检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiulong Liu Kun Su Eli Shlizerman Department of Electrical & Computer Engineering University of Washington Seattle Department of Applied Mathematics and Department of Electrical & Computer Engineering University of Washington Seattle

ISBN: (纸本)9798331314385

The content of visual and audio scenes is multi-faceted such that a video stream can be paired with various audio streams and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description (caption) of the audio. Such a framework has two unique advantages: i) Video-to-Audio generation process can be refined and controlled via text which complements the context of the visual information, and ii) The model can suggest what audio to generate for the video by generating audio captions. VATT consists of two key modules: VATT Converter, which is an LLM that has been fine-tuned for instructions and includes a projection layer that maps video features to the LLM vector space, and VATT Audio, a bi-directional transformer that generates audio tokens from visual frames and from optional text prompt using iterative parallel decoding. The audio tokens and the text prompt are used by a pretrained neural codec to convert them into a waveform. Our experiments show that when VATT is compared to existing video-to-audio generation methods in objective metrics, such as VGGSound audiovisual dataset, it achieves competitive performance when the audio caption is not provided. When the audio caption is provided as a prompt, VATT achieves even more refined performance (with lowest KLD score of 1.41). Furthermore, subjective studies asking participants to choose the most compatible generated audio for a given silent video, show that VATT Audio has been chosen on average as a preferred generated audio than the audio generated by existing methods. VATT enables controllable video-to-audio generation through text as well as suggest

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing 6G mmWave Beam Prediction in V2I with Class Imbalance Mitigation 35

Enhancing 6G mmWave Beam Prediction in V2I with Class Imbala...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Makadia, Omikumar B. Patel, Dhaval K. Raval, Mehul S. Zaveri, Mukesh Merchant, S.N. Ahmedabad University School of Engineering and Applied Science India Svnit Department of Computer Science and Engineering Gujarat Surat India Iit Bombay Department of Electrical Engineering Powai Mumbai India

ISBN: (纸本)9798350362244

The increase in the use of autonomous vehicles has motivated a paradigm shift in the transportation domain as it redefines the boundaries of urban mobility by augmenting safety measures. This research paper explores an innovative approach to enhance 6G millimeter-wave (mmWave) beam prediction for vehicle-to-infrastructure (V2I) communications by using generative adversarial networks (GANs). By generating synthetic data samples effectively and balancing the real-world dataset, we improve the accuracy of beam prediction models significantly. Our proposed method of training random forests on synthetic data (RFGAN) to predict beam indices provides the solution for imbalanced class issues and significantly improves the predictive performance of mmWave beam selection, contributing to more reliable and efficient V2I communications. This work also performs comparative analysis with state-of-the-art models in top-K evaluation metrics, average power loss, and overhead savings related to adapting to the new approach. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Millimeter- Wave Vehicle-to-Infrastructure Communications for Autonomous Vehicles: Location-Aided Beam Forecasting in 6G 16

Millimeter- Wave Vehicle-to-Infrastructure Communications fo...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Makadia, Omikumar B. Patel, Dhaval K. Shah, Kashish D. Raval, Mehul S. Zaveri, Mukesh Merchant, S.N. School of Engineering and Applied Science Ahmedabad University India Svnit Department of Computer Science and Engineering Gujarat Surat India Iit Bombay Department of Electrical Engineering Mumbai Powai India

ISBN: (纸本)9798350383119

The rise of autonomous vehicles has generated substantial interest due to their potential to transform transportation, enhance safety, and reduce traffic congestion in urban areas. This research investigates strategies to facilitate communication among various elements in driving environments, such as vehicles, pedestrians, and emergency responders, primarily focusing on vehicle-to-infrastructure (V2I) communication. Furthermore, advancements in wireless technology, including 6G and millimetre waves, offer improved connectivity but face challenges in signal propagation. The study emphasizes the importance of beam-forming as a solution, exploring alternative, resource-efficient methods to predict optimal signal directions using user positions. Positive simulation results suggest real-world applicability, and the study addresses critical questions about utilizing future positions and their impact on overhead complexity. This research provides valuable insights into position-based approaches for enhancing wireless communication in autonomous driving scenarios. © 2024 IEEE.

关键词： 6G Autonomous vehicles beam prediction overhead complexity training overhead

来源：评论

学校读者我要写书评

暂无评论

Deep RL-Based Smart Signaling Using Space-Time Vehicular Features Under C-V2X Scenario 16

Deep RL-Based Smart Signaling Using Space-Time Vehicular Fea...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Shah, Kashish D. Patel, Dhaval K. Raval, Mehul S. Zaveri, Mukesh Merchant, S.N. School of Engineering and Applied Science Ahmedabad University India Svnit Department of Computer Science and Engineering Gujarat Surat India LIT Bombay Department of Electrical Engineering Mumbai Powai India

ISBN: (纸本)9798350383119

As of recent, the majority of developing countries have faced traffic congestion issues. As a result, vehicular communication technologies such as DSRC and Cellular-V2X are standardized by the 3GPP to support the transportation community. The C-V2X standard proposed in 3GPP Re114 provides high data transmission facilities for V2V and V2I communication. In this paper, we attempt to solve the traffic congestion problem by considering the V2I communication facility as per the C-V2X standard. We propose an online learning strategy based on Deep Reinforcement Learning for smart signaling to avoid traffic congestion at the intersections. These are the key aspects to address the congestion issue. We conduct extensive near-real-time simulations in PTV VISSIM considering the Swastik Cross Road intersection at Ahmedabad, Gujarat, India, imported via OpenStreetMap. With the proposed smart signaling strategy, we found significant improvement in vehicles' average travel time and average space occupancy compared to existing traffic signaling methods. Uplifting this research and implementing such real-time strategies will significantly impact the current transportation system. © 2024 IEEE.

关键词： Cellular-V2X Deep Reinforcement Learning Intelligent Transportation Systems Smart Signaling Vehicular Communication

来源：评论

学校读者我要写书评

暂无评论

On Error-Based Step Size Control for Discontinuous Galerkin Methods for Compressible Fluid Dynamics

引用

应用数学与计算数学学报 2025年第1期7卷 3-39页

作者： Hendrik Ranocha Andrew R.Winters Hugo Guillermo Castro Lisandro Dalcin Michael Schlottke-Lakemper Gregor J.Gassner Matteo Parsani Applied Mathematics University of HamburgBundesstr.5520146 HamburgGermany Department of Mathematics Applied Mathematics Linköping UniversityLinköpingSweden Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Applied and Computational Mathematics RWTH Aachen UniversityAachenGermany High-Performance Computing Center Stuttgart University of StuttgartStuttgartGermany Department of Mathematics and Computer Science University of CologneCologneGermany Center for Data and Simulation Science University of CologneCologneGermany Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Physical Science and Engineering Division(PSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We study a temporal step size control of explicit Runge-Kutta(RK)methods for com-pressible computational fluid dynamics(CFD),including the Navier-Stokes equations and hyperbolic systems of conservation laws such as the Euler *** demonstrate that error-based approaches are convenient in a wide range of applications and compare them to more classical step size control based on a Courant-Friedrichs-Lewy(CFL)*** numerical examples show that the error-based step size control is easy to use,robust,and efficient,e.g.,for(initial)transient periods,complex geometries,nonlinear shock captur-ing approaches,and schemes that use nonlinear entropy *** demonstrate these properties for problems ranging from well-understood academic test cases to industrially relevant large-scale computations with two disjoint code bases,the open source Julia pack-ages *** with *** and the C/Fortran code SSDC based on PETSc.

关键词： Explicit Runge-Kutta(RK)methods Step size control Compressible fluid dynamics Adaptivity in space and time Shock capturing

来源：评论

学校读者我要写书评

暂无评论

Error Exponent and Strong Converse for Quantum Soft Covering

引用

IEEE Transactions on Information Theory 2024年第5期70卷 3499-3511页

作者： Cheng, Hao-Chung Gao, Li The Graduate Institute of Communication Engineering The Institute of Applied Mathematical Sciences National Taiwan University Center for Quantum Science and Engineering The Department of Electrical Engineering The Department of Mathematics Taipei10617 Taiwan National Center for Theoretical Sciences Physics Division Taipei10617 Taiwan Quantum Computing Center New Taipei City236 Taiwan University of Houston Department of Mathematics HoustonTX77204 United States

How well can we approximate a quantum channel output state using a random codebook with a certain size? In this work, we study the quantum soft covering problem, which uses a pairwise-independent random codebook to approximate the target output state of a quantum channel. We establish a one-shot error exponent bound and a one-shot strong converse bound on the approximation error measured in terms of the expected trace distance between the codebook-induced state and the true channel output state. When using independent and identically-distributed random codebook with a rate above the quantum mutual information I(X:B)ρ , we prove that the error decays exponentially with its error exponent expressed by the sandwiched Rényi information. On the other hand, when the rate of the codebook size is below the quantum mutual information, the error converges to one exponentially fast. Similar results are obtained using a random constant composition codebook, whereas the sandwiched Augustin information gives the error exponent. In addition to the above large deviation analysis, our results also hold in the moderate deviation regime. © 1963-2012 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Wide and fault diameter in Kneser graphs for enhanced fault tolerance in parallel computing

引用

International Journal of Networking and Virtual Organisations 2024年第3期31卷 169-190页

作者： Sundara Rajan, R. Kirithiga Nandini, G. Lin, Yuqing Reji, Remi Mariam Department of Mathematics Hindustan Institute of Technology and Science Chennai603 103 India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai603 103 India School of Electrical Engineering and Computing The University of Newcastle CallaghanNSW2308 Australia Department of Mathematics Christian College Kerala Chengannur689 122 India

A system’s fault tolerance is its capacity to function even if one or more of its components fail. Implementing a fault-tolerant network becomes an important criterion for reliable computing. Reliability measures play a significant part in recognising the role of faulty and non-faulty processors in a parallel computing system. Parallel computing is used primarily for saving time, solving big problems, and doing multiple tasks at once at the same time. Various reliability measures have been introduced to evaluate a network’s fault-tolerance capability. We have measured the wide diameter and fault diameter of the Kneser graphs in this study. Also, we have verified the fault diameter obtained using an experimental study. Further, we have described some applications of wide diameter and fault diameter in parallel and distributed computing. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Fault tolerant computer systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Resource Allocation Algorithm for 5G Vehicular Cloud Communication

引用

computers, Materials & Continua 2024年第8期80卷 2199-2219页

作者： Huanhuan Li Hongchang Wei Zheliang Chen Yue Xu School of Mathematics and Computer Sciences Nanchang UniversityNanchang330031China Department of Electrical Engineering Jiangxi Vocational College of Mechanical&Electrical TechnologyNanchang330013China Kehua Data Co. Ltd.Xiamen361006China

The current resource allocation in 5G vehicular networks for mobile cloud communication faces several challenges,such as low user utilization,unbalanced resource allocation,and extended adaptive allocation *** propose an adaptive allocation algorithm for mobile cloud communication resources in 5G vehicular networks to address these *** study analyzes the components of the 5G vehicular network architecture to determine the performance of different *** is ascertained that the communication modes in 5G vehicular networks for mobile cloud communication include in-band and out-of-band ***,this study analyzes the single-hop and multi-hop modes in mobile cloud communication and calculates the resource transmission rate and bandwidth in different communication *** study also determines the scenario of one-way and two-way vehicle lane cloud communication network connectivity,calculates the probability of vehicle network connectivity under different mobile cloud communication radii,and determines the amount of cloud communication resources required by vehicles in different lane *** on the communication status of users in 5G vehicular networks,this study calculates the bandwidth and transmission rate of the allocated channels using Shannon’s *** determines the adaptive allocation of cloud communication resources,introduces an objective function to obtain the optimal solution after allocation,and completes the adaptive allocation *** experimental results demonstrate that,with the application of the proposed method,the maximum utilization of user communication resources reaches approximately 99%.The balance coefficient curve approaches 1,and the allocation time remains under 2 *** indicates that the proposed method has higher adaptive allocation efficiency.

关键词： 5G vehicular networks mobile cloud communication resource allocation channel capacity network connectivity communication radius objective function

来源：评论

学校读者我要写书评

暂无评论

Near-field Source Localization in 3-D Using Two Parallel Centrally Symmetric Unfold Coprime Array

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4738-4749页

作者： Chen, Hua Li, Junjie Yang, Songjie Liu, Wei Eldar, Yonina C. Yuen, Chau Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu610054 China The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Kowloon Hong Kong Weizmann Institute of Science Faculty of Mathematics and Computer Science Rehovot7610001 Israel Nanyang Technological University School of Electrical and Electronics Engineering Singapore639798 Singapore

Most near-field (NF) localization algorithms cannot deal with the underdetermined case, while those which can are computationally expensive due to employment of fourth-order cumulants. In this work, a low-complexity solution is provided for underdetermined three-dimensional (3-D) NF localization, by employing second-order statistics with a tailored array configuration named two parallel centrally symmetric unfold coprime (TPSC) array. Its implementation can be divided into three stages. Firstly, the proposed algorithm constructs two cross-correlation matrices based on the received array data, which eliminates the non-linear range-related information of NF signals. Secondly, covariance and vectorization operations are applied to these two cross-correlation matrices to form a virtual array with extended aperture. Finally, the two-dimensional (2-D) angle parameters are estimated by the sparse and parametric approach (SPA) and a phase retrieval operation, and then the one-dimensional (1-D) range parameter is achieved by the multiple signal classification (MUSIC) algorithm. One specific feature is that the estimated angle and range parameters are matched automatically. An analysis of the properties of the TPSC array is provided, and an optimal parameter configuration is derived, given that the total number of array elements is fixed. Simulation results demonstrate that the designed TPSC array can achieve underdetermined 3-D NF localization, and deliver enhanced estimation capabilities, surpassing those of established algorithms. © 2002-2012 IEEE.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Improve Harris Hawkes optimizer algorithm via Laplace crossover

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第4期15卷 2057-2072页

作者： Nasab, Seyed Taha Mousavi Abualigah, Laith Department of Applied Mathematics Iran University of Science and Technology Tehran Iran Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

Nowadays, the speed of solving optimization problems by increasing various issues and the number of variables is critical. The Harris Hawk optimization method is a brand-new, intelligent system that resolves optimization issues by mathematically simulating the natural behavior of hawks. In this study, the Harris Hawks optimization method and the Laplace crossover operator are merged, and a new enhanced Harris Hawks algorithm (LX-HHO) based on the Laplace optimization algorithm is suggested. The purpose of improving this algorithm is to increase the convergence speed while maintaining good accuracy in achieving the optimal solution. The results of the proposed method on the test functions demonstrate that the algorithm has achieved faster convergence than the original version of the Harris Hawks algorithm and other meta-heuristic algorithms. This is due to the algorithm's accuracy in obtaining the best answer in these functions and to a reduction in the evaluation of the optimization function. Also, comparing and evaluating the proposed algorithm with other algorithms by Friedman and MAE test shows the superiority of the LX-HHO algorithm. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Optimization

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：