EdgeAl: A Vision for Deep Learning in the IoT Era

Bhardwaj, Kartikeya; Suda, Naveen; Mărculescu, Radu

doi:10.1109/mdat.2019.2952350

Cited by 13 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI-enabled IoT devices are paving the way to implement new and increasingly complex cyber-physical systems (CPS) in distinct application domains [93][94][95]. The increasing complexity of such devices is typically specified based on SWaP requirements (i.e., reduced Size, Weight, and Power) [96].…”

Section: Ai-enabled Iot Hardwarementioning

confidence: 99%

Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case

Fraga‐Lamas

Lopes

Fernández‐Caramés

2021

Sensors

200

View full text Add to dashboard Cite

Internet of Things (IoT) can help to pave the way to the circular economy and to a more sustainable world by enabling the digitalization of many operations and processes, such as water distribution, preventive maintenance, or smart manufacturing. Paradoxically, IoT technologies and paradigms such as edge computing, although they have a huge potential for the digital transition towards sustainability, they are not yet contributing to the sustainable development of the IoT sector itself. In fact, such a sector has a significant carbon footprint due to the use of scarce raw materials and its energy consumption in manufacturing, operating, and recycling processes. To tackle these issues, the Green IoT (G-IoT) paradigm has emerged as a research area to reduce such carbon footprint; however, its sustainable vision collides directly with the advent of Edge Artificial Intelligence (Edge AI), which imposes the consumption of additional energy. This article deals with this problem by exploring the different aspects that impact the design and development of Edge-AI G-IoT systems. Moreover, it presents a practical Industry 5.0 use case that illustrates the different concepts analyzed throughout the article. Specifically, the proposed scenario consists in an Industry 5.0 smart workshop that looks for improving operator safety and operation tracking. Such an application case makes use of a mist computing architecture composed of AI-enabled IoT nodes. After describing the application case, it is evaluated its energy consumption and it is analyzed the impact on the carbon footprint that it may have on different countries. Overall, this article provides guidelines that will help future developers to face the challenges that will arise when creating the next generation of Edge-AI G-IoT systems.

show abstract

Section: Ai-enabled Iot Hardwarementioning

confidence: 99%

Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case

Fraga‐Lamas

Lopes

Fernández‐Caramés

2021

Sensors

200

View full text Add to dashboard Cite

show abstract

“…Therefore, compressing models must not only account for hardware constraints, but also for the communication costs resulting from distributed inference. In other words, since IoT consists of connected devices, this massive network must be exploited to obtain true edge intelligence [5].…”

Section: Data Privacy and Network Of Devices In Regards To Trainingmentioning

confidence: 99%

“…When deep learning models are trained on private datasets, the industries trying to deploy such models on edge devices cannot use the original datasets for model compression. Below, we describe our recent research targeting this problem [4], [5].…”

Section: Data-independent Model Compressionmentioning

confidence: 99%

“…In other words, the network of IoT devices must be exploited to improve the accuracy without increasing the communication latency. Towards this communication-aware model compression, we present our recent idea on Network-of-Neural Networks (NoNN) [3], [5].…”

Section: Communication-aware Model Compressionmentioning

confidence: 99%

“…From a deep learning standpoint, model compression aims to reduce the size of deep networks in order to meet the hardware constraints of IoT devices without sacrificing accuracy [8], [10], [12]. However, in practice, additional challenges like data privacy and network considerations often severely limit the widespread deployment of deep learning on IoT devices [5]. More specifically, the above fundamental challenges manifest themselves in training and inference, which are both integral parts of any learning-based system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design

Bhardwaj¹,

Chen²,

Mărculescu³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we first highlight three major challenges to large-scale adoption of deep learning at the edge: (i) Hardware-constrained IoT devices, (ii) Data security and privacy in the IoT era, and (iii) Lack of network-aware deep learning algorithms for distributed inference across multiple IoT devices. We then provide a unified view targeting three research directions that naturally emerge from the above challenges: (1) Federated learning for training deep networks, (2) Data-independent deployment of learning algorithms, and (3) Communicationaware distributed inference. We believe that the above research directions need a network-centric approach to enable the edge intelligence and, therefore, fully exploit the true potential of IoT.

show abstract

Edge AI prospect using the NeuroEdge computing system: Introducing a novel neuromorphic technology

et al. 2021

View full text Add to dashboard Cite

EdgeAl: A Vision for Deep Learning in the IoT Era

Cited by 13 publications

References 10 publications

Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case

Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case

New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design

Edge AI prospect using the NeuroEdge computing system: Introducing a novel neuromorphic technology

Contact Info

Product

Resources

About