检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yu, Peilin Wu, Yuwei Gao, Zhi Fan, Xiaomeng Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimization on Riemannian manifolds. However, existing Riemannian meta-optimization methods take up huge memory footprints in large-scale optimization settings, as the learned optimizer can only adapt gradients of a fixed size and thus cannot be shared across different Riemannian parameters. In this paper, we propose an efficient Riemannian meta-optimization method that significantly reduces the memory burden for large-scale optimization via a subspace adaptation scheme. Our method trains neural networks to individually adapt the row and column subspaces of Riemannian gradients, instead of directly adapting the full gradient matrices in existing Riemannian meta-optimization methods. In this case, our learned optimizer can be shared across Riemannian parameters with different sizes. Our method reduces the model memory consumption by six orders of magnitude when optimizing an orthogonal mainstream deep neural network (e.g. ResNet50). Experiments on multiple Riemannian tasks show that our method can not only reduce the memory consumption but also improve the performance of Riemannian meta-optimization. © 2025, CC BY-NC-ND.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Structured Sparse Coding With the Group Log-regularizer for Key Frame Extraction

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1818-1830页

作者： Zhenni Li Yujie Li Benying Tan Shuxue Ding Shengli Xie the School of Automation Guangdong University of TechnologyGuangzhou 510006 the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology(GDUT)Guangzhou 510006China the School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China the National Institute of Advanced Industrial Science and Technology TsukubaIbaraki 305-8560Japan IEEE the Key Laboratory of Intelligent Information Processing and System Integration of Io T(GDUT) Ministry of Education Guangdong Key Laboratory of IoT Information Technology(GDUT) Guangzhou 510006China

Key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structured sparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.

关键词： Difference of convex algorithm(DCA) group logregularizer key frame extraction structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

An Entity Alignment Algorithm Based on Ontology Enhancement and Multi-Feature Fusion

An Entity Alignment Algorithm Based on Ontology Enhancement ...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Hao Song Yuxia Lei Kangli Zi Fuyuan Quan Tianhang Zhang Qi Li School of Computer Science Qufu Normal University Rizhao Shandong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Entity alignment plays a crucial role in the integration of knowledge graphs. However, current knowledge graphs often suffer from inconsistent construction standards, structural heterogeneity, and imprecise semantic representation of entities, which can lead to suboptimal embedding of structural information. Moreover, most existing entity alignment methods rely heavily on structural information, which limits alignment efficiency. To address these challenges, this paper presents Onto-IMF, an ontology-enhanced entity alignment method based on multi-feature fusion. This approach aims to enhance the semantic representation of entities by incorporating ontology information, thereby reducing structural discrepancies among heterogeneous graphs and improving the embedding of structural information. The multi-feature fusion entity alignment leverages diverse semantic features, including relations, attributes, and entity names, to achieve more accurate alignment. Experimental results on various DBP15K subsets indicate that the proposed method achieves Hits@l scores of 86.6%, 93.0%, and 97.7%, respectively, representing an average improvement of 7.9 % over the best-performing baseline models.

关键词： Accuracy Semantics Knowledge graphs Contrastive learning Ontologies Data models Standards

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Approach for PM2.5 Concentration Prediction in Smart Environmental Monitoring

引用

intelligent Automation & Soft computing 2023年第6期36卷 3029-3041页

作者： Minh Thanh Vo Anh HVo Huong Bui Tuong Le Faculty of Information Technology HUTECH UniversityHo Chi Minh CityVietnam Natural Language Processing and Knowledge Discovery Laboratory Faculty of Information TechnologyTon Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Computing Fundamentals FPT UniversityHo Chi Minh CityVietnam Laboratory for Artificial Intelligence Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh CityVietnam Faculty of Information Technology Van Lang UniversityHo Chi Minh CityVietnam

Nowadays,air pollution is a big environmental problem in develop-ing *** this problem,particulate matter 2.5(PM2.5)in the air is an air *** its concentration in the air is high in developing countries like Vietnam,it will harm everyone’s *** prediction of PM2.5 concentrations can help to make the correct decision in protecting the health of the *** study develops a hybrid deep learning approach named PM25-CBL model for PM2.5 concentration prediction in Ho Chi Minh City,***,this study analyzes the effects of variables on PM2.5 concentrations in Air Quality HCMC *** variables that affect the results will be selected for PM2.5 concentration ***,an efficient PM25-CBL model that integrates a convolutional neural network(CNN)andBidirectionalLongShort-TermMemory(Bi-LSTM)*** model consists of three following modules:CNN,Bi-LSTM,and Fully connected ***,this study conducts the experiment to compare the performance of our approach and several state-of-the-art deep learning models for time series prediction such as LSTM,Bi-LSTM,the combination of CNN and LSTM(CNN-LSTM),and *** empirical results confirm that PM25-CBL model outperforms other methods for Air Quality HCMC dataset in terms of several metrics including Mean Squared Error(MSE),Root Mean Squared Error(RMSE),Mean Absolute Error(MAE),and Mean Absolute Percentage Error(MAPE).

关键词： Time series prediction PM2.5 concentration prediction CNN Bi-LSTM network

来源：评论

学校读者我要写书评

暂无评论

Video Summarization Using Denoising Diffusion Probabilistic Model 39

Video Summarization Using Denoising Diffusion Probabilistic ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Shang, Zirui Zhu, Yubo Li, Hongxi Yang, Shuo Wu, Xinxiao Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

ISBN: (纸本)157735897X

Video summarization aims to eliminate visual redundancy while retaining key parts of video to construct concise and comprehensive synopses. Most existing methods use discriminative models to predict the importance scores of video frames. However, these methods are susceptible to annotation inconsistency caused by the inherent subjectivity of different annotators when annotating the same video. In this paper, we introduce a generative framework for video summarization that learns how to generate summaries from a probability distribution perspective, effectively reducing the interference of subjective annotation noise. Specifically, we propose a novel diffusion summarization method based on the Denoising Diffusion Probabilistic Model (DDPM), which learns the probability distribution of training data through noise prediction, and generates summaries by iterative denoising. Our method is more resistant to subjective annotation noise, and is less prone to overfitting the training data than discriminative methods, with strong generalization ability. Moreover, to facilitate training DDPM with limited data, we employ an unsupervised video summarization model to implement the earlier denoising process. Extensive experiments on various datasets (TVSum, SumMe, and FPVSum) demonstrate the effectiveness of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Multi-objective firefly algorithm with hierarchical learning

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第3期6卷 411-427页

作者： Lv, Li Zhou, Xiao-Dong Kang, Ping Fu, Xue-Feng Tian, Xiu-Mei Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang330099 China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China

In the optimization process of multi-objective firefly algorithm, the population is easy to fall into local optimum, which leads to poor population distribution and convergence. In order to solve this problem, this paper proposes a multi-objective firefly algorithm with hierarchical learning (MOFA-HL). Firstly, the hierarchical learning method is proposed, population is layered by non-dominant sorting to obtain individuals at each level, and the dominant individuals at the front level guide the individuals at the back level to learn, which is beneficial to search more high-quality solutions. Then, mutation operation is carried out on the population to enhance the local search ability of the algorithm. Finally, the mutated population is merged with the previous generation population, and the excellent individuals with the same population size as the previous generation are selected to enter the next generation by non-dominant sorting and crowding distance calculation. Eight test functions in the series of ZDT and DTLZ are used to test MOFA-HL. MOFA-HL is compared with four classical algorithms and four new algorithms. The results show that MOFA-HL can better improve the distribution and convergence of the population. © 2021 ISSN 2414-8105 (Online).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Interval Type-2 Fuzzy Hierarchical Adaptive Cruise Following-Control for intelligent Vehicles

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1658-1672页

作者： Hong Mo Yinghui Meng Fei-Yue Wang Dongrui Wu the College of Electric and Information Engineering Changsha University of Science and TechnologyChangsha 410114China the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Qingdao Academy of Intelligent Industries Qingda 266109 the Center of China Economic and Social Security University of Chinese Academy of SciencesBeijing 100190China the Ministry of Education Key Laboratory on Image Information Processing and Intelligent Control the School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China

intelligent vehicles can effectively improve traffic congestion and road traffic *** cruise followingcontrol(ACFC)is a vital part of intelligent *** this paper,a new hierarchical vehicle-following control strategy is presented by synthesizing the variable time headway model,type-2 fuzzy control,feedforward+fuzzy proportion integration(PI)feedback(F+FPIF)control,and inverse longitudinal dynamics model of ***,a traditional variable time headway model is improved considering the acceleration of the lead ***,an interval type-2 fuzzy logic controller(IT2 FLC)is designed for the upper structure of the ACFC system to simulate the driver's operating *** reduce the nonlinear influence and improve the tracking accuracy for the desired acceleration,the control strategy of F+FPIF is given for the lower control ***,the lower control method proposed in this paper is compared with the fuzzy PI control and the traditional method(no lower controller for tracking desired acceleration)***,the proportion integration differentiation(PID),linear quadratic regulator(LQR),subsection function control(SFC)and type-1 fuzzy logic control(T1 FLC)are respectively compared with the IT2 FLC in control performance under different ***,the simulation results show the effectiveness of IT2 FLC for the upper structure and F+FPIF control for the lower structure.

关键词： Adaptive cruise following-control(ACFC) feedforward+fuzzy proportion integration(PI)feedback(F+FPIF) type-2 fuzzy control variable time headway

来源：评论

学校读者我要写书评

暂无评论

FoodSky: A Food-Oriented Large Language Model Can Pass the Chef and Dietetic Examination

SSRN

引用

SSRN 2024年

作者： Zhou, Pengfei Min, Weiqing Fu, Chaoran Jin, Ying Huang, Mingyu Li, Xiangyang Mei, Shuhuan Jiang, Shuqiang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou China Zhongke Shenjian Technology Co. Ltd. Suzhou China

Food is the cornerstone of both survival and social life. With the increasing complexity of global dietary needs and preferences, there is a growing demand for food intelligence to enable tasks like recipe recommendation and diet-disease correlation discovery. To address this, we introduce the Food-oriented Large Language Model (LLM) FoodSky, which offers fine-grained perception and reasoning of food data. We constructed a food corpus, FoodEarth, from various authoritative sources to enhance FoodSky's knowledge. We also developed the Topic-based Selective State Space Model and Hierarchical Topic Retrieval Augmented Generation algorithms to improve FoodSky's ability to capture fine-grained food semantics and generate context-aware food-relevant text. Extensive experiments show that FoodSky outperforms general-purpose LLMs on the Chinese National Chef Exam and Dietetic Exam, achieving accuracies of 67.2% and 66.4%, respectively. FoodSky not only enhances culinary creativity and promotes healthier eating patterns but also establishes a new standard for domain-specific LLMs tackling real-world food-related issues. © 2024, The Authors. All rights reserved.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Efficient Finite-Difference Time-Domain Method for Solving Electromagnetic Scattering in Layered Anisotropies

Efficient Finite-Difference Time-Domain Method for Solving E...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Yilin Kang Yuxian Zhang Xiaoli Feng Lixia Yang Zhixiang Huang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education and with the Information Materials and Intelligent Sensing Laboratory of Anhui Province Industry-Education-Research Institute of Advanced Materials and Technology for Integrated Circuits and with School of Electronic and Information Engineering Anhui University Hefei China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

In this article, we propose an efficient numerical method for layered models based on the conventional finite difference time-domain (FDTD) method. The three-dimensional (3-D) layered model is compressed into one-dimensional (1-D) calculation, which improves the problem of large space memory and long running time for 3-D modeling while ensuring the accuracy and feasibility of the algorithm. On the one hand, by employing the transformation relationship between the transverse wave vector and the field in space, the expanded Maxwell's rotation equations are simplified, so that the equation system only retains the spatial transformation in the propagation direction. This processing allows for the calculation of the propagation characteristics of layered media without requiring more computational resources. On the other hand, to ensure the universality of the algorithm, a fully tensor anisotropic medium is selected for detecting the propagation data. At the same time, we design the layered structure and conduct the consistent 3-D modeling in the simulation software COMSOL. The results showed that our proposed efficient numerical algorithm greatly reduced the loss of computing resources while ensuring accuracy.

关键词： Solid modeling Three-dimensional displays Accuracy Tensors Software algorithms Vectors Mathematical models Numerical models Time-domain analysis Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Method Based on Ant Colony Optimization Algorithm and Improved Neighborhood Discernibility Matrix 16th

Feature Selection Method Based on Ant Colony Optimization Al...

引用

16th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2021

作者： Yang, Zhenyu Ye, Jun Ao, Jiaxin Ji, Yuxuan College of Information Engineering Nanchang Institute of Technology Nanchang330000 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang330000 China

ISBN: (纸本)9789811912559

Under the condition that the classification ability of the characterization data remains unchanged, selecting the smallest feature subset from the feature set is one of the problems that many researches try to solve. In view of the existing neighborhood rough set and ant colony optimization feature selection methods, the algorithms are premature, and the searched feature subset contains redundancy and other problems. Improvements have been made in three aspects. One is to extend the discrimination matrix based on equivalence to the rough set of neighborhoods, and define a neighborhood discernibility matrix;second, to give a method for the importance of neighborhood discrimination matrix features;The third is to use the importance of the neighborhood feature as the heuristic information factor of the ant colony algorithm, and propose a feature selection method based on the ant colony optimization algorithm and the improvement of the neighborhood discernibility matrix. Numerical examples and data set experiments show that the new feature selection method improves accuracy and reduces the number of iterations. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Feature Selection

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：