检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Wang, Xiaobo Liang, Wenyi Yu, Fenfen Hu, Yiren Cheng, Libo Xie, Anhuan Research Center for Intelligent Equipment Zhejiang Lab Hangzhou China Online Marketing Service Center China Mobile Communications Co. Ltd. Hangzhou China Space-based Computing System Research Center Zhejiang Lab Hangzhou China Frontier Basic Research Center Zhejiang Lab Hangzhou China

ISBN: (纸本)9798350368604

The avionics system plays a critical role in ensuring the operation of an aircraft, facilitating communication between the aircraft and ground, detecting and displaying aircraft status, as well as coordinating data exchange and processing among various systems. This paper presents an architecture of the avionics system for a manned electric vertical takeoff and landing (eVTOL) aircraft, which mainly includes the flight control system, navigation sensor system, communication system, intelligent onboard computer system, and cloud monitoring system. Detailed descriptions are provided for the redundant flight control system, sensor redundancy design, and intelligent onboard computer system. Various flight tests, including manned flight, cargo transportation, endurance, range, speed, and fault tolerance tests, are conducted on the aircraft equipped with this avionics system. The flight tests have exceeded a thousand. Analysis of flight log data demonstrates that the designed avionics system meets the safety and functionality requirements of the manned eVTOL aircraft. © 2024 IEEE.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

Design and Experiment of Soft Gripper with Shape Memory Alloy Actuator

Design and Experiment of Soft Gripper with Shape Memory Allo...

引用

第43届中国控制会议

作者： Xiaobo Wang Wenyi Liang Fenfen Yu Yutao Chen Research Center for Intelligent Equipment Zhejiang Lab Online Marketing Service Center China Mobile Communications Co. Ltd. Research Center for Intelligent Manufacturing Computing Zhejiang Lab

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Compared to traditional rigid mechanical grippers, soft grippers have higher flexibility, stronger adaptability, simpler control, and are less likely to cause damage to objects. This paper first designs a soft actuator that uses the memory effect of shape memory alloy for motion, and the structure and control system of the soft actuator are simple. Based on the soft actuator, a five-finger soft gripper(Gripper-Ⅰ) composed of the soft actuators and a base was designed. A series of gripping experiments were conducted on Gripper-Ⅰ, which proved the effectiveness, stability, and safety of Gripper-Ⅰ grips. However, limitations were observed in the gripping radius of Gripper-Ⅰ during the experiment. To address this issue, a new type of three-finger soft gripper(Gripper-Ⅱ) based on machine vision was developed to automatically adjust the gripping radius. Gripper-Ⅱ consists of a base,servo adjustment devices, and soft actuators. Experiments were also performed on Gripper-Ⅱ, which verified the function of automatic radius adjustment.

关键词： soft gripper shape memory alloy soft actuator gripping experiment automatic radius adjustment

来源：评论

学校读者我要写书评

暂无评论

Service decoupling for open and intelligent service-based RAN

引用

Frontiers of Information Technology & Electronic Engineering 2025年第2期26卷 230-245页

作者： Chunjing YUAN Tong LEI Ze XUE Lin TIAN Shuyuan ZHANG Na LI Zhou TONG Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China Hubei Intelligent Cloud Network Operation Center China TelecomWuhan 430024China Nanjing Institute of InforSuperBahn Nanjing 210008China Future Research Lab China Mobile Research InstituteBeijing 100053China

Task diversity is one of the biggest challenges for future sixth-generation(6G)*** the task as the center and driving the dynamic 6G radio access network(RAN)with artificial intelligence(AI)are necessary to accurately meet the personalized demands of ***,AI can only configure the parameters of a monolithic RAN and cannot schedule the *** development trend of 6G RANs is to enhance dynamic capability and scheduling *** this paper,we propose a service-based RAN architecture that can deploy decoupled RAN functions and customize networks according to *** analysis shows that the interactive relationship between RAN control plane(CP)functions is complex and needs to be decoupled according to the principles of high cohesion and low *** on the graph theory rather than expert experience,we design a RAN decoupling *** functional connection and interaction of the CP are represented by constructing an undirected weighted graph,followed by achieving decoupling of the CP through a minimum spanning *** an integration decoupling scheme of a RAN-CN(core network)is introduced considering the duplicate and redundant functions of the RAN and *** granularity of decoupling in a service-based RAN is determined by analyzing the flexibility of decoupling,complexity of signaling,and processing *** find that it is more appropriate to decouple the RAN CP into four *** integration decoupling of the RAN-CN resolves the technical bottleneck of low serial efficiency in the Ng interface,supporting AI-based global service scheduling.

关键词： Service decoupling Open and intelligent Service-based radio access network(RAN) Graph theory Full-service 6G network

来源：评论

学校读者我要写书评

暂无评论

Auto Encoding Neural Process for Multi-interest Recommendation 39

Auto Encoding Neural Process for Multi-interest Recommendati...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jiang, Yiheng Xu, Yuanbo Yang, Yongjian Yang, Funing Wang, Pengyang Li, Chaozhuo Lab of Mobile Intelligent Computing College of Computer Science and Technology Jilin University China Department of Computer and Information Science The State Key Laboratory of Internet of Things for Smart City University of Macau Macao Beijing University of Aeronautics and Astronautics China

ISBN: (纸本)157735897X

Multi-interest recommendation constantly aspires to an oracle individual preference modeling approach, one that satisfies the diverse and dynamic properties. Fueled by deep learning technologies, existing neural network (NN)-based recommender systems employ single-point or multi-point interest representation strategies for preference modeling, and boost the recommendation performance with remarkable margins. However, as the parameterized approximate function nature, NN-based methods remain deficiencies regarding the adaptability towards distinctive preference patterns cross different users, and the calibration over individual current intents. In this paper, we revisit multi-interest recommendation with the lens of stochastic process and Bayesian inference. Specifically, we propose to learn a distribution over functions to depict the individual diverse preferences rather than a unified function to approximate preference. Subsequently, the recommendation is equipped with the uncertainty estimation which conforms to the dynamic shifting intent. Along these lines, we establish the connection between multi-interest recommendation and neural processes by proposing NP-Rec, which realizes the flexible multiple interests modeling and uncertainty estimation, simultaneously. Empirical study on 4 real world datasets demonstrates that our NP-Rec attains superior recommendation performances to several state-of-the-art baselines, where the average improvement achieves up to 13.94%. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward 3-D AAV-Ground BS CoMP-NOMA Transmission: Optimal Resource Allocation and Trajectory Design

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 9671-9686页

作者： Zeng, Haiyong Zhang, Rui Zhu, Xu Wei, Zhongxiang Jiang, Yufei Sun, Sumei Zheng, Fu-Chun Cao, Bin Guangxi Normal Univ Sch Elect & Informat Engn Sch Integrated Circuits Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin 541001 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Guilin 541001 Peoples R China Guangxi Normal Univ Sch Elect & Informat Engn Sch Integrated Circuits Guangxi Key Lab Brain Inspired Computing & Intelli Guilin 541001 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Guilin 541001 Peoples R China Harbin Inst Technol Shenzhen Guangdong Prov Key Lab Aerosp Commun & Networking Sch Elect & Informat Engn Shenzhen 510855 Peoples R China Harbin Inst ofTechnol Shenzhen Key Lab AIoT Commun Shenzhen 518055 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200070 Peoples R China Tongji Univ Coll Elect & Informat Engn Shanghai 200070 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 211102 Peoples R China Agcy Sci Technol & Res Inst Infocomm Res Dept Commun & Networks Singapore Singapore

In this article, we focus on the resource allocation and autonomous aerial vehicle (AAV) 3-D trajectory design for the AAV-ground base station (GBS) coordinated multipoint nonorthogonal multiple access (CoMP-NOMA) system to maximize the sum-rate of CoMP users while maintaining users' high Quality of Service requirements. The main contributions of this article are summarized as follows: 1) with the assistance of closed-form power allocation result, a generalized joint user scheduling and power allocation (G-USPA) algorithm is proposed to derive the optimal user scheduling solution;2) by revealing the monotone increasing relationship between the sum transmit power and the transmit rates of non-CoMP users, the optimal rate of each non-CoMP users turns out to be its inherent minimum required rate, consequently, the optimal transmit rates and power allocation of all users can also be derived;and 3) moreover, considering the Line of Sight (LoS) and non-LoS factors in the air-ground channel, the 3-D trajectory of AAV is designed based on successive convex approximation to provide a flexible user-centric service. The proposed G-USPA algorithm is compatible with the AAV trajectory design, which is optimized alternatively and can lead to fast convergence. Numerical results verify that the 3-D AAV-GBS CoMP-NOMA model and the G-USPA scheme have a superior performance in terms of total system sum rate and the sum rate of CoMP users over the non-CoMP AAV assisted nonorthogonal multiple access (NOMA) systems.

关键词： Autonomous aerial vehicles NOMA Resource management Trajectory Three-dimensional displays Interference Air to ground communication Quality of service Scheduling Internet of Things 3-D trajectory design air-ground (A2G) coordinated multipoint (CoMP) transmission nonorthogonal multiple access (NOMA) resource allocation autonomous aerial vehicle (AAV)

来源：评论

学校读者我要写书评

暂无评论

Avionics System Architecture Design of a Manned eVTOL Aircraft

Avionics System Architecture Design of a Manned eVTOL Aircra...

引用

Chinese Automation Congress (CAC)

作者： Xiaobo Wang Wenyi Liang Fenfen Yu Yiren Hu Libo Cheng Anhuan Xie Research Center for Intelligent Equipment Zhejiang Lab Hangzhou China Online Marketing Service Center China Mobile Communications Co. Ltd. Hangzhou China Space-based Computing System Research Center Zhejiang Lab Hangzhou China Frontier Basic Research Center Zhejiang Lab Hangzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

关键词： Redundancy Fault tolerant systems Systems architecture Computer architecture Aerospace electronics Aircraft navigation Sensor systems Safety Aircraft Aerospace control

来源：评论

学校读者我要写书评

暂无评论

Aligning Recommendation and Conversation via Dual Imitation

Aligning Recommendation and Conversation via Dual Imitation

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Zhou, Jinfeng Wang, Bo Huang, Minlie Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition People's Daily Online Beijing China The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics. © 2022 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Resilient Over-the-Air Federated Learning under Zero-Trust Architecture

arXiv

引用

arXiv 2025年

作者： Yao, Jiacheng Shi, Wei Xu, Wei Yang, Zhaohui Swindlehurst, A. Lee Niyato, Dusit The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China The Research Institute of Intelligent Networks Zhejiang Lab Hangzhou311121 China The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Center for Pervasive Communications and Computing Henry Samueli School of Engineering University of California at Irvine IrvineCA92697 United States The School of Computer Science and Engineering Nanyang Technological University Singapore308232 Singapore

Over-the-air computation (AirComp) has emerged as an essential approach for enabling communication-efficient federated learning (FL) over wireless networks. Nonetheless, the inherent analog transmission mechanism in AirComp-based FL (AirFL) intensifies challenges posed by potential Byzantine attacks. In this paper, we propose a novel Byzantine-robust FL paradigm for over-the-air transmissions, referred to as federated learning with secure adaptive clustering (FedSAC). FedSAC aims to protect a portion of the devices from attacks through zero trust architecture (ZTA) based Byzantine identification and adaptive device clustering. By conducting a one-step convergence analysis, we theoretically characterize the convergence behavior with different device clustering mechanisms and uneven aggregation weighting factors for each device. Building upon our analytical results, we formulate a joint optimization problem for the clustering and weighting factors in each communication round. To facilitate the targeted optimization, we propose a dynamic Byzantine identification method using historical reputation based on ZTA. Furthermore, we introduce a sequential clustering method, transforming the joint optimization into a weighting optimization problem without sacrificing the optimality. To optimize the weighting, we capitalize on the penalty convex-concave procedure (P-CCP) to obtain a stationary solution. Numerical results substantiate the superiority of the proposed FedSAC over existing methods in terms of both test accuracy and convergence rate. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Aligning Recommendation and Conversation via Dual Imitation

arXiv

引用

arXiv 2022年

作者： Zhou, Jinfeng Wang, Bo Huang, Minlie Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition People’s Daily Online Beijing China The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

MAC-AC: A Novel Distributed MAC Protocol for Accessing Channel in Vehicular Ad Hoc Networks

MAC-AC: A Novel Distributed MAC Protocol for Accessing Chann...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Baozhu Li Fen Hou Changyue Zhang Shaohua Li Shujuan Ji Shanzhi Chen School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network-based Intelligent Computing Jinan China Faculty of Science and Technology University of Macau Macau China Automotive Research Institute China National Heavy Duty Truck Group Co. Ltd Jinan China Shandong Key Laboratory of Wisdom Mine Information Technology Qingdao China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China State Key Lab of Wireless Mobile Communication Beijing China China Academy of Telecommunication Technology Beijing China

ISBN: (数字)9781728194844

ISBN: (纸本)9781728194851

As a promising paradigm, VANET has been attracting more and more attention from the industry and academia recently. However, due to rapid movement of vehicles and highly dynamic topology, designing efficient MAC protocol for VANET is still challenging. In this paper, we propose MAC-AC, a novel TDMA-based distributed MAC protocol designed specifically for a vehicular ad hoc network. In MAC-AC, when multiple vehicles compete for the same time slot within their two-hop communication range, one of contending vehicle can obtain this time slot by a simple method, which increases the success probability of vehicles accessing channel. Analysis results are presented to demonstrate the efficiency of MAC-AC and compare it to ADHOC MAC, an existing MAC protocol based on TDMA.

关键词： Vehicular and wireless technologies Time division multiple access Network topology Vehicular ad hoc networks Media Access Protocol Topology Vehicle dynamics

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：