检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

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

ISBN: (纸本)9798331314385

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed adaptive finite-time time-varying group formation tracking for high-order multi-agent systems with directed topologies

Distributed adaptive finite-time time-varying group formatio...

引用

第三十九届中国控制会议

作者： Lei Tian Yongzhao Hua Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Beihang University Department of Aerospace Engineering University of Bristol Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

This paper investigates finite-time time-varying group formation（TVGF） tracking control problems for high-order multi-agent systems（MASs） with directed topologies. Firstly, the agents are classified into three types, i.e., the virtual leader, the group leader and the follower. A virtual leader is used to control the macroscopic movement of MASs. Subgroups can be interacted and coordinated with each other by the communication among group leaders. Secondly, a novel finite-time group formation tracking protocol using only the neighboring interaction is constructed based on adaptive integral sliding mode control. Then sufficient conditions for MASs with unknown external disturbances and directed topologies to realize finite-time TVGF tracking are derived using Lyapunov theory. Finally, a numerical simulation example is performed to demonstrate the effectiveness of theoretical results.

关键词： TVGF tracking finite-time control MASs adaptive integral sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A Secure Healthcare 5.0 System Based on Blockchain Technology Entangled with Federated Learning Technique

arXiv

引用

arXiv 2022年

作者： Rehman, Abdur Abbas, Sagheer Khan, M.A. Ghazal, Taher M. Adnan, Khan Muhammad Mosavi, Amir School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Riphah School of Computing and Innovation Faculty of Computing Riphah International university Pakistan School of Information Technology Skyline University College University City Sharjah Sharjah1797 United Arab Emirates Selangor Bangi43600 Malaysia Department of Software Gachon University Seongnam13120 Korea Republic of Institute of Information Engineering Automation and Mathematics Slovak University of Technology in Bratislava Bratislava81107 Slovakia John von Neumann Faculty of Informatics Obuda University Budapest1034 Hungary Faculty of Civil Engineering TU-Dresden Dresden01062 Germany

In recent years, the global Internet of Medical Things (IoMT) industry has evolved at a tremendous speed. Security and privacy are key concerns on the IoMT, owing to the huge scale and deployment of IoMT networks. Machine learning (ML) and blockchain (BC) technologies have significantly enhanced the capabilities and facilities of healthcare 5.0, spawning a new area known as "Smart Healthcare." By identifying concerns early, a smart healthcare system can help avoid long-term damage. This will enhance the quality of life for patients while reducing their stress and healthcare costs. The IoMT enables a range of functionalities in the field of information technology, one of which is smart and interactive health care. However, combining medical data into a single storage location to train a powerful machine learning model raises concerns about privacy, ownership, and compliance with greater concentration. Federated learning (FL) overcomes the preceding difficulties by utilizing a centralized aggregate server to disseminate a global learning model. Simultaneously, the local participant keeps control of patient information, assuring data confidentiality and security. This article conducts a comprehensive analysis of the findings on blockchain technology entangled with federated learning in healthcare. 5.0. The purpose of this study is to construct a secure health monitoring system in healthcare 5.0 by utilizing a blockchain technology and Intrusion Detection System (IDS) to detect any malicious activity in a healthcare network and enables physicians to monitor patients through medical sensors and take necessary measures periodically by predicting diseases. The proposed system demonstrates that the approach is optimized effectively for healthcare monitoring. In contrast, the proposed healthcare 5.0 system entangled with FL Approach achieves 93.22% accuracy for disease prediction, and the proposed RTS-DELM-based secure healthcare 5.0 system achieves 96.18% accuracy for the e

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

How to Exploit Optimization Experience? Revisiting Evolutionary Sequential Transfer Optimization: Part A - Benchmark Problems

TechRxiv

引用

TechRxiv 2022年

作者： Xue, Xiaoming Yang, Cuie Feng, Lianghuan Zhang, Kai Song, Linqi Tan, Kay Chen The Department of Computer Science City University of Hong Kong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The College of Computer Science Chongqing University Chongqing400044 China The Civil Engineering School Qingdao University of Technology Qingdao266520 China The Department of Computing Hong Kong Polytechnic University Hong Kong

Evolutionary sequential transfer optimization (ESTO), which attempts to enhance the evolutionary search of a target task using the knowledge captured from several previously-solved source tasks, has been receiving increasing research attention in recent years. Despite the tremendous approaches developed, it is worth noting that existing benchmark problems for ESTO are not well designed, as they are often simply extended from other benchmarks in which the relationships between the source and target tasks are not well analyzed. Consequently, the comparisons conducted on these problems are not systematic and can only provide numerical results without a deeper analysis of how an ESTO algorithm performs on problems with different properties. Taking this clue, this two-part paper revisits a large body of solution-based ESTO algorithms on a group of newly developed test problems, to help researchers and practitioners gain a deeper understanding of how to better exploit optimization experience towards enhanced optimization performance. Part A of the series designs a problem generator based on several newly defined concepts to generate benchmark problems with diverse properties, which are competitive in resembling real-world problems. Part B of the series empirically revisits various algorithms by answering five key research questions related to knowledge transfer. The results demonstrated that the performance of many ESTO algorithms is highly problem-dependent, which suggest the necessity of more research efforts on transferability measurement and enhancement in ESTO algorithm design. The source code of the benchmark suite developed in part A is available at https://***/XmingHsueh/Revisiting-S-ESTOs-PartA. © 2022-12-08, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

APG-DPNet: A dual-path network with anatomical priors for perigastric veins segmentation and varicosity quantification

引用

Neurocomputing 2025年 649卷

作者： Kun Zhang Chenggang Wu Wenkai Wei Fengxiu Yan Lin Wang Peijian Zhang Liang Hua Lei Cui School of Electrical Engineering and Automation Nantong University Nantong 226001 Jiangsu China Nantong Key Laboratory of Intelligent Control and Intelligent Computing Nantong Institute of Technology Nantong 226001 Jiangsu China Department of Radiology Affiliated Hospital 2 of Nantong University Nantong 226001 Jiangsu China

The precise diagnosis of Pancreatic Portal Hypertension (PPH) hinges on the accurate anatomical localization and quantitative morphological assessment of perigastric veins. In order to address the deficiencies of conventional methods, which are prone to missegmentation and omission in complex vascular environments, this study proposes an Anatomical Prior Guided Dual-Path Network (APG-DPNet) to achieve improved segmentation of perigastric veins. The proposed network comprises two complementary pathways: the Anatomical Prior Path and the Vein Segmentation Path. The Anatomical Prior Path leverages gastric anatomical masks to provide spatial constraints, effectively mitigating interference from adjacent structures such as the portal vein. The Vein Segmentation Path adopts a cascaded U-Net architecture for pixel-level segmentation and integrates a scale-adaptive vein diameter estimation module for precise morphological quantification. Additionally, a Multi-Condition Constraint Module (MCCM) is designed to incorporate vein-specific characteristics, including morphological features, contrast enhancement, and diameter evaluation, to refine candidate regions and improve segmentation accuracy, particularly for the identification of varicose veins. Experimental results indicate that the proposed APG-DPNet outperforms state-of-the-art (SOTA) methods in perigastric vein segmentation. On internal, external validation, and public datasets, the model achieved Dice scores of 82.3%, 79.6%, and 80.6%, respectively. Moreover, the correlation between predicted vein diameters and manual measurements reached 0.90, validating the model’s accuracy and reliability in vein morphology quantification. APG-DPNet serves as a robust and dependable auxiliary tool for the automated quantitative diagnosis of PPH, offering strong generalization capability and substantial clinical applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to Exploit Optimization Experience? Revisiting Evolutionary Sequential Transfer Optimization: Part B - Algorithm Analysis

TechRxiv

引用

TechRxiv 2022年

This paper is the second part of a two-part series on evolutionary sequential transfer optimization (ESTO). The first part designs a problem generator to generate benchmark problems with diverse properties that can better resemble real-world problems. This part proposes five research questions (RQs) to empirically revisit a large body of knowledge transfer techniques in the context of solution-based ESTO (S-ESTO). Particularly, knowledge transfer techniques are organized from a perspective of transfer strategy, including solution selection, solution adaptation, and the integration of them. The results reveal that the performance of many algorithms is highly sensitive to similarity distribution of STOPs, which suggest the necessity of more flexible algorithm design in future studies. Specifically, when an STOP is full of source tasks that are highly similar to the target task in terms of optimum, one can randomly select one source task and reuse its elite solution(s) to accelerate the target search significantly. When an STOP contains source tasks with mixed similarities to the target task, an effective similarity metric that can represent the transferability is able to identify highly transferable solution(s). When an STOP is full of source tasks with low similarities to the target task, the transferability is expected to be improved by solution adaptation. In solution adaptation, a similarity metric in the form of a maximization (or minimization) objective function that is responsible for representing the transferability is optimized to obtain a mapping function for adapting source solution(s). The source code for reproducing our experiments is available at https://***/XmingHsueh/Revisiting-S-ESTOs-PartB. © 2022-12-08, CC BY.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Initial Study on Implementation of Smoothing Filters for the Purpose of Bioimpedance Spectroscopy Parameters Classification

引用

IFAC-PapersOnLine 2022年第4期55卷 393-398页

作者： Aleksandra Kawala-Sterniuk Amir F. Al-Bakri Mariusz Pelc Katarzyna Cichoń Wojciech Chlewicki Stepan Ozana Radek Martinek Jakub Możaryn Volodymyr Khoma Halyna Kenyo Edward Jacek Gorzelańczyk Michał Podpora Jarosław Zygarlicki Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics 45-758 Opole Poland Department of Biomedical Engineering College of Engineering University of Babylon 51001 Babylon Iraq University of Greenwich School of Computing and Mathematical Sciences SE10 9LS London UK West Pomeranian University of Technology in Szczecin Faculty of Electrical Engineering 70-313 Szczecin Poland Faculty of Mechatronics Warsaw University of Technology 02-525 Warsaw Poland Lviv Polytechnic National University Institute of Computer Technologies Automation and Metrology Lviv Ukraine Institute of Philosophy Kazimierz Wielki University 85-092 Bydgoszcz Poland Faculty of Mathematics and Computer Science Adam Mickiewicz University in Poznań 61-614 Poznań Poland

Bioimpedance is a commonly used method for various conditions monitoring. In this paper, the authors carried out some research where they implemented various smoothing filters to enable identification of the bioimpedance spectroscopy parameters. The proposed filtering methods may also be used for application on embedded systems, which have smaller computing power but have become recently very popular. The obtained results with the implementation of smoothing filters were promising, however, some of the obtained results were unsatisfactory. This work also contains a brief introduction to bioimpedance spectroscopy and smoothing filters.

关键词： Bioimpedance Spectroscopy smoothing-filtering Savitzky-Golay Filter Median Filtering Moving-Average Filters

来源：评论

学校读者我要写书评

暂无评论

Foundation models and intelligent decision-making: Progress, challenges, and perspectives

引用

Innovation 2025年第6期6卷 100948页

作者： Huang, Jincai Xu, Yongjun Wang, Qi Wang, Qi [Cheems] Liang, Xingxing Wang, Fei Zhang, Zhao Wei, Wei Zhang, Boxuan Huang, Libo Chang, Jingru Ma, Liantao Ma, Ting Liang, Yuxuan Zhang, Jie Guo, Jian Jiang, Xuhui Fan, Xinxin An, Zhulin Li, Tingting Li, Xuefei Shao, Zezhi Qian, Tangwen Sun, Tao Diao, Boyu Yang, Chuanguang Yu, Chenqing Wu, Yiqing Li, Mengxian Zhang, Haifeng Zeng, Yongcheng Zhang, Zhicheng Zhu, Zhengqiu Lv, Yiqin Li, Aming Chen, Xu An, Bo Xiao, Wei Bai, Chenguang Mao, Yuxing Yin, Zhigang Gui, Sheng Su, Wentao Zhu, Yinghao Gao, Junyi He, Xinyu Li, Yizhou Jin, Guangyin Ao, Xiang Zhai, Xuehao Tan, Haoran Yun, Lijun Shi, Hongquan Li, Jun Fan, Changjun Huang, Kuihua Harrison, Ewen Leung, Victor C.M. Qiu, Sihang Dong, Yanjie Zheng, Xiaolong Wang, Gang Zheng, Yu Wang, Yuanzhuo Guo, Jiafeng Wang, Lizhe Cheng, Xueqi Wang, Yaonan Yang, Shanlin Fu, Mengyin Fei, Aiguo Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Department of Automation Tsinghua University Beijing100084 China Huazhong University of Science and Technology Wuhan430074 China School of Automation Beijing Institute of Technology Beijing100081 China School of Information Science and Engineering Dalian Polytechnic University Dalian116034 China National Engineering Research Center for Software Engineering Peking University Beijing100871 China Department of Oral Implantology Peking University School and Hospital of Stomatology Beijing100081 China Guangzhou511453 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China IDEA Research International Digital Economy Academy Shenzhen518057 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China College of Science National University of Defense Technology Changsha410073 China Center for Systems and Control College of Engineering Peking University Beijing100871 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China College of Systems Engineering National University of Defense Technology Changsha410073 China Laboratory for Big Data and Decision National University of Defense Technology Changsha410073 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore School of Electrical Engineering Chongqing University Chongqing400044 China Department of Mathematics The University of Hong Kong Hong Kong SAR999077 China School of Food Science and Technology Dalian Polytechnic University Dalian116034 China Centre for Medical Informatics University of Edinburgh EdinburghEH16 4UX United Kingdom Department of Stomatology Peking Union Medical College Hospital Chinese Academ

Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM's evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems. © 2025 The Authors

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based approach to extracting periosteal and endosteal contours of proximal femur in quantitative CT images

arXiv

引用

arXiv 2021年

作者： Deng, Yu Wang, Ling Zhao, Chen Tang, Shaojie Cheng, Xiaoguang Deng, Hong-Wen Zhou, Weihua School of Automation Xi'an University of Posts and Telecommunications Xi'an Shaanxi710121 China Department of Radiology Beijing Jishuitan Hospital Beijing100035 China College of computing Michigan Technological university HoughtonMI49931 United States Tulane University Department of Biomedical Engineering New OrleansLA70118 United States

Objective: Automatic CT segmentation of proximal femur is crucial for the diagnosis and risk stratification of orthopedic diseases. In this study, we proposed an approach based on deep learning for the automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments. Methods: A three-dimensional (3D) end-to-end fully convolutional neural network, which can better combine the information between neighbor slices and get more accurate segmentation results, was developed for our segmentation task. 100 subjects aged from 50 to 87 years with 24,399 slices of proximal femur CT images were enrolled in this study. The separation of cortical and trabecular bone derived from the QCT software MIAF-Femur was used as the segmentation reference. We randomly divided the whole dataset into a training set with 85 subjects for 10-fold cross-validation and a test set with 15 subjects for evaluating the performance of models. Results: Two models with the same network structures were trained and they achieved a dice similarity coefficient (DSC) of 97.87% and 96.49% for the periosteal and endosteal contours, respectively. To verify the excellent performance of our model for femoral segmentation, we measured the volume of different parts of the femur and compared it with the ground truth and the relative errors between predicted result and ground truth are all less than 5%. It demonstrated a strong potential for clinical use, including the hip fracture risk prediction and finite element analysis. Significance: This approach is helpful to measure the BMD of cortical bone and trabecular bone respectively, and to evaluate the bone strength based on finite element analysis. Copyright © 2021, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Prompt engineering for Healthcare: Methodologies and Applications

arXiv

引用

arXiv 2023年

作者： Wang, Jiaqi Shi, Enze Yu, Sigang Wu, Zihao Ma, Chong Dai, Haixing Yang, Qiushi Kang, Yanqing Wu, Jinru Hu, Huawen Yue, Chenxi Zhang, Haiyang Liu, Yiheng Pan, Yi Liu, Zhengliang Sun, Lichao Li, Xiang Ge, Bao Jiang, Xi Zhu, Dajiang Yuan, Yixuan Shen, Dinggang Liu, Tianming Zhang, Shu The School of Computer Science Northwestern Polytechnical University Xi’an710072 China The School of Automation Northwestern Polytechnical University Xi’an710072 China The School of Computing The University of Georgia Athens30602 United States The Department of Computer Science and Engineering Lehigh University PA18015 United States The Department of Radiology Massachusetts General Hospital Harvard Medical School Boston02115 United States The Department of Computer Science and Engineering The University of Texas at Arlington Arlington76019 United States The School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200230 China Shanghai Clinical Research and Trial Center Shanghai201210 China The Department of Electronic Engineering City University of Hong Kong 999077 Hong Kong The Department of Electronic Engineering Chinese University of Hong Kong 999077 Hong Kong The School of Physics and Information Technology Shaanxi Normal University Xi’an710119 China The School of Glasgow College University of Electronic Science and Technology of China Chengdu611731 China The School of Life Science and Technology University of Electronic Science and Technology of China Chengdu611731 China

Prompt engineering is a critical technique in the field of natural language processing that involves designing and optimizing the prompts used to input information into models, aiming to enhance their performance on specific tasks. With the recent advancements in large language models, prompt engineering has shown significant superiority across various domains and has become increasingly important in the healthcare domain. However, there is a lack of comprehensive reviews specifically focusing on prompt engineering in the medical field. This review will introduce the latest advances in prompt engineering in the field of natural language processing for the medical field. First, we will provide the development of prompt engineering and emphasize its significant contributions to healthcare natural language processing applications such as question-answering systems, text summarization, and machine translation. With the continuous improvement of general large language models, the importance of prompt engineering in the healthcare domain is becoming increasingly prominent. The aim of this article is to provide useful resources and bridges for healthcare natural language processing researchers to better explore the application of prompt engineering in this field. We hope that this review can provide new ideas and inspire for research and application in medical natural language processing. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical applications

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：