13 Hits in 1.1 sec

FastVA: Deep Learning Video Analytics Through Edge Processing and NPU in Mobile [article]

Tianxiang Tan, Guohong Cao
2020 arXiv   pre-print
Many mobile applications have been developed to apply deep learning for video analytics.  ...  on mobile devices.To address this issue, we propose a framework called FastVA, which supports deep learning video analytics through edge processing and Neural Processing Unit (NPU) in mobile.  ...  CONCLUSIONS In this paper, we proposed a framework called FastVA, which supports deep learning video analytics through edge processing and Neural Processing Unit (NPU) in mobile.  ... 
arXiv:2001.04049v1 fatcat:l4lkweukuje2lhxzc6lqcy2v7u


Zheng Yang, Xiaowu He, Jiaxing Wu, Xu Wang, Yi Zhao
2021 Scientia Sinica Informationis  
Deep learning with edge computing: a review. Proc IEEE, 2019, 107: 1655-1674 7 Mach P, Becvar Z. Mobile edge computing: a survey on architecture and computation offloading.  ...  Edge computing technologies for streaming video analytics (in Chinese).  ... 
doi:10.1360/ssi-2021-0133 fatcat:qs7jnvnknjhdrhfrru6rfbwuge

Multimedia Data Analysis With Edge Computing

Shu-Ching Chen
2021 IEEE Multimedia  
Chen, served during both the training and inference of the “DeepDecision: A mobile deep learning framework for models.  ...  edge video analytics,” in Proc. IEEE Conf. Comput.  ... 
doi:10.1109/mmul.2021.3124292 fatcat:kc6nmnnkvbhg3pbyzdqih4ns7y

Deep Learning on Mobile Devices Through Neural Processing Units and Edge Computing [article]

Tianxiang Tan, Guohong Cao
2021 arXiv   pre-print
To address the low accuracy problem, we propose a Confidence Based Offloading (CBO) framework for deep learning video analytics.  ...  Deep Neural Network (DNN) is becoming adopted for video analytics on mobile devices. To reduce the delay of running DNNs, many mobile devices are equipped with Neural Processing Units (NPU).  ...  Chen, “DeepDecision: A Mobile Deep Learning Framework for Edge Video Analytics,” IEEE INFOCOM, [2] A. Krizhevsky, I.  ... 
arXiv:2112.02439v1 fatcat:wh5kenqwqrelbijp24glf2dm6q

Deep Learning for Edge Computing Applications: A State-of-the-art Survey

Fangxin Wang, Miao Zhang, Xiangxiang Wang, Xiaoqiang Ma, Jiangchuan Liu
2020 IEEE Access  
In this article, we provide a comprehensive survey of the latest efforts on the deep-learning-enabled edge computing applications and particularly offer insights on how to leverage the deep learning advances  ...  Besides, the recent breakthroughs in deep learning have greatly facilitated the data processing capacity, enabling a thrilling development of novel applications, such as video surveillance and autonomous  ...  There are also a series of surveys for mobile edge computing [2] , [14] - [16] and deep learning [17] , [18] , respectively, while they focused on either of them without a comprehensive review on  ... 
doi:10.1109/access.2020.2982411 fatcat:43atfhktujbuxns2bsl2cfpnay

Extending reference architecture of big data systems towards machine learning in edge computing environments

P. Pääkkönen, D. Pakkala
2020 Journal of Big Data  
However, the utilisation of machine learning (ML) as part of the edge computing infrastructure is still an area for further research [8] .  ...  Findings: The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments.  ...  Juha-Pekka Soininen (VTT) is acknowledged for providing feedback to the development of the architectural views.  ... 
doi:10.1186/s40537-020-00303-y fatcat:6se2bbyprnfejezrzubyq4mv4e

Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang
2019 Proceedings of the IEEE  
We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge.  ...  | With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems  ...  video analytics.  ... 
doi:10.1109/jproc.2019.2918951 fatcat:d53vxmklgfazbmzjhsq3tuoama

CANS: Communication Limited Camera Network Self-Configuration for Intelligent Industrial Surveillance [article]

Jingzheng Tu, Qimin Xu, Cailian Chen
2021 arXiv   pre-print
Realtime and intelligent video surveillance via camera networks involve computation-intensive vision detection tasks with massive video data, which is crucial for safety in the edge-enabled industrial  ...  Multiple video streams compete for limited communication resources on the link between edge devices and camera networks, resulting in considerable communication congestion.  ...  Besides, SurveilEdge [2] presents a framework of offline clustering and online finetuning on a cloud center. Then, SurveilEdge deploys the finetuned deep learning networks on each edge node.  ... 
arXiv:2109.05665v1 fatcat:jdgqy47avbcxjixjnqki7icesu

Measurement-driven Analysis of an Edge-Assisted Object Recognition System [article]

A. Galanopoulos, V. Valls, G. Iosifidis, D. J. Leith
2020 arXiv   pre-print
for real time conditions, over the standard transmission method.  ...  We develop an edge-assisted object recognition system with the aim of studying the system-level trade-offs between end-to-end latency and object recognition accuracy.  ...  ACKNOWLEDGMENTS The authors would like to thank Domenico Guistianino for helpful input and discussions during development of the system.  ... 
arXiv:2003.03584v1 fatcat:7ccq63odrzfzndenc2gsue4wy4

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey [article]

Xiaofei Wang and Yiwen Han and Victor C.M. Leung and Dusit Niyato and Xueqiang Yan and Xu Chen
2019 arXiv   pre-print
In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management  ...  As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications  ...  Fig. 11 . 11 The collaboration of the end, edge and cloud layer for performing real-time video analytic by deep learning. Fig. 14 . 14 Segmentation of DL models in the edge.  ... 
arXiv:1907.08349v2 fatcat:4hfqgdto4fhvlguwfjxuz3ik5q

AutoML for Video Analytics with Edge Computing

Apostolos Galanopoulos, Jose Ayala-Romero, Douglas Leith, George Iosifidis
2021 Zenodo  
To overcome this obstacle, we propose an Automated Machine Learning (AutoML) framework for jointly configuring the service and wireless network parameters, towards maximizing the analytics' accuracy subject  ...  Video analytics constitute a core component of many wireless services that require processing of voluminous data streams emanating from handheld devices.  ...  Here we take a fundamentally different approach and develop a Bayesian learning framework towards automating the configuration of multi-user video edge analytic services. Methodology & Contributions.  ... 
doi:10.5281/zenodo.4966558 fatcat:lgn5eydypvespjrt5aduuyldju

Network-Aware Optimization of Distributed Learning for Fog Computing [article]

Su Wang, Yichen Ruan, Yuwei Tu, Satyavrat Wagle, Christopher G. Brinton, Carlee Joe-Wong
2021 arXiv   pre-print
Unlike traditional federated learning frameworks, our method enables devices to offload their data processing tasks to each other, with these decisions determined through a convex data transfer optimization  ...  We analytically characterize the optimal data transfer solution for different fog network topologies, showing for example that the value of offloading is approximately linear in the range of computing  ...  Shmatikov, “Privacy-Preserving Deep Learning,” in A Mobile Deep Learning Framework for Edge Video Analytics,” in ACM Conference on Computer and Communications Security (SIGSAC),  ... 
arXiv:2004.08488v4 fatcat:jjon4swlnfbgzbgaguu6oog3du

Empowering video applications for mobile devices [article]

He, Jian (Ph. D. In Computer Science), Austin, The University Of Texas At, Lili Qiu
It is critical to design a light-weight video codec to provide fast video coding as well as high compression e ciency for mobile devices.  ...  We identify a few major challenges to guarantee high user experience for running video applications on mobile devices. First, existing video applications call for high-resolution videos(e.g., 4K).  ...  It runs locally on mobile devices to perform real-time analytics for 30 fps videos without powerful edge/cloud servers or network connectivity.  ... 
doi:10.26153/tsw/10178 fatcat:vsa5x5jupbgfro4jepmopglify