检索结果-内蒙古大学图书馆

Distributed Task-Oriented Communication Networks with Multimodal Semantic Relay and Edge Intelligence

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Jie Chen, Hao Song, Bin Chi, Yuhao Yuen, Chau Yu, Fei Richard Li, Geoffrey Ye Niyato, Dusit The State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China The Hangzhou Institute of Technology Xidian University Hangzhou311231 China The School of Electrical and Electronics Engineering The School of Computer Science and Engineering Respectively Nanyang Technological University 639798 Singapore The Department of Systems and Computer Engineering Carleton University OttawaK1S 5B6 Canada The Faculty of Engineering Imperial College London LondonSW7 2AZ United Kingdom

In this article, we present a novel framework, named distributed task-oriented communication networks (DTCN), based on recent advances in multimodal semantic transmission and edge intelligence. In DTCN, the multimodal knowledge of semantic relays and the adaptive adjustment capability of edge intelligence can be integrated to improve task performance. Specifically, we propose the key techniques in the framework, such as semantic alignment and complement, a semantic relay scheme for deep joint source-channel relay coding, and collaborative device-server optimization and inference. Furthermore, a multimodal classification task is used as an example to demonstrate the benefits of the proposed DTCN over existing methods. Numerical results validate that DTCN can significantly improve the accuracy of classification tasks, even in harsh communication scenarios (e.g., low signal-to-noise regime), thanks to multimodal semantic relay and edge intelligence. © 2024, CC BY-NC-SA.

关键词： Signal to noise ratio

Energy-Based Control Approaches for Weakly Coupled Electromechanical systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Javanmardi, Najmeh Borja, P. Yazdanpanah, M.J. Scherpen, J.M.A. Jan C. Willems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen Groningen Netherlands School of Engineering Computing and Mathematics University of Plymouth Plymouth United Kingdom Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

This paper addresses the regulation and trajectory-tracking problems for two classes of weakly coupled electromechanical systems. To this end, we formulate an energy-based model for these systems within the port-Hamiltonian framework. Then, we employ Lyapunov theory and the notion of contractive systems to develop control approaches in the port-Hamiltonian framework. Remarkably, these control methods eliminate the need for solving partial differential equations or implementing any change of coordinates, and are endowed with a physical interpretation. We also investigate the effect of coupled damping on the transient performance and convergence rate of the closed-loop system. Finally, the applicability of the proposed approaches is illustrated in two applications of electromechanical systems via simulations. © 2024, CC BY.

关键词： Damping

Multiagent Reinforcement Learning with an Attention Mechanism for Improving Energy Efficiency in LoRa Networks

学校读者我要写书评

暂无评论

Multiagent Reinforcement Learning with an Attention Mechanis...

IEEE Conference on Global Communications (GLOBECOM)

作者： Xu Zhang Ziqi Lin Shimin Gong Bo Gu Dusit Niyato School of Intelligent Systems Engineering Sun Yat-sen University China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

Long Range (LoRa) wireless technology, characterized by low power consumption and a long communication range, is regarded as one of the enabling technologies for the Industrial Internet of Things (IIoT). However, as the network scale increases, the energy efficiency (EE) of LoRa networks decreases sharply due to severe packet collisions. To address this issue, it is essential to appropriately assign transmission parameters such as the spreading factor and transmission power for each end device (ED). However, due to the sporadic traffic and low duty cycle of LoRa networks, evaluating the system EE performance under different parameter settings is time-consuming. Therefore, we first formulate an analytical model to calculate the system EE. On this basis, we propose a transmission parameter allocation algorithm based on multiagent reinforcement learning (MALoRa) with the aim of maximizing the system EE of LoRa networks. Notably, MALoRa employs an attention mechanism to guide each ED to better learn how much “attention” should be given to the parameter assignments for relevant EDs when seeking to improve the system EE. Simulation results demonstrate that MALoRa significantly improves the system EE compared with baseline algorithms with an acceptable degradation in packet delivery rate (PDR).

关键词：

Multiagent Reinforcement Learning with an Attention Mechanism for Improving Energy Efficiency in LoRa Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xu Lin, Ziqi Gong, Shimin Gu, Bo Niyato, Dusit School of Intelligent Systems Engineering Sun Yat-sen University China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

Long Range (LoRa) wireless technology, characterized by low power consumption and a long communication range, is regarded as one of the enabling technologies for the Industrial Internet of Things (IIoT). However, as the network scale increases, the energy efficiency (EE) of LoRa networks decreases sharply due to severe packet collisions. To address this issue, it is essential to appropriately assign transmission parameters such as the spreading factor and transmission power for each end device (ED). However, due to the sporadic traffic and low duty cycle of LoRa networks, evaluating the system EE performance under different parameter settings is time-consuming. Therefore, we first formulate an analytical model to calculate the system EE. On this basis, we propose a transmission parameter allocation algorithm based on multiagent reinforcement learning (MALoRa) with the aim of maximizing the system EE of LoRa networks. Notably, MALoRa employs an attention mechanism to guide each ED to better learn how much "attention" should be given to the parameter assignments for relevant EDs when seeking to improve the system EE. Simulation results demonstrate that MALoRa significantly improves the system EE compared with baseline algorithms with an acceptable degradation in packet delivery rate (PDR). Copyright © 2023, The Authors. All rights reserved.

关键词： Energy efficiency

Is Underwater Image Enhancement All Object Detectors Need?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yudong Guo, Jichang He, Wanru Gao, Huan Yue, Huihui Zhang, Zenan Li, Chongyi The School of Electrical and Information Engineering Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China The School of Computer Science Nankai University Tianjin300071 China

Underwater object detection is a crucial and challenging problem in marine engineering and aquatic robot. The difficulty is partly because of the degradation of underwater images caused by light selective absorption and scattering. Intuitively, enhancing underwater images can benefit high-level applications like underwater object detection. However, it is still unclear whether all object detectors need underwater image enhancement as pre-processing. We therefore pose the questions "Does underwater image enhancement really improve underwater object detection?" and "How does underwater image enhancement contribute to underwater object detection?". With these two questions, we conduct extensive studies. Specifically, we use 18 state-of-the-art underwater image enhancement algorithms, covering traditional, CNN-based, and GAN-based algorithms, to pre-process underwater object detection data. Then, we retrain 7 popular deep learning-based object detectors using the corresponding results enhanced by different algorithms, obtaining 126 underwater object detection models. Coupled with 7 object detection models retrained using raw underwater images, we employ these 133 models to comprehensively analyze the effect of underwater image enhancement on underwater object detection. We expect this study can provide sufficient exploration to answer the aforementioned questions and draw more attention of the community to the joint problem of underwater image enhancement and underwater object detection. The pre-trained models and results are publicly available and will be regularly updated. Project page: https://***/BIGWangYuDong/lqit/tree/main/configs/detection/uw_enhancement_affect_detection. © 2023, CC BY.

关键词： Object detection

Train Timetable Optimization with Consideration of Passenger Choices in a Multi-modal Rail-Transit System

学校读者我要写书评

暂无评论

Train Timetable Optimization with Consideration of Passenger...

2024 世界交通运输大会

作者： Yiyao Zhang Jiateng Yin D'Ariano Andrea Yihui Wang State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University School of Systems Science Beijing Jiaotong University Department of Civil Computer Science and Aeronautical Technologies EngineeringRoma Tre University

With the emerging of Mobility-as-a-Service(MaaS),the coordination of multi-modal transportation,such as urban rail transit and buses,has received tremendous attention in recent years.A key challenge in the coordination of multi-modal transportation is the interaction between the operational plan and passenger choices,since passengers have different travel choices according to their individual *** address the above challenge,this study proposes a novel bi-level optimization framework,where the upper level aims to design a timetable for the trains in a rail-transit network to maximize the overall profit,while the lower level determines the itinerary choice of passengers,given the operational timetable from the upper *** solve the difficult bi-level model,we developed an iterative method,where the timetables and passenger choices are iteratively updated and improved to a local optimal *** experiments on a real-world case study in Beijing demonstrate the effectiveness of the proposed *** found that the consideration of passenger choice preferences has an obvious impact on the timetable planning.

关键词： Rail Transit Network Passenger Choice Behaviours Train Timetable Scheduling Bi-level Optimization Model

Enhancing Quantum Emission from Spin Defects in Hexagonal Boron Nitride with a Plasmonic Nanocavity

学校读者我要写书评

暂无评论

Enhancing Quantum Emission from Spin Defects in Hexagonal Bo...

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Xu, Xiaohui Solanki, Abhishek B. Sychev, Demid Gao, Xingyu Peana, Samuel Baburin, Alexander S. Pagadala, Karthik Martin, Zachariah O. Chowdhury, Sarah N. Chen, Yong P. Taniguchi, Takashi Watanabe, Kenji Rodionov, Ilya A. Kildishev, Alexander Li, Tongcang Upadhyaya, Pramey Boltasseva, Alexandra Shalaev, Vladimir M. School of Materials Engineering Purdue University West LafayetteIN47907 United States School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Department of Physics and Astronomy Purdue University West LafayetteIN47907 United States FMN Laboratory BaumanMoscow State Technical University Moscow105005 Russia National Institute for Materials Science Namiki Tsukuba305-0044 Japan Moscow127055 Russia

We report a 250-fold photoluminescence enhancement of VB- spin-defects in hBN by coupling them to nanopatch antennas (NPA). Considering the relative size of the NPAs and laser-spot, an actual enhancement of 1695 times... 详细信息

ISBN: (纸本)9781957171258

关键词： Defects

An Agile Adaptation Method for Multi-mode Vehicle Communication Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Shiwen Chen, Kanghong Huang, Shiyue Huang, Wei An, Zhenyu The School of Computer Science and Engineering Central South University Changsha410083 China The Purple Mountain Laboratories Nanjing211111 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China The Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei230601 China The Purple Mountain Laboratories Nanjing210096 China

This paper focuses on discovering the impact of communication mode allocation on communication efficiency in the vehicle communication networks. To be specific, Markov decision process and reinforcement learning are applied to establish an agile adaptation mechanism for multi-mode communication devices according to the driving scenarios and business requirements. Then, Q-learning is used to train the agile adaptation reinforcement learning model and output the trained model. By learning the best actions to take in different states to maximize the cumulative reward, and avoiding the problem of poor adaptation effect caused by inaccurate delay measurement in unstable communication scenarios. The experiments show that the proposed scheme can quickly adapt to dynamic vehicle networking environment, while achieving high concurrency and communication efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Vehicle to vehicle communications

A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ji, Zhong Yang, Shuo Liu, Jingren Pang, Yanwei Han, Jungong School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Department of Computer Science The University of Sheffield United Kingdom

Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix Ā based on cosine similarity, failing to achieve zero base-novel regions and adequate sparsity in base and novel domains. To address these deficiencies, we propose a Non-Negative Generalized Category Discovery (NN-GCD) framework. It employs Symmetric Non-negative Matrix Factorization (SNMF) as a mathematical medium to prove the equivalence of optimal K-means with optimal SNMF, and the equivalence of SNMF solver with non-negative contrastive learning (NCL) optimization. Utilizing these theoretical equivalences, it reframes the optimization of Ā and K-means clustering as an NCL optimization problem. Moreover, to satisfy the nonnegative constraints and make a GCD model converge to a near-optimal region, we propose a GELU activation function and an NMF NCE loss. To transition Ā from a suboptimal state to the desired Ā∗, we introduce a hybrid sparse regularization approach to impose sparsity constraints. Experimental results show NN-GCD outperforms state-of-the-art methods on GCD benchmarks, achieving an average accuracy of 66.1% on the Semantic Shift Benchmark, surpassing prior counterparts by 4.7%. Copyright © 2024, The Authors. All rights reserved.

关键词： Non-negative matrix factorization