A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
AccMPEG: Optimizing Video Encoding for Accurate Video Analytics
2022
Conference on Machine Learning and Systems
With more videos being recorded by edge sensors (cameras) and analyzed by computer-vision deep neural nets (DNNs), a new breed of video streaming systems has emerged, with the goal to compress and stream ...
AccMPEG provides a suite of techniques that, given a new server-side DNN, can quickly create a cheap model to infer the accuracy gradient on any new frame in near realtime. ...
Video encoding for edge video analytics Distributed video analytics: As accurate analytics requires compute-intensive DNNs that cheap video sensors cannot afford, the video frames are often compressed ...
dblp:conf/mlsys/DuZAWXJ22
fatcat:uzoli6ce2bcebfphrewue7puva
DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation
[article]
2022
arXiv
pre-print
This paper introduces STAC, a DNN-driven compression scheme tailored for edge-assisted semantic video segmentation. ...
Practical issues include varying spatial sensitivity and huge bandwidth consumption for compression strategy feedback and offloading. ...
Driven by mobile edge computing (MEC), a promising solution to alleviate this conflict is to offload DNN inference tasks to the edge servers. ...
arXiv:2203.14481v1
fatcat:gw7uvyd275cphkp2vwwomgjjhy
AccMPEG: Optimizing Video Encoding for Video Analytics
[article]
2022
arXiv
pre-print
With more videos being recorded by edge sensors (cameras) and analyzed by computer-vision deep neural nets (DNNs), a new breed of video streaming systems has emerged, with the goal to compress and stream ...
AccMPEG provides a suite of techniques that, given a new server-side DNN, can quickly create a cheap model to infer the accuracy gradient on any new frame in near realtime. ...
Video encoding for edge video analytics Distributed video analytics: As accurate analytics requires compute-intensive DNNs that cheap video sensors cannot afford, the video frames are often compressed ...
arXiv:2204.12534v1
fatcat:ou73kl7y25agngtrqhjixggrfu
Extending reference architecture of big data systems towards machine learning in edge computing environments
2020
Journal of Big Data
Findings: The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments. ...
Finally, a system view is provided of the software engineering aspects of ML model development and deployment. ...
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
Streaming Video Analytics On The Edge With Asynchronous Cloud Support
[article]
2022
arXiv
pre-print
We focus specifically on object detection in videos (applicable in many video analytics scenarios) and show that the fused edge-cloud predictions can outperform the accuracy of edge-only and cloud-only ...
In this work, we develop REACT, a framework that leverages cloud resources to execute large DNN models with higher accuracy to improve the accuracy of models running on edge devices. ...
Moreover, for many video analytics applications not all edge devices are operational at all times. For example, one might use an AR/MR app on a mobile device for just 20 minutes a day. ...
arXiv:2210.01402v1
fatcat:t63ucr4kencexdpg33gfjppk44
Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques
[article]
2023
arXiv
pre-print
video analytics (VA). ...
The resulting new intersection, edge video analytics (EVA), begins to attract widespread attention. Nevertheless, only a few loosely-related surveys exist on this topic. ...
EDGE VIDEO ANALYTICS SYSTEM Large-scale real-time VA is becoming the "killer app" for edge computing [94] . ...
arXiv:2211.15751v2
fatcat:l23bztidufaufm64w7uu7iyaum
AccDecoder: Accelerated Decoding for Neural-enhanced Video Analytics
[article]
2023
arXiv
pre-print
In this paper, we present AccDecoder, a novel accelerated decoder for real-time and neural-enhanced video analytics. ...
AccDecoder provides efficient inference capability via filtering important frames using DRL for DNN-based inference and reusing the results for the other frames via extracting the reference relationship ...
To accelerate analytics, AccDecoder applies DRL for adaptive frame selection for quality enhancement or/and DNN-based inference. ...
arXiv:2301.08664v2
fatcat:ehtxoxrqhnbstgrdku2r7zbffm
Distributing Deep Neural Networks with Containerized Partitions at the Edge
2019
USENIX Workshop on Hot Topics in Edge Computing
In this paper, we propose a containerized partition-based runtime adaptive convolutional neural network (CNN) acceleration framework for Internet of Things (IoT) environments. ...
Deploying machine learning on edge devices is becoming increasingly important, driven by new applications such as smart homes, smart cities, and autonomous vehicles. ...
Acknowledgments The authors would like to thank the anonymous reviewers for their feedback. We also extend special thanks to Irfan Ahmad for suggestions on the camera ready. ...
dblp:conf/hotedge/ZhouWTD19
fatcat:lu7d7x23ljdpfo5fgzixmx3eja
Holistic Network Virtualization and Pervasive Network Intelligence for 6G
[article]
2023
arXiv
pre-print
In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. ...
., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, ...
Dongxiao Liu for helpful discussions on open issues related to data privacy and security. ...
arXiv:2301.00519v1
fatcat:6j2awx2lfjhwhnfmodk7z3qc44
Evaluation of Thermal Imaging on Embedded GPU Platforms for Application in Vehicular Assistance Systems
2022
IEEE Transactions on Intelligent Vehicles
This study is focused on evaluating the real-time performance of thermal object detection for smart and safe vehicular systems by deploying the trained networks on GPU & single-board EDGE-GPU computing ...
The smaller network variant of YOLO is further optimized using TensorRT inference accelerator to explicitly boost the frames per second rate. ...
in data collection and Quentin Noir from Lynred France for giving their feedback. ...
doi:10.1109/tiv.2022.3158094
fatcat:an5ak2v3l5hndogfw5xigxftr4
Hardware Solutions for Low-Power Smart Edge Computing
2022
Journal of Low Power Electronics and Applications
A survey of the mainstream embedded computing devices for low power IoT and edge computing is then presented. Finally, CYSmart is introduced as an innovative smart edge computing system. ...
Traditionally, low-power smart edge devices have been realized using resource-constrained systems executing machine learning (ML) algorithms for identifying objects or features, making decisions, etc. ...
Acknowledgments: The authors would like to thank Guillaume Devic and Gilles Sassatelli for their feedback in early discussions on part of the current work. ...
doi:10.3390/jlpea12040061
fatcat:egb7a6o2wbb5jk4nfziweylsku
Trends in Intelligent Communication Systems: Review of Standards, Major Research Projects, and Identification of Research Gaps
2021
Journal of Sensor and Actuator Networks
The increasing complexity of communication systems, following the advent of heterogeneous technologies, services and use cases with diverse technical requirements, provide a strong case for the use of ...
For instance, 3GPP has introduced the network data analytics function (NWDAF) at the 5G core network for the control and management of network slices, and for providing predictive analytics, or statistics ...
Essentially, the ENI and the assisted systems together create a closed loop so that the ENI system always receives updated data from the assisted system, and in turn, provides AI/ML-driven recommendations ...
doi:10.3390/jsan10040060
fatcat:x4rppitvj5awnie6nquclglgie
Green Edge AI: A Contemporary Survey
[article]
2023
arXiv
pre-print
Guided by these principles, we then explore energy-efficient design methodologies for the three critical tasks in edge AI systems, including training data acquisition, edge training, and edge inference ...
The transformative power of AI is primarily derived from the utilization of deep neural networks (DNNs), which require extensive data for training and substantial computational resources for processing ...
In [218] , the frame quality for video analytics, including frame rate, resolution, and bitrate, was controlled considering both the energy cost and inference accuracy under a data-driven framework. ...
arXiv:2312.00333v1
fatcat:56wzmwywebhqjdf3tlgpp7mmge
Communication-Efficient Edge AI: Algorithms and Systems
[article]
2020
arXiv
pre-print
We then introduce communication-efficient techniques, from both algorithmic and system perspectives for training and inference tasks at the network edge. ...
By pushing inference and training processes of AI models to edge nodes, edge AI has emerged as a promising alternative. ...
Zhi Ding from the University of California at Davis for insightful and constructive comments to improve the presentation of this work. ...
arXiv:2002.09668v1
fatcat:nhasdzb7t5dt5brs2r7ocdzrnm
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
[article]
2021
arXiv
pre-print
By embedding model training and inference capabilities into the network edge, edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence ...
New design principles of wireless networks, service-driven resource allocation optimization methods, as well as a holistic end-to-end system architecture to support edge AI will be described. ...
In particular, the chip design procedure for edge AI hardware can be significantly accelerated by the recent proposal of deep RL assisted fast chip floorplanning [298] . ...
arXiv:2111.12444v1
fatcat:crrbtfylvjeihogumggdnxcbpq
« Previous
Showing results 1 — 15 out of 485 results