Eleonora Melissa

Eleonora Melissa

Auto-generated profile, based on publicly available information

Eleonora Melissa

Institute of Clinical Physiology, National Research Council (CNR), Pisa, Italy

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 October 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CMCarlotta Marinai
Carlotta Marinai
EMEleonora Melissa
Eleonora Melissa
LALucia Arcarisi
Lucia Arcarisi
Francesco Di RienzoFrancesco Di Rienzo
Francesco Di Rienzo
Carlo VallatiCarlo Vallati
Carlo Vallati
NCNicola Carbonaro
Nicola Carbonaro
Extracting sleep-related parameters is essential for assessing health and detecting sleep disorders. However, traditional methods are invasive, costly, and impractical for daily use. To address these limitations, we propose the smart mattress cover system (SMCS), a noninvasive and scalable solution for real-world sleep monitoring. The SMCS includes two components: the smart mattress cover (SMC), a compact low-density textile-based pressure matrix (PM) with embedded accelerometers (ACCs), and the bedroom box hub (BBH), which manages data collection and integrates environmental sensors. The SMC acquires key patient-related parameters (PPs) as heart rate (HR), breathing rate (BR), movements, and on-/off-bed status, while the BBH records environmental parameters (EPs). We present the SMCS design, a systematic requirement analysis, and custom algorithms to extract PP. Results showed a low HR RMSE of 2.02 bpm and a good BR RMSE of 4.29 act/min across sleep positions and respiratory frequencies. On-/off-bed detection and movement classification algorithm achieved an overall accuracy of 98.4%. Algorithms were validated across multiple SMCS prototypes, bed types, positions, and breathing patterns, confirming robustness. The SMCS demonstrates scalability for home use, with over 80 units deployed in the TOLIFE project. To the best of our knowledge, the SMCS is the most compact low-density textile-based system capable of extracting all core PP simultaneously.

22 October 2025
Verified
Conference Paper
Closed access
FBFrancesco Bossi
Francesco Bossi
Alberto GrecoAlberto Greco
Alberto Greco
Gianluca RhoGianluca Rho
Gianluca Rho
CMCarlotta Marinai
Carlotta Marinai
PBPasquale Bufano
Pasquale Bufano
Alessandro TognettiAlessandro Tognetti
Alessandro Tognetti
Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality worldwide, with progressive lung function decline severely affecting patients' quality of life. Spirometric assessment, particularly Forced Expiratory Volume in one second as a percentage of predicted (FEV1% predicted), is central to monitoring disease progression but is often impractical for regular use due to its invasive and burdensome nature. This study explores an alternative approach for predicting longitudinal changes in FEV1% predicted using passive data collected via wearable sensors and demographic variables. Utilizing data from 423 patients in the COSYCONET cohort, physical activity metrics - such as accelerometer readings, step counts, and energy expenditure - were processed from one-week recordings. After constructing paired observations to reflect FEV1 changes between clinical visits, the problem was reformulated as a binary classification task (improvement vs. worsening). Principal Component Analysis was used for dimensionality reduction, followed by training six classification models. Naive Bayes and Quadratic Discriminant Analysis (QDA) achieved the highest overall accuracy, with k-Nearest Neighbors (k-NN) offering the best sensitivity. Results suggest that non-linear and non-parametric models are more suitable for capturing the complexity of COPD progression. However, performance remains modest, likely due to the simplistic binary threshold applied to FEV1 changes. Future research should focus on refining thresholds to better reflect clinically meaningful variations and improve model precision.