检索结果-南通市图书馆

An Improved Particle Swarm Optimization for Feature Selection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2011年第2期8卷 191-200页

作者： yuanning liu College of Computer Science and Technology Jilin University Changchun 130012 P. R. China Key Laboratory of S.vmbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 P. R. China

Particle Swarm Optimization （PSO） is a popular and bionic algorithm based on the social behavior associated with bird flocking for optimization problems. To maintain the diversity of swarms, a few studies of multi-swarm strategy have been reported. However, the competition among swarms, reservation or destruction of a swarm, has not been considered further. In this paper, we formulate four rules by introducing the mechanism for survival of the fittest, which simulates the competition among the swarms. Based on the mechanism, we design a modified Multi-Swarm PSO （MSPSO） to solve discrete problems, which consists of a number of sub-swarms and a multi-swarm scheduler that can monitor and control each sub-swarm using the rules. To further settle the feature selection problems, we propose an Improved Feature Selection （1FS） method by integrating MSPSO, Support Vector Machines （SVM） with F-score method. The IFS method aims to achieve higher generalization capa- bility through performing kernel parameter optimization and feature selection simultaneously. The performance of the proposed method is compared with that of the standard PSO based, Genetic Algorithm （GA） based and the grid search based mcthods on 10 benchmark datasets, taken from UCI machine learning and StatLog databases. The numerical results and statistical analysis show that the proposed IFS method performs significantly better than the other three methods in terms of prediction accuracy with smaller subset of features.

关键词： particle swarm optimization feature selection data mining support vector machines

基于偏好和虚拟适应度的两阶段依赖任务卸载算法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

吉林大学学报（理学版） 2024年第4期62卷 923-932页

作者：董立岩齐竞则刘元宁冯嘉辉吉林大学计算机科学与技术学院长春130012 吉林大学符号计算与知识工程教育部重点实验室长春130012

针对云边端协同环境中依赖任务卸载时效率低以及任务卸载失败的问题,提出一种基于偏好和虚拟适应度的两阶段依赖任务卸载算法.第一阶段,根据提出的二维卸载偏好因子对依赖任务的部分子任务进行直接卸载决策,从而有效缩小遗传算法初始种... 详细信息

针对云边端协同环境中依赖任务卸载时效率低以及任务卸载失败的问题,提出一种基于偏好和虚拟适应度的两阶段依赖任务卸载算法.第一阶段,根据提出的二维卸载偏好因子对依赖任务的部分子任务进行直接卸载决策,从而有效缩小遗传算法初始种群的规模.第二阶段,提出基于虚拟适应度的启发式交叉方法,并对基于参考点的快速非支配排序遗传算法(non-dominated sorting genetic algorithmⅢ, NSGA-Ⅲ)的交叉算子进行改进,保留了种群多样性并提升了算法收敛速度,最后使用改进的算法对所有依赖任务的子任务进行最优卸载决策集的搜索.实验结果表明,与其他算法相比,该算法在任务完成时间、任务能耗和边缘云集群成本方面平均优化了10.2%~18.3%,并且将任务失败率平均降低了10.7%~25.6%.

关键词：云边端协同环境依赖任务卸载多目标优化虚拟适应度遗传算法

The Improved Characteristics of Bionic Gabor Representations by Combining with SIFT Key-points for Iris Recognition

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2015年第3期12卷 504-517页

作者： yuanning liu Fei He Xiaodong Zhu Zhen liu Ying Chen Ye Han Lijiao Yu 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 Chanschun 130012 China Graduate School of Engineering Nagasaki Institute of Applied Science Japan College of Software Nanchang Hangkong University Nanchang 330063 China

Gabor filters are generally regarded as the most bionic filters corresponding to the visual perception of human. Their filtered coefficients thus are widely utilized to represent the texture information of irises. However, these wavelet-based iris representations are inevitably being misaligned in iris matching stage. In this paper, we try to improve the characteristics of bionic Gabor representations of each iris via combining the local Gabor features and the key-point descriptors of Scale Invariant Feature Transformation （SIFT）, which respectively simulate the process of visual object class recognition in frequency and spatial domains. A localized approach of Gabor features is used to avoid the blocking effect in the process of image division, meanwhile a SIFT key point selection strategy is provided to remove the noises and probable misaligned key points. For the combination of these iris features, we propose a support vector regression based fusion rule, which may fuse their matching scores to a scalar score to make classification decision. The experiments on three public and self-developed iris datasets validate the discriminative ability of our multiple bionic iris features, and also demonstrate that the fusion system outperforms some state-of-the-art methods.

关键词： iris recognition bionic Gabor features scale invariant feature transformation support vector regression score level fusion

Systematic study of human long intergenic non-coding RNAs and their impact on cancer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Life Sciences) 2013年第4期56卷 324-334页

作者： SUN Liang LUO HaiTao LIAO Qi BU DeChao ZHAO GuoGuang liu ChangNing liu yuanning ZHAO Yi College of Computer Science and Technology Jilin University Bioinformatics Research Group Advanced Computing Research Laboratory Institute of Computing TechnologyChinese Academy of Sciences Department of Preventive Medicine School of Medicine Ningbo University

The functional impact of several long intergenic non-coding RNAs (lincRNAs) has been characterized in previous studies. However, it is difficult to identify lincRNAs on a large-scale and to ascertain their functions or predict their structures in laboratory experiments because of the diversity, lack of knowledge and specificity of expression of lincRNAs. Furthermore, although there are a few well-characterized examples of lincRNAs associated with cancers, these are just the tip of the iceberg owing to the complexity of cancer. Here, by combining RNA-Seq data from several kinds of human cell lines with chromatin-state maps and human expressed sequence tags, we successfully identified more than 3000 human lincRNAs, most of which were new ones. Subsequently, we predicted the functions of 105 lincRNAs based on a coding-non-coding gene co-expression network. Finally, we propose a genetic mediator and key regulator model to unveil the subtle relationships between lincRNAs and lung cancer. Twelve lincRNAs may be principal players in lung tumorigenesis. The present study combines large-scale identification and functional prediction of human lincRNAs, and is a pioneering work in characterizing cancer-associated lincRNAs by bioinformatics.

关键词： lincRNA identification functional annotation cancer

An Intrusion Detection Approach Based on Particle Method

在线全文

学校读者我要写书评

暂无评论

通讯和计算机（中英文版） 2021年第2期18卷 6-18页

作者： Tao Yu Zhen liu Li Fu yuanning liu Graduate School of Engineering Nagasaki Institute of Applied ScienceJapan College of Computer Science and Technology Jilin UniversityChina School of Mathematics and Statistics Qinghai Nationalities UniversityChina

In recent years,the network continues to enter people’s lives,followed by network security issues that continue to appear,causing substantial economic losses to the *** an effective method to tackle the network security issues,intrusion detection system has been widely used and *** this paper,the NSL-KDD data set is used to reduce the dimension of data features,remove the features of low correlation and high interference,and improve the computational *** improve the detection rate and accuracy of intrusion detection,this paper introduces the particle method for the first time that we call it intrusion detection with particle(IDP).To illustrate the effectiveness of this method,experiments are carried out on three kinds of data-before dimension reduction,after dimension reduction and importing particle method based on dimension *** comparing the results of DT,NN,SVM,K-NN,and NB,it is proved that the particle method can effectively improve the intrusion detection rate.

关键词： Intrusion detection dimension reduction sort out NSL-KDD particle method

Mannogalactoglucan from mushrooms protects pancreatic islets via restoring UPR and promotes insulin secretion in TIDM mice

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2024年第3期13卷 1390-1401页

作者： Ting liu Si Chen Yunhe Qu Lujuan Zheng Xiaoxuan Yang Shuhan Men yuanning Wang Hanrui Ma Yifa Zhou Yuying Fan Engineering Research Center of Glycoconjugates Ministry of EducationJilin Provincial Key Laboratory of Chemistry and Biology of Changbai Mountain Natural DrugsSchool of Life SciencesNortheast Normal UniversityChangchun 130024China

Type 1 diabetes mellitus(T1DM) lacks insulin secretion due to autoimmune deficiency of pancreaticβ-*** pancreatic islets and enhancing insulin secretion has been therapeutic *** is the main type of polysaccharide from natural mushroom,which has potential medicinal ***,the antidiabetic property of mannogalactoglucan in T1DM has not been fully *** this study,we obtained the neutral fraction of alkali-soluble Armillaria mellea polysaccharide(AAMP-N) with the structure of mannogalactoglucan from the fruiting body of *** and investigated the potential therapeutic value of AAMP-N in *** demonstrated that AAMP-N lowered blood glucose and improved diabetes symptoms in T1DM ***-N activated unfolded protein response(UPR) signaling pathway to maintain ER protein folding homeostasis and promote insulin secretion in *** that,AAMP-N promoted insulin synthesis via upregulating the expression of transcription factors,increased Ca^(2+) signals to stimulate intracellular insulin secretory vesicle transport via activating calcium/calmodulin-dependent kinase Ⅱ(CamkⅡ) and cAMP/PKA signals,and enhanced insulin secretory vesicle fusion with the plasma membrane via vesicle-associated membrane protein 2(VAMP2).Collectively,these studies demonstrated that the therapeutic potential of AAMP-N on pancreatic islets function,indicating that mannogalactoglucan could be natural nutraceutical used for the treatment of T1DM.

关键词： Mannogalactoglucan Mushroom Pancreatic islets Insulin secretion Insulin synthesis Unfolded protein response(UPR) Type 1 diabetes mellitus(T1DM)

CHASE:Discovery of Cancer Heterogeneity and Chromosomal Aberrations from SNP-array Experiments

在线全文

学校读者我要写书评

暂无评论

CHASE:Discovery of Cancer Heterogeneity and Chromosomal Aber...

基于隐Markov模型的RNA二级结构预测新方法

第五届全国生物信息学与系统生物学学术大会暨国际生物信息学前沿研讨会高通量时代的生物信息学与系统生物学

作者：李骜 Hong Xial yuanning liu Minghui Wang School of Information Science and Technology University of Science and Technology of China Center for Biomedical Engineering Research University of Science and Technology of China

Background:With the advance of single nucleotide polymorphism(SNP) genotyping arrays,there is increasing interest in using this powerful technology for profiling chromosomal aberrations in ***,currently a critical issue hampering further applications of SNP-array in cancer research lies in the fact that cancer is often heterogeneous with multiple sub-clones that exhibit distinct biological characteristic including chromosomal *** addition,cancer heterogeneity is of great interest to oncologists as study on it may shed light on the origin of cancer and carcinogenesis. Methods:To address the issue of cancer heterogeneity,we developed a novel statistical model named CHASE(Cancer Heterogeneity and Chromosomal Aberrations from SNP-array Experiments) based on the framework of global parameter hidden Markov model(HMM).By quantitatively delineating the genomic similarity and discrepancy between two cancer sub-clones using global parameters representing the percentage of different sub-clones,we generated empirical emission probability density functions and incorporated them with the *** modeling fitting and parameter estimation,ECM algorithm was adopted in CHASE and formulas were derived for parameter updating. Results:Test on both simulated and real SNP-array data showed that CHASE can automatically determine cancer heterogeneity from the results of SNP-array experiment. For each cancer sub-clone,various kinds of chromosomal aberrations,such as amplification,deletion,LOH,etc,can be precisely discovered by *** example, by applying CHASE to breast cancer sample "BLCB1T45" that was manually identified as heterogeneous,we successfully identified two cancer sub-clones with two chromosomal regions exhibiting distinct chromosomal aberrations. Conclusions:To the best of our knowledge,CHASE is currently the most powerful computational methods that can discover cancer heterogeneity and chromosomal aberrations for each sub-clone from SNP-array data.

关键词： SNP-array cancer heterogeneity chromosomal aberration HMM

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

计算机研究与发展 2012年第4期49卷 812-817页

作者：董浩刘元宁张浩王刚吉林大学通信工程学院长春130012 吉林大学计算机科学与技术学院长春130022

有效预测RNA二级结构是生物信息学中的重要研究领域.提出一种基于隐Markov模型预测RNA二级结构的新方法.首先,应用前后缀匹配算法快速找到所有可能(包括假结)的茎区,建立RNA-HMM,寻找最优的茎区组合方法,得到包含假结的RNA二级结构.实... 详细信息

有效预测RNA二级结构是生物信息学中的重要研究领域.提出一种基于隐Markov模型预测RNA二级结构的新方法.首先,应用前后缀匹配算法快速找到所有可能(包括假结)的茎区,建立RNA-HMM,寻找最优的茎区组合方法,得到包含假结的RNA二级结构.实验结果表明,提出的新方法降低了计算复杂性,提高了预测的特异性和敏感性,具有较高的准确率,可以预测RNA的假结结构.

关键词：生物信息学 RNA二级结构假结自由能隐Markov模型(HMM)

在线全文

学校读者我要写书评

暂无评论

一种基于信息增益的新垃圾邮件特征选择算法

吉林大学学报（理学版） 2017年第2期55卷 379-382页

作者：李猛刘元宁吉林大学计算机科学与技术学院长春130012

基于传统信息增益特征选择算法,通过提出类内分散度与类间集中度的概念,结合传统信息增益算法,解决了信息增益算法因忽略特征项的分布而导致的性能下降问题,提高了信息增益算法的效率.使用改进的特征选择算法进行垃圾邮件过滤实验,在不... 详细信息

基于传统信息增益特征选择算法,通过提出类内分散度与类间集中度的概念,结合传统信息增益算法,解决了信息增益算法因忽略特征项的分布而导致的性能下降问题,提高了信息增益算法的效率.使用改进的特征选择算法进行垃圾邮件过滤实验,在不同的分类器下,与传统的特征选择算法进行对比,实验结果表明,改进的特征选择算法性能较优.

关键词：信息增益类内分散度类间集中度垃圾邮件特征选择