The Internet of Things (IoT) offers healthcare applications that benefit customers, physicians, hospitals, and insurance companies. Wearable technology like fitness bands and other wirelessly connected gadgets like blood pressure monitors, blood glucose meters, and heart rate monitors are examples of these uses. The wearable sensor devices utilized in IoT-based Electrocardiogram (ECG) denoising systems continuously produce a huge volume of signals. IoT sensor devices produce ECG signals at a very rapid rate. As a result, the IoT-based health monitoring system generates ECG signals with very high noise levels. A clean ECG signal is needed for effective heart disease management. Imbalanced electrolytes cause an abnormal ECG reading. The noise can also cause fluctuations the ECG signals. This study shows a novel IoT-based ECG denoising method by combining two filters: the Median Modified Weiner (MMW) and the Extended Kalman filter (EKF), to overcome this issue. The characteristic of ECG signals are first subjected to the MMW filter. The extracted ECG signal is then explained with the Extended Kalman filter. MAT LAB simulates the proposed method. Root mean square error (RMSE), contrast-to-noise ratio (CNR), signal contrast, and coefficient of variation (COV) are used in the proposed MMW-EKF framework to the current systems are compared to Signal-to-noise ratio (SNR). We demonstrate how the suggested technique effectively distinguishes between various ECG signals from a noisy sample input.