检索结果-内蒙古大学图书馆

One-to-Many Semantic Communication systems: Design, Implementation, Performance Evaluation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Han Zhu, Xingwu Zhou, Fuhui Wu, Wei Hu, Rose Qingyang Zhu, Hongbo The Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Nanjing210003 China The Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of Education Nanjing University of Posts and Telecommunications Nanjing210003 China College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics 210000 China The College of Communication and Information Engineering Nanjing University of Posts and Telecommunications 210003 China The Department of Electrical and Computer Engineering Utah State University LoganUT United States

Semantic communication in the 6G era has been deemed a promising communication paradigm to break through the bottleneck of traditional communications. However, its applications for the multi-user scenario, especially the broadcasting case, remain under-explored. To effectively exploit the benefits enabled by semantic communication, in this paper, we propose a one-to-many semantic communication system. Specifically, we propose a deep neural network (DNN) enabled semantic communication system called MR_DeepSC. By leveraging semantic features for different users, a semantic recognizer based on the pre-trained model, i.e., DistilBERT, is built to distinguish different users. Furthermore, the transfer learning is adopted to speed up the training of new receiver networks. Simulation results demonstrate that the proposed MR_DeepSC can achieve the best performance in terms of BLEU score than the other benchmarks under different channel conditions, especially in the low signal-to-noise ratio (SNR) regime. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Pre-manufacturing Portfolio Management Decisions in the Defense Industry

学校读者我要写书评

暂无评论

Pre-manufacturing Portfolio Management Decisions in the Defe...

Industry Conference (MIC), IEEE Midwest

作者： Rahul Dixit Ratna Babu Chinnam Harpreet Singh Industrial & System Engineering Wayne State University Detroit MI Electrical & Computer Engineering Wayne State University Detroit MI

ISBN: (数字)9781728183862

ISBN: (纸本)9781728183879

Defense Industry production quantities and manufacturing timeline are different from commercial industry. Specifically, the platforms take years to develop, are in field-use for multiple-decades. The installed payload systems on these platforms must be backward compatible when upgraded. The production volumes are small, and many products are highly integrated to fit size, weight & power (SWaP) constraints. Cost, while important, is not the primary driving factor in design for manufacturability. Under these conditions, the Portfolio Managers in the industry make technology and material readiness decisions several years ahead of manufacture. Data needed for such decisions is often sparse, inaccurate, compartmentalized and deliberately obfuscated. Our modified Delphi method based qualitative research shows that under these constraints, middle managers in the defense industry, make tactical and strategic decisions based on best-consensus, using paired-comparison processes. And, when they choose to make `more unilateral' decisions regarding portfolio management (PM) and new product development (NPD) investments, these are less robust.

关键词： Defense industry Portfolios Investment Decision making Production

OVERCONSTRAINED LOCOMOTION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Haoran Huang, Bangchao Zhang, Zishang Xu, Ronghan Huang, Guojing Feng, Shihao Huang, Guangyi Yin, Jiayi Qiu, Nuofan Chen, Hua Zhang, Wei Pan, Jia Wan, Fang Song, Chaoyang Department of Mechanical and Energy Engineering Southern University of Science and Technology China Department of Computer Science The University of Hong Kong Hong Kong School of Design Southern University of Science and Technology China ZJU-University of Illinois Urbana-Champaign Institute Zhejiang University China System Design and Intelligent Manufacturing Southern University of Science and Technology China Design & Learning Research Group Southern University of Science and Technology China

This paper studies the design, control, and learning of a novel robotic limb that produces overconstrained locomotion by employing the Bennett linkage for motion generation, capable of parametric reconfiguration between a reptile- and mammal-inspired morphology within a single quadruped. In contrast to the prevailing focus on planar linkages, this research delves into adopting overconstrained linkages as the limb mechanism. The overconstrained linkages have solid theoretical foundations in advanced kinematics but are under-explored in robotic applications. This study showcases the morphological superiority of Overconstrained Robotic Limbs (ORLs) that can transform into planar or spherical limbs, exemplified using the simplest case of a Bennett linkage as an ORL. We apply Model Predictive Control (MPC) to simulate a range of overconstrained locomotion tasks, revealing its superiority in energy efficiency against planar limbs when considering foothold distances and speeds. The results are further verified in overconstrained locomotion policies optimized from Reinforcement Learning (RL). From an evolutionary biology perspective, these findings highlight the mechanism distinctions in limb design between reptiles and mammals and represent the first documented instance of ORLs outperforming planar limb designs in dynamic locomotion. Future studies will focus on deploying the model-based and learning-based overconstrained locomotion skills in the robotic hardware to close the Sim2Real gap for developing evolutionary-inspired, energy-efficient control of novel robotic limbs. © 2023, CC BY-NC-ND.

关键词： Deep reinforcement learning

Dynamic Event-triggered Formation Control for Multi-agent systems: A Co-design Optimization Approach

学校读者我要写书评

暂无评论

Dynamic Event-triggered Formation Control for Multi-agent Sy...

American Control Conference

作者： Amir Amini Amir Asif Arash Mohammadi Electrical and Computer Engineering Concordia University Montreal Canada Concordia Institute for Information System Engineering Concordia University Montreal Canada

ISBN: (数字)9781538682661

ISBN: (纸本)9781538682678

This paper studies formation control in general linear multi-agent systems where communication between the neighbouring agents is based on the fulfillment of dynamic event-triggering (DET) conditions. A novel co-design optimization is proposed to simultaneously design all required control and DET parameters. We use the flexibility of the proposed co-design method to optimize the inter-event interval for a predefined formation convergence rate. The optimization is based on the scalarization (weighted sum) approach which provides a structured trade-off between the formation convergence rate and intensity of the event-triggerings. Simulations for multi-agent systems consisting a class of unmanned aerial vehicles (UAV) quantify the effectiveness of the proposed approach.

关键词： Optimization Convergence Eigenvalues and eigenfunctions Symmetric matrices Vehicle dynamics Multi-agent systems Unmanned aerial vehicles

A High Probability Analysis of Adaptive SGD with Momentum

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xiaoyu Orabona, Francesco Division of System Engineering Boston University MA United States Electrical & Computer Engineering Boston University MA United States

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the enormous success of these methods, our theoretical understanding of these variants in the nonconvex setting is not complete, with most of the results only proving convergence in expectation and with strong assumptions on the stochastic gradients. In this paper, we present a high probability analysis for adaptive and momentum algorithms, under weak assumptions on the function, stochastic gradients, and learning rates. We use it to prove for the first time the convergence of the gradients to zero in high probability in the smooth nonconvex setting for Delayed AdaGrad with momentum. Copyright © 2020, The Authors. All rights reserved.

关键词： Momentum

Fire Detection Method Based on Improved Fruit Fly Optimization-Based SVM

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第1期62卷 199-216页

作者： Fangming Bi Xuanyi Fu Wei Chen Weidong Fang Xuzhi Miao Biruk Assefa College of Computer Science and Technology China University of Mining and TechnologyXuzhou221116China College of Computer Science and Technology Mine Digitization Engineering Research Center of the Ministry of EducationChina University of Mining and TechnologyXuzhou221116China College of Computer Science and Technology Xi’an University of Science and TechnologyXi’an710054China Key Laboratory of Wireless Sensor Network&Communication Shanghai Institute of Micro-System and Information TechnologyChinese Academy of SciencesShanghai201899China Infromation Communication Technology Department Wollo UniversityDessie EthiopiaP.o Box 1145Ethiopia

Aiming at the defects of the traditional fire detection methods,which are caused by false positives and false negatives in large space buildings,a fire identification detection method based on video images is *** algorithm first uses the hybrid Gaussian background modeling method and the RGB color model to perform fire prejudgment on the video image,which can eliminate most non-fire ***,the traditional regional growth algorithm is improved and the fire image segmentation effect is effectively ***,based on the segmented image,the dynamic and static features of the fire flame are further analyzed and extracted in the area of the suspected fire ***,the dynamic features of the extracted fire flame images were fused and classified by improved fruit fly optimization support vector machine,and the recognition results were *** video-based fire detection method proposed in this paper greatly improves the accuracy of fire detection and is suitable for fire detection and identification in large space scenarios.

关键词： Fire detection image segmentation feature extraction fruit fly optimization support vector machine

A New Model to Analyze Power and Communication system Intra-and-Inter Dependencies

学校读者我要写书评

暂无评论

A New Model to Analyze Power and Communication System Intra-...

Conference on Technologies for Sustainability (Sustech)

作者： Sohini Roy Harish Chandrasekaran Anamitra Pal Arunabha Sen School of Computing Informatics and Decision System Engineering School of Electrical Computer and Energy Engineering Arizona State University Arizona USA

ISBN: (数字)9781728131085

ISBN: (纸本)9781728131092

The reliable and resilient operation of the smart grid necessitates a clear understanding of the intra-and-inter dependencies of its power and communication systems. This understanding can only be achieved by accurately depicting the interactions between the different components of these two systems. This paper presents a model, called modified implicative interdependency model (MIIM), for capturing these interactions. Data obtained from a power utility in the U.S. Southwest is used to ensure the validity of the model. The performance of the model for a specific power system application namely, state estimation, is demonstrated using the IEEE 118-bus system. The results indicate that the proposed model is more accurate than its predecessor, the implicative interdependency model (IIM) [1], in predicting the system state in case of failures in the power and/or communication systems.

关键词： Substations Phasor measurement units Logic gates Bandwidth Servers Smart grids SONET

Hybrid Optimization Method Using Simulated-Annealing-Based Ising Machine and Quantum Annealer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kikuchi, Shuta Togawa, Nozomu Tanaka, Shu Department of Applied Physics and Physico-Informatics Keio University Kanagawa223-8522 Japan Department of Computer Science and Communications Engineering Waseda University Tokyo169-8555 Japan Keio University Tokyo108-8345 Japan Green Computing System Research Organization Waseda University Tokyo162-0042 Japan International Research Frontiers Initiative Tokyo Institute of Technology Tokyo108-0023 Japan

Ising machines have the potential to realize fast and highly accurate solvers for combinatorial optimization problems. They are classified based on their internal algorithms. Examples include simulated-annealing-based Ising machines (non-quantum-type Ising machines) and quantum-annealing-based Ising machines (quantum annealers). Herein we propose a hybrid optimization method, which utilizes the advantages of both types. In this hybrid optimization method, the preprocessing step is performed by solving the non-quantum-annealing Ising machine multiple times. Then sub-Ising models with a reduced size by spin fixing are solved using a quantum annealer. The performance of the hybrid optimization method is evaluated via simulations using Simulated Annealing (SA) as a non-quantum-type Ising machine and D-Wave Advantage as a quantum annealer. Additionally, we investigate the parameter dependence of the proposed hybrid optimization method. The hybrid optimization method outperforms the preprocessing SA and the quantum annealing machine alone in fully connected random Ising models. Copyright © 2023, The Authors. All rights reserved.

关键词： Simulated annealing

Semidiscrete optical vortex droplets in quasi-phase-matched photonic crystals

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Xiaoxi Zhao, Feiyan Huang, Jiayao He, Hexiang Zhang, Li Chen, Zhaopin Nie, Zhongquan Malomed, Boris A. Li, Yongyao School of Physics and Optoelectronic Engineering Foshan University Foshan528000 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China Physics Department Solid-State Institute Technion Haifa32000 Israel Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi Province College of Electronic Information and Optical Engineering Taiyuan University of Technology Taiyuan030024 China Department of Physical Electronics School of Electrical Engineering Faculty of Engineering Tel Aviv University Tel Aviv69978 Israel Instituto de Alta Investigación Universidad de Tarapacá Casilla 7D Arica Chile Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology Foshan University Foshan528000 China

A new scheme for producing semidiscrete self-trapped vortices ("swirling photon droplets") in photonic crystals with competing quadratic (χ(2)) and self-defocusing cubic (χ(3)) nonlinearities is proposed. The photonic crystal is designed with a striped structure, in the form of spatially periodic modulation of the χ(2) susceptibility, which is imposed by the quasi-phase-matching technique. Unlike previous realizations of semidiscrete optical modes in composite media, built as combinations of continuous and arrayed discrete waveguides, the semidiscrete vortex "droplets" are produced here in the fully continuous medium. This work reveals that the system supports two types of semidiscrete vortex droplets, viz., onsite- and intersite-centered ones, which feature, respectively, odd and even numbers of stripes, N. Stability areas for the states with different values of N are identified in the system's parameter space. Some stability areas overlap with each other, giving rise to the multistability of states with different N. The coexisting states are mutually degenerate, featuring equal values of the Hamiltonian and propagation constant. An experimental scheme to realize the droplets is outlined, suggesting new possibilities for the long-distance transmission of nontrivial vortex beams in nonlinear media. © 2023, CC BY.

关键词： Photonic crystals