KRNN: A hybrid data and knowledge oriented time series forecasting approach for health care applications

Muhammad Ali Chattha, Muhammad Imran Malik, Andreas Dengel, Sheraz Ahmed

Abstract: Highlights•This work presents KRNN a hybrid knowledge and data framework for forecasting.•KRNN uses strengths of both knowledge and data domain in a complementary manner.•KRNN improves State-Of-The-Art by an average of 33%.•KRNN gives prediction that are better than commonly used ensemble methods.