检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Zhengliang Zhong, Aoxiao Li, Yiwei Yang, Longtao Ju, Chao Wu, Zihao Ma, Chong Shu, Peng Chen, Cheng Kim, Sekeun Dai, Haixing Zhao, Lin Sun, Lichao Zhu, Dajiang Liu, Jun Liu, Wei Shen, Dinggang Li, Xiang Li, Quanzheng Liu, Tianming School of Computing University of Georgia United States Department of Electrical Engineering Harvard University United States Department of Radiology Second Xiangya Hospital China School of Automation Northwestern Polytechnical University China Department of Radiology Massachusetts General Hospital Harvard Medical School United States Department of Computer Science and Engineering Lehigh University United States Department of Computer Science and Engineering University of Texas Arlington United States Department of Radiation Oncology Mayo Clinic United States School of Biomedical Engineering ShanghaiTech University China Shanghai United Imaging Intelligence Co. Ltd. China Shanghai Clinical Research Trial Center China

We introduce Radiology-GPT, a large language model for radiology. Using an instruction tuning approach on an extensive dataset of radiology domain knowledge, Radiology-GPT demonstrates superior performance compared to general language models such as StableLM, Dolly and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication. This work serves as a catalyst for future developments in clinical NLP. The successful implementation of Radiology-GPT is indicative of the potential of localizing generative large language models, specifically tailored for distinctive medical specialties, while ensuring adherence to privacy standards such as HIPAA. The prospect of developing individualized, large-scale language models that cater to specific needs of various hospitals presents a promising direction. The fusion of conversational competence and domain-specific knowledge in these models is set to foster future development in healthcare AI. A demo of Radiology-GPT is available at https://***/spaces/allen-eric/radiology-gpt. © 2023, CC BY.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

A SURVEY ON COMPUTATIONAL SOLUTIONS FOR RECONSTRUCTING COMPLETE OBJECTS BY REASSEMBLING THEIR FRACTURED PARTS

arXiv

引用

arXiv 2024年

作者： Lu, Jiaxin Liang, Yongqing Han, Huijun Hua, Jiacheng Jiang, Junfeng Li, Xin Huang, Qixing Computer Science Department The University of Texas at Austin 2317 Speedway AustinTX United States Department of Computer Science and Engineering Texas A&M University 435 Nagle St College StationTX United States Department of Computer Science and Technology Tsinghua University 30 Shuangqing Road Beijing China College of Artificial Intelligence and Automation Hohai University 1915 Hohai Avenue Jiangsu Changzhou China Section of Visual Computing & Computational Media Department of Computer Science and Engineering Texas A&M University 789 Ross Street College StationTX United States

Reconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. This reassembly problem requires understanding the attributes of individual pieces and establishing matches between different pieces. Many approaches also model priors of the underlying complete object. Existing approaches are tightly connected problems of shape segmentation, shape matching, and learning shape priors. We provide existing algorithms in this context and emphasize their similarities and differences to general-purpose approaches. We also survey the trends from early procedural approaches to more recent deep learning approaches. In addition to algorithms, this survey will also describe existing datasets, open-source software packages, and applications. To the best of our knowledge, this is the first comprehensive survey on this topic in computer graphics. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

arXiv

引用

arXiv 2024年

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Fireclay

来源：评论

学校读者我要写书评

暂无评论

Future Networks 2030: Challenges in Intelligent Transportation Systems 8

Future Networks 2030: Challenges in Intelligent Transportati...

引用

8th IEEE International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2020

作者： Pop, Madalin-Dorin Pandey, Jitendra Ramasamy, Velmani University of Timioara Automation and Applied Informatics Timioara Romania Middle East College Department of Computing Muscat Oman Siddhartha Institute of Technology and Sciences Department of Electronics and Communication Engineering Narapally Hyderabad India

ISBN: (纸本)9781728170169

Many cities around the world implement the Intelligent Transportation Systems (ITS) concept to reduce road traffic congestion. This concept implies the usage of Internet of Things (IoT) technologies to ensure a better traffic flow, especially in crowded urban areas. Sensors networks became part of road infrastructure and have as main responsibilities to collect real-time traffic data and to send them to Traffic Management Centres (TMCs) which control further the traffic lights timings. Today's technologies meet some limitations in terms of efficiency. This paper starts with an overview of these limitations to create a path for discussing the challenges that the development of ITS will meet in the context of Future Networks (FN) 2030 concept. Based on this development path, the identification of current limitations and possible future challenges consists of an important step of this research. Further, the main contribution in this research is to show how the ITS shall adapt to meet the requirements of FN 2030 by providing an architecture for Future ITS 2030 that meets the general ITS needs. © 2020 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Trust Online Over-the-air Computation for Wireless Federated Learning

引用

IEEE Transactions on Mobile computing 2025年

作者： Sun, Mingjie Zheng, Jie Du, Hongyang Zhang, Haijun Niyato, Dusit Kang, Jiawen Wang, Jiacheng Ren, Jie Gao, Ling Wang, Zheng Northwest University State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Shaanxi Xian710127 China University of Hong Kong department of electrical and electronic engineering Hong Kong University of Science and Technology Beijing Institute of Artificial Intelligence Beijing100083 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Guangdong University of Technology Automation of School Guangzhou510006 China Shaanxi Normal University School of Computer Science Xi'an710062 China University of Leeds School of Computing LS2 9JT United Kingdom

Using the wireless waveform superposition property, over-the-air computation (OAC) enables federated learning (FL) to achieve fast model aggregation. However, this computing paradigm is vulnerable to poisoning attacks due to the openness of a wireless channel over time, where malicious mobile devices can introduce cumulative errors for the global FL model in a time-varying wireless environment for each communication round. This article presents a trust online OAC (TO-OAC) scheme to minimize impacts on the global model introduced by malicious devices adjusting to dynamic attack and wireless channel fluctuations over time. TO-OAC achieves this by utilizing trustworthy security quantification of OAC for each FL training round. To optimize the cumulative training loss at the aggregation node with the long-term power and trust constraints of mobile devices, we propose a joint trust, power, and channel-aware algorithm to flexibly update local and global models in response to the dynamic changes in the wireless and secure environment. We analyze the performance limits for the aggregation of trust models, considering metrics for computation and communication through time. We then propose another trust online regularization over-the-air computation (TOR-OAC) as an improved version of the TO-OAC scheme to decrease convergence time while ensuring long-term trust and power limitation. Experimental results performed on real-life datasets show that the two proposed schemes (TO-OAC and TOR-OAC) outperform prior works, especially in noisy, time-varying wireless channels and malicious attacks. 2002-2012 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Legibility in Multiagent Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Liu, Yanyu Pan, Yinghui Zeng, Yifeng Ma, Biyang Prashant, Doshi School of Automation Central South University No.605 South Lushan Road Hunan Changsha410083 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle United Kingdom School of Computer Science Minnan Normal University Fujian Zhangzhou China Department of Computer Science University of Georgia AthensGA United States

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others’ behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Graph Neural Network Driven Recurrent Reinforcement Learning for GNSS Position Correction 36

Efficient Graph Neural Network Driven Recurrent Reinforcemen...

引用

36th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2023

作者： Zhao, Haoli Tang, Jianhao Li, Zhenni Wu, Zhuoyu Xie, Shengli Wu, Zhaofeng Liu, Ming Kumara, Banage T.G.S. School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Guangzhou510006 China Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China Techtotop Microelectronics Technology Co. Ltd. Guangzhou510000 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Computing and Information Systems Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka

ISBN: (纸本)9780936406350

With the wide applications of the Global Navigation Satellite System (GNSS) in autonomous driving scenarios, the demand for high-precision positioning of navigation systems has increased dramatically in complex multipath environments. Conventional model-based methods are constrained by strict assumptions about noise models and can hardly model complex environment errors. In contrast, approaches based on artificial intelligent learning have become an important direction to solving the problem of high-precision positioning because learning-based approaches only require simple assumptions. However, current learning-based approaches are facing the following issues. The existing Graph Neural Network-based (GNN) method could hardly adapt to dynamically changing driving environment scenarios since it considers positioning discretely. On the other hand, existing Reinforcement Learning-based (RL) approaches ignore the relationship between multi-constellation satellites, resulting in an inadequate description of the driving correction environment observations. In this paper, we construct a GNN-driven recurrent reinforcement learning method to consider the GNSS measurement of multi-constellation satellites and to learn real-time correction strategy in the dynamic driving environment. To establish a comprehensive positioning correction environment, we construct a multi-constellation graph observation, based on the feature vector concerning GNSS measurement of multi-constellation satellites and edges for satellites in and between constellations. To make more effective use of GNSS measurements, we employ the graph embedding module to deal with the multi-constellation graph inputs, to extract hidden topological features to form the brief states about relationships between multi-constellation satellites for the RL environment. Finally, we construct a recurrent actor-critic structured RL model with cumulative reward and continuous action space to exploit historical information and a

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization for Multi-UAV-assisted Mobile Edge computing

arXiv

引用

arXiv 2024年

作者： Sun, Geng Wang, Yixian Sun, Zemin Wu, Qingqing Kang, Jiawen Niyato, Dusit Leung, Victor C.M. College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China School of Automation Guangdong University of Technology Guangzhou510006 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6T 1Z4 Canada

Recent developments in unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) have provided users with flexible and resilient computing services. However, meeting the computing-intensive and latency-sensitive demands of users poses a significant challenge due to the limited resources of UAVs. To address this challenge, we present a multi-objective optimization approach for multi-UAV-assisted MEC systems. First, we formulate a multi-objective optimization problem aiming at minimizing the total task completion delay, reducing the total UAV energy consumption, and maximizing the total amount of offloaded tasks by jointly optimizing task offloading, computation resource allocation, and UAV trajectory control. Since the problem is a mixed-integer non-linear programming (MINLP) and NP-hard problem which is challenging, we propose a joint task offloading, computation resource allocation, and UAV trajectory control (JTORATC) approach to solve the problem. However, since the decision variables of task offloading, computation resource allocation, and UAV trajectory control are coupled with each other, the original problem is split into three sub-problems, i.e., task offloading, computation resource allocation, and UAV trajectory control, which are solved individually to obtain the corresponding decisions. Moreover, the sub-problem of task offloading is solved by using distributed splitting and threshold rounding methods, the sub-problem of computation resource allocation is solved by adopting the Karush-Kuhn-Tucker (KKT) method, and the sub-problem of UAV trajectory control is solved by employing the successive convex approximation (SCA) method. Simulation results show that the proposed JTORATC has superior performance compared to the other benchmark methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Global-threshold and backbone high-resolution weather radar networks are significantly complementary in a watershed

arXiv

引用

arXiv 2022年

作者： Jorge, Aurelienne A.S. da Silva Diniz, Iuri Freitas, Vander L.S. Costa, Izabelly C. Santos, Leonardo B.L. National Institute for Space Research SP Cachoeira Paulista Brazil Department of Computing Federal University of Ouro Preto Ouro Preto Brazil SP São José dos Campos Brazil Department of Control and Automation Engineering Federal University of Ouro Preto Ouro Preto Brazil

There are several criteria for building up networks from time series related to different points in geographical space. The most used criterion is the Global-Threshold (GT). Using a weather radar dataset, this paper shows that the Backbone (BB) - a local-threshold criterion - generates networks whose geographical configuration is complementary to the GT networks. We compare the results for two well-known similarities measures: the Pearson Correlation (PC) coefficient and the Mutual Information (MI). The extracted backbone network (miBB), whose number of links is the same as the global MI (miGT), has the lowest average shortest path and presents a small-world effect. Regarding the global PC (pcGT) and its corresponding BB network (pcBB), there is a significant linear relationship: R2 = 0.77 with a slope of 1.15 (p-value © 2022, CC BY-NC-SA.

关键词： Watersheds

来源：评论

学校读者我要写书评

暂无评论

GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

arXiv

引用

arXiv 2022年

作者： Liu, Jianan Bai, Liping Xia, Yuxuan Huang, Tao Zhu, Bing Han, Qing-Long Vitalent Consulting Gothenburg Sweden The School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Electrical Engineering Chalmers University of Technology Gothenburg41296 Sweden College of Science and Engineering James Cook University SmithfieldQLD4878 Australia The School of Science Computing and Engineering Technologies Swinburne University of Technology MelbourneVIC3122 Australia

Multi-object tracking (MOT) is among crucial applications in modern advanced driver assistance systems (ADAS) and autonomous driving (AD) systems. The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry. The development of random finite set (RFS) theory facilitates a mathematically rigorous treatment of the MOT problem, and different variants of RFS-based Bayesian filters have then been proposed. However, their effectiveness in the real ADAS and AD application is still an open problem. In this paper, it is demonstrated that the latest RFS-based Bayesian tracking framework could be superior to typical random vector-based Bayesian tracking framework via a systematic comparative study of both traditional random vector-based Bayesian filters with rule-based heuristic track maintenance and RFS-based Bayesian filters on the nuScenes validation dataset. An RFS-based tracker, namely Poisson multi-Bernoulli filter using the global nearest neighbor (GNN-PMB), is proposed to LiDAR-based MOT tasks. This GNN-PMB tracker is simple to use, and it achieves competitive results on the nuScenes dataset. Specifically, the proposed GNN-PMB tracker outperforms most state-of-the-art LiDAR-only trackers and LiDAR and camera fusion-based trackers, ranking the 3rd among all LiDAR-only trackers on nuScenes 3D tracking challenge leader board at the time of submission. Our code is available at https://***/chisyliu/GnnPmbTracker. © 2022, CC BY.

关键词： Automotive industry

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：