Edge-Cloud Computing for IoT Data Analytics: Embedding Intelligence in the Edge with Deep Learning

Ghosh, Ananda Mohon; Grolinger, Katarina

doi:10.1109/tii.2020.3008711

Cited by 91 publications

(66 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research to deploy computationally expensive DL models on edge nodes is still being conducted [94]- [96]. This calls for another potential architecture that involves the edge and the cloud for implementation.…”

Section: ) Observations On Device-edge Architecturementioning

confidence: 99%

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

Hafeez

McArdle

2021

IEEE Access

View full text Add to dashboard Cite

The use of IoT has become pervasive and IoT devices are common in many domains. Industrial IoT (IIoT) utilises IoT devices and sensors to monitor machines and environments to ensure optimal performance of equipment and processes. Predictive Maintenance (PM) which monitors the health of machines to determine the probable failure of components is one IIoT technique which is receiving attention lately. To achieve effective PM, massive amounts of data are collected, processed and ultimately analysed by Machine Learning (ML) algorithms. Traditionally IoT sensors transmit their data readings to the cloud for processing and modelling. Handling and transmitting massive amounts of data between IoT devices and infrastructure has a cost. Edge Computing (EC) in which both sensors and intermediate nodes can process data provides opportunities to reduce data transmission costs and increase processing speed. This article examines IIoT for PM and discusses how and where data can be processed and analysed. Initially, this article presents sampling and data reduction techniques. These techniques allow for a reduction in the amount of data transmitted to the cloud for processing but there are potential accuracy trade-offs when ML algorithms utilise reduced datasets. An alternative approach is to move ML algorithms closer to the data to reduce data transmission. There are three main techniques that utilise the EC paradigm to perform ML and data processing on intermediary nodes. These techniques are categorized according to where data processing occurs: Device and Edge, Edge and Cloud and Device and Cloud (Federated Learning). In addition to exploring traditional approaches, these three state-of-the-art techniques are examined in this article and their benefits and weaknesses are presented. A novel architecture to demonstrate how EC can be utilized both for data reduction and PM in IIoT is also proposed.

show abstract

Section: ) Observations On Device-edge Architecturementioning

confidence: 99%

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

Hafeez

McArdle

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…ii) The methodology ensured the integrity and privacy of data albeit there were countless collusive and sophisticated attackers who could take control over the device. Ghosh & Grolinger (2021) have presented the edgecloud computing for Internet of Things based Data Analytics review. Here the embedded intelligence approach for the Edge cloud is performed based on Deep Learning approach.…”

Section: Literature Reviewmentioning

confidence: 99%

An Optimized Deep Learning Based Security Enhancement and Attack Detection on IoT Using IDS and KH-AES for Smart Cities

Duraisamy¹,

Subramaniam²,

Robin³

2021

STUD INFORM CONTROL

View full text Add to dashboard Cite

Today, smart cities are being built with the wide deployment of the Internet of Things (IoT). Smart cities (SCs) set out in real time to ameliorate the quality of human life in respect of efficiency and comfort. Security along with privacy are the main issues in most SCs. The IoT-centric frameworks impose certain security threats on smart city applications as they are susceptible to security issues. On this account, an Intrusion Detection System (IDS) is requisite for mitigating the IoTassociated security attacks which take advantage of certain security vulnerabilities. The aim of this paper is to improve the security and attack detection rate as early as possible. In existing works, the accuracy of the attack detection rate and security are the main challenge. To overcome any drawbacks, this work proposes an IDS for detecting the IoT attacks in a city centered on the DLMNN classification. First, the sensor values from a SC are sent to the IDS system (the training phase), which is utilized for testing the respective values. Next, the preprocessing step is performed, and then feature selection (FS) is carried out with the utilization of the Entropy-HOA method. Further on, the classification using DLMNN is performed for detecting the IoT attacks. Then, the results of the classification are analyzed and the attack is identified. Next, a secure data sharing task is performed by using the KH-AES algorithm. Last, the resulting data is forecast. The weights for each layer of the DLMNN have a high impact on the classifier's output. The comparison of the existing technique and of the proposed technique with regard to FS, classification and secure data sharing reveals that the proposed technique obtained the best results.

show abstract

“…Meanwhile, CEC can collaboratively handle tasks, such as computation offloading through social networks and connections among users. CEC is a crucial technique for SIoT based on edge computing, which provides connections for users with low latency, high bandwidth, and high reliability [8], [9]. For instance, it can support high-quality communications for vehicles to implement unmanned driving [10], [11] and intelligent transportation system [12], [13].…”

Section: Introductionmentioning

confidence: 99%

“…However, CEC migrates the users' private information to network edge from data centers. In this case, it is much easier for attackers to steal the privacy of users by taking advantage of the vulnerability of edge nodes [8], [14]. The general environment of SIoTs based on collaborative edge networks is shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Detection for Secure Social Internet of Things Based on Collaborative Edge Computing: A Generative Adversarial Network-Based Approach

Nie

Wang

et al. 2022

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

The Social Internet of Things (SIoT) now penetrates our daily lives. As a strategy to alleviate the escalation of resource congestion, collaborative edge computing (CEC) has become a new paradigm for solving the needs of the Internet of Things (IoT). CEC can provide computing, storage, and network connection resources for remote devices. Because the edge network is closer to the connected devices, it involves a large amount of users' privacy. This also makes edge networks face more and more security issues, such as Denial-of-Service (DoS) attacks, unauthorized access, packet sniffing, and man-inthe-middle attacks. To combat these issues and enhance the security of edge networks, we propose a deep learning-based intrusion detection algorithm. Based on the generative adversarial network (GAN), we designed a powerful intrusion detection method. Our intrusion detection method includes three phases. First, we use the feature selection module to process the collaborative edge network traffic. Second, a deep learning architecture based on GAN is designed for intrusion detection aiming at a single attack. Finally, we propose a new intrusion detection model by combining several intrusion detection models that aim at a single attack. Intrusion detection aiming at multiple attacks is realized through the designed GAN-based deep learning architecture. Besides, we provide a comprehensive evaluation to verify the effectiveness of the proposed method. Index Terms-Collaborative edge computing (CEC), generative adversarial network (GAN), intrusion detection, social internet of things (SIoT).

show abstract

Edge-Cloud Computing for IoT Data Analytics: Embedding Intelligence in the Edge with Deep Learning

Cited by 91 publications

References 31 publications

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

An Optimized Deep Learning Based Security Enhancement and Attack Detection on IoT Using IDS and KH-AES for Smart Cities

Intrusion Detection for Secure Social Internet of Things Based on Collaborative Edge Computing: A Generative Adversarial Network-Based Approach

Contact Info

Product

Resources

About