Median-KNN Regressor-SMOTE-Tomek Links for Handling Missing and Imbalanced Data in Air Quality Prediction

The Air Quality Index (AQI) dataset contains information on measurements of pollutants and ambient air quality conditions at certain location that can be used to predict quality. Unfortunately, this often has many missing observations imbalanced classes. Both these problems affect the performance prediction model. In particular, predictions for minority class are very important because inaccurate fatal or cause big losses. Moreover, data may lead biased results. This paper proposes single imputation median multiple imputations k-Nearest Neighbor (KNN) regressor handle values less than equal 10% more 10%, respectively. At same time, SMOTE-Tomek Links address class. These proposed approaches both issues then assess India AQI using Naive Bayes (NB), KNN, C4.5. five treatments show method Median-KNN regressor-SMOTE-Tomek is able improve other words, succeeds in overcoming imbalance.