Deep learning-based Attack Detection in Internet of Medical Things Network using Deep Convolutional Neural Network and Long Short-Term Memory

Abstract

The rapid growth of Industry 4.0 has led to the use of artificial intelligence and the Internet of Medical Things (IoMT) in many healthcare applications, facilitating remote diagnosis, data collection, data analysis, and healthcare management. The IOMT provides a healthcare framework that collects biomedical data from patients via sensors or devices, stores it in the cloud, analyzes it, and provides clinical diagnoses. However, the privacy, security, reliability, and integrity of the healthcare data is challenging due to different cyber attacks on the IoMT framework. Therefore, this paper presents a deep learning-based network attack detection method, IoMT attack detection (IADNet), based on a 1-D deep convolutional neural network to capture multilevel correlations and a long short-term memory (LSTM) to capture long-term dependencies in network attributes. Further, it provides the dynamic synthetic minority oversampling technique (DSMOTE) for data augmentation, mitigating data scarcity by generating synthetic samples for training.  The IADNet provides the overall accuracy of 99.12%, precision of 99.12%, recall of 95.50%, and F1-score of 97.24% for the original dataset, whereas it resulted in improved accuracy of 99.80%, recall of 98.80%, precision of 98.80%, and F1-score of 98.80% for the DSMOTE augmented dataset.