Deep Learning for Edge Computing Applications: A State-of-the-Art Survey

Wang, Fangxin; Zhang, Miao; Wang, Xiangxiang; Ma, Xiaoqiang; Liu, Jiangchuan

doi:10.1109/access.2020.2982411

Cited by 128 publications

(57 citation statements)

References 146 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Where on one hand complex DL models are being developed, on the other hand, research on EC is accelerating to provide more computing resources to DL models to support more applications [71]. Various ready-to-use ML frameworks with EC are presented by the authors in [14].…”

Section: Edge Computing Based and Machine Learning Enabled Approachesmentioning

confidence: 99%

See 1 more Smart Citation

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: Edge Computing Based and Machine Learning Enabled Approachesmentioning

confidence: 99%

“…This comes from the fact that DL models are generally trained on the bulk of data and provide high accuracy. A review on deploying DL models on the edge is given in [71]. However, using reduced data to train these models requires further exploration.…”

Section: B Techniques Using Edge-cloud 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

“…Linear regression, k-nearest neighbor classifiers, and Q learning are some examples of DL. DL algorithms have the ability to hierarchically extract information from raw data using several layers of nonlinear processing units for making predictions or taking actions according to the target objective [10]. The network used in DL for learning is called a deep neural network (DNN), which is one kind of artificial neural network.…”

Section: Overview Of Deep Learningmentioning

confidence: 99%

“…Also, the discussion of the existing challenges and open research issues will provide a research direction to the current and future researchers in this field. Although several surveys have been conducted on the applications of DL for edge cellular networks [10]- [12], no survey exists in literature solely based on DL applications in C-RAN. In order to fill this gap in the literature, this survey provides a detailed review of the state-of-the-art applications of DL in C-RAN.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Applications of Deep Learning in Cloud Radio Access Network

Rodoshi

Choi

2021

IEEE Access

View full text Add to dashboard Cite

The necessity for high-speed and low-latency connectivity of the vast number of mobile users is rising with the immense usage of mobile applications. A cloud radio access network (C-RAN) is a promising framework for next-generation cellular communication, which can satisfy the requirements of significantly increasing data traffic and user demands. In C-RAN, the data processing unit can be centralized and virtualized in data centers and can be shared among distributed base stations. Deep learning (DL) appears to be a feasible approach for facilitating the data processing capability, resource management in the cloud, and predicting dynamic traffic in cellular communication. The convergence of C-RAN and DL is expected to bring new prospects to both interdisciplinary research and industrial applications. In this regard, different approaches have been proposed for DL-based C-RAN in the literature. This article provides a comprehensive survey of the state-of-the-art DL techniques applied in C-RAN. A brief introduction of the C-RAN architecture and DL techniques is given to provide insights into these two emerging technologies. Existing surveys are also discussed to highlight the research gap. The reviewed works are categorized into power consumption optimization, network performance maximization, and QoS maximization based on their optimization objectives. The key ideas of DL applied in the reviewed schemes are also mentioned, and the performance evaluation techniques used in the research are discussed and compared. Lastly, research challenges and open research issues are highlighted to provide future research directions.INDEX TERMS Cloud radio access network, deep learning, evaluation techniques, optimization objectives, performance metrics.

show abstract

“…Therefore, in view of analysis on above difficulties and requirements for health care system, and in combination with IoT [15], [16], Artificial Intelligence(AI) [17]- [19], edge computing [20], [21] and medical & health technology, a health and emotion management assistant for depression patients is proposed, called MEMO box system. The "MEMO" therein means "Medicine", "Emotion" and "Memory", and it expressed three health care goals for depression patients.…”

Section: Introductionmentioning

confidence: 99%

MEMO Box: Health Assistant for Depression With Medicine Carrier and Exercise Adjustment Driven by Edge Computing

et al. 2020

View full text Add to dashboard Cite

According to the report by the World Health Organization, depression, as the leading disabling disease in the world, has aroused widespread social concern. However, the shortage of medical and nursing staff in psychiatry conflicts with the rising nursing needs of depressed patients. First, depression is a chronic mental illness, its cure course is relatively long, and stable drug treatment and healthy living habits are keys to the curing process. Second, the disease feature where depression patients have stronger emotional needs and more sensitive mental states is ignored in existing health monitoring systems. In consideration of the above two aspects, a health management assistant is proposed in this paper, called MEMO box system, that focuses on emotion and with smart medicine box as carrier. Specifically, the MEMO box system is composed of electronic medicine box and smart applications on mobile device, and electronic medicine box can collect the multi-mode data of patients, including their medication behaviors, daily activities, physical exercise data, and so on, which provide data basis for the health assistant. Emotion recognition and exercise recommend algorithms are deployed in the edge cloud, which can quickly respond to health service requests from patients. With the cooperation of hardware and software in this system, patients are urged to take medicines on time to effectively control their conditions, and emotion cognition and exercise adjustment recommendation can be realized for depression patients, thus providing patients with empathic sports recommendations.

show abstract

Deep Learning for Edge Computing Applications: A State-of-the-Art Survey

Cited by 128 publications

References 146 publications

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

Edge Intelligence for Data Handling and Predictive Maintenance in IIOT

A Survey on Applications of Deep Learning in Cloud Radio Access Network

MEMO Box: Health Assistant for Depression With Medicine Carrier and Exercise Adjustment Driven by Edge Computing

Contact Info

Product

Resources

About