Sara Comai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sara Comai has a total of 205 co-authors. Here are the top co-authors by number of shared publications:
- Fabio Salice
Politecnico di Milano, Milano, Italy
38 shared publications - Andrea Masciadri
Politecnico di Milano, Milan, Italy
23 shared publications Piero Fraternali
13 shared publicationsFabio Salice
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy
12 shared publications- Marco Brambilla
Politecnico di Milano, Milan, Italy
11 shared publications Davide Mazza
Politecnico di Milano
10 shared publications
Latest Publications
- Open Access
- 12 September 2026
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 124
Nonintrusive PIR sensor-based method for indoor distance estimation
- 12 September 2026
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 124
Open AccessNonintrusive PIR sensor-based method for indoor distance estimation
- Open Access
- 2 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 569-576
Invisible Preventive Health Awareness: A Context-Aware Smart Belt for Posture and Physiological Sensing
- 2 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 569-576
Open AccessInvisible Preventive Health Awareness: A Context-Aware Smart Belt for Posture and Physiological Sensing
- 17 July 2026
- Published by Springer Nature
- p. 232-239
Smart Wheelchair System for Surface Type Classification and Obstacle Detection
- 17 July 2026
- Published by Springer Nature
- p. 232-239
Smart Wheelchair System for Surface Type Classification and Obstacle Detection
- 16 July 2026
- Published by Springer Nature
- p. 217-224
Wearable Instrumented Insoles for Continuous Gait Monitoring for Daily-Life Rehabilitation Support
- 16 July 2026
- Published by Springer Nature
- p. 217-224
Wearable Instrumented Insoles for Continuous Gait Monitoring for Daily-Life Rehabilitation Support
- 1 April 2026
- Published by Springer Nature
- p. 214-219
Non-intrusive Monitoring of Daily Habits in Older Adults: A Chaos Game Representation-Based Approach
- 1 April 2026
- Published by Springer Nature
- p. 214-219
Non-intrusive Monitoring of Daily Habits in Older Adults: A Chaos Game Representation-Based Approach
- 1 April 2026
- Published by Springer Nature
- p. 190-202
Estimation of Human Localisation Using Low-Resolution IR Sensors
- 1 April 2026
- Published by Springer Nature
- p. 190-202
Estimation of Human Localisation Using Low-Resolution IR Sensors
- 1 April 2026
- Published by Springer Nature
- p. 177-189
24 GHz Radar-Based Monitoring of Respiratory Rate During Sleep
- 1 April 2026
- Published by Springer Nature
- p. 177-189
24 GHz Radar-Based Monitoring of Respiratory Rate During Sleep
- 11 February 2026
- Published by Springer Nature
- p. 301-319
Towards Defining an Intelligent System to Enhance Dentistry Experience for Children with Autism Spectrum Disorder
- 11 February 2026
- Published by Springer Nature
- p. 301-319
Towards Defining an Intelligent System to Enhance Dentistry Experience for Children with Autism Spectrum Disorder
- Open Access
Noninvasive Acoustic Recognition of Water Flow Sources for Human Activity Monitoring in Smart Homes
This paper presents a noninvasive system for identifying water flow sources with the final goal of supporting human activity recognition (HAR) in activities of daily living (ADL). The system employs a single microphone to capture ambient sounds within a room and detects active water sources based on their acoustic signatures. The audio signals are converted into time-resolved spectrograms, which are processed via time- and frequency-domain convolution and subsequently classified using a neural network. This approach enables both the identification of specific water sources, even combined, and the measurement of their usage duration with an overall accuracy of 90.6%. The study focuses on four common bathroom fixtures: toilet, bidet, shower, and washbasin. The proposed system is adaptable to various environments, requires no modifications to plumbing infrastructure, making it suitable for smart home and digital health applications.
Open AccessNoninvasive Acoustic Recognition of Water Flow Sources for Human Activity Monitoring in Smart Homes
This paper presents a noninvasive system for identifying water flow sources with the final goal of supporting human activity recognition (HAR) in activities of daily living (ADL). The system employs a single microphone to capture ambient sounds within a room and detects active water sources based on their acoustic signatures. The audio signals are converted into time-resolved spectrograms, which are processed via time- and frequency-domain convolution and subsequently classified using a neural network. This approach enables both the identification of specific water sources, even combined, and the measurement of their usage duration with an overall accuracy of 90.6%. The study focuses on four common bathroom fixtures: toilet, bidet, shower, and washbasin. The proposed system is adaptable to various environments, requires no modifications to plumbing infrastructure, making it suitable for smart home and digital health applications.
- Open Access
- 6 October 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3124
A configurable simulator for low-resolution infrared thermal sensors: accuracy assessment and practical applications in indoor environments
Thermal sensors are increasingly used in various applications such as environmental monitoring, smart homes, and surveillance. These sensors detect infrared radiation to monitor human presence and movement, enabling sophisticated sensing capabilities. However, determining the number of sensors and optimizing their placement through real-world experimentation is often impractical due to cost and logistical constraints. This article introduces ThermalSim, a highly configurable simulator for low-resolution thermal sensors, designed to address these issues and enable pre-testing of sensor setups in virtual environments. The simulator allows for detailed customization of environmental parameters, object properties, and sensor characteristics and supports modelling a dynamic agent with configurable trajectories and speeds. Experimental validation against real-world data demonstrates the simulator’s high accuracy in replicating static and dynamic scenarios. Metrics such as correlation, entropy and mutual information, and similarity of temperature images have been used to evaluate the simulator’s output. Some case studies show the tool’s flexibility, showcasing its practical applications across various scenarios.
- 6 October 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3124
Open AccessA configurable simulator for low-resolution infrared thermal sensors: accuracy assessment and practical applications in indoor environments
Thermal sensors are increasingly used in various applications such as environmental monitoring, smart homes, and surveillance. These sensors detect infrared radiation to monitor human presence and movement, enabling sophisticated sensing capabilities. However, determining the number of sensors and optimizing their placement through real-world experimentation is often impractical due to cost and logistical constraints. This article introduces ThermalSim, a highly configurable simulator for low-resolution thermal sensors, designed to address these issues and enable pre-testing of sensor setups in virtual environments. The simulator allows for detailed customization of environmental parameters, object properties, and sensor characteristics and supports modelling a dynamic agent with configurable trajectories and speeds. Experimental validation against real-world data demonstrates the simulator’s high accuracy in replicating static and dynamic scenarios. Metrics such as correlation, entropy and mutual information, and similarity of temperature images have been used to evaluate the simulator’s output. Some case studies show the tool’s flexibility, showcasing its practical applications across various scenarios.