检索结果-内蒙古大学图书馆

2023 IEEE/CIC International Conference on communications in China, ICCC 2023

作者： Xu, Xinmian Dou, Haie Chen, Mingkai Wang, Lei Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing210003 China

ISBN: (纸本)9798350345384

In recent years, there has been significant attention and development in the Tactile Internet (TI) as a new type of network that supports typical applications such as remote healthcare and virtual reality. However, the demand for ultra-low latency and the inflexibility of traditional network architecture have presented serious challenges. In this paper, we propose a utility function for TI based on 5G network function virtualization (NFV) technology to evaluate network performance. The utility function considers the transmission of haptic and video data flows, as well as their latency and cost. We then formulate a network optimization problem with the utility function as the objective, strictly constraining latency and cost. To address this problem, we design two algorithms: the VNF deployment and routing of haptic and video flows (DRHV) algorithm tackles the VNF deployment and path selection issue, while the deep deterministic policy gradient(DDPG)-based traffic scheduling (DTS) algorithm allocates traffic resources and saves costs. Simulation results demonstrate that our algorithms achieve excellent optimization performance under the given constraints, and parameter changes align with the expected relationships and trends. © 2023 IEEE.

关键词： network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning from Human-like Feedback Enhances Semantic communication with Multimodal LLMs 16

Reinforcement Learning from Human-like Feedback Enhances Sem...

引用

16th International Conference on wireless communications and Signal Processing, WCSP 2024

作者： Zhang, Xinyu He, Xitao Chen, Mingkai Wang, Lei Ministry of Education Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing210003 China

ISBN: (纸本)9798350390643

Semantic communication is an emerging intelligent paradigm that provides some special solutions for the various future applications. With the rise of large language model (LLM), it may enhance well on semantic communication. However, how to balance on the accuracy and the efficiency of compression remains an urgent issue to semantic communication with LLMs. In this paper, we design a multimodal large language models (MLLMs)-enabled semantic communication system specifically designed for image transmission, where the reinforcement learning from human-like feedback (RLHLF) framework is proposed to apply reasoning and self-reflection capabilities of MLLMs to enhance the quality of semantic extraction and image generation. For one thing, we first optimize the image semantic information at the transmitter by RLHLF framework. For another thing, the generated images are optimized at the receiver by RLHLF framework. Simulation results show that our proposed system provides bandwidth savings and enables graceful performance improvement as the channel quality improves, which proves the potential of MLLMs for future semantic communication. © 2024 IEEE.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

AN IMPROVED HYBRID SEMANTIC MATCHING ALGORITHM WITH LEXICAL SIMILARITY

引用

Journal of Electronics(China) 2010年第6期27卷 838-847页

作者： Peng Rongqun Mi Zhengkun Wang Lingjiao Broadband Wireless Communication and Sensor Network Technology Key Lab of Ministry of Education Nanjing University of Posts and Telecommunications Nanjing 210003 China

In this paper, we proposed an improved hybrid semantic matching algorithm combining Input/Output (I/O) semantic matching with text lexical similarity to overcome the disadvantage that the existing semantic matching algorithms were unable to distinguish those services with the same I/O by only performing I/O based service signature matching in semantic web service discovery techniques. The improved algorithm consists of two steps, the first is logic based I/O concept ontology matching, through which the candidate service set is obtained and the second is the service name matching with lexical similarity against the candidate service set, through which the final precise matching result is concluded. Using Ontology Web Language for Services (OWL-S) test collection, we tested our hybrid algorithm and compared it with OWL-S Matchmaker-X (OWLS-MX), the experimental results have shown that the proposed algorithm could pick out the most suitable advertised service corresponding to user's request from very similar ones and provide better matching precision and efficiency than OWLS-MX.

关键词： Hybrid matching algorithm Semantic matching Lexical similarity WordNet Ontology Web Language for Services (OWL-S)

来源：评论

学校读者我要写书评

暂无评论

Multidimensional Speaker Information Recognition based on Proposed Baseline System 2

Multidimensional Speaker Information Recognition based on Pr...

引用

2017 IEEE 第2届先进信息技术,电子与自动化控制国际会议(IAEAC 2017)

作者： Shan Li Longting Xu Zhen Yang Broadband Wireless Communication and Sensor Network Technology Key Lab.Nanjing University of Posts and Telecommunications Institute for Infocomm Research ASTAR

Traditional speech-related identity recognition commonly pays attention to individual aspect of speech signals but in reality, the speech signals are made up of semantics, speaker dependent features,

ISBN: (纸本)9781467389808

Traditional speech-related identity recognition commonly pays attention to individual aspect of speech signals but in reality, the speech signals are made up of semantics, speaker dependent features,

关键词： Speech recognition Speech Feature extraction Support vector machines Emotion recognition Training Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic compatibility analysis and optimization of electronic device based on metamaterials 9

Electromagnetic compatibility analysis and optimization of e...

引用

9th IEEE Joint International Information technology and Artificial Intelligence Conference, ITAIC 2020

作者： Zhang, Shine Wuhan University of Technology Hubei Key Laboratory of Broadband Wireless Communication and Sensor Networks Wuhan China

In this paper, the sources of electromagnetic interference (EMI) in electronic device is analyzed. Resonance analysis and decoupling of printed circuit board (PCB) are carried out through simulation software, and the EMI on PCB is optimized. The combination of metamaterial structure and electromagnetic shielding further optimizes the electromagnetic compatibility (EMC) of electronic device. The simulation results validate the proposed analysis and optimization method. Compared with before the shielding design, the proposed electromagnetic shielding method can reduce the electric field radiation intensity of the electronic device by 3. 75dB on average in the low frequency band. In the high frequency band, the radiation intensity can be reduced by 16.4dB at the maximum. © 2020 IEEE.

关键词： Printed circuit boards

来源：评论

学校读者我要写书评

暂无评论

FoVs correlation model for wireless multimedia sensor networks based on three-dimensional perception

引用

Advances in Information Sciences and Service Sciences 2012年第3期4卷 27-34页

作者： Han, Chong Sun, Lijuan Xiao, Fu Guo, Jian Wang, Ruchuan College of Computer Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Jiangsu Province Nanjing 210003 China

wireless multimedia sensor networks have become the focus of research in a wide variety of areas in recent years. The camera sensor nodes observe the phenomenon at different locations in the field, and the spatially proximal cameras could have highly overlapped field of views (FoVs). Based on the three-dimensional sensing model of camera sensor node, a FoVs correlation model was proposed in this paper. Then, a grid-based and a relative position-based approach were respectively designed to calculate the correlation coefficient between two cameras. Simulation results and algorithm complexity analysis demonstrate that the relative position-based method has highly efficiency and nearly reduces two orders of magnitude of time complexity to the former.

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A NEW APPROACH TO DVC COMBINED WITH ROI EXTRACTION AND RESIDUAL VIDEO CODING FOR MULTIMEDIA sensor networkS

引用

Journal of Electronics(China) 2013年第1期30卷 17-24页

作者： Lin Zhaoxiao Sun Lijuan Xiao Fu Wang Ruchuan College of Computer Nanjing University of Posts and Telecommunications Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications) Ministry of Education Jiangsu Province

The Wyner-Ziv distributed video coding scheme is characterized for its intraframe encoder and interframe decoder which can also approach the efficiency of an interframe encoder-decoder system. In Wyner-Ziv residual coding of video, the residual of a frame with respect to a reference frame is Wyner-Ziv encoded, which can reduces the input entropy and leads to a higher coding efficiency than directly encoding the original frame. In this paper, we propose a new approach of residual coding combined with Region Of Interest (ROI) extraction. Experimental results show that, the proposed scheme achieves better rate-distortion performance compared to conventional Wyner-Ziv coding scheme.

关键词： Distributed Video Coding (DVC) Residual video coding Region Of Interest (ROI)

来源：评论

学校读者我要写书评

暂无评论

Single image super resolution through neighbor embedding with non-local means and field of experts

引用

Journal of Computational Information Systems 2014年第5期10卷 1973-1981页

作者： Cao, Mingming Gan, Zongliang Cui, Ziguan Guo, Quanzhan Zhu, Xiuchang Key Lab. of Broadband Wireless Communication and Sensor Network Technology Min. of Edu. Image Process and Image Communication Lab. Nanjing University of Posts and Telecommunications Nanjing 210003 China

Super resolution (SR) through neighbor embedding is recognized as an effective way to produce a high resolution (HR) image. However, this learning-based method is clumsy at preserving sharper edges and suppressing unwanted artifacts. To reduce these artifacts, in this paper we proposed a novel single image super resolution through neighbor embedding with non-local means (NLM) and field of experts. The proposed SR approach is based upon an observation that small patches in natural images tend to redundantly repeat themselves many times, which could be exploited to improve the image reconstruction quality. In addition, considering the existence of un-normal texture in the reconstruction of HR images, which reduce the accuracy of the search process, we apply the Field of Experts model to remove the un-normal texture, which could also make the final image match the statistical characteristics of natural images. The experimental results show that the proposed method can achieve comparable performance to other leading algorithms. © 2014 Binary Information Press.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Mixed-norm subspace pursuit algorithm for compressed sensing in the presence of impulsive noise

引用

Journal of Computational Information Systems 2014年第13期10卷 5637-5648页

作者： Ji, Yunyun Yang, Zhen College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing China

The subspace pursuit algorithm in compressed sensing cannot achieve desirable reconstruction performance in the presence of impulsive noise based on the fact that the support detection and least squares are not robust to the impulsive noise. And then we propose a mixed-norm subspace pursuit algorithm to achieve sparse reconstruction in the impulsive noise environment. The mixed-norm subspace pursuit algorithm takes advantage of mutual influence of two different residuals to iteratively improve the performance of support detection and measurement set detection. It has significant characteristics: effectiveness in additive Gaussian white noise environment and robustness to impulsive noise, which have been verified by theoretical and experimental results. © 2014 by Binary Information Press

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Satellite Interference Source Location Algorithm 7

Analysis of Satellite Interference Source Location Algorithm

引用

7th International Conference on Computer and communications, ICCC 2021

作者： Yan, Hui Zhao, Laiding Zhang, Gengxin Ruan, Cen 'Telecommunication and Network' National Engineering Research Center Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing China

ISBN: (纸本)9781665409506

There are many methods and principles of satellite interference source location, but no matter which method is chosen, the positioning equation is nonlinear. Therefore, it is very important to solve the nonlinear equations accurately for the accuracy of the final positioning results. In this paper, an improved particle swarm optimization (PSO) algorithm is proposed. Based on the combination of PSO and grid search algorithm, the precision requirement is set in the iterative stop condition. When the calculation results meet the set precision, iteration can be stopped. Compared with the ordinary particle swarm optimization algorithm, the results can be obtained more quickly and accurately. © 2021 IEEE.

关键词： Satellites

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：