检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4163-4175页

作者： Ma, Chong Wu, Zihao Wang, Jiaqi Xu, Shaochen Wei, Yaonai Liu, Zhengliang Zeng, Fang Jiang, Xi Guo, Lei Cai, Xiaoyan Zhang, Shu Zhang, Tuo Zhu, Dajiang Shen, Dinggang Liu, Tianming Li, Xiang Northwestern Polytechnical University School of Automation Xi'an710072 China University of Georgia School of Computing AthensGA30602 United States Northwestern Polytechnical University School of Computer Science Xi'an710072 China Massachusetts General Hospital Department of Radiology BostonMA02114 United States University of Electronic Science and Technology of China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China The University of Texas at Arlington Department of Computer Science and Engineering ArlingtonVA76019 United States ShanghaiTech University School of Biomedical Engineering Shanghai201210 China Shanghai United Imaging Intelligence Company Ltd. Department of Research and Development Shanghai200030 China Shanghai Clinical Research and Trial Center Shanghai201210 China

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians. Typically written by radiologists, this part is derived from the 'Findings' section, which can be laborious and error-prone. Although deep-learning-based models, such as bidirectional encoder representation from transformers (BERT), have achieved promising results in automatic impression generation (AIG), such models often require substantial amounts of medical data and have poor generalization performance. Recently, large language models (LLMs) like Chat Generative Pre-trained Transformer (ChatGPT) have shown strong generalization capabilities and performance, but their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, leveraging the contextual learning capabilities of LLMs through our dynamic prompt and iterative optimization algorithm to accomplish the AIG task. ImpressionGPT initially employs a small amount of domain-specific data to create a dynamic prompt, extracting contextual semantic information closely related to the test data. Subsequently, the iterative optimization algorithm automatically evaluates the output of LLMs and provides optimization suggestions, continuously refining the output results. The proposed ImpressionGPT model achieves superior performance of AIG task on both the Medical Information Mart for Intensive Care - Chest X-ray database (MIMIC-CXR) and Open Access Biomedical Image Search Engine (OpenI) datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Immense Impact of Reverse Edges on Large Hierarchical Networks

引用

Engineering 2024年第5期36卷 240-249页

作者： Haosen Cao Bin-Bin Hu Xiaoyu Mo Duxin Chen Jianxi Gao Ye Yuan Guanrong Chen Tamás Vicsek Xiaohong Guan Hai-Tao Zhang MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Intelligent Manufacturing Equipment and TechnologySchool of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore 639798Singapore Jiangsu Key Laboratory of Networked Collective Intelligence School of MathematicsSoutheast UniversityNanjing 210096China Department of Computer Science Rensselaer Polytechnic InstituteTroyNY 12180USA Department of Electronic Engineering City University of Hong KongHong Kong 999077China Department of Biological Physics Eötvös UniversityBudapest 1117Hungary MOE Key Laboratory for Intelligent Networks and Network Security School of Automation Science and EngineeringXi’an Jiaotong UniversityXi’an 710049China

Hierarchical networks are frequently encountered in animal groups,gene networks,and artificial engineering systems such as multiple robots,unmanned vehicle systems,smart grids,wind farm networks,and so *** structure of a large directed hierarchical network is often strongly influenced by reverse edges from lower-to higher-level nodes,such as lagging birds’howl in a flock or the opinions of lowerlevel individuals feeding back to higher-level ones in a social *** study reveals that,for most large-scale real hierarchical networks,the majority of the reverse edges do not affect the synchronization process of the entire network;the synchronization process is influenced only by a small part of these reverse edges along specific *** surprisingly,a single effective reverse edge can slow down the synchronization of a huge hierarchical network by over 60%.The effect of such edges depends not on the network size but only on the average in-degree of the involved *** overwhelming majority of active reverse edges turn out to have some kind of“bunching”effect on the information flows of hierarchical networks,which slows down synchronization *** finding refines the current understanding of the role of reverse edges in many natural,social,and engineering hierarchical networks,which might be beneficial for precisely tuning the synchronization rhythms of these *** study also proposes an effective way to attack a hierarchical network by adding a malicious reverse edge to it and provides some guidance for protecting a network by screening out the specific small proportion of vulnerable nodes.

关键词： Synchronizability Large hierarchical networks Reverse edges Information flows Complex networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Cross-Lingual Features and Weight Fusion for Cross-Cultural Humor Detection 4

Multimodal Cross-Lingual Features and Weight Fusion for Cros...

引用

4th Multimodal Sentiment Analysis Challenge and Workshop, MuSe 2023, In conjunction with ACM Multimedia 2023

作者： Xie, Heng Cui, Jizhou Cao, Yuhang Chen, Junjie Tao, Jianhua Fan, Cunhang Liu, Xuefei Wen, Zhengqi Lu, Heng Yang, Yuguang Lv, Zhao Li, Yongwei Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China School of Information Science and Technology ShanghaiTech University Shanghai China Ximalaya Inc. Shanghai China College of Computer and Information Engineering Tianjin Normal University Tianjin China Department of Automation Tsinghua University Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400702709

Sentiment analysis plays a crucial role in interpreting human interactions across different modalities. This paper addresses the Cross-Cultural Multilingual Humour Detection Sub-Challenge in the MuSe 2023 Multi-modal Sentiment Analysis Challenge, which aims to identify humor instances in cross-cultural situations using multimodal data. In this paper, we explore the unique window length processing of audio data to more accurately and fully capture humor information. Furthermore, we employ a data augmentation technique for text to bridge the gap between the train set and the test set. This augmentation involves converting German and English samples in the database to each other, as well as translating both languages into Chinese. These techniques aim to enhance the model's generalization across different languages and alleviate the scarcity of humor samples. For multimodal fusion, we use the late fusion technique applied to different Gated Recurrent Unit (GRU) models with modality-specific weights obtained through gradient descent. Experimental results demonstrate the effectiveness of our approach, achieving an Area Under the Curve (AUC) score of 0.872 on the MuSe-Humor test set. This performance ranked second place in the sub-challenge. © 2023 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Approximation Schemes for Geometric Knapsack for Packing Spheres and Fat Objects

arXiv

引用

arXiv 2024年

作者： Acharya, Pritam Bhore, Sujoy Gupta, Aaryan Khan, Arindam Mondal, Bratin Wiese, Andreas Department of Mathematics Indian Institute of Science Education and Research Pune India Department of Computer Science and Engineering Indian Institute of Technology Bombay India Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Mathematics Technical University of Munich Germany

We study the geometric knapsack problem in which we are given a set of d-dimensional objects (each with associated profits) and the goal is to find the maximum profit subset that can be packed non-overlappingly into a given d-dimensional (unit hypercube) knapsack. Even if d = 2 and all input objects are disks, this problem is known to be NP-hard [Demaine, Fekete, Lang, 2010]. In this paper, we give polynomial time (1 + Ε)-approximation algorithms for the following types of input objects in any constant dimension d: disks and hyperspheres, a class of fat convex polygons that generalizes regular k-gons for k ≥ 5 (formally, polygons with a constant number of edges, whose lengths are in a bounded range, and in which each angle is strictly larger than π/2), arbitrary fat convex objects that are sufficiently small compared to the knapsack. We remark that in our PTAS for disks and hyperspheres, we output the computed set of objects, but for a OΕ(1) of them, we determine their coordinates only up to an exponentially small error. However, it is unclear whether there always exists a (1 + Ε)-approximate solution that uses only rational coordinates for the disks’ centers. We leave this as an open problem that is related to well-studied geometric questions in the realm of circle packing. © 2024, CC BY.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Region-Based Optimization in Continual Learning for Audio Deepfake Detection 39

Region-Based Optimization in Continual Learning for Audio De...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Yujie Yi, Jiangyan Fan, Cunhang Tao, Jianhua Ren, Yong Zeng, Siding Zhang, Chu Yuan Yan, Xinrui Gu, Hao Xue, Jun Wang, Chenglong Lv, Zhao Zhang, Xiaohui School of Computer Science and Technology Anhui University China Institute of Automation Chinese Academy of Sciences China Department of Automation Tsinghua University China Beijing National Research Center for lnformation Science and Technology Tsinghua University China

ISBN: (纸本)157735897X

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive optimization ensures an appropriate trade-off between memory stability and learning plasticity. Additionally, to address the increase of redundant neurons from old tasks, we further introduce the Ebbinghaus forgetting mechanism to release them, thereby promoting the model’s ability to learn more generalized discriminative features. Experimental results show our method achieves a 21.3 percent improvement in EER over the state-of-the-art continual learning approach RWM for audio deepfake detection. Moreover, the effectiveness of RegO extends beyond the audio deepfake detection domain, showing potential significance in other tasks, such as image recognition. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning 37

ALIM: Adjusting Label Importance Mechanism for Noisy Partial...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Xu, Mingyu Lian, Zheng Feng, Lei Liu, Bin Tao, Jianhua The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Automation Tsinghua University China Beijing National Research Center for Information Science and Technology Tsinghua University China

ISBN: (纸本)9781713899921

Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate label set. To address this challenging problem, most of the existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample. However, detection errors are unavoidable. These errors can accumulate during training and continuously affect model optimization. To this end, we propose a novel framework for noisy PLL with theoretical interpretations, called "Adjusting Label Importance Mechanism (ALIM)". It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs. ALIM is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets demonstrate that our method can achieve state-of-the-art performance on noisy PLL. Our code is available at: https://***/zeroQiaoba/ALIM. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Four-Beam Phased Antenna Array Based on Multi-Element End-Fed Dipole-Like Radiator 25

Four-Beam Phased Antenna Array Based on Multi-Element End-Fe...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Kolesnikov, Andrey A. Parshin, Yury N. Alekseytsev, Sergey A. Dept. of Radio Receivers and Radio Transmitters Novosibirsk State Technical University Novosibirsk Russia JSC "Research Institute of Measuring Instruments Novosibirsk Plant named after. Comintern" Novosibirsk Russia Dept. of Automation and Computer Science Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350389234

The paper aimed on the development of a four-beam printed phased antenna array employing a Butler matrix for radiation pattern formation and end-fed multi-element dipole-like radiators. Simulation results using "CST Studio Suite" and experimental measurements validate the authors' hypothesis about the improvement in gain and input impedance through the parallel connection of multiple radiators with end feeds of varying lengths. Additionally, it presents the design and analysis of a Butler matrix as a radiation pattern forming unit. The design, electrodynamic simulation, and experimental verification of the antenna array are described in detail, and its broadband performance is highlighted. The comparative analysis of electrodynamic simulation results with experimental result in an anechoic chamber provides a comprehensive overview of the design and performance of the proposed four-beam phased antenna array, recommending its application in modern microwave circuits for communication, satellite navigation, and radar systems. Future research aims to improve the technical and mass-size properties of the components. © 2024 IEEE.

关键词： Antenna phased arrays

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Multi-Class Collaborative Teaching and Learning Optimizer for High-Dimensional Industrial Optimization Problems

Surrogate-Assisted Multi-Class Collaborative Teaching and Le...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Wang, Ziqi Yuan, Haitao Yang, Jinhong Zhang, Jia College of Computer Beijing University of Technology Beijing100124 China Beijing University of Technology Beijing Laboratory of Smart Environmental Protection Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Cssc Systems Engineering Research Institute Beijing China Lyle School of Engineering Southern Methodist University Dept. of Computer Science DallasTX United States

ISBN: (纸本)9781665410205

Swarm intelligence and evolutionary algorithms are widely applied in industrial scheduling, mobile edge computing, etc due to their strong robustness and fast optimization speed. However, some real-world industrial optimization problems involve numerous decision variables, known as high-dimensional problems. Current algorithms often require considerable computational resources to evaluate objective function values because of high-dimensional decision spaces. Moreover, they are also prone to be trapped in local optima. To solve the above problems, this work proposes an improved algorithm named Surrogate-assisted Multi-class Collaborative Teaching and learning optimizer (SMCT). A multi-class collaborative teaching and learning optimizer is proposed as a base optimizer to improve exploration and exploitation abilities. Furthermore, an autoencoder-assisted radial basis function is proposed as the surrogate model to replace true function evaluations, thereby saving computational resources and balancing the complexity and accuracy in fitting true models. Finally, experimental results demonstrate that SMCT surpasses its existing peers in both search accuracy and convergence speed across eight high-dimensional benchmark functions. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Joint Class-Balanced Client Selection and Bandwidth Allocation for Cost-Efficient Federated Learning in Mobile Edge Computing Networks

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5681-5698页

作者： Tang, Jian Li, Xiuhua Li, Hui Li, Penghua Wang, Xiaofei Leung, Victor C. M. Chongqing University School of Big Data & Software Engineering Chongqing400000 China Chongqing University of Posts and Telecommunications School of Automation Chongqing400065 China Tianjin University College of Intelligence and Computing Tianjin300072 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T1Z4 Canada

Federated Learning (FL) has significant potential to protect data privacy and mitigate network burden in mobile edge computing (MEC) networks. However, due to the system and data heterogeneity of mobile clients (MCs), client selection and bandwidth allocation is key for achieving cost-efficient FL in MEC networks with limited bandwidth. To address these challenges, we investigate the issue of joint client selection and bandwidth allocation for reducing the cost (i.e., latency and energy consumption) of FL training. We formulate the problem and decompose it into a holistic subproblem to reduce the number of rounds and a partial subproblem to reduce the costs of FL each round. We propose a joint class-balanced client selection and bandwidth allocation (CBCSBA) framework to address the whole problem. Specifically, for the holistic subproblem, CBCSBA combines MCs into groups, each having data distribution as close as possible to class-balanced distribution;For the partial subproblem, CBCSBA reduces costs by exploratively selecting a group and sequentially optimizing the latency and energy consumption of MCs within the group. Experimental results show that CBCSBA outperforms the baseline frameworks in reducing latency by 28.2% and energy consumption by 25.3% on average in the considered four datasets. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Study of Encapsulation Temperature Field of Dry-type Air-core Reactor with the Structure of Equivalent and Aluminum Wire-Insulation

引用

Distributed Generation and Alternative Energy Journal 2022年第5期37卷 1665-1680页

作者： Wan, Xiaorong Wang, Han Li, Yingna Li, Chuan Zhao, Zhengang Cui, Zhigang Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming650500 China Electric Power Research Institute of Yunnan Power Grid Co. Ltd Kunming650217 China

During the operation of the Dry-type Air-core Reactor (DAR), the insulation material deteriorates due to local overheating of the encapsulation, and the reactor is burned in severe conditions. Therefore, studying the temperature rise of the reactor plays an important role in the reliability of its operation and the economy of design and production. According to the structural characteristics of the reactor, the three-dimensional thermal field model of the aluminum wire-insulation structure of the reactor is established, and the encapsulation temperature field distribution of the reactor under steady state is obtained. Compare the simulation result with the encapsulation temperature field distribution of the equivalent structure. The results show that the highest temperature of the aluminum wire-insulation structure encapsulation rises to 73.51◦C, which is located in the middle of the reactor. Each encapsulation hotspot is located about 20% from the upper edge of the encapsulation. In the temperature rise test, a Fiber Bragg Grating (FGB) temperature sensor is installed about 20% from the upper edge of the encapsulation. The test shows that the most significant value of temperature rise of the reactor is 73◦C, which is located in the middle of the reactor. The temperature rise test results verify the accuracy of the simulated calculation value of the temperature field of the aluminum wire-insulated reactor and provide a reference for the temperature rise calculation and temperature rise monitoring of the DAR. © 2022 River Publishers.

关键词： Fiber Bragg gratings

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：