检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Cong, Mou Liu, Lu Han, Jiayu Zhu, Beibei Yuan, Xiaosong Peng, Tao College of Computer Science and Technology Jilin University 2699 Qianjin Street Jilin Changchun130012 China College of Software Jilin University 2699 Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University 2699 Qianjin Street Jilin Changchun130012 China Department of Linguistics University of Washington SeattleWA98195 United States

Fake news detection becomes a critical challenge in NLP. Batch processing with attention-derivative models is a popular solution for fake news detection. Models with attention mechanisms could mitigate the long-distance dependence problem. However, we find that extracting local dependencies using convolutional networks is as important as extracting global dependencies using attention mechanisms. Besides, fake news datasets often suffer from problems such as imbalance and are hard to understand by current models. To address these problems, we propose DRIVE, which is short for an adjustable parallel architecture based on evidence awareness for fake news detection to alleviate the above problems, in which we introduce Claim as a supporting clue to enhance the model’s comprehension ability. Specifically, we propose a novel method for unbalanced datasets and design adjustable parallel branches, using Claim Additives Network (ClaimAddNet) and the MLP with convolutional gating mechanism (CPMLP) to capture global and local information in distinct branches, respectively. Experiments conducted on 5 public datasets demonstrate that DRIVE outperforms all baselines, improving accuracy by approximately 1.7 %. Furthermore, we implement an anti-noise interference test and evaluate the weighted average of the two branches along with ablation studies. © 2024, The Authors. All rights reserved.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Optimal partition algorithm of RBF neural network and its applications to stock price prediction

引用

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence 2005年第3期18卷 374-379页

作者： Sun, Yan-Feng Liang, Yan-Chun Zhang, Wen-Li Lu, Ying-Hua Key Laboratory for Symbol Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Changchun 130012 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Department of Computer Science Northeast Normal University Changchun 130024 China

The optimal partition algorithm (OPA) is applied to the training of parameters in the radial basis function (RBF) neural network. The appropriate modification for the OPA is performed according to the characteristics of the RBF neural network. The approach for determining the centers and widths of the clustering is added in the modified OPA and applied to choose the centers and widths of the neural network. A method for adjusting the structure of the neural network dynamically is presented by using the difference of the objective functions of the clustering. Thus it is realized to select the number of the hidden nodes adaptively. Simulation results of the stock price prediction demonstrate the effectiveness of the proposed approach. Comparisons with traditional algorithms show that the proposed OPA method possesses obvious advantages in the precision of forecasting, generalization, and forecasting trends. Simulations also show that the algorithm combining the OPA with the orthogonal least squares (OLS) possesses more superior performance in the rightness of forecasting trends.

关键词： Optimal partition algorithm (OPA) Ordered sample Radial basis function (RBF) neural network Stock price prediction

来源：评论

学校读者我要写书评

暂无评论

A Sustainable City Planning Algorithm Based on TLBO and Local Search

引用

IOP Conference Series: Materials Science and engineering 2017年第1期242卷

作者： Ke Zhang Li Lin Xuanxuan Huang Yiming Liu Yonggang Zhang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering (Jilin University) Ministry of Education Changchun 130012 China

Nowadays, how to design a city with more sustainable features has become a center problem in the field of social development, meanwhile it has provided a broad stage for the application of artificial intelligence theories and methods. Because the design of sustainable city is essentially a constraint optimization problem, the swarm intelligence algorithm of extensive research has become a natural candidate for solving the problem. TLBO (Teaching-Learning-Based Optimization) algorithm is a new swarm intelligence algorithm. Its inspiration comes from the 'teaching' and 'learning' behavior of teaching class in the life. The evolution of the population is realized by simulating the 'teaching' of the teacher and the student 'learning' from each other, with features of less parameters, efficient, simple thinking, easy to achieve and so on. It has been successfully applied to scheduling, planning, configuration and other fields, which achieved a good effect and has been paid more and more attention by artificial intelligence researchers. Based on the classical TLBO algorithm, we propose a TLBO_LS algorithm combined with local search. We design and implement the random generation algorithm and evaluation model of urban planning problem. The experiments on the small and medium-sized random generation problem showed that our proposed algorithm has obvious advantages over DE algorithm and classical TLBO algorithm in terms of convergence speed and solution quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic watermarking scheme based on the Shamir threshold and branch structure

引用

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (engineering and Technology Edition) 2008年第SUPPL. 2期38卷 221-225页

作者： Yin, Ke Wang, Zhi-Quan Zhu, Jian-Qi Dong, Gang School of Automation Nanjing University of Science and Technology Nanjing 210094 China Electric Power Simulation and Control Engineering Center Nanjing Institute of Technology Nanjing 211167 China Key Laboratory of Symbol Computation and Knowledge Engineer College of Computer Science and Technology Jilin University Changchun 130012 China

A novel dynamic software watermark scheme based on the Shamir threshold and branch structure is presented. First, we split the watermark into a set of shares using the Shamir threshold scheme. Second, these values are encrypted with the DES block cipher that forms the watermark shares to be embedded into different methods of program according to the dynamic behavior of the branch structure. Our scheme can withstand most semantics-preserving attacks and can retrieve the original watermark based on partial information. Simulation tests show that our scheme is very robust, stealthy and has a high price performance rate compared with other methods.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification of Cancer Samples Based on Co-Expression Analyses

Multi-Classification of Cancer Samples Based on Co-Expressio...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hongyang Jiang Qiang Huang Liang Chen Zhi Li Ying Xu Huiyan Sun Yi Chang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun China College of Engineering Key Laboratory of Intelligent ManufacturingTechnology of Ministry of Education Shantou University Shantou China Key Laboratory of Anticancer Drugs and Biotherapy of Liaoning Province The First Hospital of China Medical University Shenyang China The China-Japan Union Hospital Cancer Systems Biology Center Jilin University Changchun China The China-Japan Union Hospital School of Artificial Intelligence Cancer Systems Biology Center Jilin University Changchun China School of Artificial Intelligence Jilin University Changchun China

Cancer staging, grading and subtyping all represent important problems for precision diagnosis, treatment and mechanistic studies of cancer. The majority of the existing computational methods solve this problem via multi-classification of differential gene-expressions of cancer samples of specific classes (Stages, Grades and subtypes) vs. controls. However, the performance of such classification techniques is generally not satisfactory since the discerning power of differential expression patterns in such classifications is limited. We present here a multi-classification technique, based on co-expression patterns specific to individual subclasses in provided training data as co-expression patterns tend to be more conserved than differential expressions within each subclass. A challenge in implementing this strategy lies in how to effectively derive co-expression patterns in individual samples, which is solved through comparing co-expression patterns within a subclass and those in the subclass plus a new sample. Compared with the state-of-the-art gene expression-based classification methods, our method outperforms them in cancer staging, grading and subtyping of cancer samples from TCGA in almost all the measures used. In addition, the co-expressed genes computationally selected for classifications are biologically meaningful, which will prove important for diagnostic biomarker design, treatment plan selection and possibly mechanistic studies of cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Surrogate Model Based Genetic Algorithm for Complex Problem Solving

引用

Journal of Physics: Conference Series 2020年第1期1646卷

作者： Ying Pei Hao Gao Xiaosong Han The College of Information Engineering Changchun University of Finance and Economics Changchun 130122 China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology College of Software Jilin University Changchun 130012 China

It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely huge. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem, to reduce the number of actual calculated fitness values. In this paper, BP neural network, the least square method and support vector machine were fused in the genetic algorithm to evaluate partial individuals' fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the calculating counts of fitness function on similar accuracy basis compared with simple genetic algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient and effective automatic image annotation using positive and negative example images

引用

ICIC Express Letters 2011年第8 B期5卷 2927-2932页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Bao, Cuizhu Dong, Yuying Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University No. 2699 Qianjin Avenue Changchun 130012 China Institute of Computer Graphics and Image Processing Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China College of Computer Science and Engineering Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China College of Life Science Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China

Automatic image annotation is an active topic and difficult task in computer vision domain, which has attracted more and more researchers' attention. Many approaches have been proposed to automatically annotate images. To improve the annotation quality, most of them have profound principlessophisticated modelsand high time complexities. How to efficiently annotate image is becoming one key issue in the field of computer vision. We propose a very efficient and effective approach called keyword vector classification approach, whose model is very simple. Experiments on Corel5K dataset show that the annotation performance of the our proposed approach is almost four times better than translation model and twice better than CMRM (in terms of precision, recall and F1) while the time cost of ours surprisingly decreases. In addition, to our knowledge, our proposed approach outperforms most of existing ones in terms of N+. © 2011 ISSN 1881-803X.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Design of a Daily Brief Business Report Generator based on Web Scraping with KNN Algorithm

引用

Journal of Physics: Conference Series 2019年第5期1345卷

作者： Gang Lin Yanchun Liang Xiaoyang Fu Guangshun Chen Shaocan Cai Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Department of Computer Science and Technology School of Computer Science Zhuhai 519041 Guangdong China Department of Computer Science and Technology School of Computer Science Zhuhai College of Jilin University Zhuhai 519041 Guangdong China

In order to generate a report for an enterprise where there is neither the API supporting from their existing website systems nor the granted database access rights approval, a daily business report generator system based on web scraping with k nearest neighbor (kNN) classification algorithm is proposed in this paper. It covers the web crawler technology that is to access existing website system and extract business data. The kNN algorithm is applied to identify the verification code on the login page, and the brief daily report generating in a spread-sheet style grid. Compared with some OCR engine for image recognition, the system in Python can automatically generate the brief daily business reports by the kNN algorithm, which is better than some library with default training set on validating the verification code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Catalog segmentation with double constraints in business” [Pattern Recognition Letters 30 (4) (2009) 440–448]

引用

Pattern Recognition Letters 2009年第15期30卷 1440-1440页

作者： Xiujuan Xu Yu Liu Zhe Wang Chunguang Zhou Yanchun Liang College of Computer Science Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun 130012 China School of Software Dalian University of Technology Dalian Economic and Technological Development Zone Liaoning Number 8 Road Dalian 116620 China

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Multi-label Deep Learning for Gene Function Annotation in Cancer Pathways

引用

Scientific reports 2018年第1期8卷 8995页

作者： Renchu Guan Xu Wang Mary Qu Yang Yu Zhang Fengfeng Zhou Chen Yang Yanchun Liang Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun 130012 China. MidSouth Bioinformatics Center and Joint Bioinformatics Ph.D. Program of University of Arkansas at Little Rock and Univ. of Arkansas Medical Sciences Little Rock AR 72204 USA. Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Beijing 100093 China. College of Earth Sciences Jilin University Changchun 130061 China. yangc616@***. Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun 130012 China. ycliang@***. Zhuhai Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041 China. ycliang@***.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper.

关键词：

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：