in behavior recognition across different environments.

Abstract

A reliable comfort model is essential to improve occupant satisfaction and reduce building energy consumption. As two types of the most common and intuitive thermal adaptive behaviors, precise recognition of dressing and undressing can effectively support thermal comfort prediction. However, traditional activity recognition suffers from shortcomings in privacy, cost, and performance. To address the above issues, this study proposes a cross-domain transfer learning method for human dressing and undressing adaptive behavior recognition with WiFi. First, we determine the activity interval by calculating the sliding variance for denoised WiFi signals. Subsequently, short-time Fourier transform and discrete wavelet transform are performed to extract action information on the basis of time-frequency analysis. Ultimately, an efficient 1D CNN pre-trained model is integrated with the SVM algorithm as a hybrid model to enhance the identification robustness in new scenarios. Experiment results show that the hybrid model based on transfer learning provides a more accurate prediction for the adaptative behavior of target subjects, achieving 96.9% and 94.9% accuracy in two cases, respectively.