An Efficient Deep Learning Architecture for Internet of Medical Things

Data analysis in the Internet of Medical Things (IoMT) plays a significant role in making the healthcare system more efficient and automatic. The ECG and EEG signals are used to analyze different health conditions using machine learning (ML). Deep Learning (DL) is a very successful ML technique, and it is widely used with different time-varying signals. In this experiment, we used both EEG and ECG signal datasets collected from the physionet biosignal repository and developed a hybrid DL architecture. The proposed method achieved an accuracy of 96 percent for classifying ECG signals and 97 percent for identifying bodily activity from EEG signals.