Anomaly detection in internet of medical things with artificial intillegence

Internet of things (IoT) becomes the most popular term in recent advances Healthcare devices. The healthcare data IoT process and structure is very sensitive critical terms healthy technical considerations. Outlier detection approaches are considered as principal tool or stage any system mainly categorized statistical probabilistic, clustering classification-based outlier detection. Recently, fuzzy logic (FL) used ensemble cascade systems with other ML-based tools to enhance performance but its limitation involves false outliers. In this paper, we propose a that uses anomaly score each point using local factor (LOF), connectivity-based (COF) generalized LOF eliminate confusion classifying points outliers inliers. Regarding human activity recognition (HAR) dataset, FL achieved value 98.2 %. Compared LOF, COF, GLOF individually, accuracy increased slightly, increase precision recall indicates an correctly classified neither true nor abnormal wrongly. results show which data. Thus, it can be confirmed input scores desired goal mitigating cases anomalous By comparing proposed different types density study, outcomes presents new way elaborating fusing same purpose