检索结果-南通市图书馆

Towards understanding residual and dilated dense neural networks via convolutional sparse coding

在线全文

学校读者我要写书评

暂无评论

National Science Review 2021年第3期8卷 127-139页

作者： Zhiyang zhang shihua zhang National Center for Mathematics and Interdisciplinary Sciences Center for Excellence in Mathematical Science Key Laboratory of Random Complex Structures and Data ScienceAcademy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences Center for Excellence in Animal Evolution and Genetics Chinese Academy of Sciences Key Laboratory of Systems Biology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences

Convolutional neural network(CNN) and its variants have led to many state-of-the-art results in various ***,a clear theoretical understanding of such networks is still ***,a multilayer convolutional sparse coding(ML-CSC) model has been proposed and proved to equal such simply stacked networks(plain networks).Here,we consider the initialization,the dictionary design and the number of iterations to be factors in each layer that greatly affect the performance of the ML-CSC *** by these considerations,we propose two novel multilayer models:the residual convolutional sparse coding(Res-CSC) model and the mixed-scale dense convolutional sparse coding(MSD-CSC) *** are closely related to the residual neural network(ResNet) and the mixed-scale(dilated) dense neural network(MSDNet),***,we derive the skip connection in the ResNet as a special case of a new forward propagation rule for the ML-CSC *** also find a theoretical interpretation of dilated convolution and dense connection in the MSDNet by analyzing the MSD-CSC model,which gives a clear mathematical understanding of *** implement the iterative soft thresholding algorithm and its fast version to solve the Res-CSC and MSD-CSC *** unfolding operation can be employed for further ***,extensive numerical experiments and comparison with competing methods demonstrate their effectiveness.

关键词： convolutional neural network convolutional sparse coding residual neural network mixed-scale dense neural network dilated convolution dense connection

Integrative cancer genomics： models, algorithms and analysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2017年第3期11卷 392-406页

作者： Jinyu CHEN shihua zhang National Center for Mathematics and Interdisciplinary Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China

In the past decade, the remarkable development of high-throughput sequencing technology accelerates the generation of large amount of multiple dimensional data such as genomic, epigenomic, transcriptomic and proteomic data. The comprehensive data make it possible to understand the underlying mechanisms of biology and disease such as cancer systematically. It also provides great challenges for computa- tional cancer genomics due to the complexity, scale and noise of data. In this article, we aim to review the recent develop- ments and progresses of computational models, algorithms and analysis of complex data in cancer genomics. These topics of this paper include the identification of driver mutations, the genetic heterogeneity analysis, genomic markers discovery of drug response, pan-cancer scale analysis and so on.

关键词： cancer genomics model algorithm data integration bioinformatics computational biology

Imputing single-cell RNA-seq data by considering cell heterogeneity and prior expression of dropouts

维普期刊数据库评论

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 Molecular Cell Biology 2021年第1期13卷 29-40页

作者： Lihua zhang shihua zhang NCMIS CEMSRCSDSAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Center for Excellence in Animal Evolution and Genetics Chinese Academy of SciencesKunming 650223China Key Laboratory of Systems Biology Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesChinese Academy of SciencesHangzhou 310024China

Single-cell RNA sequencing(scRNA-seq)provides a powerful tool to determine expression patterns of thousands of individual ***,the analysis of scRNA-seq data remains a computational challenge due to the high technical noise such as the presence of dropout events that lead to a large proportion of zeros for expressed *** into account the cell heterogeneity and the relationship between dropout rate and expected expression level,we present a cell sub-population based bounded low-rank(PBLR)method to impute the dropouts of scRNA-seq *** application to both simulated and real scRNA-seq datasets,PBLR is shown to be effective in recovering dropout events,and it can dramaimprove the low・dimensional representation and the recovery of gene-gene relationships masked by dropout events compared to several state-of-the-art methods・Moreover,PBLR also detects accurate and robust cell sub-populations automatically,shedding light on its flexibility and generality for scRNA-seq data analysis.

关键词： single-cell RNA-seq dropout imputation low订ank systems biology

Large-scale determination and characterization of cell type-specific regulatory elements in the human genorne

维普期刊数据库评论

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 Molecular Cell Biology 2017年第6期9卷 463-476页

作者： Can Wang shihua zhang NCMIS CEMS RCSDS Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China

Histone modifications have been widely elucidated to play vital roles in gene regulation and cell identity. The Roadmap Epigenomics Consortium generated a reference catalog of several key histone modifications across 〉lOOs of human cell types and tissues. Decoding these epJgenomes into functional regulatory elements is a challenging task in computational biology. To this end, we adopted a differential chromatin modification analysis framework to comprehensively determine and characterize cell type-specific regulatory elements （CSREs） and their histone modification codes in the human epigenomes of five histone modifications across 127 tissues or cell types. The CSREs show significant relevance with cell type-specific biological functions and diseases and cell identity. Clustering of CSREs with their specificity signals reveals distinct histone codes, demonstrating the diversity of functional roles of CSREs within the same cell or tissue. Last but not least, dynamics of CSREs from close cell types or tissues can give a detailed view of developmental processes such as normal tissue development and cancer occurrence.

关键词： epigenomics histone modification celL type-specific regulatory elements bioinformatics

呋喃基磷杂菲阻燃剂的合成及在阻燃环氧树脂中的应用

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

高等学校化学学报 2024年第4期45卷 142-150页

作者：唐刚陶熠邓丹张冬欣张诗华刘秀玉伍强沈海峰孙俊杰安徽工业大学建筑工程学院马鞍山243032 嘉兴学院高分子材料与工程系嘉兴314001 安徽工业大学分子工程与应用化学研究所马鞍山243002

以5-羟甲基糠醛、糠胺、三氯氧磷和9,10-二氢-9-氧杂-10-磷杂菲-10-氧化物(DOPO)为原料合成了一种呋喃基磷杂菲阻燃剂(Furan-2DOPO),并利用傅里叶变换红外光谱(FTIR)、核磁共振波谱(^(1)H NMR和^(31)P NMR)对其结构进行了表征.进一步利... 详细信息

以5-羟甲基糠醛、糠胺、三氯氧磷和9,10-二氢-9-氧杂-10-磷杂菲-10-氧化物(DOPO)为原料合成了一种呋喃基磷杂菲阻燃剂(Furan-2DOPO),并利用傅里叶变换红外光谱(FTIR)、核磁共振波谱(^(1)H NMR和^(31)P NMR)对其结构进行了表征.进一步利用Furan-2DOPO对环氧树脂进行阻燃改性,得到一系列阻燃环氧固化物.考察了Furan-2DOPO的用量对阻燃环氧固化物的力学性能、热稳定性以及阻燃性能的影响.研究结果表明,当Furan-2DOPO的添加量(质量分数)仅为5%时(磷质量分数为0.47%),环氧固化物的氧指数达到31.0%,且能够通过UL-94垂直燃烧V-0级测试.与未改性环氧树脂相比,添加2.5%和5%Furan-2DOPO的环氧固化物的最大热释放速率分别下降了31%和35%.此外,2种添加Furan-2DOPO的环氧固化物的拉伸强度均比未改性环氧树脂提升了约28%.炭层分析结果表明,Furan-2DOPO具有良好的催化成炭性能,有利于减少燃烧过程中可燃性气体的逸出,从而提升阻燃性能.

关键词：环氧树脂呋喃基磷杂菲阻燃剂热降解

Sparse Weighted Canonical Correlation Analysis

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2018年第3期27卷 459-466页

作者： MIN Wenwen LIU Juan zhang shihua State Key Laboratory of Software Engineering School of Computer Wuhan University National Center for Mathematics and Interdisciplinary Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences School of Mathematics Sciences University of Chinese Academy of Sciences

Given two data matrices X and Y, Sparse canonical correlation analysis（SCCA） is to seek two sparse canonical vectors u and v to maximize the correlation between Xu and Yv. Classical and sparse Canonical correlation analysis（CCA） models consider the contribution of all the samples of data matrices and thus cannot identify an underlying specific subset of samples. We propose a novel Sparse weighted canonical correlation analysis（SWCCA）,where weights are used for regularizing different *** solve the L;-regularized SWCCA（L;-SWCCA） using an alternating iterative algorithm. We apply L;-SWCCA to synthetic data and real-world data to demonstrate its effectiveness and superiority compared to related methods. We consider also SWCCA with different penalties like Least absolute shrinkage and selection operator（LASSO）and Group LASSO, and extend it for integrating more than three data matrices.

关键词： Canonical correlation analysis(CCA) Sparse canonical correlation analysis(SCCA) Sparse weighted CCA(SWCCA) Group LASSO regularized SWCCA Multi-view SWCCA

Network diffusion for scalable embedding of massive single-cell ATAC-seq data

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science Bulletin 2021年第22期66卷 2271-2276,M0003页

作者： Kangning Dong shihua zhang NCMIS CEMSRCSDSAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Center for Excellence in Animal Evolution and Genetics Chinese Academy of SciencesKunming 650223China Key Laboratory of Systems Biology Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China

Cell type-specific genomic regulation is driven by the binding of transcription factors(TFs)in accessible genomic ***,chromatin accessibility can be used to identify cis-regulatory elements and directly depict cellular ***-cell Assay for Transposase-Accessible Chromatin using sequencing(Single-cell ATAC-seq or scATAC-seq)has enabled genome-wide profiling of chromatin accessibility at single-cell resolution and can thus reveal epigenetic heterogeneity at cellular level[1].

关键词：数据稀疏性二值化扩散算法超大规模数据解析 CAN 生物信息学二部图

Sparse Deep Nonnegative Matrix Factorization

在线全文

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2020年第1期3卷 13-28页

作者： Zhenxing Guo shihua zhang the Academy of Mathematics and Systems Science Chinese Academy of Sciences(CAS)Beijing 100190China NCMIS CEMSRCSDSAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China the School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

Nonnegative Matrix Factorization(NMF)is a powerful technique to perform dimension reduction and pattern recognition through single-layer data representation ***,deep learning networks,with their carefully designed hierarchical structure,can combine hidden features to form more representative features for pattern *** this paper,we proposed sparse deep NMF models to analyze complex data for more accurate classification and better feature *** models are designed to learn localized features or generate more discriminative representations for samples in distinct classes by imposing L1-norm penalty on the columns of certain *** extending a one-layer model into a multilayer model with sparsity,we provided a hierarchical way to analyze big data and intuitively extract hidden features due to *** adopted the Nesterov’s accelerated gradient algorithm to accelerate the computing *** also analyzed the computing complexity of our frameworks to demonstrate their *** improve the performance of dealing with linearly inseparable data,we also considered to incorporate popular nonlinear functions into these frameworks and explored their *** applied our models using two benchmarking image datasets,and the results showed that our models can achieve competitive or better classification performance and produce intuitive interpretations compared with the typical NMF and competing multilayer models.

关键词： sparse Nonnegative Matrix Factorization(NMF) deep learning Nesterov’s accelerated gradient algorithm

Effect of aeration rate on composting of penicillin mycelial dreg

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2015年第11期27卷 172-178页

作者： Zhiqiang Chen shihua zhang Qinxue Wen Jun Zheng State Key Laboratory of Urban Water Resource and Environment School of Municipal and Environmental Engineering Harbin Institute of Technology School of Civil Engineering and Architecture Anhui University of Technology

Pilot scale experiments with forced aeration were conducted to estimate effects of aeration rates on the performance of composting penicillin mycelial dreg using sewage sludge as inoculation. Three aeration rates of 0.15, 0.50 and 0.90 L/（min·kg） organic matter（OM） were examined. The principal physicochemical parameters were monitored during the 32 day composting period. Results showed that the higher aeration rate of 0.90 L/（min·kg） did not corresponded to a longer thermophilic duration and higher rates of OM degradation;but the lower aeration rate of 0.15 L/（min·kg） did induce an accumulation of NH＋4-N contents due to the inhibition of nitrification. On the other hand, aeration rate has little effect on degradation of penicillin. The results show that the longest phase of thermophilic temperatures ≥ 55°C, the maximum NO-3-N content and seed germination, and the minimum C/N ratio were obtained with 0.50 L/（min·kg） OM. Therefore, aeration rates of0.50 L/（min·kg） OM can be recommended for composting penicillin mycelial dreg.

关键词： Aeration rate Composting Penicillin mycelial dreg Sewage sludge