AI-Enabled Framework for Fog Computing Driven E-Healthcare Applications

Abstract

Artificial Intelligence (AI) is the revolutionary paradigm to empower sixth generation (6G) edge computing based e-healthcare for everyone. Thus, this research aims to promote an AI-based cost-effective and efficient healthcare application. The cyber physical system (CPS) is a key player in the internet world where humans and their personal devices such as cell phones, laptops, wearables, etc., facilitate the healthcare environment. The data extracting, examining and monitoring strategies from sensors and actuators in the entire medical landscape are facilitated by cloud-enabled technologies for absorbing and accepting the entire emerging wave of revolution. The efficient and accurate examination of voluminous data from the sensor devices poses restrictions in terms of bandwidth, delay and energy. Due to the heterogeneous nature of the Internet of Medical Things (IoMT), the driven healthcare system must be smart, interoperable, convergent, and reliable to provide pervasive and cost-effective healthcare platforms. Unfortunately, because of higher power consumption and lesser packet delivery rate, achieving interoperable, convergent, and reliable transmission is challenging in connected healthcare. In such a scenario, this paper has fourfold major contributions. The first contribution is the development of a single chip wearable electrocardiogram (ECG) with the support of an analog front end (AFE) chip model (i.e., ADS1292R) for gathering the ECG data to examine the health status of elderly or chronic patients with the IoT-based cyber physical system (CPS). The second proposes a fuzzy-based sustainable, interoperable, and reliable algorithm (FSIRA), which is an intelligent and self-adaptive decision-making approach to prioritize emergency and critical patients in association with the selected parameters for improving healthcare quality at reasonable costs. The third is the proposal of a specific cloud-based architecture for mobile and connected healthcare. The fourth is the identification of the right balance between reliability, packet loss ratio, convergence, latency, interoperability, and throughput to support an adaptive IoMT driven connected healthcare. It is examined and observed that our proposed approaches outperform the conventional techniques by providing high reliability, high convergence, interoperability, and a better foundation to analyze and interpret the accuracy in systems from a medical health aspect. As for the IoMT, an enabled healthcare cloud is the key ingredient on which to focus, as it also faces the big hurdle of less bandwidth, more delay and energy drain. Thus, we propose the mathematical trade-offs between bandwidth, interoperability, reliability, delay, and energy dissipation for IoMT-oriented smart healthcare over a 6G platform.

The future of care and healthcare provision to communitydwelling disa-bled elderly people in an ageing society

“…As access to the Internet is virtually ubiquitous in developed countries thanks to numerous data transmission technologies, both wire-dependent and wireless, the limiting factor for IoT based solutions becomes end user acceptance and digital competence, which are often limited in case of the elderly [17]. The traditional data transmission limitations of bandwidth, delay, and energy pose much smaller and more surmountable obstacles [18]. This demands urgent innovations capable of breaking through the reluctance of the elderly to accept and use new technologies, both stationary products used at home and wearable devices (wearables) for when on the move [19], and finding workarounds to constraints in the form of additional cost, inconveniences, social constraints, or privacy issues by utilizing existing standard equipment, such as in the analysis of wi-Fi signal equivalents for the movement of people [20] or even smart TV usage [21].…”

Efficient Use of Biological Data in the Web 3.0 Era by Applying Nonfungible Token Technology

“…Perhaps biobanks could be a foundational platform for the convenient sharing of all health care data in the Web 3.0 era. In addition to clinical and experimental data, remote monitoring of health and epidemiology data generated by wearable devices, implanted microchips, and the internet of things will be incorporated into storage and management [ 34 ].…”

Latency-Aware Task Scheduling for IoT Applications Based on Artificial Intelligence with Partitioning in Small-Scale Fog Computing Environments

“…Recently, various techniques based on artificial intelligence for fog computing resource and task management have been proposed [ 12 , 13 ]. The state-of-the-art studies for fog resource and task management proved that adopting artificial intelligence and related techniques (including artificial neural networks and reinforcement learning) is promising [ 14 , 15 ].…”