Skip to main content

Table 5 XGBoost model evaluation for Annisse Church, for prediction of episodes of indoor relative humidity outside 45–75% RH

From: Prediction of the indoor climate in cultural heritage buildings through machine learning: first results from two field tests

Prediction for next 24 h

Precision

Recall

F1-score

Humidity too high (> 75% RH)

0.73

0.83

0.78

Humidity too low (< 45% RH)

0.98

0.45

0.62

  1. In this model temperature was excluded, so the results are based only on relative humidity, absolute humidity, indoors and outdoors