Zgadzam się
Nasza strona zapisuje niewielkie pliki tekstowe, nazywane ciasteczkami (ang. cookies) na Twoim urządzeniu w celu lepszego dostosowania treści oraz dla celów statystycznych. Możesz wyłączyć możliwość ich zapisu, zmieniając ustawienia Twojej przeglądarki. Korzystanie z naszej strony bez zmiany ustawień oznacza zgodę na przechowywanie cookies w Twoim urządzeniu.
Accurate determination of moisture in buildings helps to prevent many problems, structural or health and hygiene. The Time Domain Reflectometry (TDR) technique can be used to determine moisture in buildings. This technique offers the possibility to perform measurements directly in the field without major destruction of the measured buildings. This technique is an indirect measurement technique, where the apparent permittivity of the environment is measured. To convert apparent permittivity into moisture content (volumetric or mass), empirical or physical models are used. Empirical models are developed specifically for the measured material and show greater accuracy than physical models. A prerequisite for the correct determination of moisture is a model with the greatest possible accuracy. This paper presents the possibility of using Machine Learning in the processing of data measured by TDR for volumetric water content. Machine Learning as a subdomain of Artificial Intelligence creates a mathematical model for predicting new data based on input and output data. This potential is precisely due to the model's ability to learn from training data.
