Mobile edge intelligence and computing for the internet of vehicles
J Zhang, KB Letaief - Proceedings of the IEEE, 2019 - ieeexplore.ieee.org
The Internet of Vehicles (IoV) is an emerging paradigm that is driven by recent
advancements in vehicular communications and networking. Meanwhile, the capability and …
advancements in vehicular communications and networking. Meanwhile, the capability and …
Architecting AI deployment: A systematic review of state-of-the-art and state-of-practice literature
Companies across domains are rapidly engaged in shifting computational power and
intelligence from centralized cloud to fully decentralized edges to maximize value delivery …
intelligence from centralized cloud to fully decentralized edges to maximize value delivery …
Pruning edge research with latency shears
Edge computing has gained attention from both academia and industry by pursuing two
significant challenges: 1) moving latency critical services closer to the users, 2) saving …
significant challenges: 1) moving latency critical services closer to the users, 2) saving …
Secure edge computing-assisted video reporting service in 5G-enabled vehicular networks
Since traffic accidents occur frequently, a real-time video traffic reporting service is
necessary in vehicular networks for a prompt response to accidents. Although the fifth …
necessary in vehicular networks for a prompt response to accidents. Although the fifth …
Dyno: Dynamic onloading of deep neural networks from cloud to device
Recently, there has been an explosive growth of mobile and embedded applications using
convolutional neural networks (CNNs). To alleviate their excessive computational demands …
convolutional neural networks (CNNs). To alleviate their excessive computational demands …
Synergistically exploiting cnn pruning and hls versioning for adaptive inference on multi-fpgas at the edge
FPGAs, because of their energy efficiency, reconfigurability, and easily tunable HLS
designs, have been used to accelerate an increasing number of machine learning …
designs, have been used to accelerate an increasing number of machine learning …
RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition
Y Hu, Y Cheng, Z Zhou, Z Cao, A Lu… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
Deploying compute-intensive deep neural networks (DNNs) on resource-constrained end
devices has become a prominent trend, enabling localized intelligence. However, efficiently …
devices has become a prominent trend, enabling localized intelligence. However, efficiently …
How to reach real-time AI on consumer devices? Solutions for programmable and custom architectures
The unprecedented performance of deep neural networks (DNNs) has led to large strides in
various Artificial Intelligence (AI) inference tasks, such as object and speech recognition …
various Artificial Intelligence (AI) inference tasks, such as object and speech recognition …
Quantifying the latency benefits of near-edge and in-network FPGA acceleration
RA Cooke, SA Fahmy - Proceedings of the Third ACM International …, 2020 - dl.acm.org
Transmitting data to cloud datacenters in distributed IoT applications introduces significant
communication latency, but is often the only feasible solution when source nodes are …
communication latency, but is often the only feasible solution when source nodes are …
Edge AI Inference in Heterogeneous Constrained Computing: Feasibility and Opportunities
The network edge's role in Artificial Intelligence (AI) inference processing is rapidly
expanding, driven by a plethora of applications seeking computational advantages. These …
expanding, driven by a plethora of applications seeking computational advantages. These …