Anomaly Detection In Ioht Using Deep Learning: Enhancing Wearable Medical Device Security

Abstract

Anomaly detection has been a focal point in research within the data mining community, with numerous methods developed over the years. A significant challenge that has emerged in recent years, impacting the practical implementation of [1]these algorithms, is the lack of trust from end-users. This research introduces a novel model that capitalizes on correlations among physiological data attributes, integrating hybrid Convolutional Long Short-Term Memory (ConvLSTM) techniques. The efficiency of the proposed model in enhancing the reliability of healthcare data in WBAN settings is explored, highlighting its potential impact on the advancement of healthcare technology.