We are excited to share a new, outstanding achievement accomplished by University Of Patras, within the context of TwinAir project!
The article “Toward Personalized Short-Term PM2.5 Forecasting Integrating a Low-Cost Wearable Device and an Attention-Based LSTM” has been published at “air” Journal, by MDPI.
The authors of the article are: Christos Mountzouris, Protopsaltis, John Gialelis and its respective DOI is the following: https://doi.org/10.3390/air3040029
The abstract and the keywords of the publication can be found below:
Abstract
Exposure to degraded indoor air quality (IAQ) conditions represents a major concern for health and well-being. PM2.5 is among the most prevalent indoor air pollutants and constitutes a key indicator in IAQ assessment. Conventional IAQ frameworks often neglect personalization, which in turn compromises the reliability of exposure estimation and the interpretation of associated health implications. In response to this limitation, the present study introduces a human-centric framework that couples wearable sensing with deep learning, employing a low-cost wearable device to capture PM2.5 concentrations in the immediate human vicinity and an attention-based Long-Short Term Memory (LSTM) to deliver 5-min-ahead exposure predictions. During evaluation, the proposed framework demonstrated strong and consistent performance across both stable conditions and transient spikes in PM2.5, yielding a Mean Absolute Error (MAE) of 0.181 µg/m3. These findings highlighted the synergistic potential between wearable sensing and data-driven modeling in advancing personalized IAQ forecasting, informing proactive IAQ management strategies, and ultimately promoting healthier built environments
Keywords:
indoor air quality; PM2.5; time-series forecasting; LSTM; deep learning
You can reach the full article following this link: https://www.mdpi.com/2813-4168/3/4/29