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.
Sara Meletani, G. Sartini, S. Casaccia et al.· 2026 IEEE International Work...· 0 citations
Human Activity Recognition (HAR) focuses on measuring human activities from inertial sensor signals acquired through wearable devices. While machine learning and deep learning approaches achieve high classification performance, they often suffer from limited interpretability, high computational cost, and reduced generalization across users. From a measurement perspective, there is therefore increasing interest in identifying simple, physically meaningful descriptors that can be reliably derived from sensor data. In this work, we investigate jerk magnitude, defined as the time derivative of acceleration, as a standalone kinematic measurand for activity discrimination. Triaxial acceleration data were acquired using an Empatica EmbracePlus smartwatch from 20 subjects performing five Activities of Daily Living (ADLs) with different intensity levels. The jerk magnitude was computed through a signal processing pipeline and summarized over short temporal windows using basic statistical features, with particular focus on the mean jerk. To evaluate the discriminative capability of this descriptor, a fully non-parametric statistical framework was adopted, combining the Kruskal–Wallis test for global analysis and Dunn's post-hoc test with Bonferroni correction for pairwise comparisons. The results show that mean jerk magnitude exhibits statistically significant differences across all activity classes $(p<0.001$), enabling clear discrimination between static, low-intensity, and highly dynamic movements. Pairwise analysis confirms strong separability for most activity combinations, while highlighting limitations in distinguishing tasks with similar motion smoothness but different spatial orientation. These findings demonstrate that a single, computationally lightweight and physically interpretable measurand can provide robust activity discrimination without relying on complex models. The proposed approach establishes a reproducible baseline for HAR and highlights the potential of measurement-driven, physics-based descriptors for low-power wearable applications.
G. Sartini, Sara Meletani, S. Casaccia et al.· 2026 IEEE International Work...· 0 citations
