SPECIAL SESSION #24

Valentina Casadei

University of Bergen, Norway

• Valentina.Casadei@uib.no

Grazia Iadarola

Polytechnic University of Marche, Italy

• g.iadarola@staff.univpm.it

Alessandra Galli

Eindhoven University of Technology, Netherlands

Chiara Romano

University Campus Bio-Medico of Rome, Italy

A growing portion of society is composed of people with various impairments. Tele-rehabilitation and remote monitoring systems have therefore become a crucial tool for indoor assisted living, supporting continuum of care. Modern and cutting-edge technologies now enable remote health assessments, personalized interventions, and continuous patient monitoring. Within this context, the evolution of measurement systems dedicated to indoor assisted living and real-world health monitoring has become a cornerstone for enhancing the autonomy, safety, and well-being across different populations and life stages. Beyond environmental assistance, there is an increasing need for accurate, non-invasive, and longitudinal monitoring of physiological and behavioral signals in everyday environments. Such approaches enable early detection of health deterioration, assessment of development or recovery, and personalized, data-driven decision support.

This special session aims to explore the latest advancements in sensor fusion, artificial intelligence (AI), and innovative measurement methodologies that enable real-time and longitudinal health and context-aware monitoring in assisted living and real word environments.

Key topics of discussion will include the integration of multimodal sensors - ranging from wearable and smart solutions for health monitoring to indoor environmental sensors - as well as electrophysiological, biomechanical, and behavioral sensing modalities, for applications such as air quality monitoring, ambient tracking, light and noise exposure assessment, and physiological state characterization. Such complex multimodal systems can indeed provide effective and non-invasive support for the target population while enabling clinically meaningful interpretation of health-related signals.

This session will address the application of machine learning and semantic segmentation techniques for multimodal biomedical signal analysis, digital biomarker extraction, and decision support, not just for biomedical monitoring, but also for indoor localization and obstacle classification. These approaches facilitate health assessment and mobility within home environments, thereby reducing the risk of accidents and improving overall safety and quality of care.

Topics of interest include but are not restricted to:

• Measurement methods in clinical and real-world environment;
• Sensor fusion and AI integrated solutions for ambient assisted living decision support systems;
• Wearable solutions for continuous physiological and health monitoring;
• Signal processing for physiological and health monitoring;
• Machine learning and semantic segmentation for indoor localization and obstacle classification;
• Tele-rehabilitation and tele-monitoring for continuum of care;
• Monitoring of vulnerable populations (e.g., pregnancy, elderly, chronic conditions);
• Multimodal biomedical signal analysis and digital biomarkers.

Valentina Casadei (Memeber, IEEE) received her M.Sc. in Biomedical Engineering from Università Politecnica delle Marche, Italy, in 2019 and her PhD in Electrical Engineering from the University of Liverpool, UK, in 2024. She is currently a postdoctoral researcher at the Faculty of Medicine, University of Bergen, Norway. Within the DARK.DEM RCT project, her research focuses on developing models for digital phenotyping of dementia and on quantifying the associated uncertainties. Her work investigates the feasibility of using wearable devices in clinical dementia care and in isolation studies conducted by the European Space Agency (ESA).

Grazia Iadarola received the bachelor’s degree (cum laude) in telecommunications engineering, the master’s degree (cum laude) in electronic engineering, and the Ph.D. degree in information technologies for engineering from the University of Sannio, Benevento, Italy, in 2013, 2015, and 2019, respectively. She is currently an Assistant Professor of electrical and electronic measurements at the Polytechnic University of Marche, Ancona, Italy. Her research interests include sub-Nyquist sampling, characterization and testing of data converters, modeling of electronic circuits and non-idealities, signal reconstruction based on compressed sensing, as well as their applications to telecommunications and biomedical instrumentation.

Alessandra Galli received the B.Sc. and M.Sc. degrees in Biomedical Engineering from the University of Padova, Italy, in 2015 and 2017, respectively. In 2021, she received a Ph.D. degree in Information and Communication Technology from the School of Information Engineering of the University of Padova, with a dissertation about IoT measurements for long-term monitoring applications. In 2021-2022, she was a postdoctoral researcher of the Instrumentation and Measurements Group of the University of Padova. In September 2023, she joined the Eindhoven University of Technology, Netherlands supported by a Marie Skłodowska-Curie Postdoctoral fellowship. Her research interests include biomedical signal processing, compression, anomaly detection, and machine learning. In particular, she is devoted to electrophysiological signals for cardiac non-invasive and long-term monitoring.

Chiara Romano (Student Member, IEEE) received the M.Sc. (cum laude) degree in biomedical engineering from the Università Campus Bio-Medico di Roma (UCBM), Rome, Italy, in 2021, where she is currently Post-Doc Researcher. Her main research interests include the design, development, and testing of wearable systems for integrated monitoring of physiological and motion-related signals, with a specific focus on applications in daily-life, occupational, and sports environments. She contributes to the design and characterization of wearable sensors and devices, the integration of embedded electronics and wireless connectivity solutions, and the definition of robust data acquisition pipelines suitable for real-world deployment. In parallel, she develops signal processing algorithms and machine learning models aimed at extracting physiological indicators relevant to both clinical and everyday-life contexts.