Document Type : Primary Research paper
Assistant Professor, Dept. of Computer Applications Bishop Heber College (Autonomous), Tiruchirappalli - 620 017.
Associate Professor & Head, Dept. of Computer Science Bishop Heber College (Autonomous) Tiruchirappalli - 620 017.
The precision of input data is vital in healthcare research. Data Imputation, on the other hand, is a common occurrence in this sector for a variety of reasons. The mainstream of current research is focused on establishing innovative data imputation methodologies, though there is a need to conduct research on a worldwide evaluation of current algorithms.We assessed the performance of four central missing data imputation algorithms, Regularized Expectation- Maximization (EM), Multiple Imputation (MI), kNN Imputation (kNNI), and Mean Imputation, on two real health care datasets, the MHEALTH dataset and the University of Queensland Vital Signs dataset, in this study.Root Mean Squared Error (RMSE) and execution time were used as the best performing evaluation metrics under the Missing Completely At Random (MCAR) assumption. Conferring to the results of the experiments, EM is an imputation algorithm that is likely to be a good fit for dealing with missing data in the healthcare sector.