This paper presents the results from the experimental application of smartwatch sensors to predict occupants' thermal comfort under varying environmental conditions. The goal is to investigate the measurement accuracy of smartwatches when used as thermal comfort sensors to be integrated into Heating, Ventilation and Air Conditioning (HVAC) control loops. Ten participants were exposed to various environmental conditions as well as warm - induced and cold-induced discomfort tests and 13 participants were exposed to a transient-condition while a network of sensors and a smartwatch collected both environmental parameters and heart rate variability (HRV). HRV features were used as input to Machine Learning (ML) classification algorithms to establish whether a user was in discomfort, providing an average accuracy of 92.2 %. ML and Deep Learning regression algorithms were trained to predict the thermal sensation vote (TSV) in a transient environment and the results show that the aggregation of environmental and physiological quantities provide a better TSV prediction in terms of Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE), 1.2 and 20% respectively, than just the HRV features used for the prediction. In conclusion, this experiment supports the assumption that physiological quantities related to thermal comfort can improve TSV prediction when combined with environmental quantities.

This paper presents an approach to assess the measurement uncertainty of human thermal comfort by using an innovative method that comprises a heterogeneous set of data, made by physiological and environmental quantities, and artificial intelligence algorithms, using Monte Carlo method (MCM). The dataset is made up of heart rate variability (HRV) features, air temperature, air velocity and relative humidity. Firstly, MCM is applied to compute the measurement uncertainty of the HRV features: results have shown that among 13 participants, there are uncertainty values in the measurement of HRV features that ranges from ±0.01% to ±0.7 %, suggesting that the uncertainty can be generalized among different subjects. Secondly, MCM is applied by perturbing the input parameters of random forest (RF) and convolutional neural network (CNN) algorithm, trained to measure human thermal comfort. Results show that environmental quantities produce different uncertainty on the thermal comfort: RF has the highest uncertainty due to the air temperature (14 %), while CNN has the highest uncertainty when relative humidity is perturbed (10.5 %). A sensitivity analysis also shows that air velocity is the parameter that causes a higher deviation of thermal comfort

Dementia is a condition that affects more and more elderly people around the world. The number of people affected by dementia is expected to increase in the future due to increasing longevity and the growing elderly population. According to the World Health Organization (WHO), the number of people with dementia worldwide is expected to double by 2030 and triple by 2050. This will pose a significant challenge to the health and social systems of many nations and will require increased attention and resources for the prevention, diagnosis and treatment of dementia. As the disease spreads, the workload of formal caregivers will inevitably increase. The HAAL project (HeAlthy Aging eco-system for peopLe with dementia) responds to this challenge by developing a dashboard that integrates all the relevant information coming from a set or a subset of nine already experimented devices. The dashboard is designed to show the most relevant information regarding the patient (fall events, sleep data, wellbeing data) to the formal caregiver. The purpose of this paper is therefore to present the experimental results obtained from the usability test performed on the HAAL dashboard by 26 formal caregivers in three pilot sites: Italy, Taiwan, and the Netherlands. Quantitative and qualitative results of this preliminary study confirm the suitability of the dashboard, highlighting inter-country differences.

Air pollution is a major environmental and public health challenge, especially in urban areas where fine-grained air quality data are essential to effective interventions. Traditional monitoring networks, while accurate, often lack spatial resolution and public engagement. This study presents a novel wearable wireless sensor node (WSN) that was developed within the Horizon Europe SOCIO-BEE project to support air quality monitoring through citizen science (CS). The low-cost, body-mounted WSN measures NO₂, O₃, and PM_2.5. Three pilot campaigns were conducted in Ancona (Italy), Maroussi (Greece), and Zaragoza (Spain), and involved diverse user groups—seniors, commuters, and students, respectively. PM_2.5 sensor data were validated through two approaches: direct comparison with reference stations and spatial clustering analysis using K-means. The results show strong correlation with official PM_2.5 data (R² = 0.75), with an average absolute error of 0.54 µg/m³ and a statistical confidence interval of ±3.3 µg/m³. In Maroussi and Zaragoza, where no reference stations were available, the clustering approach yielded low intra-cluster coefficients of variation (CV = 0.50 ± 0.40 in Maroussi, CV = 0.28 ± 0.30 in Zaragoza), indicating that the measurements had high internal consistency and spatial homogeneity. Beyond technical validation, user engagement and perceptions were evaluated through pre-/post-campaign surveys. Across all pilots, over 70% of participants reported satisfaction with the system’s usability and inclusiveness. The findings demonstrate that wearable low-cost sensors, when supported by a structured engagement and data validation framework, can provide reliable, actionable air quality data, empowering citizens and informing evidence-based environmental policy.