Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications

With the exponential growth of the Internet of things (IoT) in remote sensing image applications, network resource orchestration and data privacy are significant aspects to handle in bigdata cellular networks. The image data sharing procedure toward central cloud servers in order to perform real-tim...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Prohim Tam, Sa Math, Chaebeen Nam, Seokhoon Kim
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Convolutional neural networks (CNN) deep q-learning (DQL) federated learning (FL) quality of service (QoS) real-time image classifications Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/d4fbb6f14bb64e78a81101f8fc2a147f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d4fbb6f14bb64e78a81101f8fc2a147f
record_format	dspace
spelling	oai:doaj.org-article:d4fbb6f14bb64e78a81101f8fc2a147f2021-11-18T00:00:14ZAdaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications2151-153510.1109/JSTARS.2021.3120724https://doaj.org/article/d4fbb6f14bb64e78a81101f8fc2a147f2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9580651/https://doaj.org/toc/2151-1535With the exponential growth of the Internet of things (IoT) in remote sensing image applications, network resource orchestration and data privacy are significant aspects to handle in bigdata cellular networks. The image data sharing procedure toward central cloud servers in order to perform real-time classifications has leaked client personalization and heavily burdened the communication networks. Thus, the deployment of IoT image sensors in privacy-constrained sectors requires an optimized federated learning (FL) scheme to efficiently consider both aspects of securing data privacy and maximizing the model accuracy with sufficient communication and computation resources. In this article, an adaptive model communication scheme with virtual resource optimization for edge FL is proposed by converging a deep q-learning algorithm to enforce a self-learning agent interacting with network functions virtualization orchestrator and software-defined networking based architecture. The agent targets to optimize the resource control policy of virtual multi-access edge computing entities in virtualized infrastructure manager. The proposed scheme trains the learning model and weighs the optimal actions for particular network states by using an epsilon-greedy strategy. In the exploitation phase, the scheme considers multiple spatial-resolution sensing conditions and allocates computation offloading resources for global multiconvolutional neural networks model aggregation based on the congestion states. In the simulation results, the quality of service and global collaborative model performance metrics were evaluated in terms of delay, packet drop ratios, packet delivery ratios, loss values, and overall accuracy.Prohim TamSa MathChaebeen NamSeokhoon KimIEEEarticleConvolutional neural networks (CNN)deep q-learning (DQL)federated learning (FL)quality of service (QoS)real-time image classificationsOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 10929-10940 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Convolutional neural networks (CNN) deep q-learning (DQL) federated learning (FL) quality of service (QoS) real-time image classifications Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Convolutional neural networks (CNN) deep q-learning (DQL) federated learning (FL) quality of service (QoS) real-time image classifications Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Prohim Tam Sa Math Chaebeen Nam Seokhoon Kim Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
description	With the exponential growth of the Internet of things (IoT) in remote sensing image applications, network resource orchestration and data privacy are significant aspects to handle in bigdata cellular networks. The image data sharing procedure toward central cloud servers in order to perform real-time classifications has leaked client personalization and heavily burdened the communication networks. Thus, the deployment of IoT image sensors in privacy-constrained sectors requires an optimized federated learning (FL) scheme to efficiently consider both aspects of securing data privacy and maximizing the model accuracy with sufficient communication and computation resources. In this article, an adaptive model communication scheme with virtual resource optimization for edge FL is proposed by converging a deep q-learning algorithm to enforce a self-learning agent interacting with network functions virtualization orchestrator and software-defined networking based architecture. The agent targets to optimize the resource control policy of virtual multi-access edge computing entities in virtualized infrastructure manager. The proposed scheme trains the learning model and weighs the optimal actions for particular network states by using an epsilon-greedy strategy. In the exploitation phase, the scheme considers multiple spatial-resolution sensing conditions and allocates computation offloading resources for global multiconvolutional neural networks model aggregation based on the congestion states. In the simulation results, the quality of service and global collaborative model performance metrics were evaluated in terms of delay, packet drop ratios, packet delivery ratios, loss values, and overall accuracy.
format	article
author	Prohim Tam Sa Math Chaebeen Nam Seokhoon Kim
author_facet	Prohim Tam Sa Math Chaebeen Nam Seokhoon Kim
author_sort	Prohim Tam
title	Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
title_short	Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
title_full	Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
title_fullStr	Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
title_full_unstemmed	Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
title_sort	adaptive resource optimized edge federated learning in real-time image sensing classifications
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/d4fbb6f14bb64e78a81101f8fc2a147f
work_keys_str_mv	AT prohimtam adaptiveresourceoptimizededgefederatedlearninginrealtimeimagesensingclassifications AT samath adaptiveresourceoptimizededgefederatedlearninginrealtimeimagesensingclassifications AT chaebeennam adaptiveresourceoptimizededgefederatedlearninginrealtimeimagesensingclassifications AT seokhoonkim adaptiveresourceoptimizededgefederatedlearninginrealtimeimagesensingclassifications
_version_	1718425253123719168

Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications

Ejemplares similares