检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yunjie Cai Zeqi Zheng Shanling Nie Yue Guo Ruijie Zhang Hai Yang Department of Computer Science and Engineering East China University of Science and Technology Shanghai PR China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China School of Electronics and Computer Science University of Southampton UK

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

The grim situation of novel coronavirus pneumonia 2019 (COVID-19) and its terrible spreading speed have already constituted a severe risk to human life, so it is ultimately essential to rapidly and accurately diagnose for COVID-19 pneumonia. Based on this study’s 746 lung CT images, we propose Multi-MedVit, a novel auxiliary COVID-19 diagnosis framework based on the multi-input Transformer. We compare Multi-MedVit with state-of-the-art deep learning methods, such as CNN, VGG16, and ResNet50. Multi-MedVit outperformed the other methods on the benchmark dataset and proved that multiscale data input for data augmentation helped enhance model stability. Based on an interpretable analysis of the input and output of Multi-MedVit, we found that with the support of the training set data, the model has been possible to accurately focus on the lesion area for diagnosis of COVID-19 without expert annotations, which can provide initial references containing more potential information to doctors more precisely and fleetly.

关键词： COVID-19 Deep learning Training Computed tomography Pulmonary diseases Lung Transformers

来源：评论

学校读者我要写书评

暂无评论

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis and Treatment through Efficient and Meaningful Segmentation of 3D Medical Images

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Chenhang Wang Yujian Jin Jiayi Liang YuHan Yang Shanling Nie Yang Hai Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Faculty of Engineering The University of Sydney Sydney Australia

Hepatocellular Carcinoma (HCC) holds a record of high incidence and severe global harm. In tasks of liver cancer segmentation based on 3D medical images, the majority of methods have endeavored to enhance the 3D U-net by integrating the latest modules from the field of computer Vision (such as the transformer), often overlooking the distinct characteristics of liver components. We introduced a novel deep learning architecture, Modif-SegUnet, to circumvent this limitation. This architecture extends the U-net model by incorporating a 3D-modifiable attention module, thereby fostering a heightened focus on distinguishing between normal liver sections and lesions. Furthermore, Modif-SegUnet ingeniously amalgamates the 3D-modifiable attention module with the Modif-transformer block, enabling efficient capture of relevant and valuable full-text information in CT images that contain liver or tumor regions. We subjected the proposed Modif-SegUnet to evaluation on the Liver Tumor Segmentation benchmark dataset. Experimental outcomes indicate that our methodology surpasses state-of-the-art approaches in liver tumor segmentation, suggesting potential pathways for advancing the diagnosis and treatment of liver cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An empirical study on clustering approach combining fault prediction for test case prioritization

An empirical study on clustering approach combining fault pr...

引用

International Conference on computer and Information Science (ACIS)

作者： Lei Xiao Huaikou Miao Weiwei Zhuang Shaojun Chen School of Computer Engineering and Science Shanghai University Shanghai China School of Computer and Information Engineering Xiamen University of Technology Xiamen China Shanghai Key Laboratory of Computer Software Testing & Evaluating Shanghai China Meitu corporation Xiamen China

ISBN: (纸本)9781509055081

Using Clustering algorithm to improve the effectiveness of test case prioritization has been well recognized by many researchers. software fault prediction has been one of the active parts of software engineering, but to date, there are few test cases prioritization technique using fault prediction. We conjecture that if the code has a fault-proneness, the test cases covering the code will find fault with higher probability. In addition, most of the existing test cases prioritization techniques using clustering algorithm don't consider the number of clusters. Thus, in this paper, we design a test case prioritization based on clustering approach combining fault prediction. We consider the method to obtain the best number of clusters and the clustering prioritization based on the results of fault prediction. To investigate the effectiveness of our approach, we perform an empirical study using an object which contains test cases and faults. The experiment results indicate that our techniques can improve the effectiveness of test case prioritization.

关键词： Clustering algorithms Prediction algorithms Feature extraction software testing Complexity theory Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

A practical test method for scalability of the cluster

A practical test method for scalability of the cluster

引用

International Conference on New Trends in Information and Service Science, NISS

作者： Shiyan Wei Lizhi Cai Donglin Liu Zhenyu Liu Leilei Chen Pan Liu School of Information Science & Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Evaluating & Testing Shanghai China College of Computer Engineering and Science Shanghai Business School Shanghai China

Scalability is an important metric which is used to evaluate the scalability of the cluster system. Although, there have been a lot of scalability metrics, the research of scalability of the cluster system is very few. Common scalability evaluation methods are usually used to analyze the scalability of the algorithm. They can also be used to analyze the scalability of the cluster. These methods are not only theoretically feasible, but not suitable for specific testing. In order to eliminate this defect, a simple and efficient testing method is proposed. This method, in the paper, is mainly used for the actual test. Using the method given in the paper, we can measure the scalability performance of the cluster system easily and effectively.

关键词： cluster system performance evaluation metric scalability

来源：评论

学校读者我要写书评

暂无评论

An optimized method for generating cases of metamorphic testing

An optimized method for generating cases of metamorphic test...

引用

International Conference on New Trends in Information and Service Science, NISS

作者： Leilei Chen Lizhi Cai Jiang Liu Zhenyu Liu Shiyan Wei Pan Liu School of Information Science & Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory Computer Software Evaluating & Testing Shanghai China Shanghai Business School College of Computer Engineering and Science Shanghai China

The information contained in the successful test case has been fully tapped by metamorphic testing which can effectively solve the oracle problem of software testing. One of the key factors affecting the results of the metamorphic testing is the generation of test cases. In this paper, we propose a criterion called ECCEM (Equivalence-Class Coverage for Every Metamorphic Relation), which covers the test cases based on equivalence classes, the criterion can availably generate fewer test case sets with high detection rate. This paper also proposes a new measure of test cases - the Test Case Rate of utilization (TCR), which can comprehensively assess the generated test suite.

关键词： ECCEM criterion measurement criterion metamorphic testing test case rate of utilization

来源：评论

学校读者我要写书评

暂无评论

Verifiable reputation management scheme based on RSA threshold secret sharing in P2P networks

引用

Journal of Computational Information Systems 2011年第8期7卷 2770-2778页

作者： Sun, Hua Yu, Huiqun Yang, Nianhua Li, Li Department of Computer Science and Engineering East China University of Science and Technology Shanghai 200237 China School of Information Science and Engineering Xinjiang University Urumqi 830046 Xinjiang China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai 201112 China

In this paper we propose an innovative verifiable reputation management scheme based on RSA threshold secret sharing in P2P networks. This scheme employs RSA threshold secret sharing theory to realize management of the reputation information. The dealer divides reputation information into n secret shadows and distributes them to n different participants. The reputation information can be reconstructed by any t or more participants, and cannot be done by any fewer than t participants. The dealer also distributes the validation shadows corresponding to the secret shadows to the participants at the same time. Any unlawful participant arguing itself holding secret shadow or rightful participant offering false secret shadow will be recognized for its unable to break through RSA cryptography, so the scheme is secure and verifiable. © 2005 by Binary Information Press.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Personalized Recommendation Algorithm Based on Trust Relevancy Degree

A Novel Personalized Recommendation Algorithm Based on Trust...

引用

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

作者： Weimin Li Heng Zhu Xiaokang Zhou Shohei Shimizu Mingjun Xin Qun Jin School of Computer Engineering and Technology Shanghai University Shanghai China Faculty of Data Science Shiga University Hikone Japan Software Evaluating and Testing Shanghai Key Laboratory of Computer Shanghai China Faculty of Human Sciences Waseda University Japan

ISBN: (纸本)9781538675199

The rapid development of the Internet and ecommerce has brought a lot of convenience to people's life. Personalized recommendation technology provides users with services that they may be interested according to users' information such as personal characteristics and historical behaviors. The research of personalized recommendation has been a hot point of data mining and social networks. In this paper, we focus on resolving the problem of data sparsity based on users' rating data and social network information, introduce a set of new measures for social trust and propose a novel personalized recommendation algorithm based on matrix factorization combining trust relevancy. Our experiments were performed on the Dianping datasets. The results show that our algorithm outperforms traditional approaches in terms of accuracy and stability.

关键词： Social network services Collaboration Filtering Prediction algorithms Training Data science Internet

来源：评论

学校读者我要写书评

暂无评论

Accountable authority identity-based encryption with public traceability

Accountable authority identity-based encryption with public ...

引用

Cryptographers' Track at the RSA Conference 2013, CT-RSA 2013

作者： Lai, Junzuo Deng, Robert H. Zhao, Yunlei Weng, Jian School of Information Systems Singapore Management University Singapore Singapore Software School Fudan University China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences China Department of Computer Science Emergency Technology Research Center of Risk Evaluation and Prewarning on Public Network Security Jinan University China Shanghai Key Laboratory of Integrate Administration Technologies for Information Security China

ISBN: (纸本)9783642360947

At Crypto'07, Goyal introduced the notion of accountable authority identity-based encryption (A-IBE) in order to mitigate the inherent key escrow problem in identity-based encryption, and proposed two concrete constructions. In an A-IBE system, if the private key generator (PKG) distributes a decryption key or produces an unauthorized decryption box for a user maliciously, it runs the risk of being caught and sued in the court of law with the help of a tracing algorithm. Subsequent efforts focused on constructions of A-IBE schemes with enhanced security. In these A-IBE constructions, the tracing algorithm needs to take a user's decryption key as input. If the user lost his key or is deliberately uncooperative in court, then we cannot implicate the PKG or the user. An interesting open problem left by Goyal et al. at CCS'08 is to consider the possibility of tracing a decryption box using only a public tracing key, or with the assistance of a tracing authority. In this paper, we address this problem positively. We first extend the original model of A-IBE to accommodate public traceability, and then propose an A-IBE scheme in the new model. To the best of our knowledge, the proposed scheme is the first A-IBE with public traceability. © 2013 Springer-Verlag.

关键词： Accountable Authority Identity Based Encryption Public Traceability

来源：评论

学校读者我要写书评

暂无评论

Research on Quality Model for Quantum Simulator software

Research on Quality Model for Quantum Simulator Software

引用

software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter), ACIS International Winter Conference on

作者： Chao Wang Jingwei Chen JianXin Ge XueZhong Wu QianQian Qu Le Luo Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology Shanghai China QUDOOR Technologies Inc. Hefei China Software Engineering of Computer and Information Engineering College Shanghai Polytechnic University Shanghai China QUDOOR Technologies Inc. School of Physics and Astronomy Sun Yat-Sen University Zhuhai China

In recent years, the demand for arithmetic power from all walks of life is growing, especially the increasing popularity of AIGC, which makes people realize that huge technological progress cannot be made without the support of large arithmetic power. Quantum computing may bring a leap in computing power and become a ”trigger” and “catalyst” to accelerate the development of science and technology innovation, and its technical development trend and application prospects have become a hot issue of concern, and quantum simulators are a very important part of the development process. The development of quantum simulators is a very important part of the process. However, due to the lack of systematic evaluation theories and methods, it is difficult to quantify and analyze the quality of the increasing number of simulators on the market, which may hinder researchers from practicing their quantum algorithms objectively or developing quantum technologies. For these reasons, this paper proposes a quality model for quantum simulator software, which reflects the quality characteristics of simulators in seven aspects, such as functionality and performance efficiency, and selects some simulators for experimental validation of the proposed model to prove its rationality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CRCS: Learning Synergistic Cascade Correlation for Microscopic Cascade Prediction

CRCS: Learning Synergistic Cascade Correlation for Microscop...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Huacheng Li Chunhe Xia Tianbo Wang Haopeng Zhao Key Laboratory of Beijing Network Technology Beihang University Beijing China Key Laboratory of Beijing Network Technology Beijing China School of Cyber Science and Technology Beihang University Beijing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

Information diffusion prediction is the basis of many fundamental tasks, such as social recommendation and community detection. Currently, most researchers infer user correlation based on cascade records to predict future infected users. However, they only consider whether the infected users at each location are correctly predicted, ignoring the semantic differences between users who participate in the retweets of similar content and other users. This naturally leads to learning biased user features. In this paper, we compute semantic relevance between two different cascades (e.g., c m and c n ) based on user coincidence and develop the cascade correlation graph (CCG) to learn user features. Afterward, we devise a position-independent sequence similarity loss (SSL) function combined with an auxiliary predictor to optimize the user encoder. The above two methods make users participating in the relevant cascades more relevant than others. Experiments show that the two methods are effective, and the combination of them can improve performance more significantly.

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：