EdgeOptimizer: A programmable containerized scheduler of time-critical tasks in Kubernetes-based edge-cloud clusters

Y Qiao, S Shen, C Zhang, W Wang, T Qiu… - Future Generation …, 2024 - Elsevier
Edge computing has garnered significant attention in recent years, leading to the evolution
of more delay-sensitive applications towards a three-tier architecture with edge-cloud …

CRIMP: C ompact & R eliable DNN Inference on I nM emory P rocessing via Crossbar-Aligned Compression and Non-ideality Adaptation

S Huai, H Kong, X Luo, S Li, R Subramaniam… - ACM Transactions on …, 2023 - dl.acm.org
Crossbar-based In-Memory Processing (IMP) accelerators have been widely adopted to
achieve high-speed and low-power computing, especially for deep neural network (DNN) …

TinyCL: An Efficient Hardware Architecture for Continual Learning on Autonomous Systems

E Ressa, A Marchisio, M Martina, G Masera… - arxiv preprint arxiv …, 2024 - arxiv.org
The Continuous Learning (CL) paradigm consists of continuously evolving the parameters of
the Deep Neural Network (DNN) model to progressively learn to perform new tasks without …

EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems

S Huai, H Kong, S Li, X Luo… - IEEE Embedded …, 2023 - ieeexplore.ieee.org
Edge devices are increasingly utilized for deploying deep learning applications on
embedded systems. The real-time nature of many applications and the limited resources of …

Resource Management in Edge Clouds: Latency-Aware Approaches for Big Data Analysis

AHJ Pozveh, HS Shahhoseini, E Khabareh - Resource Management in …, 2024 - Springer
The growing demand for time-sensitive services has led to the necessity for effective
resource management strategies in edge clouds. These strategies are tailored to handle …

IoT-based Real-time Passenger Safety System with Machine Vision at the Edge (Mez) Technology.

AA Alawad, MT Chughtai - Przeglad Elektrotechniczny, 2023 - search.ebscohost.com
Passenger safety is a critical issue in the transportation industry. There is an additional
concern for children's safety with other regular issues. And that is the risk of having accidents …

Enabling efficient edge intelligence: a hardware-software codesign approach

S Huai - 2023 - dr.ntu.edu.sg
Deep Neural Networks (DNNs) have made significant advancements in various domains,
including computer vision (CV), natural language processing (NLP), etc. With the Internet of …