Sick Building Syndrome and Indoor Air Quality: Leveraging Kolmogorov-Arnold Networks for Predictive Pollutant Control

Linares Alzamora R.G.; Maia Sampaio P.N.; Rodríguez Peralta L.M.; Posada Barrera A.I.; de Oliveira Nunes É. · Lecture Notes in Networks and Systems (2025) · DOI: 10.1007/978-3-031-93109-3_37

Resumen

Air pollution, especially in enclosed spaces, poses serious health risks due to everyday activities like cooking and cleaning. Poor indoor air quality can lead to conditions such as Sick Building Syndrome (SBS), highlighting the need for advanced predictive models. Kolmogorov-Arnold Networks (KAN) provide an innovative solution for predicting pollutants such as CO2, TVOC, PM2.5, and PM10 using historical and real-time data. This study applies KANs to forecast pollution risk levels and demonstrates their potential for integration with IoT technologies to enable continuous, precise monitoring for safer indoor environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Instituciones: Universidad de Lima