Unleashing the power of edge-cloud generative ai in mobile networks: A survey of aigc services

M Xu, H Du, D Niyato, J Kang, Z Xiong… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
Artificial Intelligence-Generated Content (AIGC) is an automated method for generating,
manipulating, and modifying valuable and diverse data using AI algorithms creatively. This …

Edge computing and its role in Industrial Internet: Methodologies, applications, and future directions

T Zhang, Y Li, CLP Chen - Information Sciences, 2021 - Elsevier
Abstract Proliferation of Industrial Internet has dramatically changed the way we live and
work. It brings convenience to our society and sometimes requires real-time processing of …

Computation offloading and task scheduling for DNN-based applications in cloud-edge computing

Z Chen, J Hu, X Chen, J Hu, X Zheng, G Min - IEEE Access, 2020 - ieeexplore.ieee.org
Due to the high demands of deep neural network (DNN) based applications on
computational capability, it is hard for them to be directly run on mobile devices with limited …

Optimizing Inference Distribution for Efficient Kidney Tumor Segmentation Using a UNet-PWP Deep-Learning Model with XAI on CT Scan Images

PK Rao, S Chatterjee, M Janardhan, K Nagaraju… - Diagnostics, 2023 - mdpi.com
Kidney tumors represent a significant medical challenge, characterized by their often-
asymptomatic nature and the need for early detection to facilitate timely and effective …

An intelligent collaborative inference approach of service partitioning and task offloading for deep learning based service in mobile edge computing networks

X Li, Y Qin, H Zhou, Z Zhang - Transactions on Emerging …, 2021 - Wiley Online Library
As the rapid evolution of smart devices and real‐time applications, many new kinds of
computation‐intensive services have been emerged successively and the corresponding …

AI: Distributed Inference with Local Edge Devices and Minimal Latency

M Hemmat, A Davoodi, YH Hu - 2022 27th Asia and South …, 2022 - ieeexplore.ieee.org
We propose Edge^n AI, a framework to decompose a complex deep neural networks (DNN)
over n available local edge devices with minimal communication overhead and overall …

SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models

Y Li, Y Lu, Z Dong, C Yang, Y Chen, J Gou - arXiv preprint arXiv …, 2024 - arxiv.org
The deployment of Deep Neural Network (DNN)-based networks on resource-constrained
devices remains a significant challenge due to their high computational and parameter …

DISTINQT: A Distributed Privacy Aware Learning Framework for QoS Prediction for Future Mobile and Wireless Networks

N Koursioumpas, L Magoula, I Stavrakakis… - arXiv preprint arXiv …, 2024 - arxiv.org
Beyond 5G and 6G networks are expected to support new and challenging use cases and
applications that depend on a certain level of Quality of Service (QoS) to operate smoothly …

[HTML][HTML] Layer-wise partitioning and merging for efficient and scalable deep learning

SB Akintoye, L Han, H Lloyd, X Zhang… - Future Generation …, 2023 - Elsevier
Abstract Deep Neural Network (DNN) models are usually trained sequentially from one layer
to another, which causes forward, backward and update locking problems, leading to poor …

Scenario-aware program specialization for timing predictability

J Benz, O Bringmann - ACM Transactions on Architecture and Code …, 2021 - dl.acm.org
The successful application of static program analysis strongly depends on flow facts of a
program such as loop bounds, control-flow constraints, and operating modes. This problem …