Edge Computing

Kumari, Khushbu; Sadasivam, G. Sudha; Dharani, D.; Niranjanamurthy, M.

doi:10.1201/9781003230946

Cited by 6 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where DBP is the diastolic blood pressure, SBP is the systolic blood pressure, and PP is the pulse pressure. This method is often more conducive to measuring MAP in most clinical settings as it offers a quick means of calculation if the blood pressure is known as discussed by Kumari et al [65]. Annotated dataset incorporating attributes as specified in Table 6.…”

Section: ) Detection Module A: Hypotensionmentioning

confidence: 99%

Design and Simulation of an Edge Compute Architecture for IoT-Based Clinical Decision Support System

Kumar,

Rajaram

2024

IEEE Access

View full text Add to dashboard Cite

Clinical Decision Support Systems (CDSS) have revolutionized healthcare by leveraging modern technologies such as internet of things (IoT), artificial intelligence (AI), predictive analysis, nanomedicine, and virtual & augmented reality. IoT-based CDSS is of interest in particular. In a hospital scenario, a patient's vital signs like heart rate, blood pressure, respiration rate, ECG, EEG etc. are monitored with the use of embedded sensor devices, also called smart medical devices. These devices collect real-time data which is relayed to a compute device where several algorithms are employed to perform computations on said data to arrive at a prognosis e.g. real-time onset of hypotension can be detected by running predictive algorithms on real-time blood pressure data. The computation in IoT-based CDSS is done predominantly on the cloud, wherein the real-time data collected is relayed to a centralized cloud server. However, latency is a major drawback in a cloud-based monitoring system. Increased latency is of greater concern in healthcare applications as the decision-making process is time-sensitive. Edge computing can potentially overcome this drawback, wherein computation is done on edge-network devices rather than the cloud. While edge computing for IoT-based CDSS has been explored in literature, there are gaps in their implementations. A majority of literature dealing with edge computing for IoT-based healthcare only demonstrates a single application and does not address the varying data acquisition rates for different vital signs. Each prognosis or diagnosis requires different subsets of vital signs, and the underlying algorithm uses different sizes of data e.g. detecting arrhythmia requires processing of ECG data which is a time series data, and detecting cardiovascular disease requires blood pressure, cholesterol and certain habits of the patient which are mostly single points of data. This paper explores the use of edge computing in CDSS, quantifies its performance with respect to number of devices, sense time interval or intertransmission rate, and the size of data, and proposes a unified IoT edge gateway architecture to combine multiple patterns of data and computation algorithms to achieve reduced latency and network utilization. Simulation results show that edge computing reduces the latency of decision by approximately 87 times, and the network utilization by 1.5 times. The results show the efficacy of edge computing for implementing IoT-based CDSS and also demonstrate scalability with regard to the number of devices and the size and intertransmission rate of data. INDEX TERMSEdge computing , smart healthcare, vital sign monitoring, Internet of things, Clinical Decision support system. I. INTRODUCTIONC LINICAL Decision Support Systems (CDSS) are used in healthcare to provide stakeholders of the healthcare system including doctors, nursing staff, and patients with information necessary to make efficient decisions [1]. A traditional CDSS is a software system which aids in clinicaldecision-making wherei...

show abstract

Section: ) Detection Module A: Hypotensionmentioning

confidence: 99%

Design and Simulation of an Edge Compute Architecture for IoT-Based Clinical Decision Support System

Kumar,

Rajaram

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recent technological advancements have paved the way for cost-effective parallelization solutions such as clusters, making them increasingly popular options across all sectors of computing, including high-performance applications where high-throughput and reliability are critical [16]. A computer cluster utilizes collections of interconnected computers combined collaboratively to achieve better computational processing efficiency than traditional single device platforms [17]. A cluster is defined as a collection of nodes, each having independent control over stand-alone workloads while collaborating in real-time with others via high-speed local-area networks [18].…”

Section: Cluster Computingmentioning

confidence: 99%

Optimizing Clustering Approaches in Cloud Environments

Al-Ghuwairi,

Al-Fraihat,

Sharrab

et al. 2023

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments.

show abstract

MEHE based Prediction of Health Condition using LBM in Edge Computing Systems

Kumari

Roshini

2022

2022 3rd International Conference for Emerging Technology (INCET)

View full text Add to dashboard Cite

Edge Computing

Cited by 6 publications

References 0 publications

Design and Simulation of an Edge Compute Architecture for IoT-Based Clinical Decision Support System

Design and Simulation of an Edge Compute Architecture for IoT-Based Clinical Decision Support System

Optimizing Clustering Approaches in Cloud Environments

MEHE based Prediction of Health Condition using LBM in Edge Computing Systems

Contact Info

Product

Resources

About