检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Xuanchen Niu, Yan Zhao, Bo Shi, Haoyuan An, Zitong State Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Ministry of Education Jilin University Changchun China The College of Software Jilin University Changchun130012 China

3D convolutions are commonly employed by demosaicking neural models, in the same way as solving other image restoration problems. Counter-intuitively, we show that 3D convolutions implicitly impede the RGB color spectra from exchanging complementary information, resulting in spectral-inconsistent inference of the local spatial high frequency components. As a consequence, shallow 3D convolution networks suffer the Moiré artifacts, but deep 3D convolutions cause over-smoothness. We analyze the fundamental difference between demosaicking and other problems that predict lost pixels between available ones (e.g., super-resolution reconstruction), and present the underlying reasons for the confliction between Moiré-free and detail-preserving. From the new perspective, our work decouples the common standard convolution procedure to spectral and spatial feature aggregations, which allow strengthening global communication in the spectral dimension while respecting local contrast in the spatial dimension. We apply our demosaicking model to two tasks: Joint Demosaicking-Denoising and Independently Demosaicking. In both applications, our model substantially alleviates artifacts such as Moiré and over-smoothness at similar or lower computational cost to currently top-performing models, as validated by diverse evaluations. Source code will be released along with paper publication. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Extracting Attributes from Deep Web Interface Using Instances

Extracting Attributes from Deep Web Interface Using Instance...

引用

Computer Science and Information engineering, CSIE, WRI World Congress on FLAGGED

作者： Hao Liang Fei Ren Wanli Zuo Fengling He Junhua Wang College of Computer Science and Technology Jilin University Changchun China Department of Information Changchun Taxation College Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun China

There is myriad high quality information in the Deep Web and the feasible method to access the Deep Web is through the query interface of the Deep Web. Itpsilas necessary to extract abundant attributes and semantic relation description from the query interface. Automatic extracting attributes from the query interface and automatically translating a query is a solvable way for addressing the current limitations in accessing Deep Web data sources. We design a framework to automatically extract the attributes and instances from the query interface using the WordNet as a kind of ontology technique to enrich the semantic description of the attributes. Each attribute is extended into a candidate attribute set in the form of a hierarchy tree. At the same time, the hierarchy tree generated by ontology describes the semantic relation of the attributes in the same query interface. We carry out our experiments in the real-world domain. The results of the experiments showed the validation of query translation framework.

关键词： Data mining Ontologies Computer science Educational institutions Databases Programming profession HTML Laboratories Computer interfaces knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Drawings Retrieval System Based on Spatial Relationships and Shape

Research and Design of Drawings Retrieval System Based on Sp...

引用

ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM

作者： Haiyu Song Pengjie Wang Xiongfei Li Houjie Li Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin China The Research Institute of Computer Graphics and Image Processing Dalian Nationalities of University Dalian Liaoning China

CAD drawings reuse is of great importance in promoting design efficiency and productivity. The ability to retrieve CAD drawings is the core of drawings reuse task. Most of the existing drawings retrieval systems rely only on text descriptions. Due to complexity of visual feature, a little system is based on content. A simplified topological relationship is proposed to describe visual features for dimension reduction. An effective topological relationship vector is constructed by graph spectra. A novel retrieval system based on visual contents, including topological relationships, shape, and directional relationships, is proposed. The experiments show that the proposed approach and system are superior to the text-based and traditional content-based retrieval systems.

关键词： Shape Feature extraction Topology Indexing Design automation Data mining Visualization

来源：评论

学校读者我要写书评

暂无评论

Shortcut Learning in In-Context Learning: A Survey

arXiv

引用

arXiv 2024年

作者： Song, Rui Li, Yingji Shi, Lida Giunchiglia, Fausto Xu, Hao College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Information Engineering and Computer Science University of Trento Italy

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of Large Language Models (LLMs) in recent years, an increasing number of studies have shown the impact of shortcut learning on LLMs. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL). It conducts a detailed exploration of the types of shortcuts in ICL tasks, their causes, available benchmarks, and strategies for mitigating shortcuts. Based on the corresponding observations, we summarize the unresolved issues in existing research and attempts to outline the future research landscape of shortcut learning. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Medicine composition concentration analysis based on least square support vector machine

Medicine composition concentration analysis based on least s...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Xin-Chen Guo Zhou-Yi Chen Li-Rong Teng Chun-Guo Wu Tian-Bao Du Jia-Huilu Qing-Fan Meng Yan-Chun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun China College of Science Northeast China Institute of Electric Power Engineering Jilin China EAAF of PLA Institute of General Development and Evaluation of Equipment Beijing China College of Life Science Jilin University Changchun China

This paper presents a method of medicine composition concentration analysis based on least square support vector machines (LS-SVMs) and examines the importance of the hyperparameter choice in improvement of algorithm performance. Simulation results show that the proposed method obtains high quality precision in the generalization, compared with multiple linear regression, and that it is an efficient approach to regression estimation.

关键词： Least squares methods Support vector machines Educational institutions Performance analysis Algorithm design and analysis knowledge engineering Linear regression Spectral analysis Quadratic programming Lagrangian functions

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm with affinity propagation

Genetic algorithm with affinity propagation

引用

International Conference on Information and Automation (ICIA)

作者： Chunguo Wu Hao Gao Lianjiang Yu Yanchun Liang Rongwu Xiang College of Computer Science and Technology Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry Jilin University Changchun China School of Basic Courses Shenyang Pharmaceutical University Shenyang China

ISBN: (纸本)9781424457014

Classical genetic algorithm suffers heavy pressure of fitness evaluation for time-consuming optimization problems, e.g., aerodynamic design optimization, qualitative model learning in bioinformatics. To address this problem, we present a combination between genetic algorithms and clustering methods. Specifically, the clustering method used in this paper is affinity propagation. The numerical experiments demonstrate that the proposed method performs promisingly for well-known benchmark problems in the term of optimization accuracy.

关键词： Genetic algorithms Clustering methods Evolutionary computation Design optimization Optimization methods Design automation Computer science Educational technology Pharmaceutical technology knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Fast Explainable Recommendation Model by Combining Fine-Grained Sentiment in Review Data

引用

computational Intelligence and Neuroscience 2022年第0期2022卷 4940401页

作者： Wang, Ying He, Xin Wang, Hongji Sun, Yudong Wang, Xin College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China College of Artificial Intelligence Jilin University Changchun130012 China

With the rapid development of e-commerce, recommendation system has become one of the main tools that assists users in decision-making, enhances user's experience, and creates economic value. Since it is difficult to explain the implicit features generated by matrix factorization, explainable recommendation system has attracted more and more attention recently. In this paper, we propose an explainable fast recommendation model by combining fine-grained sentiment in review data (FSER, (Fast) Fine-grained Sentiment for Explainable Recommendation). We innovatively construct user-rating matrix, user-aspect sentiment matrix, and item aspect-descriptive word frequency matrix from the review-based data. And the three matrices are reconstructed by matrix factorization method. The reconstructed results of user-aspect sentiment matrix and item aspect-descriptive word frequency matrix can provide explanation for the final recommendation results. Experiments in the Yelp and Public Comment datasets demonstrate that, compared with several classical models, the proposed FSER model is in the optimal recommendation accuracy range and has lower sparseness and higher training efficiency than tensor models or neural network models;furthermore, it can generate explanatory texts and diagrams that have high interpretation quality. © 2022 Ying Wang et al.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

The TPSO algorithm to solve geometric constraint problems

引用

Journal of computational Information Systems 2006年第4期2卷 1311-1316页

作者： Yuan, Hua Li, Wenhui Yi, Rongqin Zhao, Kong Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Changchun 130012 China School of Computer Science and Engineering Changchun University of Technology Changchun 130012 China Suzhou Top Institute of Information Technology Suzhuo 215311 China

The constraint problem can be transformed to an optimization problem. Particle swarm optimization (PSO) is a new evolutionary computation technique. Even PSO has many attractive properties, but it lacks global search ability at the end of the run. This paper introduce a hybrid approach called the TPSO that simultaneously applies particle swarm optimization (PSO), and tabu search (TS) to create a generally well-performing search heuristics, and combat the problem of premature convergence. The new algorithm considers candidate solutions and their fitness as individuals, which are based on their recent search progress. The tabu search makes each particle to reset its record of its best position, to avoid making direction and velocity decisions on the basis of outdated information. The feasibility of the proposed method is demonstrated on Solving Geometric Constraint Problems.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

Methods for gene selection in microarrays based on data clustering on local SVM-RFE

引用

Journal of computational Information Systems 2015年第16期11卷 5825-5832页

作者： Cao, Zhongbo Du, Wei Sun, Ying Liang, Yanchun Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China Department of Computer Science and Technology Zhuhai College of Jilin University Zhuhai China School of Management Science and Information Engineering Jilin University of Finance and Economics Changchun China

Most of the microarray expression data have tens of thousands of genes but very small number of samples. Feature selection has been widely used to extract the subset of informative genes. Though many feature selection methods have been proposed, the Support Vector Machine-Recursive Feature Elimination (SVM-RFE) algorithm is one of the best for microarray expression data analysis. However, SVM-RFE is not a stable and robust algorithm in some cases. The purpose of this article is to design a novel gene selection method for microarray expression data analysis, which is more effective, flexible and robust than normal SVM-RFE. In this article, the Local SVM-RFE (L-SR), Cluster SVM-RFE (C-SR) and Cluster Local SVM-RFE (CL-SR) methods for feature selection are proposed which eliminate irrelevant genes effectively and automatically. Experimental results obtained by using six cancer related datasets on different classifiers demonstrate that the proposed methods in this article are superior to normal SVM-RFE. Moreover, compared with the mRMR, GA-KNN and SVM-RCE, the proposed algorithm shows better performance in best and average accuracies comparison. © 2015 by Binary Information Press

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Fold-based meta-analysis: a method for identifying differentially expressed genes in microarray data

引用

Journal of Information and computational Science 2013年第11期10卷 3453-3462页

作者： Tian, Yuan Bai, Tian Liu, Guixia Li, Zhangxiu Wu, Jianan Zhou, Chunguang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China College of Computer Science and Technology Changchun University Changchun 130022 China

The increase of microarray experiments brings a fresh challenge to analyze microarray data across datasets. Several methods have been developed and implemented. But the current tools were either complicated software with inefficiency methods or web applications, among which some were limited to specific data format. In this paper, we propose Fold-based Meta-analysis (FM), a method to identify Differentially Expressed Genes (DEGs) in microarray data. It could meta-analyze datasets in either the same or different platforms. We test FMT, respectively, on two published Arabidopsis datasets in one platform and three Mouse datasets in three different platforms, and then analyze the Gene Ontology (GO) terms or metabolic pathways of the most DEGs. Our results show that they are highly agreed on DEGs, and many of them are crucial and functional. In summary, our method is fast and practical. © 2013 Binary Information Press.

关键词： Genes

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：