检索结果-内蒙古大学图书馆

2009 International Conference on Computational Intelligence and software Engineering, CiSE 2009

作者： Dong, Lanfang Wu, Yuan Zhou, Shanhai Anhui Province Key Lab. of Software in Computing and Communication College of Computer Science and Technology USTC Hefei China College of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781424445073

By researching Voronoi diagram, parallel algorithm, and divide-and-conquer method, we present a special data structure(change doubly-connected list little) for Voronoi diagram generation in parallel. In this paper we also present two proposal, they are one processor gradually to merge and 22-merger on the parallel machine, the experiment results show that the present algorithm runs faster than the serial program. By analyzing the various results, we should choose the most suitable number of processors according to the point set scale. At last, we can conclude that gradually merger with one processor is better proposal for Voronoi diagram parallel generation. ©2009 IEEE.

关键词： Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

NURBS model for chaotic time series

NURBS model for chaotic time series

引用

2011 3rd International Conference on Computer Research and Development, ICCRD 2011

作者： Shao, Chenxi Xiao, Lipeng Department of Computer Science and Technology University of Science and Technology of China Hefei China Department of Modern Physics Nonlinear Science Center University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Software in Computing and Communication Hefei China

ISBN: (纸本)9781612848372

NURBS method is extensively used in the field of Geometric Modeling. Since the original NURBS method does not have time factor, it can not display the huge advantage in the dynamics field. In this article, inspired by the segmented nature of basis functions, we propose a time factor method which can be directly applied in reconstruction of missing data, with remarkable performance in matching the original data. This work does not only give an expression of chaotic time series, but also highlights a possible way for the challenge in reconstruction of missing data. © 2011 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Generating an Approximately Optimal Detector Set by Evolving Random Seeds

Generating an Approximately Optimal Detector Set by Evolving...

引用

IEEE International Symposium on Dependable, Autonomic and Secure computing (DASC)

作者： Jie Zhang Wenjian Luo Baoliang Xu Anhui Key Laboratory of Software in Computing and Communication University of Science and Technology Hefei Anhui China University of Science and Technology of China Hefei Anhui CN

The detector generation algorithm is the core of a negative selection algorithm (NSA). In most previous work, the NSAs generate the detector set randomly, which cannot guarantee to obtain an efficient detector set. To generate an approximately optimal detector set, in this paper, a novel detector generation algorithm for the real-valued negative selection algorithm (RNSA) is proposed. The proposed algorithm, named as the EvoSeedRNSA, adopts a genetic algorithm to evolve the random seeds to obtain an optimized detector set. The experimental results demonstrate that the EvoSeedRNSA has a better performance.

关键词： Detectors Genetic algorithms Shape software algorithms Computer science Laboratories Immune system Artificial immune systems Intrusion detection State-space methods

来源：评论

学校读者我要写书评

暂无评论

Adaptive Algorithm Based on Reversible Data Hiding Method for JPEG Images 7th

Adaptive Algorithm Based on Reversible Data Hiding Method fo...

引用

7th EAI International Conference on Cloud computing, CloudComp 2016 and 1st EAI International Conference on Security and Privacy in New computing Environments, SPNCE 2016

作者： Zhang, Hao Yin, Zhaoxia Zhang, Xinpeng Chen, Jianpeng Wang, Ruonan Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China School of Communication and Information Engineering Shanghai University Shanghai200072 China

ISBN: (纸本)9783319696041

This paper presents an adaptive reversible information hiding algorithm that can maintain thee JPEG file sizes by using RLC (Run Length Coding) AC coefficient coded for embedding, the key point is to choose the appropriate number of participation to hide information. By calculating the maximum storage capacity of the image at different system, select the appropriate RLC pairs to rotate and embed data. In the extraction stage, by calculating the sequence of the original RLC pairs status, then consult the mapping relationships between the current sequence and the original RLC pairs sequence, we extract the secret message and recover the original image. Test results proved that the proposed method can improve the rate-distortion performance to some extent. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Complete separable reversible data hiding in encrypted image 1st

Complete separable reversible data hiding in encrypted image

引用

1st International Conference on Cloud computing and Security, ICCCS 2015

作者： Zhaoxia, Yin Huabin, Wang Haifeng, Zhao Bin, Luo Xinpeng, Zhang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China School of Communication and Information Engineering Shanghai University Shanghai200072 China

ISBN: (纸本)9783319270500

Reversible data hiding in encrypted image (RDHEI) is an emerging technology since it has good potential for practical applications such as encrypted image authentication, content owner identification and privacy protection. But there is one key problem of many existing published works, that the embedded data only can be extracted either before or after image decryption. In this paper, a complete separable reversible data hiding scheme in encrypted images is proposed. Additional data can be embedded into a cipher image which is encrypted by RC4 and can be extracted error-free both from the cipher domain and the plaintext domain. Moreover, the proposed method is simpler to calculate, while offering better performance. The results demonstrate that larger payload, better image quality, and error-free data extraction as well as image recovery are achieved. © Springer International Publishing Switzerland 2015.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

An improved lossless data hiding scheme in JPEG bitstream by VLC mapping 1

引用

13th International Conference on Mobile Ad-hoc and Sensor Networks, MSN 2017

作者： Du, Yang Yin, Zhaoxia Zhang, Xinpeng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China School of Communication and Information Engineering Shanghai University Shanghai200072 China

ISBN: (数字)9789811088902

ISBN: (纸本)9789811088896

This paper proposed a lossless data hiding scheme by variable length code (VLC) mapping, which focused on embedding additional data into JPEG bitstream. The entropy-coded data in JPEG bitstream consists of a sequence of VLCs and the appended bits. Not all VLCs defined in the JPEG file header are used in the entropy-coded data and the replacement of unused-VLCs do nothing with image decompression. Hence, additional data can be embedded by mapping the unused-VLCs to the used-VLCs. To obtain higher embedding capacity, we improved the mapping rules in this paper. Employing the proposed mapping scheme, larger embedding capacity and no image distortion are both achieved while the filesize of JPEG is preserved after data embedding. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Tumor type classification and candidate cancer-specific biomarkers discovery via semi-supervised learning

引用

Biophysics Reports 2023年第2期9卷 57-66页

作者： Peng Chen Zhenlei Li Zhaolin Hong Haoran Zheng Rong Zeng School of Computer Science and Technology University of Science and Technology of China Anhui Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Department of Systems Biology University of Science and Technology of China CAS Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences School of Life Science and Technology ShanghaiTech University

Identifying cancer-related differentially expressed genes provides significant information for diagnosing tumors, predicting prognoses, and effective treatments. Recently, deep learning methods have been used to perform gene differential expression analysis using microarray-based high-throughput gene profiling and have achieved good results. In this study, we proposed a new robust multiple-datasetsbased semi-supervised learning model, MSSL, to perform tumor type classification and candidate cancer-specific biomarkers discovery across multiple tumor types and multiple datasets, which addressed the following long-lasting obstacles:(1) the data volume of the existing single dataset is not enough to fully exert the advantages of deep learning;(2) a large number of datasets from different research institutions cannot be effectively used due to inconsistent internal variances and low quality;(3) relatively uncommon cancers have limited effects on deep learning methods. In our article, we applied MSSL to The Cancer Genome Atlas(TCGA) and the Gene Expression Comprehensive Database(GEO) pan-cancer normalized-level3 RNA-seq data and got 97.6% final classification accuracy, which had a significant performance leap compared with previous approaches. Finally, we got the ranking of the importance of the corresponding genes for each cancer type based on classification results and validated that the top genes selected in this way were biologically meaningful for corresponding tumors and some of them had been used as biomarkers, which showed the efficacy of our method.

关键词： Deep learning Tumor type classification Cancer-specific biomarkers MSSL

来源：评论

学校读者我要写书评

暂无评论

Error-minimization approach to reduce protease bias 2

Error-minimization approach to reduce protease bias

引用

2nd International Conference on Biological Information and Biomedical Engineering, BIBE 2018

作者： Chen, Chong Zheng, Haoran School of Computer Science and Technology University of Science and Technology of China Hefei China Anhui Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei China Department of Systems Biology University of Science and Technology of China Hefei China

ISBN: (纸本)9783800747276

The main goal in proteomics is to describe the proteome in a comprehensive and accurate way, and enzymolysis is a key step in the process of large-scale proteomics experiments. For the same protein samples, using different proteases may introduce a strong bias into protein analysis results. This situation will make proteomics experiments irreproducible and will have a serious impact on the experimental results. To reduce this protease bias, we present EMQ (Error-Minimization-based Quantification for Protein), an approach based on error minimization. In contrast to the existing method, our model includes information on shared peptides, which are ubiquitous in mass spectrometric datasets. The abundance of shared peptides will be assigned to related proteins accurately, thereby determining the protein abundance. Based on this feature, we used the proposed model with several datasets, and compared its performance with the other. Finally, our model is shown to have better performance than other approach (average Pearson correlation of ~0.83 obtained by EMQ, while ~0.63 by other model). © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

An adaptive strategy for updating the memory in Evolutionary Algorithms for dynamic optimization

An adaptive strategy for updating the memory in Evolutionary...

引用

IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments (CIDUE)

作者： Tao Zhu Wenjian Luo Zhifang Li Anhui Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology Hefei Anhui China University of Science and Technology of China Hefei Anhui CN

The memory scheme is one of the most widely employed techniques in Evolutionary Algorithms for solving dynamic optimization problems. The updating strategy is a key concern for the memory scheme. Unfortunately, the existent memory updating strategies neglect the characteristics of the memory updating behaviors, and sometimes this could lead results against the original intention. In this paper, a novel updating strategy is proposed, which can adaptively update the memory according to the characteristics of the memory updating behaviors. Experiments are carried out in different kinds of dynamic environments, and the experimental results show that the proposed strategy is better than the traditional strategies.

关键词： Memory management Heuristic algorithms Optimization Generators Evolutionary computation Associative memory Redundancy

来源：评论

学校读者我要写书评

暂无评论

AN APPROACH BASED ON TSA-TREE FOR ACCURATE TIME SERIES CLASSIFICATION

AN APPROACH BASED ON TSA-TREE FOR ACCURATE TIME SERIES CLASS...

引用

2012 IEEE 2nd International Conference on Cloud computing and Intelligence Systems

作者： Xiaoxu He Chenxi Shao School of Computer Science and Technology University of Science and Technology of China Anhui Province Key Laboratory of Software in Computing and Communication

In order to improve the performance of time series classification, we introduce a new approach of time series classification. The first step of the approach is to design a feature exaction model based on Trend and Surprise Abstraction tree （TSA-tree）. The second step of the approach is to combine the exacted global feature and 1 nearest neighbor to classify time series. The proposed approach is compared with a number of known classifiers by experiments in artificial and real-world data sets. The experimental results show it can reduce the error rates of time series classification, so it is highly competitive with previous approaches.

关键词： Feature exaction dimension reduction classification TSA-tree

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：