Energy Efficiency through the Implementation of an AI Model to Predict Room Occupancy Based on Thermal Comfort Parameters

Room occupancy prediction based on indoor environmental quality may be the breakthrough to ensure energy efficiency and establish an interior ambience tailored each user. Identifying whether temperature, humidity, lighting, CO2 levels used as efficient predictors of room accuracy is needed help designers better utilize readings data collected in order improve design, effort suit users. It also aims saving ever-increasing crisis dangerous climate change. This paper evaluated recognition using a dataset with diverse amounts light, CO2, humidity. As classification algorithms, K-nearest neighbors (KNN), hybrid Adam optimizer–artificial neural network–back-propagation network (AO–ANN (BP)), decision trees (DT) were used. Furthermore, this research machine learning interpretability methodologies. Shapley additive explanations (SHAP) by estimating significance values for feature classifiers applied. The results indicate that KNN performs than DT AO-ANN (BP) models have 99.5%. Though two are designed evaluate variations interpretations, we must they accurate detection. show SHAP provides successful implementation following these metrics, differences detected amongst classifier support assumption model complexity plays significant role when predictability taken into account.