Federated Internet of Things and Cloud Computing Pervasive Patient Health Monitoring System
Abstract:
The exponentially growing healthcare costs coupled with the increasing interest of patients in receiving care in the comfort of their own homes have prompted a serious need to revolutionize healthcare systems. This has prompted active research in the development of solutions that enable healthcare providers to remotely monitor and evaluate the health of patients in the comfort of their residences. However, existing works lack flexibility, scalability, and energy efficiency. This article presents a pervasive patient health monitoring (PPHM) system infrastructure. PPHM is based on integrated cloud computing and Internet of Things technologies. In order to demonstrate the suitability of the proposed PPHM infrastructure, a case study for real-time monitoring of a patient suffering from congestive heart failure using ECG is presented. Experimental evaluation of the proposed PPHM infrastructure shows that PPHM is a flexible, scalable, and energy-efficient remote patient health monitoring system.
Existing System:
One possible way to address the challenges facing the healthcare industry is by caring for patients in their environments such as their residences. A lot of patient categories such as those with chronic disease who need only therapeutic supervision, elderly patients, and patients with congenital heart defects do not need to use a hospital bed as they can be cared for in their homes [2–4]. The challenge, however, is how healthcare professionals can accurately, reliably, and securely monitor the health status of their patients without physically visiting them at their residences. The system must be able to facilitate patient mobility, while at the same time improve their safety and increase their autonomy. This study addresses this challenge by augmenting existing healthcare systems with inexpensive but flexible and scalable pervasive technologies that enable long-term remote patient health status monitoring.
Proposed System:
The middleware consists of a virtual machine (VM) manager and a service scheduler, a others. The VM manager is responsible for managing the virtual sensors, which are virtualized counterparts of physical sensors in BSNs, collecting sensor data from personal servers, and storing those data in the “sensor data” store. As compared to the standard cloud workloads such as non-real-time data for scientific computation and storage, the workload from the IoT subsystem is characterized by high inter-arrival rates and highly variant runtimes but with low parallelism. Thus, it becomes important to have cloud resource management and scheduling that can be adapted to handle such different workloads. Thus, service scheduling is necessary to properly schedule many real-time and non-real-time service requests to improve resource usage efficiency. Also, the scheduler performs dynamic load balancing and adaptive resource management in an energy-efficient manner. The ECG dataset is processed by the dimensionality reduction algorithm, which is the rank correlation coefficient (RCC) algorithm to obtain fewer features that effectively capture the behavior of the ECG signals.
Conclusion:
In the conventional hospital-centric healthcare system, patients are often tethered to several monitors. In this article, we develop an inexpensive but flexible and scalable remote health status monitoring system that integrates the capabilities of the IoT and cloud technologies for remote monitoring of a patient’s health status. Through experimental analysis, we have shown that the proposed framework is scalable and energy-efficient with very high classification accuracy. We believe that the proposed work can address the healthcare spending challenges by substantially reducing inefficiency and waste as well as enabling patients to stay in their own homes and get the same or better care. We are currently implementing the proposed algorithm and testing it in a real-life environment. We are also extending the proposed work to include the privacy and security aspects.
References:
[1] www.cmos.gov, “Centers for Medicare and Medicaid Services, National Health Expenditures Projections 2011–2021”; https://www.cms.gov/research-statistics-data- and-systems/statistics-trends-and-reports/nationalhealthexpenddata/ downloads/proj2012.pdf, accessed: 04/10/2016.
[2] M. S. Hossain and G. Muhammad, “Cloud-Assisted Industrial Internet of Things (IIoT) — Enabled Framework for Health Monitoring,” Computer Networks, vol. 101, June 2016, pp. 192–202.
[3] B. Townsend and J. Abawajy, “Security Considerations for Wireless Carrier Agonistic Bio-Monitoring Systems,” Security and Privacy in Commun. Networks, vol. 164, Jan. 2016, pp. 725–37.
[4] S. Ghanavati, J. Abawajy, and D. Izadi, “An Alternative Sensor Cloud Architecture for Remote Patient HealthCare Monitoring and Analysis,” 2016 IEEE Int’l. Joint Conf. Neural Networks, 24–29 July 2016, Vancouver, Canada.
[5] M. M. Hassan et al., “A Multimedia Healthcare Data Sharing Approach through Cloud-Based Body Area Network,” Future Generation Computer Systems, vol. 66, Jan. 2017, pp. 48–58.
[6] K. Zhang et al., “Security and Privacy for Mobile Healthcare Networks: From a Quality of Protection Perspective,” IEEE Wireless Commun. Mag., vol. 22, no. 4, Aug. 2015, pp. 104–12.
[7] G. Fortino, D. Parisi, and V. Pirrone, “BodyCloud: A SaaS Approach for Community Body Sensor Networks,” Future Generation Computer Systems, vol. 35, June 2014, pp. 62–79.
[8] P. D. Kaur and I. Chana, “Cloud Based Intelligent System for Delivering Health Care as a Service,” Computer Methods and Programs in Biomedicine, vol. 113, no. 1, Jan. 2014, pp. 346–59.
[9] S. Luo, and B. Ren, “The Monitoring and Managing Application of Cloud Computing Based on Internet of Things,” Computer Methods and Programs in Biomedicine, vol. 130, July 2016, pp. 154–61.
[10] L. Yang et al., “People-Centric Service for mHealth of Wheelchair Users in Smart Cities,” Internet of Things Based on Smart Objects, Apr. 2014, pp. 163–79.