Scientific Publications

This study implements a novel integrated care model combining continuous IAQ monitoring, advanced lung function assessment using oscillometry, digital adaptive case management, and predictive modelling for early detection and management of exacerbations. These interventions are designed to identify environmental and clinical triggers of acute events, optimise personalized care, and reduce unplanned hospitalisations in high risk patients.

Social media provides valuable information during disasters, but the lack of geographical data often limits its use by first responders. This paper proposes combining text from social media posts with information extracted from images to improve geolocation. Using ChatGPT for location prediction and real Twitter data from events like floods and earthquakes, the study shows that this approach enhances both the quantity and accuracy of location predictions. The findings could help policymakers implement this methodology in disaster response.

This study introduces a social media image classifier aimed at enhancing crowdsourced geolocation. The model’s main goal is to reduce the difficulty of geolocating images by detecting those that are “easy” to geolocate.

This study introduces an automated image classifier aimed at accelerating crowdsourced geolocation. Trained by crisis experts, the classifier predicts how difficult it is to geolocate a photo. This approach can speed up the process by focusing on images that are easier to geolocate, helping volunteers work more efficiently.

The aim of this study was to systematically review the available evidence regarding the sources, determinants and concentrations of indoor air pollutants in a set of scenarios under study in K-HEALTHinAIR project. To this end, a systematic review was performed to review the available studies published between the years 2013–2023, for several settings (schools, homes, hospitals, lecture halls, retirement homes, public transports and canteens), conducted in Europe, where sources and determinants of the indoor pollutants concentrations was assessed. 

Indoor air quality (IAQ) significantly impacts human health, particularly in enclosed spaces where people spend most of their time. This study evaluates the performance of low-cost IAQ sensors, focusing on their ability to measure carbon dioxide (CO2) and particulate matter (PM) under real-world conditions.

This study aims to investigate the volatile organic compounds (VOCs) emission pattern, intensity, and profile of nine commercially untreated and treated wood panels commonly used in indoor environments, focusing on how wood type and surface treatments influence emission characteristics.