Bringing Deep Learning at the Edge of Information-Centric Internet of Things

Khelifi, Hakima; Luo, Senlin; Nour, Boubakr; Sellami, Akrem; Moungla, Hassine; Ahmed, Syed Hassan; Guizani, Mohsen

doi:10.1109/lcomm.2018.2875978

Cited by 98 publications

(39 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various distributed AI and DL algorithms were proposed in distributed computing, cloud computing, fog computing, and edge computing environments to improve their performance and scalability [15][16][17][18][19][20]. In our previous work, we proposed a two-layer parallel CNN training architecture in a distributed computing cluster [15].…”

Section: Related Workmentioning

confidence: 99%

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Chen

Deng

et al. 2024

IEEE Trans. Ind. Inf.

184

View full text Add to dashboard Cite

In this paper, we propose a Distributed Intelligent Video Surveillance (DIVS) system using Deep Learning (DL) algorithms and deploy it in an edge computing environment. We establish a multi-layer edge computing architecture and a distributed DL training model for the DIVS system. The DIVS system can migrate computing workloads from the network center to network edges to reduce huge network communication overhead and provide low-latency and accurate video analysis solutions. We implement the proposed DIVS system and address the problems of parallel training, model synchronization, and workload balancing. Task-level parallel and model-level parallel training methods are proposed to further accelerate the video analysis process. In addition, we propose a model parameter updating method to achieve model synchronization of the global DL model in a distributed EC environment. Moreover, a dynamic data migration approach is proposed to address the imbalance of workload and computational power of edge nodes. Experimental results showed that the EC architecture can provide elastic and scalable computing power, and the proposed DIVS system can efficiently handle video surveillance and analysis tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Chen

Deng

et al. 2024

IEEE Trans. Ind. Inf.

184

View full text Add to dashboard Cite

show abstract

“…This will drastically enhance the content access/delivery during vehicles mobility. Moreover, applying deep learning and reinforcement learning approaches in vehicle mobility and the most frequently used content, can enhance the data delivery process [200]. Furthermore, ensuring a communication with high performance under wireless communication medium requires on-demand and advertised content retrieval support, with a careful study on the negativity effects of mobility.…”

Section: Mobilitymentioning

confidence: 99%

Named Data Networking in Vehicular Ad Hoc Networks: State-of-the-Art and Challenges

Khelifi

Luo

Nour

et al. 2020

IEEE Commun. Surv. Tutorials

Self Cite

253

121

View full text Add to dashboard Cite

Information-Centric Networking (ICN) has been proposed as one of the future Internet architectures. It is poised to address the challenges faced by today's Internet that include, but not limited to, scalability, addressing, security, and privacy. Furthermore, it also aims at meeting the requirements for new emerging Internet applications. To realize ICN, Named Data Networking (NDN) is one of the recent implementations of ICN that provides a suitable communication approach due to its clean slate design and simple communication model. There are a plethora of applications realized through ICN in different domains where data is the focal point of communication. One such domain is Intelligent Transportation System (ITS) realized through Vehicular Ad hoc NETwork (VANET) where vehicles exchange information and content with each other and with the infrastructure. To date, excellent research results have been yielded in the VANET domain aiming at safe, reliable, and infotainment-rich driving experience. However, due to the dynamic topologies, host-centric model, and ephemeral nature of vehicular communication, various challenges are faced by VANET that hinder the realization of successful vehicular networks and adversely affect the data dissemination, content delivery, and user experiences. To fill these gaps, NDN has been extensively used as underlying communication paradigm for VANET. Inspired by the extensive research results in NDN-based VANET, in this paper, we provide a detailed and systematic review of NDN-driven VANET. More precisely, we investigate the role of NDN in VANET and discuss the feasibility of NDN architecture in VANET environment. Subsequently, we cover in detail, NDN-based naming, routing and forwarding, caching, mobility, and security mechanism for VANET. Furthermore, we discuss the existing standards, solutions, and simulation tools used in NDN-based VANET. Finally, we also identify open challenges and issues faced by NDN-driven VANET and highlight future research directions that should be addressed by the research community.

show abstract

“…A Mobile and Edge Computing (M/EC) solution was proposed in [9] to bring computation near the IoT end-nodes by applying CNNs, RNNs and RL at the edge of IoT networks. The very idea of this work is to implement Information-Centric Networking on top of the IoT via some techniques namely shared weights, pooling, and in-network caching to solve storage issues on IoT nodes.…”

Section: A Learning Algorithms For Constrained Environmentsmentioning

confidence: 99%

Machine Learning based Access Control Framework for the Internet of Things

Outchakoucht¹,

Kalam²,

Es-Samaali³

et al. 2020

IJACSA

View full text Add to dashboard Cite

The main challenge facing the Internet of Things (IoT) in general, and IoT security in particular, is that humans have never handled such a huge amount of nodes and quantity of data. Fortunately, it turns out that Machine Learning (ML) systems are very effective in the presence of these two elements. However, can IoT devices support ML techniques? In this paper, we investigated this issue and proposed a twofold contribution: a thorough study of the IoT paradigm and its intersections with ML from a security perspective; then, we actually proposed a holistic ML-based framework for access control, which is the defense head of recent IT systems. In addition to learning techniques, this second pillar was based on the organization and attribute concepts to avoid role explosion problems and applied to a smart city case study to prove its effectiveness.

show abstract

Bringing Deep Learning at the Edge of Information-Centric Internet of Things

Cited by 98 publications

References 14 publications

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Named Data Networking in Vehicular Ad Hoc Networks: State-of-the-Art and Challenges

Machine Learning based Access Control Framework for the Internet of Things

Contact Info

Product

Resources

About