检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ming, Yuhang Ma, Di Dai, Weichen Yang, Han Fan, Rui Zhang, Guofeng Kong, Wanzeng School of Computer Science Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou Dianzi University Hangzhou310018 China College of Electronics & Information Engineering Shanghai Institute of Intelligent Science and Technology Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China

Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC2-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as they are only used for better reconstruction. In this paper, we propose a simple yet effective way to detect potential loops using the same latent codes as local features. To further improve the loop detection performance, we use the semantic information, which are also decoded from the same latent codes to guide the aggregation of local features. Finally, with the potential loops detected, we close them with a graph optimization followed by bundle adjustment to refine both the estimated poses and the reconstructed scene. To evaluate the performance of our SLC2-SLAM, we conduct extensive experiments on Replica and ScanNet datasets. Our proposed semantic-guided loop closure significantly outperforms the pre-trained NetVLAD and ORB combined with Bag-of-Words, which are used in all the other NeRF SLAM with loop closure. As a result, our SLC2-SLAM also demonstrated better tracking and reconstruction performance, especially in larger scenes with more loops, like ScanNet. Copyright © 2025, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Safety: A Brief Review of Agent-Based Modeling for Fire Evacuation Simulation 16

Enhancing Building Safety: A Brief Review of Agent-Based Mod...

引用

16th International Conference on Ambient systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Kasereka, Selain K. Kabwe, Ortega M. Kinyanta, Maria W.K. Kasongo, Audrey L. Ilunga, Godwill W.K. Muhambya, Katya Tashev, Tasho Kyamakya, Kyandoghere Mathematics Statistics and Computer Science Department University of Kinshasa Kinshasa Democratic Republic Congo Faculty of English Engineering Studies Technical University of Sofia Sofia Bulgaria ABIL Research Center Kinshasa Democratic Republic Congo Faculty of Computer Science Université Nouveaux Horizons Lubumbashi Democratic Republic Congo Ganpat University Faculty of Computer Application Gujarat India Université Libre des Pays des Grands Lacs Faculty of Sciences and Technology Goma Democratic Republic Congo Institute of Smart Systems Technologies University of Klagenfurt Klagenfurt Austria Polytechnic Faculty University of Kinshasa Kinshasa Democratic Republic Congo

The issue of building evacuation in the event of a fire is a significant concern in urban planning and architecture. In the absence of appropriate measures, an emergency situation can potentially result in disastrous outcomes. In this review article, we explore the application of agent-based modeling (ABM) in the simulation of building evacuations in the event of a free breakout. To address this issue, we present a synthesis of findings from several studies, highlighting the advantages of ABM in modeling complex evacuation dynamics such as crowd behavior, consideration of multiple parameters, and decision-making processes. Additionally, we provide insight into the simulation tools and techniques used in studies that demonstrate the practical applications of ABM in enhancing evacuation strategies. Furthermore, we identify current challenges, research gaps, and propose future directions to enhance the accuracy and effectiveness of fire evacuation modeling and simulations. This study aims to contribute to the improvement of proposed solutions and models for the development of successful, effective, and reliable evacuation plans to enhance the safety of occupants in buildings. © 2025 The Author(s).

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhou, Tong Ding, Chen Jing, Changhong Liu, Feng Hung, Kevin Pham, Hieu Mahmud, Mufti Lyu, Zhihan Qiao, Sibo Wang, Shuqiang Tsang, Kim-Fung Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100864 China Stevens Institute of Technology Department of Systems and Enterprises United States Hong Kong Metropolitan University School of Science and Technology Hong Kong Hong Kong VinUniversity College of Engineering and Computer Science VinUni-Illinois Smart Health Center Viet Nam King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Uppsala University Department of Game Design Faculty of Arts Sweden Tiangong University School of Software Tianjin300387 China

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Generic Drone Simulator: Design, Development and User Testing in a Virtual Search and Rescue Mission

引用

IEEE computer Graphics and Applications 2025年 PP卷 PP页

作者： Pappas, Georgios Lappas, Dimitrios Karampelas, Panagiotis Siegel, Joshua E. Templalexis, Ioannis Stavrou, Stavros Krishnan, Sriram Open University of Cyprus Lab of Educational Material and Methodology Latsia Nicosia Cyprus University of the Aegean Learning Technology and Educational Engineering Laboratory Rhodes Greece Hellenic Air Force Academy Department of Informatics & Computers Dekelia Attiki Greece Michigan State University Department of Computer Science and Engineering East LansingMI United States Hellenic Air Force Academy Department of Thermodynamics Propulsion and Power Systems Dekelia Attiki Greece Open University of Cyprus Cybersecurity and Telecommunications Research Lab Latsia Nicosia Cyprus Indian Institute of Technology The Energy Consortium Madras India

This study addresses the need for scenario-specific drone simulators to enhance research, education, pilot training, and performance evaluation across diverse mission contexts. A gamified simulator was developed for the joint master's degree program "Security and Defence" between the Open University of Cyprus (OUC) and the Hellenic Air Force Academy (HAFA), with a focus on Search and Rescue mission training and planning. The simulator balances interface design, physics accuracy, and environmental realism to support specialized professional training and research. A survey-based evaluation involving 57 participants –pilots, engineers, and air traffic controllers –demonstrated the tool's ability to provide realistic experiences for trained pilots and meaningful learning opportunities for novices. Statistical analysis revealed significant correlations between gaming familiarity, task completion times, and participant expertise. © 1981-2012 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Induction Machines Fault Using Vibration-Based Analysis under COMSOL Multiphysics within a Preventive Maintenance Framework

Early Detection of Induction Machines Fault Using Vibration-...

引用

Innovative research in Applied Science, engineering and Technology (IRASET),Conference on

作者： Hamza Sabir Mohammed Ouassaid Nourdine Herbaz Nabil Ngote Mohamed El Khaili Ahmed Abid Laboratory of Engineering Sciences & Biosciences Faculty of Sciences and Techniques of Mohammedia Hassan II University Casablanca Morocco Engineering for Smart and Sustainable Systems Research Center Mohammadia School of Engineers Mohammed V University in Rabat Rabat Morocco Laboratory of Electronics Energy Automation & Information Processing (LEEA&TI). Faculty of Sciences and Techniques of Mohammedia Hassan II University Casablanca Morocco ENSMR Engineering School Rabat Morocco IESI Lab ENSET Mohammedia Hassan 2nd University of Casablanca Casablanca Morocco Electrical Engineering Department Faculty of Sciences and Techniques of Mohammedia Hassan II University Casablanca Morocco

ISBN: (数字)9798331532970

ISBN: (纸本)9798331532987

In this paper, a predictive maintenance strategy is developed to enhance the fault identification of induction machines using the analysis of residual mechanical vibrations. Induction machines are the most widely adopted machines in many industrial environments, owing to their high robustness, simplicity and economic efficiency. Nevertheless, these machines are susceptible to both electrical and mechanical failures, including stator phase deficiencies, which may result in significant downtime and expensive maintenance charges. The approach developed is designed by combining FFT (Fast Fourier Transform) and vibration signal analysis to detect faults at an early stage. The methodology has been validated by simulations performed with COMSOL Multiphysics. The results reveal a significant improvement over traditional maintenance methods based solely on vibration analysis in the early detection of failures, resulting in reduced downtime and lower maintenance costs.

关键词： Vibrations Fault diagnosis Machine learning algorithms Fast Fourier transforms Windings Stator windings Maintenance Wind turbines Induction machines Preventive maintenance

来源：评论

学校读者我要写书评

暂无评论

Efficient multi-task learning with instance selection for biomedical NLP

引用

computers in Biology and Medicine 2025年 190卷 110050-110050页

作者： Bonfigli, Agnese Bacco, Luca Pecchia, Leandro Merone, Mario Dell'Orletta, Felice ItaliaNLP Lab Institute of Computational Linguistics "Antonio Zampolli" National Research Council Via Giuseppe Moruzzi 1 Pisa56124 Italy Research Unit of Intelligent Technology for Health and Wellbeing Department of Engineering Università Campus Bio-Medico di Roma Via Alvaro del Portillo 21 Rome00128 Italy Research Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Via Alvaro del Portillo 21 Rome00128 Italy Fondazione Policlinico Universitario Campus Bio-Medico di Roma Via Alvaro del Portillo 200 Rome00128 Italy

Background: Biomedical natural language processing (NLP) increasingly relies on large language models and extensive datasets, presenting significant computational challenges. Methods: We propose Blue5, a multi-task model based on SciFive that incorporates instance selection (IS) to enable efficient, multi-task learning (MTL) on biomedical data. We adapt the E2SC-IS framework for the biomedical domain, integrating a calibrated SVM classifier to reduce computational costs. Results: Our approach achieves an average data reduction of 26.6% across the several tasks of the BLUE (Biomedical Language Understanding Evaluation) Benchmark, while maintaining performance comparable with state-of-the-art models. The multi-task SVM configuration emerges as the most effective, demonstrating the power of combining IS with MTL for biomedical NLP. As a result of the unified framework, Blue5 effectively selects the most informative instances across tasks, ensuring model generalization while efficiently handling multiple NLP tasks. Conclusion: Our work offers a practical solution to address growing computational demands, enabling more scalable and accessible applications of advanced NLP techniques in biomedical research and healthcare. © 2025 The Authors

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving

arXiv

引用

arXiv 2025年

作者： Zhang, Yi Zhou, Guangyou Xie, Zhiwen Ma, Jinjin Huang, Jimmy Xiangji Faculty of Artificial Intelligence in Education Central China Normal University Hubei Wuhan430079 China School of Information and Safety Engineering Zhongnan University of Economics and Law Hubei Wuhan430073 China Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer Central China Normal University Hubei Wuhan430079 China Information Retrieval and Knowledge Management Research Lab York University Toronto Canada

Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e.g., Seq2Tree and Graph2Tree) to generate mathematical equations. While effective, these models struggle to generate diverse but counterpart solution equations, limiting their generalization across various math problem scenarios. In this paper, we introduce a novel Diversity-enhanced Knowledge Distillation (DivKD) model for practical MWP solving. Our approach proposes an adaptive diversity distillation method, in which a student model learns diverse equations by selectively transferring high-quality knowledge from a teacher model. Additionally, we design a diversity prior-enhanced student model to better capture the diversity distribution of equations by incorporating a conditional variational auto-encoder. Extensive experiments on four MWP benchmark datasets demonstrate that our approach achieves higher answer accuracy than strong baselines while maintaining high efficiency for practical applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A new multilevel voltage source inverter configuration with minimum number of circuit elements

引用

Journal of Central South University 2017年第4期24卷 912-920页

作者： Mohammad Reza Jannati Oskuee Masoumeh Karimi Yahya Naderi Sajad Najafi Ravadanegh Seyyed Hossein Hosseini Smart Distribution Grid Research Lab. Electrical Engineering Department Azarbaijan Shahid Madani University Tabriz Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

An advanced configuration for multilevel voltage source converters is proposed. The proposed converter is able to apply asymmetrical DC sources. The configuration of the proposed inverter is well designed in order to provide the maximum number of voltage levels in output terminals using lower number of circuit devices. The authority of the proposed inverter versus the conventional H-bridge cascaded inverter and the most recently introduced ones, is verified with a provided comparison study. The proposed inverter is able to generate the desired voltage levels using a lower number of circuit devices including power semi-conductor switches, IGBTs, diodes, related gate driver circuits of switches and DC voltage sources. As a result, the total cost and installation area are considerably reduced and the control scheme gets simpler. To confirm the feasibility of the proposed multilevel structure, both the simulation and experimental results are provided and compared which shows good agreements.

关键词： multilevel voltage source inverter reduction of circuit components symmetric inverter asymmetric inverter

来源：评论

学校读者我要写书评

暂无评论

Using artificial intelligence to predict the next deceptive movement based on video sequence analysis: A case study on a professional cricket player's movements

Journal of Engineering Research (Kuwait)

引用

Journal of engineering research (Kuwait) 2025年

作者： Mutawa, A.M. Rajesh Kumar, Korupalli V. K, Hemachandran Murugappan, M. Computer Engineering Department College of Engineering and Petroleum Kuwait University Safat 5969 13060 Kuwait CoE Sports Analytics and Management and AI Research Centre School of Business Woxsen University Hyderabad India Intelligent Signal Processing (ISP) Research Lab Department of Electronics and Communication Engineering Kuwait College of Science and Technology Block 4 Doha 13133 Kuwait Department of Electronics and Communication Engineering School of Engineering Vels Institute of Sciences Technology and Advanced Studies Tamilnadu Chennai India Center of Excellence for Unmanned Aerial Systems (CoEUAS) Universiti Malaysia Perlis Perlis 02600 Malaysia

This research develops an artificial intelligence-based model to predict the next deceptive movement of athletes by analyzing video sequences of previous movements. Utilizing advanced deep neural network models, we analyze deceptive movements to forecast the next move, with a practical application on the deceptive movements of a professional cricket player. The model employs machine learning techniques such as Random Forest (RF), Decision Trees (DT), and K-Nearest Neighbor (KNN) to enhance prediction accuracy. Achieving up to 70 % accuracy, this model rivals human capability, as even highly skilled players can easily fall for deceptive actions. The ability to predict deceptive movements sets humans apart from many intelligent creatures, allowing athletes to avoid predictable actions and gain an edge in various sports. This study applies this concept to cricket, leveraging video data to improve training methods. The results highlight the potential of artificial intelligence in revolutionizing training and performance optimization in sports. © 2025 The Authors

关键词： Artificial intelligence Cricket Deceptive movements Machine learning Performance optimization

来源：评论

学校读者我要写书评

暂无评论

CRITICAL BANDWIDTH ALLOCATION FOR THE DELIVERY OF COMPRESSED VIDEO

引用

computer COMMUNICATIONS 1995年第10期18卷 709-717页

作者： FENG, WC SECHREST, S Software Systems Research Lab Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA

The transportation of compressed video data without loss of picture quality requires the network to support large fluctuations in bandwidth requirements. These fluctuations can be smoothed, but straightforward approaches to smoothing can still suffer from excessive buffering requirements, poor buffer utilization and an excessive number of bandwidth changes. This paper introduces critical bandwidth allocation, which reduces the number of bandwidth changes to a very small number, and achieves the maximum effectiveness from client-side buffers. A comparison between critical bandwidth allocation algorithms and other smoothing algorithms is presented, the sensitivity of the algorithm to jitter is examined, and, implications for the design of network services are discussed.

关键词： VIDEO-ON-DEMAND BANDWIDTH ALLOCATION MPEG VIDEO COMPRESSION SMOOTHING

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：