HealthGuard: An Intelligent Healthcare System Security Framework Based on Machine Learning

Abstract

Utilization of the Internet of Things and ubiquitous computing in medical apparatuses have “smartified” the current healthcare system. These days, healthcare is used for more than simply curing patients. A Smart Healthcare System (SHS) is a network of implanted medical devices and wearables that monitors patients in real-time to detect and avert potentially fatal illnesses. With its expanding capabilities comes a slew of security threats, and there are many ways in which a SHS might be exploited by malicious actors. These include, but are not limited to, interfering with regular SHS functioning, inserting bogus data to modify vital signs, and meddling with medical devices. This study presents HealthGuard, an innovative security architecture for SHSs that uses machine learning to identify potentially harmful actions taken by users. HealthGuard monitors the vitals of many SHS-connected devices and compares the vitals to distinguish normal from abnormal activity. For the purpose of locating potentially dangerous actions inside a SHS, HealthGuard employs four distinct machine learning-based detection approaches (Artificial Neural Network, Decision Tree, Random Forest, and k-Nearest Neighbor). Eight different smart medical devices were used to train HealthGuard for a total of twelve harmless occurrences, seven of which are common user activities and five of which are disease-related occurrences. HealthGuard was also tested for its ability to defend against three distinct forms of harmful attack. Our comprehensive analysis demonstrates that HealthGuard is a reliable security architecture for SHSs, with a 91% success rate and in F1-score of 90% success.

Smart Patient Monitoring and Recommendation (SPMR) Using Cloud Analytics and Deep Learning

“…Comparing DL + CCE with other classifiers developed in comparable and contemporary works is provided as well (see Table 7) [59][60][61][62]. The confusion matrix serves as the primary source of most of the data mining parameters.…”

“…Other chronic conditions, such as cancer, will be tested utilizing the context-aware framework that has been presented. According to [52][53][54][55][56][57], the suggested framework will be evaluated on a variety of quality of service (QoS), energy use [58][59][60][61], and social network service (SNS) in the cloud (Cloud) criteria.…”

Revolutionizing Healthcare by Unleashing the Power of Machine Learning in Diagnosis and Treatment

“…The SVM model takes these parameters for diagnosing diabetics. Three classes for the output are taken into consideration: diabetic patients, people with a genetic history of diabetes, and non-diabetic people [12]. Regression and classification are used for identifying blood pressure.…”

“…The quality of health services can be accessed by using image recognition techniques to examine patterns in Xray reports. New medicine discoveries can be made quickly due to large data gathered from pharmaceutical trials to enhance patients' safety [12]; health tracking can be done actively, which provides pre-emptive recommendations through which future diseases can be avoided. There are various organizations that implement digital healthcare solutions, such as pharmaceuticals, the technological sector, and the government.…”

TITAN: Combining a bidirectional forwarding graph and GCN to detect saturation attack targeted at SDN

“…How to detect saturation attacks is a serious challenge in SDN. Some researchers use machine learning-based approaches to detect network attack [7]. Due to its high detection accuracy, a few studies have applied Graph Neural Networks (GNN) to DDoS attack detection in SDNs.…”