4.6 Article

Genetic Algorithm-Based Online-Partitioning BranchyNet for Accelerating Edge Inference

Related references

Note: Only part of the references are listed.
Article Computer Science, Theory & Methods

Non-cooperative game algorithms for computation offloading in mobile edge computing environments

Jianguo Chen et al.

Summary: This paper discusses the Quality-of-Experience (QoE) of User Equipment (UE) in 5G Mobile Edge Computing (MEC) systems and proposes two algorithms for computation offloading. The algorithms aim to minimize energy consumption and time delay by considering the QoE requirements of UEs. Through simulation experiments, it is shown that the proposed algorithms efficiently find the Nash Equilibrium (NE) solutions in MEC scenarios.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2023)

Article Computer Science, Information Systems

Distributed CNN Inference on Resource-Constrained UAVs for Surveillance Systems: Design and Optimization

Mohammed Jouhari et al.

Summary: The article proposes a method for distributing DNNs within UAVs to enable data classification on resource-constrained devices, and avoid delays introduced by server-based solutions. The simulation results showed that the optimization solution outperformed existing approaches.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Chemistry, Multidisciplinary

Partitioning DNNs for Optimizing Distributed Inference Performance on Cooperative Edge Devices: A Genetic Algorithm Approach

Jun Na et al.

Summary: To fully utilize the potential of edge devices, this paper proposes a layer-based DNN partitioning approach and an improved genetic algorithm to address the problem. Experimental results show that the proposed algorithm can achieve faster running time and better deployment performance.

APPLIED SCIENCES-BASEL (2022)

Proceedings Paper Computer Science, Cybernetics

Pyramid: Enabling Hierarchical Neural Networks with Edge Computing

Qiang He et al.

Summary: Machine learning is widely used in web applications and edge computing plays a crucial role in enabling low-latency inference for delay-sensitive web applications. However, the potential of edge computing for building smart cities through context-aware data processing has not been fully explored. In this paper, a novel framework called Pyramid is proposed to unleash the potential of edge AI through hierarchical ML inference. The results demonstrate superior performance in traffic prediction and weather analysis.

PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22) (2022)

Article Chemistry, Analytical

Mobility-Included DNN Partition Offloading from Mobile Devices to Edge Clouds

Xianzhong Tian et al.

Summary: The study compared the performance of local, edge cloud, and MDPO algorithm in DNN computation execution, finding that MDPO significantly reduces total latency and improves performance, adapting well to different network conditions.

SENSORS (2021)

Article Computer Science, Information Systems

Joint Optimization With DNN Partitioning and Resource Allocation in Mobile Edge Computing

Chongwu Dong et al.

Summary: With the advancement of artificial intelligence and edge computing, the proliferation of intelligent IoT devices brings both conveniences and challenges. When dealing with intelligent tasks, the partition strategy of deep neural network models and the cost-effective resource allocation are key factors.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2021)

Article Computer Science, Information Systems

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Xin Tang et al.

Summary: Mobile-edge computing (MEC) serves as a promising architecture supporting edge intelligence services by providing resources to the network edge. Optimizing DNN partitioning and resource allocation in a multiuser resource-constrained environment is a key research area.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Computer Science, Information Systems

An Energy-Efficient Fine-Grained Deep Neural Network Partitioning Scheme for Wireless Collaborative Fog Computing

Emre Kilcioglu et al.

Summary: Fog computing offers a potential solution for collaboration among resource-constrained mobile devices in running deep learning applications, which improves delay performance and reduces the need for powerful servers compared to mobile cloud computing.

IEEE ACCESS (2021)

Article Engineering, Electrical & Electronic

Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing

En Li et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2020)

Proceedings Paper Computer Science, Hardware & Architecture

Distributed Inference Acceleration with Adaptive DNN Partitioning and Offloading

Thaha Mohammed et al.

IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (2020)

Proceedings Paper Computer Science, Hardware & Architecture

Partition Pruning: Parallelization-Aware Pruning for Dense Neural Networks

Sina Shahhosseini et al.

2020 28TH EUROMICRO INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED AND NETWORK-BASED PROCESSING (PDP 2020) (2020)

Article Computer Science, Information Systems

Joint DNN Partition Deployment and Resource Allocation for Delay-Sensitive Deep Learning Inference in IoT

Wenchen He et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Article Computer Science, Information Systems

AAIoT: Accelerating Artificial Intelligence in IoT Systems

Jingyue Zhou et al.

IEEE WIRELESS COMMUNICATIONS LETTERS (2019)

Proceedings Paper Computer Science, Hardware & Architecture

ADDA: Adaptive Distributed DNN Inference Acceleration in Edge Computing Environment

Huitian Wang et al.

2019 IEEE 25TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS) (2019)

Article Computer Science, Hardware & Architecture

DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge Clusters

Zhuoran Zhao et al.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2018)

Proceedings Paper Computer Science, Theory & Methods

Real-Time Image Recognition Using Collaborative IoT Devices

Ramyad Hadidi et al.

1ST ACM REQUEST WORKSHOP/TOURNAMENT ON REPRODUCIBLE SOFTWARE/HARDWARE CO-DESIGN OF PARETO-EFFICIENT DEEP LEARNING (2018)

Article Computer Science, Artificial Intelligence

The cascading neural network: building the Internet of Smart Things

Sam Leroux et al.

KNOWLEDGE AND INFORMATION SYSTEMS (2017)

Article Computer Science, Hardware & Architecture

Energy-Efficient and Improved Image Recognition with Conditional Deep Learning

Priyadarshini Panda et al.

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS (2017)