检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Huang, Lan Guan, Hongrui Liang, Yanchun Guan, Renchu Feng, Xiaoyue Jilin University The Key Laboratory for Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Changchun China Zhuhai College of Science and Technology Zhuhai Sub Laboratory Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai China

ISBN: (纸本)9781665401265

The worldwide spread of COVID-19 has made a severe impact on human health and life. It has shown rapid propagation, long in vitro survival, and a long incubation period. More seriously, COVID-19 is more susceptible to variation, as it is an RNA virus. Mutations of COVID-19 have been reported in multiple countries worldwide, which makes drug and vaccine development a significant challenge. To search for potential drugs and vaccines and reveal the atlas of COVID-19 evolution, we extract information from massive unstructured data and construct a COVID-19 knowledge graph using the COVID-19 data. Based on machine learning approaches, we infer and predict novel coronavirus pneumonia-related diseases, drug action targets, etc. to speculate on new and more effective treatment methods. In addition, to study transcriptome of SARS-CoV-2, new ideas can be provided to biomedical experts with flexible responses to viral variation. An in-depth analysis of the COVID-19 pathomechanism at the pharmaceutical, genetic, and protein levels provides effective means and tools for novel coronavirus pneumonia vaccines, drug development, and therapeutic program design. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Structure optimization of Bayesian network based on dependency analysis of relational database

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第22期6卷 400-408页

作者： Wang, Limin Xia, Huijie Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China College of Computer Science and Technology Jilin University China State Key Laboratory for Novel Software Technology Nanjing University China

The utilization of expert knowledge to construct Bayesian Network (BN) is one of the key issues of uncertain inference. In this paper the learning procedure of BN is simplified by applying data dependencies in relational database, which help to remove extraneous attributes and build the initial network structure. The final classification model named FM-NB inherits the simplicity of Naive Bayes (NB) and the ability to maintain inter-dependencies among attributes of Tree augmented NB(TAN). The inter-dependencies are expressed by Functional dependencies (FDs) and Local Multivalued dependencies (LMVDs), which relaxed the precondition about attribute sets of Multivalued dependency (MVD) and solved the problem related to conditional independence of Embedded Multivalued dependencies (EMVDs). Experimental results are presented to show the effectiveness and efficiency of the proposed approach.

关键词： Barium compounds

来源：评论

学校读者我要写书评

暂无评论

Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2021年第6期30卷 1120-1130页

作者： ZHANG Zhe WANG Bilin YU Zhezhou LI Zhiyuan College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed regions of each interest target as pseudo-labels for training segmentation networks, which achieve inferior performance compared with the fully supervised *** propose a Dilated convolutional pixels affinity network(DCPAN) to localize and expand the seed regions of objects to bridge this gap. Although introduced dilated convolutional units enable capture of additional location information of objects, it falsely highlighted true negative regions as dilated rate enlarge. To address this problem,we properly integrate dilated convolutional units with different dilated rates and self-attention mechanisms to obtain pixel affinity measure matrix for promoting classification network to generate high-quality object seed regions as pseudo-labels; thus, the performance of the segmentation network is boosted. Furthermore,although our approach seems simple, our method obtains a competitive performance, and experiments show that the performance of DCPAN outperforms other state-ofart approaches in weakly-supervised settings, which only use image-level labels on the Pascal VOC 2012 dataset.

关键词： weakly supervised semantic segmentation pseudolabels deep classification networks high-quality object seed regions pattern classification image segmentation weakly-supervised settings dilated convolutional pixels affinity network image-level weak-supervision image classification DCPAN self-attention mechanism object recognition feature extraction object detection sparse discriminatory seed regions pixel affinity measure matrix Pascal VOC 2012 dataset

来源：评论

学校读者我要写书评

暂无评论

A two-stage HV-driven adaptive multi-objective evolutionary algorithm and its application in Fixed Polarity Reed-Muller circuits

引用

Expert Systems with Applications 2025年

作者： Lu Yang Shengsheng Wang Ruyi Dong Zihao Fu College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China College of Information and Control Engineering Jilin Institute of Chemical Technology Changchun 130012 China

To achieve a balance between convergence and diversity, we proposed a two-stage HV-driven adaptive multi-objective evolutionary algorithm (TSAMEA). TSAMEA employs a sinusoidal decreasing parameter adjustment method to enhance exploration pace in the first stage. An adaptive parameter control mechanism utilizes historical memory pools and an HV-driven degree adjustment strategy to achieve better exploitation in the second stage. Extensive experimental data demonstrate that TSAMEA outperforms nine other compared MOEAs. The component analysis illustrates the efficacy of each component of TSAMEA. In addition, area and power optimization are now the main limitations in chip design, TSAMEA is applied to area and power optimization for Fixed Polarity Reed-Muller (FPRM) logic circuits and perform well, which further verifies the ability of the TSAMEA to solve practical problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Graph Attribute Aggregation Method based on Feature engineering

引用

Journal of The Institution of Engineers (India): Series B 2022年第3期103卷 711-719页

作者： Wang, Hao Dong, Li-Yan Ma, Xin-Tao Sun, Ming-Hui College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

In the fields of social network analysis and knowledge graph, many semi-supervised learning algorithms based on graph convolutional neural network (GCN) have been widely used. Most of these algorithms usually improve the structure of the neural network and the sampling method of each layer of the neural network. However, they don’t pay much attention to the data pre-processing of the algorithm. In the analysis of the input data, the words of different quality in these original data are unevenly distributed. This may obscure some useful data and highlight some irrelevant data. In order to verify the correctness of this hypothesis, the paper proposes a feature matrix compression algorithm (FMC algorithm) for data pre-processing of GCN-based algorithms. The algorithm analyzes and arranges the word columns of the input matrix (the feature of graph) according to the frequency of the word, then merges those words in which the word frequency is smaller, so as to emphasize the role of these words in the graph and optimize the data scale. The present work uses four mainstream datasets in the field and several representative and different algorithms to complete the experiment. The experimental results show that the FMC algorithm achieves better performance. © 2021, The Institution of Engineers (India).

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Stochastic Variational Inference-Based Parallel and Online Supervised Topic Model for Large-Scale Text Processing

引用

Journal of Computer Science & Technology 2018年第5期33卷 1007-1022页

作者： Yang Li Wen-Zhuo Song Bo Yang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun 130012 China Aviation University of Air Force Changchun 130062 China

Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic models, supervised Latent Dirichlet Allocation （sLDA） is acknowledged as a popular and competitive supervised topic model. How- ever, the gradual increase of the scale of datasets makes sLDA more and more inefficient and time-consuming, and limits its applications in a very narrow range. To solve it, a parallel online sLDA, named PO-sLDA （Parallel and Online sLDA）, is proposed in this study. It uses the stochastic variational inference as the learning method to make the training procedure more rapid and efficient, and a parallel computing mechanism implemented via the MapReduce framework is proposed to promote the capacity of cloud computing and big data processing. The online training capacity supported by PO-sLDA expands the application scope of this approach, making it instrumental for real-life applications with high real-time demand. The validation using two datasets with different sizes shows that the proposed approach has the comparative accuracy as the sLDA and can efficiently accelerate the training procedure. Moreover, its good convergence and online training capacity make it lucrative for the large-scale text data analyzing and processing.

关键词： topic modeling, large-scale text classification, stochastic variational inference, cloud computing online learning

来源：评论

学校读者我要写书评

暂无评论

Fine-grained sentimental tendency analysis based on Chinese online commentary of mobile phone

Fine-grained sentimental tendency analysis based on Chinese ...

引用

2016 IEEE International Conference on Cloud Computing and Big Data Analysis, ICCCBDA 2016

作者： Huang, Jiao Sun, Haobo Guo, Pengbo Zhao, Minghao Niu, Kai Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Changchun China

ISBN: (纸本)9781509025930

In recent years, with the development of the Internet, it is more and more common for users to buy mobile phones on the Internet. On the one hand, sentiment analysis help customers to fully understand the performance of the phone, on the other hand, it provides improvement direction for producer to upgrade the goods. In this paper, we use the method of semantic analysis to analyze the sentiment of Chinese online comments about mobile phone. It is worth noting that we focus on the analysis of characteristics of different commentators for the product of the independent sentimental rather than for the product's overall feelings. On the basis of predecessors' work, we creatively put forward a solution to solve the problem of multiple-sentiment sentimental words, which remarkable improve the rate of recall. In the aspect of accuracy, we provide a more powerful method for the judgment of neutral words by analyzing the influence of the degree adverbs on neutral words. In the end of the article, several times with different experiments verify the effectiveness of the method in the aspect of accuracy rate and recall rate. © 2016 IEEE.

关键词： Cellular telephones

来源：评论

学校读者我要写书评

暂无评论

Strengthened Initialization of Adaptive Cross-Generation Differential Evolution

引用

Computer Modeling in engineering & Sciences 2022年第3期130卷 1495-1516页

作者： Wei Wan Gaige Wang Junyu Dong Department of Computer Science of Technology Ocean University of ChinaQingdao266100China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun130012China Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis Guangxi University for NationalitiesNanning530006China

Adaptive Cross-Generation Differential Evolution(ACGDE)is a recently-introduced algorithm for solving multiobjective problems with remarkable performance compared to other evolutionary algorithms(EAs).However,its convergence and diversity are not satisfactory compared with the latest *** order to adapt to the current environment,ACGDE requires improvements in many aspects,such as its initialization and mutant *** this paper,an enhanced version is proposed,namely *** incorporates a strengthened initialization strategy and optimized parameters in contrast to its *** improvements make the direction of crossgeneration mutation more clearly and the ability of searching more *** experiments show that the new algorithm has better diversity and improves convergence to a certain *** the same time,SIACGDE outperforms other state-of-the-art algorithms on four metrics of 24 test problems.

关键词： Differential Evolution(DE) multi-objective optimization(MO) opposition-based learning parameter adaptation

来源：评论

学校读者我要写书评

暂无评论

Learn to explain transformer via interpretation path by reinforcement learning

引用

Neural Networks 2025年 188卷 107496页

作者： Niu, Runliang Wang, Qi Kong, He Xing, Qianli Chang, Yi Yu, Philip S. School of Artificial Intelligence Jilin University ChangChun130012 China Engineering Research Center of Knowledge-Driven Human–Machine Intelligence Ministry of Education China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University ChangChun China Department of Computer Science University of Illinois at Chicago United States

In recent years, the Transformer model has become a key part of many AI systems, making it important to understand how it works. The large parameter size and complex structure of the Transformer make interpretation more difficult and less efficient. Fortunately, there are many internal variables in Transformers that can aid in the explanation process, including attention matrices, gradients, hidden states, and activations between layers. Effectively utilizing these internal factors can help us better understand the decision-making process of Transformers. Also, most existing works focus on one type of these features and fail to investigate the interpretability of different variables in a unified model. To address these issues, this paper introduces a Reinforcement Learning environment in which the agent makes step-by-step modifications to input sequences to construct perturbed samples and gradually reduces the model's confidence in classification labels. The environment guides the agent to choose the token modification strategy along a more targeted interpretation path instead of random sampling, which can significantly improve the interpretation effectiveness. The flexibly designed agent can utilize multiple internal variables or even combinations of variables as observation, allowing for comparisons of their contributions to the model's interpretability. Extensive experiments conducted on three real-world datasets demonstrate the superior performance of our proposed model in both model interpretation and model adversarial attack tasks. We obtain a set of interesting findings, which can inspire further research on Transformer and Transformer-based model interpretation works. The code of this paper is available at https://***/niuzaisheng/Learn-to-Explain. © 2025

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Painlevé Property and Integrability of Polynomial Dynamical Systems

引用

Communications in Mathematical Research 2014年第4期30卷 358-368页

作者： Li Wen-lei Shi Shao-yun School of Mathematics Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University

The main purpose of this paper is to investigate the connection between the Painlev′e property and the integrability of polynomial dynamical systems. We show that if a polynomial dynamical system has Painlev′e property, then it admits certain class of first integrals. We also present some relationships between the Painlev′e property and the structure of the differential Galois group of the corresponding variational equations along some complex integral curve.

关键词： Painlev′e property integrability differential Galois group

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：