A Measurement Framework for Distinguishing Human Activities Using Time-Frequency Analysis of Ultrasonic Sensors Data

Abstract

The accurate measurement of physical activity in indoor environments is crucial for Ambient Assisted Living (AAL) applications, yet current wearable and vision-based technologies suffer from user obtrusiveness and privacy concerns. To overcome these limitations, this paper proposes a privacy-preserving activity measurement framework based on a single ceiling-mounted Time-of-Flight (ToF) ultrasonic sensor. An experimental campaign was conducted involving 20 healthy subjects performing 5 different activities in a Living Lab. The proposed approach uses a time-frequency analysis by applying the Continuous Wavelet Transform (CWT) to raw one-dimensional distance signals. This process generates detailed time-frequency scalograms, from which the total sum of the wavelet power spectrum is computed as the primary quantitative feature to discriminate the activities. A statistical analysis using a Repeated-Measures ANOVA followed by post-hoc paired t-tests with Bonferroni correction demonstrated that the extracted metrological feature successfully discriminates between activities belonging to different physiological intensity zones. Specifically, the squat activity was successfully distinguished from all other activities $(p<0.05)$. The resting baseline was significantly different from cleaning, sweeping, and squats, although its difference with the filing documents activity was not statistically significant $(p=0.121)$, given the highly static nature of the latter. These results demonstrate that an advanced time-frequency analysis of ultrasonic distance measurements provides a reliable indicator for Human Activity Recognition (HAR), offering a highly effective alternative to black-box models for smart home monitoring.