Priority Detector and Classifier Techniques Based on ML for the IoMT

Emerging telemedicine trends, such as the Internet of Medical Things (IoMT), facilitate regular and efficient interactions between medical devices computing devices. The importance IoMT comes from need to continuously monitor patients’ health conditions in real-time during normal daily activities, which is realized with help various wearable sensors. One major problem workplace stress, can lead cardiovascular disease or psychiatric disorders. Therefore, monitoring employees’ stress essential. Stress levels source could be detected early fog layer so that negative consequences mitigated sooner. However, overwhelming extensive data will increase load on nodes, leading computational challenges. This study aims reduce computation by proposing machine learning (ML) models two phases. first phase ML model assesses priority situation based level. In second phase, a classifier determines cause was either interruptions time pressure while completing task. approach reduced cost for node, only high-priority records were transferred fog. Low-priority forwarded cloud. Four approaches compared terms accuracy prediction speed: K-nearest neighbors (KNN), support vector (SVM), bagged tree (BT), an artificial neural network (ANN). our experiments, ANN performed best both phases because it scored F1 score 99.97% had highest speed KNN, SVM, BT.