TY - GEN
T1 - Leveraging Quantum Machine Learning for Accurate Indoor Air Quality Forecasting and Risk Mitigation
AU - Gómez, Franco Sotelo
AU - Sampaio, Paulo Nazareno Maia
AU - Peralta, Laura Margarita Rodríguez
AU - Cuesta Astudillo, Fabián Leonardo
AU - de Oliveira Nunes, Éldman
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Air pollution is a global challenge that affects both outdoor and indoor environments. This issue is exacerbated in enclosed spaces where everyday activities like cooking or using cleaning products contribute to the accumulation of pollutants, leading to both acute and chronic health effects. Sick Building Syndrome (SBS) is one of the phenomena associated with poor indoor air quality. It is characterized by medical symptoms experienced by building occupants, which disappear once they leave the premises. In this context, the need for advanced predictive models to manage indoor air quality arises. Quantum Machine Learning (QML) offers an innovative solution for accurately predicting indoor air contaminants. By using historical and real-time data, QML can identify complex patterns and predict dangerous pollution levels, enabling proactive interventions. This model focuses on forecasting specific pollutants like CO2, TVOC, PM2.5, and PM10, and assesses its efficiency in determining risk levels. Integrating this model with IoT technologies allows for continuous and accurate monitoring, contributing to the creation of safer and healthier indoor environments.
AB - Air pollution is a global challenge that affects both outdoor and indoor environments. This issue is exacerbated in enclosed spaces where everyday activities like cooking or using cleaning products contribute to the accumulation of pollutants, leading to both acute and chronic health effects. Sick Building Syndrome (SBS) is one of the phenomena associated with poor indoor air quality. It is characterized by medical symptoms experienced by building occupants, which disappear once they leave the premises. In this context, the need for advanced predictive models to manage indoor air quality arises. Quantum Machine Learning (QML) offers an innovative solution for accurately predicting indoor air contaminants. By using historical and real-time data, QML can identify complex patterns and predict dangerous pollution levels, enabling proactive interventions. This model focuses on forecasting specific pollutants like CO2, TVOC, PM2.5, and PM10, and assesses its efficiency in determining risk levels. Integrating this model with IoT technologies allows for continuous and accurate monitoring, contributing to the creation of safer and healthier indoor environments.
KW - Big Data
KW - IoT
KW - Machine Learning Quantum Neural Networks
KW - Monitoring
KW - Sick Building Syndrome
UR - https://www.scopus.com/pages/publications/105012823987
U2 - 10.1007/978-3-031-93106-2_24
DO - 10.1007/978-3-031-93106-2_24
M3 - Articulo (Contribución a conferencia)
AN - SCOPUS:105012823987
SN - 9783031931055
T3 - Lecture Notes in Networks and Systems
SP - 276
EP - 286
BT - Information Technology and Systems, ICITS 2025
A2 - Rocha, Alvaro
A2 - Ferrás, Carlos
A2 - Calvo, Hiram
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference on Information Technology and Systems, ICITS 2025
Y2 - 22 January 2025 through 25 January 2025
ER -