Search results

Fog computing is a new field of research and has emerged as a complement to the cloud which can mitigate the problems inherent to the cloud computing model such as unreliable latency, bandwidth constraints, security and mobility. This paper aims to provide detailed survey in the field of fog computing covering the current state-of-the-art in fog computing.

Cloud was developed for IT and not for Internet of Things (IoT); as a result, cloud is unable to meet the computing, storage, control and networking demands of the IoT applications. Fog is a companion for the cloud and aims to extend the cloud capabilities to the edge of the network.

Lack of survey papers in the area of fog computing was an important motivational factor for writing this paper. This paper highlights the capabilities of the fog computing and where it fits in between IoT and cloud. This paper has also presented architecture of the fog computing model and its characteristics. Finally, the challenges in the field of fog computing have been discussed in detail which need to be overcome to realize its full potential.

This paper presents the current state-of-the-art in fog computing. Lack of such papers increases the importance of this paper. It also includes challenges and opportunities in the fog computing and various possible solutions to overcome those challenges.

The purpose of this study is to verify that if applications categories are segmented and resources are allocated based on their specific category, how effective scheduling can be done?.

This paper proposes a scheduling framework for IoT application jobs, based upon the Quality of Service (QoS) parameters, which works at coarse grained level to select a fog environment and at fine grained level to select a fog node. Fog environment is chosen considering availability, physical distance, latency and throughput. At fine grained (node selection) level, a probability triad (C, M, G) is anticipated using Naïve Bayes algorithm which provides probability of newly submitted application job to fall in either of the categories Compute (C) intensive, Memory (M) intensive and GPU (G) intensive.

Experiment results showed that the proposed framework performed better than traditional cloud and fog computing paradigms.

The proposed framework combines types of applications and computation capabilities of Fog computing environment, which is not carried out to the best of knowledge of authors.

This paper has proposed a Fog architecture-based framework, which classifies dengue patients into uninfected, infected and severely infected using a data set built in 2010. The aim of this proposed framework is to developed a latency-aware system for classifying users into different categories based on their respective symptoms using Internet of Things (IoT) sensors and audio and video files.

To achieve the aforesaid aim, a smart framework is proposed, which consist of three components, namely, IoT layer, Fog infrastructure and cloud computing. The latency of the system is reduced by using network devices located in the Fog infrastructure. Data generated by IoT layer will first be processed by Fog layer devices which are in closer proximity of the user. Raw data and data generated will later be stored on cloud infrastructure, from where it will be sent to different entities such as user, hospital, doctor and government healthcare agencies.

Experimental evaluation proved the hypothesis that using the Fog infrastructure can achieve better response time for latency sensitive applications with the least effect on accuracy of the system.

The proposed Fog-based architecture can be used with IoT to directly link it with the Fog layer.

Internet has changed radically in the way people interact in the virtual world, in their careers or social relationships. IoT technology has added a new vision to this process by enabling connections between smart objects and humans, and also between smart objects themselves, which leads to anything, anytime, anywhere, and any media communications. IoT allows objects to physically see, hear, think, and perform tasks by making them talk to each other, share information and coordinate decisions. To enable the vision of IoT, it utilizes technologies such as ubiquitous computing, context awareness, RFID, WSN, embedded devices, CPS, communication technologies, and internet protocols. IoT is considered to be the future internet, which is significantly different from the Internet we use today. The purpose of this paper is to provide up-to-date literature on trends of IoT research which is driven by the need for convergence of several interdisciplinary technologies and new applications.

A comprehensive IoT literature review has been performed in this paper as a survey. The survey starts by providing an overview of IoT concepts, visions and evolutions. IoT architectures are also explored. Then, the most important components of IoT are discussed including a thorough discussion of IoT operating systems such as Tiny OS, Contiki OS, FreeRTOS, and RIOT. A review of IoT applications is also presented in this paper and finally, IoT challenges that can be recently encountered by researchers are introduced.

Studies of IoT literature and projects show the disproportionate importance of technology in IoT projects, which are often driven by technological interventions rather than innovation in the business model. There are a number of serious concerns about the dangers of IoT growth, particularly in the areas of privacy and security; hence, industry and government began addressing these concerns. At the end, what makes IoT exciting is that we do not yet know the exact use cases which would have the ability to significantly influence our lives.

This survey provides a comprehensive literature review on IoT techniques, operating systems and trends.

The intelligence in the Internet of Things (IoT) can be embedded by analyzing the huge volumes of data generated by it in an ultralow latency environment. The computational latency incurred by the cloud-only solution can be significantly brought down by the fog computing layer, which offers a computing infrastructure to minimize the latency in service delivery and execution. For this purpose, a task scheduling policy based on reinforcement learning (RL) is developed that can achieve the optimal resource utilization as well as minimum time to execute tasks and significantly reduce the communication costs during distributed execution.

To realize this, the authors proposed a two-level neural network (NN)-based task scheduling system, where the first-level NN (feed-forward neural network/convolutional neural network [FFNN/CNN]) determines whether the data stream could be analyzed (executed) in the resource-constrained environment (edge/fog) or be directly forwarded to the cloud. The second-level NN ( RL module) schedules all the tasks sent by level 1 NN to fog layer, among the available fog devices. This real-time task assignment policy is used to minimize the total computational latency (makespan) as well as communication costs.

Experimental results indicated that the RL technique works better than the computationally infeasible greedy approach for task scheduling and the combination of RL and task clustering algorithm reduces the communication costs significantly.

The proposed algorithm fundamentally solves the problem of task scheduling in real-time fog-based IoT with best resource utilization, minimum makespan and minimum communication cost between the tasks.

The purpose of this paper is to perform a comparative analysis of the delay associated in running two real-time machine learning-based applications, namely, a video quality assessment (VQA) and a phishing detection application by using the edge, fog and cloud computing paradigms.

The VQA algorithm was developed using Android Studio and run on a mobile phone for the edge paradigm. For the fog paradigm, it was hosted on a Java server and for the cloud paradigm on the IBM and Firebase clouds. The phishing detection algorithm was embedded into a browser extension for the edge paradigm. For the fog paradigm, it was hosted on a Node.js server and for the cloud paradigm on Firebase.

For the VQA algorithm, the edge paradigm had the highest response time while the cloud paradigm had the lowest, as the algorithm was computationally intensive. For the phishing detection algorithm, the edge paradigm had the lowest response time, and the cloud paradigm had the highest, as the algorithm had a low computational complexity. Since the determining factor for the response time was the latency, the edge paradigm provided the smallest delay as all processing were local.

The main limitation of this work is that the experiments were performed on a small scale due to time and budget constraints.

A detailed analysis with real applications has been provided to show how the complexity of an application can determine the best computing paradigm on which it can be deployed.

The purpose of this study is to exploit the lowest common ancestor technique in an m-ary data aggregation tree in the fog computing-enhanced IoT to assist in contact tracing in COVID-19. One of the promising characteristics of the Internet of Things (IoT) that can be used to save the world from the current crisis of COVID-19 pandemic is data aggregation. As the number of patients infected by the disease is already huge, the data related to the different attributes of patients such as patient thermal image record and the previous health record of the patient is going to be gigantic. The authors used the technique of data aggregation to efficiently aggregate the sensed data from the patients and analyse it. Among the various inferences drawn from the aggregated data, one of the most important is contact tracing. Contact tracing in COVID-19 deals with finding out a person or a group of persons who have infected or were infected by the disease.

The authors propose to exploit the technique of lowest common ancestor in an m-ary data aggregation tree in the Fog-Computing enhanced IoT to help the health-care experts in contact tracing in a particular region or community. In this research, the authors argue the current scenario of COVID-19 pandemic, finding the person or a group of persons who has/have infected a group of people is of extreme importance. Finding the individuals who have been infected or are infecting others can stop the pandemic from worsening by stopping the community transfer. In a community where the outbreak has spiked, the samples from either all the persons or the patients showing the symptoms are collected and stored in an m-ary tree-based structure sorted over time.

Contact tracing in COVID-19 deals with finding out a person or a group of persons who have infected or were infected by the disease. The authors exploited the technique of lowest common ancestor in an m-ary data aggregation tree in the fog-computing-enhanced IoT to help the health-care experts in contact tracing in a particular region or community. The simulations were carried randomly on a set of individuals. The proposed algorithm given in Algorithm 1 is executed on the samples collected at level-0 of the simulation model, and to aggregate the data and transmit the data, the authors implement Algorithm 2 at the level-1. It is found from the results that a carrier can be easily identified from the samples collected using the approach designed in the paper.

The work presented in the paper can aid the health-care experts fighting the COVID-19 pandemic by reducing the community transfer with efficient contact tracing mechanism proposed in the paper.

Fighting COVID-19 efficiently and saving the humans from the pandemic has huge social implications in the current times of crisis.

To the best of the authors’ knowledge, the lowest common ancestor technique in m-ary data aggregation tree in the fog computing-enhanced IoT to contact trace the individuals who have infected or were infected during the transmission of COVID-19 is first of its kind proposed. Creating a graph or an m-ary tree based on the interactions/connections between the people in a particular community like location, friends and time, the authors can attempt to traverse it to find out who infected any two persons or a group of persons or was infected by exploiting the technique of finding out the lowest common ancestor in a m-ary tree.

Fog computing (FC) is a new field of research and has emerged as a complement to the cloud, which can mitigate the problems inherent to the cloud computing (CC) and internet of things (IoT) model such as unreliable latency, bandwidth constraints, security and mobility. Because there is no comprehensive study on the FC in health management processing systems techniques, this paper aims at surveying and analyzing the existing techniques systematically as well as offering some suggestions for upcoming works.

The paper complies with the methodological requirements of systematic literature reviews (SLR). The present paper investigates the newest systems and studies their practical techniques in detail. The applications of FC in health management systems have been categorized into three major groups, including review articles, data analysis, frameworks and models mechanisms.

The results have indicated that despite the popularity of FC as having real-time processing, low latency, dynamic configuration, scalability, low reaction time (less than a second), high bandwidth, battery life and network traffic, a few issues remain unanswered, such as security. The most recent research has focused on improvements in remote monitoring of the patients, such as less latency and rapid response. Also, the results have shown the application of qualitative methodology and case study in the use of FC in health management systems. While FC studies are growing in the clinical field, CC studies are decreasing.

This study aims to be comprehensive, but there are some limitations. This research has only surveyed the articles that are mined, according to a keyword exploration of FC health, FC health care, FC health big data and FC health management system. Fog-based applications in the health management system may not be published with determined keywords. Moreover, the publications written in non-English languages have been ignored. Some important research studies may be printed in a language other than English.

The results of this survey will be valuable for academicians, and these can provide visions into future research areas in this domain. This survey helps the hospitals and related industries to identify FC needs. Moreover, the disadvantages and advantages of the above systems have been studied, and their key issues have been emphasized to develop a more effective FC in health management processing mechanisms over IoT in the future.

Previous literature review studies in the field of SLR have used a simple literature review to find the tasks and challenges in the field. In this study, for the first time, the FC in health management processing systems is applied in a systematic review focused on the mediating role of the IoT and thereby provides a novel contribution. An SLR is conducted to find more specific answers to the proposed research questions. SLR helps to reduce implicit researcher bias. Through the adoption of broad search strategies, predefined search strings and uniform inclusion and exclusion criteria, SLR effectively forces researchers to search for studies beyond their subject areas and networks.

The distant data centre-centric Internet of Things (IoT) systems face the latency issue especially in the real-time-based applications, such as augmented reality, traffic analytics and ambient assisted living. Recently, Fog computing models have been introduced to overcome the latency issue by using the proximity-based computational resources, such as the computers co-located with the cellular base station, grid router devices or computers in local business. However, the increasing users of Fog computing servers cause bottleneck issues and consequently the latency issue arises again. This paper aims to introduce the utilisation of Mist computing (Mist) model, which exploits the computational and networking resources from the devices at the very edge of the IoT networks.

This paper proposes a service-oriented mobile-embedded Platform as a Service (mePaaS) framework that allows the mobile device to provide a flexible platform for proximal users to offload their computational or networking program to mePaaS-based Mist computing node.

The prototype has been tested and performance has been evaluated on the real-world devices. The evaluation results have shown the promising nature of mePaaS.

The proposed framework supports resource-aware autonomous service configuration that can manage the availability of the functions provided by the Mist node based on the dynamically changing hardware resource availability. In addition, the framework also supports task distribution among a group of Mist nodes.

Artificial Intelligence (AI) has surpassed expectations in opening up different possibilities for machines from different walks of life. Cloud service providers are pushing. Edge computing reduces latency, improving availability and saving bandwidth.

The exponential growth in tensor processing unit (TPU) and graphics processing unit (GPU) combined with different types of sensors has enabled the pairing of medical technology with deep learning in providing the best patient care. A significant role of pushing and pulling data from the cloud, big data comes into play as velocity, veracity and volume of data with IoT assisting doctors in predicting the abnormalities and providing customized treatment based on the patient electronic health record (EHR).

The primary focus of edge computing is decentralizing and bringing intelligent IoT devices to provide real-time computing at the point of presence (PoP). The impact of the PoP in healthcare gains importance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients. The impact edge computing of the PoP in healthcare gains significance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients.

The utility value of sensors data improves through the Laplacian mechanism of preserved PII response to each query from the ODL. The scalability is at 50% with respect to the sensitivity and preservation of the PII values in the local ODL.