检索结果-内蒙古大学图书馆

98th IEEE Vehicular Technology Conference (VTC-Fall)

作者： Chen, Danni Lei, Ming Zhao, Ming-Min Liu, An Sheng, Sikai Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Zhejiang Prov Key Lab Informat Proc Commun & Netw Hangzhou 310027 Peoples R China

ISBN: (纸本)9798350329285

Federated learning (FL) is an edge learning framework that has received significant attention recently. However, the cost of communication has become a major challenge for FL as the number of edge devices grows and the complexity of training models increases. Besides, data samples across all edge devices are usually not independent and identically distributed (non-IID), posing additional challenges to the convergence and model accuracy of FL. Therefore, we propose a novel personalized FL framework based on deep coded over-the-air computation, named DipFL. In this framework, we design a deep AirComp aggregation (DACA) module for n-to-1 information aggregation. Besides, a joint source-channel coding (JSCC) module is designed based on the variational auto-encoder (VAE) model, which not only encodes the transmitted data, but also reduces the bias of local samples by introducing certain regularisation terms. In addition, we propose a personalized mix module that allows local models to be more personalized by mixing the global model and the local models. Simulation results confirm that the proposed DipFL framework is able to significantly reduce the amount of transmitted data, while improving FL performance especially at low signal-to-noise regimes.

关键词： Personalized federated learning over-the-air computation deep learning joint source-channel coding

来源：评论

学校读者我要写书评

暂无评论

DeepWiVe: Deep-Learning-Aided Wireless Video Transmission

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2022年第9期40卷 2570-2583页

作者： Tung, Tze-Yang Gunduz, Deniz Imperial Coll London Informat Proc & Commun Lab IPC Lab London SW7 2AZ England

We present DeepWiVe, the first-ever end-to-end joint source-channel coding (JSCC) video transmission scheme that leverages the power of deep neural networks (DNNs) to directly map video signals to channel symbols, combining video compression, channel coding, and modulation steps into a single neural transform. Our DNN decoder predicts residuals without distortion feedback, which improves the video quality by accounting for occlusion/disocclusion and camera movements. We simultaneously train different bandwidth allocation networks for the frames to allow variable bandwidth transmission. Then, we train a bandwidth allocation network using reinforcement learning (RL) that optimizes the allocation of limited available channel bandwidth among video frames to maximize the overall visual quality. Our results show that DeepWiVe can overcome the cliff-effect, which is prevalent in conventional separation-based digital communication schemes, and achieve graceful degradation with the mismatch between the estimated and actual channel qualities. DeepWiVe outperforms H.264 video compression followed by low-density parity check (LDPC) codes in all channel conditions by up to 0.0485 in terms of the multi-scale structural similarity index measure (MS-SSIM), and H.265+ LDPC by up to 0.0069 on average. We also illustrate the importance of optimizing bandwidth allocation in JSCC video transmission by showing that our optimal bandwidth allocation policy is superior to uniform allocation as well as a heuristic policy benchmark.

关键词： Bandwidth Video compression Wireless communication Distortion channel allocation Resource management Parity check codes Deep learning joint source-channel coding video compression wireless video transmission

来源：评论

学校读者我要写书评

暂无评论

Incremental Refinements and Multiple Descriptions With Feedback

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2022年第10期68卷 6915-6940页

作者： Ostergaard, Jan Erez, Uri Zamir, Ram Aalborg Univ Dept Elect Syst DK-9000 Aalborg Denmark Tel Aviv Univ Dept Elect Engn Syst IL-69978 Tel Aviv Israel

It is well known that independent (separate) encoding of K correlated sources may incur some rate loss compared to joint encoding, even if the decoding is done jointly. This loss is particularly evident in the multiple descriptions problem, where it is the same source that is encoded in each description. We observe that under mild conditions about the source and distortion measure, the sum-rate of K separately encoded individually good descriptions tends to the rate-distortion function of the joint decoder in the limit of vanishing small coding rates of the descriptions. Moreover, we then propose to successively encode the source into K independent descriptions in each round in order to achieve a final distortion D after M rounds. We provide two examples - a Gaussian source with mean-squared error and an exponential source with one-sided error - for which the excess rate vanishes in the limit as the number of rounds M goes to infinity, for any fixed D and K. This result has an interesting interpretation for a multi-round variant of the multiple descriptions problem, where after each round the encoder gets a (block) feedback regarding which of the descriptions arrived: In the limit as the number of rounds M goes to infinity (i.e., many incremental rounds), the total rate of received descriptions approaches the rate-distortion function. We provide theoretical and experimental evidence showing that this phenomenon is in fact more general than in the two examples above.

关键词： Multiple description (MD) coding successive refinement joint source-channel coding source coding with feedback

来源：评论

学校读者我要写书评

暂无评论

Strategic Quantization over a Noisy channel 57

Strategic Quantization over a Noisy Channel

引用

57th Asilomar Conference on Signals, Systems and Computers

作者： Anand, Anju Akyol, Emrah SUNY Binghamton Elect & Comp Engn Binghamton NY 13902 USA

ISBN: (纸本)9798350325744

This paper is concerned with the strategic quantization setting where the encoder and the decoder have misaligned objectives and communicate over a noisy channel, extending the work on classical channel-optimized quantization. This problem without the quantization constraint has been well-studied under the theme of information design problems in Economics. It is more appealing and relevant to engineering applications with a constraint on the cardinality of the message space. We consider a scalar source X and develop a gradient-descent based solution in conjunction with random index assignment, which has been used in prior literature on classical channel-optimized quantizaton. In our prior work, we used dynamic programming for this problem. Here, we employ gradient descent to reduce the complexity of the algorithm. We finally present numerical results obtained via the proposed algorithm that suggest its validity and demonstrate the strategic quantization features that differentiate it from its classical counterpart. The codes are available at: https://***/asilomar2023.

关键词： Quantization joint source-channel coding game theory gradient descent

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learning-Based Wireless Image Recognition Using the PyramidNet in Edge Intelligence 34

End-to-End Learning-Based Wireless Image Recognition Using t...

引用

IEEE 34th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Lee, Kyubihn Yu, Nam Yul Gwangju Inst Sci & Technol GIST Sch Elect Engn & Comp Sci Gwangju South Korea

ISBN: (纸本)9781665464833

In edge intelligence, deep learning (DL) models are deployed at an edge device and an edge server for data processing with low latency in the Internet of Things (IoT). In this paper, we propose a new end-to-end learning-based wireless image recognition scheme using the PyramidNet in edge intelligence. We split the PyramidNet carefully into two parts for an IoT device and the edge server, which is to pursue low on-device computation. Also, we apply a squeeze-and-excitation block to the PyramidNet for the improvement of image recognition. In addition, we embed compression encoder and decoder at the splitting point, which reduces communication overhead by compressing the intermediate feature map. Simulation results demonstrate that the proposed scheme is superior to other DL-based schemes in image recognition, while presenting less on-device computation and fewer parameters with low communication overhead.

关键词： Edge intelligence end-to-end learning image recognition Internet of Things (IoT) joint source-channel coding

来源：评论

学校读者我要写书评

暂无评论

channel-Optimized Strategic Quantizer Design via Dynamic Programming 22

Channel-Optimized Strategic Quantizer Design via Dynamic Pro...

引用

22nd IEEE Statistical Signal Processing Workshop (SSP)

作者： Anand, Anju Akyol, Emrah SUNY Binghamton Elect & Comp Engn Binghamton NY 13902 USA

ISBN: (纸本)9781665452458

We consider the design problem of a strategic quantizer over a noisy channel, extending the classical work on channel-optimized quantization to strategic settings where the encoder and the decoder have misaligned objectives. Building on our recent work on strategic quantization over noiseless channels, we employ a random channel index assignment mapping, as done in prior work on classical channel-optimized quantizer design literature, combined with a dynamic programming approach to optimize quantization boundaries. Our analysis and numerical results demonstrate several interesting aspects of channel-optimized strategic quantization which do not appear in its classical (nonstrategic) counterpart. The codes are available at: https://***/ssp2023dpnoise.

关键词： Quantization joint source-channel coding game theory dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Semantics-Empowered UAV-assisted Wireless Communication System for Wildfire Detection 28

Semantics-Empowered UAV-assisted Wireless Communication Syst...

引用

IEEE 28th International Workshop on Computer-Aided Modeling and Design of Communication Links and Networks (CAMAD)

作者： Basnayaka, Chathuranga M. Wijerathna Jayakody, Dushantha Nalin K. Beko, Marko Univ Lisbon Inst Telecomunicacoes Inst Super Tecn P-1049001 Lisbon Portugal Lusofona Univ COPELABS P-1700097 Lisbon Portugal Sri Lanka Technol Campus Sch Engn Ctr Telecommun Res Padukka 10500 Sri Lanka

ISBN: (纸本)9798350303490

With the increasing occurrence of wildfires globally, quick and effective detection methods are vital. This paper proposes an innovative solution for wildfire detection using Unmanned Aerial Vehicle (UAV)-assisted detection systems. On the other hand, semantic communication, a technology designed for efficient data transmission in specialized tasks, plays a crucial role in next-generation wireless communications systems. In this paper, the deep joint source-channel coding (DJSCC) scheme has been used for efficient image transmission as a deep learning-based semantic communication technique for wildfire detection. DJSCC improves source and channel coding for semantic communications, offering advantages such as improved energy efficiency, reduced latency, and improved reliability compared to traditional source and channel code schemes. In this paper, the transmitter-receiver operations of the UAV communication system are modeled as a DJSCC, and they are jointly trained while taking into account the effects of the fading channel. The encoder transforms captured images into compact feature vectors, subsequently transmitting them using a reduced number of channels to minimize latency. Rather than engaging in the reconstruction of the input image in the receiver, the classifier performs a classification task using the received signals at the receiver. Alternatively, if the recovery of an image is required to understand the spread of the wildfire, the decoder reconstructs it by using the received signal at the receiver.

关键词： Unmanned Aerial Vehicles (UAV) joint source-channel coding semantic communication deep learning wildfire

来源：评论

学校读者我要写书评

暂无评论

Text Semantic Communication Systems with Sentence-Level Semantic Fidelity

Text Semantic Communication Systems with Sentence-Level Sema...

引用

IEEE Wireless Communications and Networking Conference (WCNC)

作者： Tang, Bing Li, Qiang Huang, Likun Yin, Yiran Huazhong Univ Sci & Technol Wuhan 430074 Peoples R China Wuhan Inst Technol Wuhan 430205 Peoples R China

ISBN: (纸本)9781665491228

Semantic communication systems have been proposed for efficient text transmissions in recent years. However, most existing methods mainly focus on word-level recovery, which fails to reflect the semantic fidelity of the model. By leveraging the sentence-level semantic information, a semantic communication system architecture is proposed within the framework of deep learning based joint source-channel coding. Then, in order to evaluate the semantic fidelity of the system, a new metric of Semantic Similarity is proposed, which is more sensitive to semantic differences as compared to existing evaluation metrics, e.g., bilingual evaluation understudy. For guaranteeing the consistency between model training and performance evaluation, the proposed new metric is then incorporated into the objective function, based on which end-to-end performance optimization is performed. Extensive simulation results on European Parliament dataset demonstrate the effectiveness and necessity of the proposed method. Compared with the state-of-the-art, e.g., DeepSC, an improvement of up to 10% is achieved in terms of Semantic Similarity. Furthermore, significant performance gains are achieved by the proposed method in both regimes of low and medium signal-to-noise ratio, as compared to traditional separate source-channel coding methods.

关键词： Semantic communications semantic fidelity semantic similarity joint source-channel coding deep learning

来源：评论

学校读者我要写书评

暂无评论

joint source-channel coding OF 3D VIDEO USING MULTIVIEW coding

JOINT SOURCE-CHANNEL CODING OF 3D VIDEO USING MULTIVIEW CODI...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Arash Vosoughi Vanessa Testoni Pamela Cosman Laurence Milstein ECE University of California San Diego

ISBN: (纸本)9781479903573

We consider the joint source-channel coding problem of a 3D video transmitted over an AWGN channel. The goal is to minimize the total number of bits, which is the sum of the number of source bits and the number of forward error correction bits, under two constraints: the quality of the primary view and the quality of the secondary view must be greater than or equal to a predetermined threshold at the receiver. The quality is measured in terms of the expected PSNR of an entire decoded group of pictures. A MVC (multiview coding) encoder is used as the source encoder, and rate compatible punctured turbo codes are utilized for protection of the encoded 3D video over the noisy channel. Equal error protection and unequal error protection are compared for various 3D video sequences and noise levels.

关键词： joint source-channel coding Multiview video coding Turbo codes Unequal error protection error protection Combined source-channel coding turbo codes source encoder Video coding Videotapes Drill bits joints Forward error correction Greater than or equal to

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-Aided Wireless Video Transmission 23

Deep-Learning-Aided Wireless Video Transmission

引用

23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)

作者： Tung, Tze-Yang Gunduz, Deniz Imperial Coll London Informat Proc & Commun Lab IPC Lab London England Univ Modena & Reggio Emilia Enzo Ferrari Dept Engn Modena Italy

ISBN: (纸本)9781665494557

We present DeepWiVe, the first-ever end-to-end joint source-channel coding (JSCC) video transmission scheme that leverages the power of deep neural networks (DNNs) to directly map video signals to channel symbols, combining video compression, channel coding, and modulation steps into a single neural transform. Our DNN decoder predicts residuals without distortion feedback, which improves video quality by accounting for occlusion/disocclusion and camera movements. We simultaneously train different bandwidth allocation networks for the frames to allow variable bandwidth transmission. Then, we train a bandwidth allocation network using reinforcement learning (RL) that optimizes the allocation of limited available channel bandwidth among video frames to maximize overall visual quality. Our results show that DeepWiVe can overcome the cliffeffect, which is prevalent in conventional separation-based digital communication schemes, and achieve graceful degradation with the mismatch between the estimated and actual channel qualities. DeepWiVe outperforms H.264 video compression followed by lowdensity parity check (LDPC) codes in all channel conditions by up to 0.0485 on average in terms of the multi-scale structural similarity index measure (MS-SSIM).

关键词： joint source-channel coding wireless video transmission deep learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：