检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Shao, Xuqiang Zhang, Yuqi Zhang, Di Gao, Tianxiang Liu, Xinyuan Gan, Zhiran Meng, Fanshun Li, Hao Yang, Weijie School of Control and Computer Engineering North China Electric Power University Baoding071003 China Tohoku University Sendai980-8577 Japan Department of Power Engineering School of Energy and Power Engineering North China Electric Power University Hebei Baoding071003 China School of Science Liaoning University of Technology Jinzhou12100l China

This paper addresses the challenges of creating efficient and high-quality datasets for machine learning potential functions. We present a novel approach, termed DV-LAE (Difference Vectors based on Local Atomic Environments), which utilizes the properties of atomic local environments and employs histogram statistics to generate difference vectors. This technique facilitates dataset screening and optimization, effectively minimizing redundancy while maintaining data diversity. We have validated the optimized datasets in high-temperature and high-pressure hydrogen systems as well as the α-Fe/H binary system, demonstrating a significant reduction in computational resource usage without compromising prediction accuracy. Additionally, our method has revealed new structures that emerge during simulations but were underrepresented in the initial training datasets. The redundancy in the datasets and the distribution of these new structures can be visually analyzed through the visualization of difference vectors. This approach enhances our understanding of the characteristics of these newly formed structures and their impact on physical processes. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Emergency Vehicle Navigation in Connected Autonomous Systems Using Enhanced Traffic Management System

引用

IEEE Internet of Things Journal 2025年

作者： Raja, Gunasekaran Anbalagan, Sudha Gurumoorthy, Sugeerthi Jegathesan, Darshini Girivel, Niveditha Subramanian Sundaram, Varsha Mani Shanmuga Khowaja, Sunder Ali Dev, Kapal Anna University NGNLab Department of Computer Technology MIT Campus Chennai600044 India Vellore Institute of Technology Chennai Centre for Smart Grid Technologies School of Computer Science and Engineering Chennai600127 India Citicorp Services Private Ltd Software Development Chennai600113 India Dublin City University School of Computing Faculty of Engineering and Computing Glasnevin Campus DublinD09 V209 Ireland Munster Technological University Department of Computer Science Bishopstown CorkT12 P928 Ireland University of Johannesburg Department of Institute of Intelligent Systems Johannesburg2006 South Africa Chitkara University Institute of Engineering and Technology Centre for Research Impact Outcome Chitkara University Punjab Rajpura140401 India

Autonomous Vehicle (AV) usage has become predominant in the rapidly evolving landscape of urban transportation. Integrating AVs and non-AVs in the existing traffic infrastructure has significantly increased the complexity of traffic patterns. This research work primes the enhanced Traffic Management System (e-TMS), a solution implemented to expedite Emergency Vehicle (EV) travel in the context of Connected AVs (CAVs) and ensured secured communication employing Public Key Infrastructure (PKI) among the Internet of Vehicles (IoV) framework. When an EV is detected, the IoV system verifies the EV's signal using PKI, ensuring its authenticity and integrity by encrypting the communication between the EV and Road Side Units (RSUs). Further, the e-TMS activates the platooning process where CAVs in the EV's lane shift to the adjacent lanes and dynamically form platoons to create a dedicated lane for the EV. To further optimize the platooning process, an Adaptive Smart Leader Selection (ASLS) algorithm is employed to select a leader vehicle spontaneously among the AVs based on the proximity to the EV, communication reliability, and lane position. Radio Detection and Ranging devices aid this platooning process by providing distance and target velocity, which are needed to maintain the required distance between the AVs and ensure safe platoon formation. The e-TMS enhances EV response times and overall traffic flow efficiency and resulted in 27.8% increase in mean speed compared to the traditional methods. © 2014 IEEE.

关键词： Emergency vehicles

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Diffusion Models

arXiv

引用

arXiv 2025年

作者： Peng, Zihao Wang, Xijun Chen, Shengbo Rao, Hong Shen, Cong School of Mathematics and Computer Science Nanchang University Nanchang330000 China School of Electronics and Information Technology Sun Yat-sen University Guangzhou510006 China School of Software Nanchang University Nanchang330000 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA22904 United States

Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. Typically, these models are constructed using centralized, independently and identically distributed (IID) training data. However, in practical scenarios, data is often distributed across multiple clients and frequently manifests non-IID characteristics. Federated Learning (FL) can leverage this distributed data to train diffusion models, but the performance of existing FL methods is unsatisfactory in non-IID scenarios. To address this, we propose FEDDDPM—Federated Learning with Denoising Diffusion Probabilistic Models, which leverages the data generative capability of diffusion models to facilitate model training. In particular, the server uses well-trained local diffusion models uploaded by each client before FL training to generate auxiliary data that can approximately represent the global data distribution. Following each round of model aggregation, the server further optimizes the global model using the auxiliary dataset to alleviate the impact of heterogeneous data on model performance. We provide a rigorous convergence analysis of FEDDDPM and propose an enhanced algorithm, FEDDDPM+, to reduce training overheads. FEDDDPM+ detects instances of slow model learning and performs a one-shot correction using the auxiliary dataset. Experimental results validate that our proposed algorithms outperform the state-of-the-art FL algorithms on the MNIST, CIFAR10 and CIFAR100 datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Federated Graph Rationale Learning with Latent Environments 25

Empowering Federated Graph Rationale Learning with Latent En...

引用

Proceedings of the ACM on Web Conference 2025

作者： Linan Yue Qi Liu Yawen Li Fangzhou Yao Weibo Gao Junping Du School of Computer Science and Engineering Southeast University Nanjing China State Key Laboratory of Cognitive Intelligence University of Science and Technology of China & Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Hefei China

ISBN: (纸本)9798400712746

The success of Graph Neural Networks (GNNs) in graph classification has heightened interest in explainable GNNs, particularly through graph rationalization. This method aims to enhance GNNs explainability by identifying subgraph structures (i.e., rationales) that support model predictions. However, existing methods often rely on centralized datasets, posing challenges in scenarios where data privacy is crucial, such as in molecular property prediction. Federated Learning (FL) offers a solution by enabling collaborative model training without sharing raw data. In this context, Federated Graph Rationalization emerges as a promising research direction. However, in each client, the rationalization methods often rely on client-specific shortcuts to compose rationales and make task predictions. Data heterogeneity, characterized by non-IID data across clients, exacerbates this problem, leading to poor prediction performance. To address these challenges, we propose the Environment-aware Data Augmentation (EaDA) method for Federated Graph Rationalization. EaDA comprises two main components: the Environment-aware Rationale Extraction (ERE) module and the Local-Global Alignment (LGA) module. The ERE module employs prototype learning to infer and share abstract environment information across clients, which are then aggregated to form a global environment. This information is used to generate counterfactual samples for local clients, enhancing the robustness of task predictions. The LGA module uses contrastive learning methods to align local and global rationale representations, mitigating performance degradation due to data heterogeneity. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of our approaches. Code is available at https://***/yuelinan/Codes-of-EaDA.

关键词： federated learning

来源：评论

学校读者我要写书评

暂无评论

ODMGIS: An Outlier Detection Method Based on Multi-Granularity Information Sets

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Zhang, Pengfei He, Zhaoxuan Wang, Dexian Jiang, Tao Li, Baolin Liu, Jia Huang, Wei Li, Tianrui The School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu611137 China The Acupuncture and Tuina School Chengdu University of Traditional Chinese Medicine Chengdu611137 China The School of Logistics Chengdu University of Information Technology Chengdu60020 China The School of Computer and Software Engineering Xihua University Chengdu610039 China The College of Computer and Data Science Fuzhou University Fuzhou35010 China The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China

In the realm of data mining, outlier detection has emerged as a pivotal research focus, aimed at uncovering anomalies within datasets to extract meaningful and valuable insights. The objective is to leverage data mining methodologies to pinpoint anomalies within datasets, thereby revealing crucial and enlightening information. Herein, we introduce a groundbreaking outlier detection methodology, ODMGIS, that seamlessly integrates multi-granularity representation and information set concepts to devise the multi-granularity information set (MGIS) model. This model adeptly characterizes the distribution patterns of data points. Firstly, we employ entropy function and their complementary function as measurement tools to accurately quantify the inherent uncertainty in data with different distributions, and considers the sum of the two as a comprehensive representation of the overall uncertainty of the information source. Subsequently, an outlier score model is constructed based on MGIS, which can deeply characterize the degree of outlierness of samples, thereby effectively identifying abnormal points in the dataset. During validation, ODMGIS was rigorously tested on practical datasets from medicine and bioinformatics, and its performance was benchmarked against both traditional and the state-of-the-art algorithms, showcasing substantial benefits. This research not only contributes a fresh perspective to outlier detection but also sparks innovative avenues for exploring and advancing the granular computing theory. © 1993-2012 I IEEE. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

Incorporating Large Vision Model Distillation and Fuzzy Perception for Improving Disease Diagnosis

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Gao, Zhan Lin, Qika Wen, Huaxuan Pu, Bin Feng, Mengling Li, Kenli Hunan University College of Computer Science and Electronic Engineering Changsha410000 China Taihe Hospital Hubei University of Medicine Shiyan442000 China National University of Singapore Saw Swee Hock School of Public Health Singapore Shenzhen Maternal Child Healthcare Hospital Southern Medical University Department of Ultrasound Shenzhen518028 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong

Early disease diagnosis is critical for timely clinical intervention and treatment. Intelligent models have shown significant potential in addressing the challenges of misdiagnosis, especially given the shortage of experienced experts. However, there exists complexity of ultrasound image information, and subtle differences between positive and negative samples, combined with limited disease data, pose challenges in feature extraction, class imbalance, and the lack of representative positive class prototypes. To this end, we propose a large vision model distillation framework with fuzzy perception to improve rare disease diagnosis. Specifically, we first fine-tune the pre-trained Medical Segment Anything Model (MedSAM) to adapt it to the target domain. Through image augmentation and latent feature relationship distillation, we enhance feature extraction robustness and reduce inter-class ambiguity, which helps mitigate the impact of class imbalance on the lightweight student model. Second, as imaging style differences in ultrasound images are often more pronounced than subtle variations between positive and negative samples, we construct image style subsets and introduce a fuzzy style matching strategy to perceive these differences. Finally, we combine features from both the differential perception and semantic enhancement branches to strengthen disease classification. Extensive experiments on an internal fetal spina bifida dataset and three widely used imbalanced benign-malignant medical datasets demonstrate the effectiveness of the proposed method. © 1993-2012 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Optimizing Route Planning in Urban Traffic

Deep Reinforcement Learning for Optimizing Route Planning in...

引用

Computational, Communication and Information technology (ICCCIT), International Conference on

作者： Mudit Mittal Archana Sehgal Neeraj Varshney Sunil Prashanth Kumar Nandini Shirish Boob R. Akhilesh Reddy Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Lovely Professional University Phagwara Department of Computer Engineering and Applications GLA University Mathura Department of Mechanical Engineering New Horizon College of Engineering Bangalore Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Urban traffic networks are efficient route design problems due to the intricacy and dynamic character of contemporary cities. Conventional methods hamper real time adjustment to continually changing traffic conditions, thereby providing suboptimal routes, a greater burden on the roadways, and greater air pollution. This thesis presents a novel deep reinforcement learning (DRL) method to optimize the route planning for urban traffic networks. With this rendering of real time traffic data, we use DRL to make autonomous decisions to reduce travel time and congestion of routes. One advantage of using sophisticated neural networks for feature extraction and policy learning is that, since the model is so adaptable to changing traffic patterns, the model guarantees that. And, in comparison to common routing algorithms, the results of simulations using real world traffic data show that this method is able to greatly enhance route efficiency and overall traffic flow management. The suggested DRL based system is feasible as a smart city program based on intelligent transportation system which can scale to grand metropolitan regions. The research presents that DRL can enhance the commuter run experience, reduce the environmental effect, and alter urban transportation. Future study will also investigate how this system can be better optimized when integrated with traffic infrastructure enabled by the Internet of Things.

关键词： Adaptation models Smart cities Computational modeling Scalability Transportation Traffic control Deep reinforcement learning Real-time systems Planning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Generalized Pointing Error Model for FSO Links with Fixed-Wing UAVs for 6G: Analysis and Trajectory Optimization

引用

IEEE Transactions on Wireless Communications 2025年

作者： Moon, Hyung-Joo Chae, Chan-Byoung Wong, Kai-Kit Alouini, Mohamed-Slim Yonsei University School of Integrated Technology Seoul03722 Korea Republic of University College London Department of Electronic and Electrical Engineering LondonWC1E 7JE United Kingdom Yonsei University Yonsei Frontier Lab Seoul03722 Korea Republic of King Abdullah University of Science and Technology Computer Electrical and Mathematical Science and Engineering Division Thuwal23955 Saudi Arabia

Free-space optical (FSO) communication is a promising solution to support wireless backhaul links in emerging 6G non-terrestrial networks. At the link level, pointing errors in FSO links can significantly impact capacity, making accurate modeling of these errors essential for both assessing and enhancing communication performance. In this paper, we introduce a novel model for FSO pointing errors in unmanned aerial vehicles (UAVs) that incorporates three-dimensional (3D) jitter, including roll, pitch, and yaw angle jittering. We derive a probability density function for the pointing error angle based on the relative position and posture of the UAV to the ground station. This model is then integrated into a trajectory optimization problem designed to maximize energy efficiency while meeting constraints on speed, acceleration, and elevation angle. Our proposed optimization method significantly improves energy efficiency by adjusting the UAV's flight trajectory to minimize exposure to directions highly affected by jitter. The simulation results emphasize the importance of using UAV-specific 3D jitter models in achieving accurate performance measurements and effective system optimization in FSO communication networks. Using our generalized model, the optimized trajectories achieve up to 11.8% higher energy efficiency compared to those derived from conventional Gaussian pointing error models. © 2002-2012 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Ground calibration tests of the laser altimeter (LIDAR) for MMX mission

引用

Progress in Earth and Planetary science 2025年第1期12卷 1-10页

作者： Senshu, Hiroki Mizuno, Takahide Nakura, Toru Suetsugu, Ryo Kasai, Kaito Ikeda, Hirokazu Noda, Hirotomo Matsumoto, Koji Araki, Hiroshi Umetani, Kazuhiro Konishi, Akihiro Sasaki, Sho Ishihara, Yoshiaki Ikuse, Yasuyuki Mayuzumi, Katsunori Kase, Teiji Planetary Exploration Research Center Chiba Institute of Technology Narashino Japan Institute of Space and Astronautical Science Japan Aerospace Exploration Agency Sagamihara Japan Department of Electronics Engineering and Computer Science Fukuoka University Fukuoka Japan National Institute of Technology Oshima College Oshima Japan Department of Mechanical Engineering Graduate School of Engineering Tokai University Hiratsukacho Japan RISE Project National Astronomical Observatory of Japan Oshu Japan SOKENDAI (The Graduate University for Advanced Studies) Hayama Japan RISE Project National Astronomical Observatory of Japan Mitaka Japan Graduate School of Environment Life Natural Science and Technology Okayama University Okayama Japan Faculty of Informatics Graduate School of Informatics Chiba University Chiba Japan Department of Earth and Space Science Graduate School of Science Osaka University Toyonaka Japan LUPEX Project Team Human Spaceflight Technology Directorate Japan Aerospace Exploration Agency Tsukuba Japan NEC Corp. Fuchu City Tokyo Japan

The spacecraft for the Japanese Martian Moon eXploration mission is equipped with a LIDAR laser altimeter. The slant range continuously measured by the LIDAR is used for the correction of the local topography and the orbit and attitude of the spacecraft. The channel and gain setting of the LIDAR in the proximity phase will be automatically controlled based on the received energy. This paper reports the result of ground-based calibration tests. The calibration function is obtained for each channel and gain settings. Then, the performance test of the auto gain control function is carried out by changing the received energy gradually. This test demonstrates that the automatic gain control system of the LIDAR works well and the obtained slant range and received energy change smoothly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDVC: Efficient Deep Video Compression with Regulable Rate and Complexity Optimization

引用

IEEE Transactions on Multimedia 2025年

作者： Wei, Xiaojie Lin, Jielian Xu, Jiawei Gao, Wei Zhao, Tiesong Putian University School of Mechanical Electrical & Information Engineering PutianFujian China Shenzhen Graduate School Peking University School of Electronic and Computer Engineering Shenzhen518055 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350108 China Tsinghua University Department of Electronic Engineering Beijing100084 China

Deep video coding has paved a way to break through the performance bottleneck of reigning hybrid video coding. However, unlike hybrid video codecs, existing deep video codecs cannot offer both flexible rates and regulable complexities within one single codec, which limits their applications. In this paper, we propose a Regulable Deep Video Codec (RDVC) to address the above issue. First, we propose an Adaptive Feature Compression (AFC) network that generates variable rates while ensuring Rate-Distortion (RD) performance. The network introduces a two-stage coarse-to-fine rate adjustment that can be controlled by a user-specified rate level. Second, we propose a Spatio-Temporal Feature Propagation (STFP) mechanism to provide high-quality reference information for AFC process. Third, we also utilize slimmable convolutional components in our framework to adjust decoding complexity constrained by user configuration. Experimental results demonstrate that RDVC can adjust the codec structure flexibly according to different user configurations while maintaining advanced performance. On average, it reduces the bit-per-pixel (bpp) by 9.35%/58.12% while maintaining the same PSNR/MS-SSIM as the reference software VTM-13.2. Sourcecode is available at: https://***/WXJ0001/RDVC. © 2025 IEEE.

关键词： Signal distortion

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：