检索结果-内蒙古大学图书馆

MA-MFIF: When misaligned multi-focus Image fusion meets deep homography estimation

Multimedia Tools and Applications 2025年第12期84卷 10877-10898页

作者： Zhao, Baojun Luo, Fei Fuentes, Joel Ding, Weichao Gu, Chunhua School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Department of Computer Science and Information Technologies Universidad del Bio-Bio Chillán3780000 Chile

Multi-focus image fusion is a technique that combines multiple out-of-focus images to enhance the overall image quality. It has gained significant attention in recent years, thanks to the advancements in deep learning. However, one of the persistent challenges in this field is the processing of misaligned data, which can negatively impact the fusion results. To overcome this problem, a novel fusion framework with pre-registration is proposed for the fusion of misaligned multi-focus images. For pre-registration, content-aware deep homography estimation is used, which performs transfer learning on a real multi-focus image dataset to adapt to registration under defocused conditions. For fusion, a fusion module with dual-branch feature interaction is utilized to avoid invalid feature fusion and trained on real light field dataset to achieve better fusion performance. Qualitative and quantitative experimental results show that the proposed method has a 2-3 percentage point improvement in multiple evaluation metrics compared to existing advanced registration and fusion methods, and a maximum improvement of 4.83 percentage points in fusion performance when tested independently on the Lytro dataset. Additionally, We find that the value of the Qcv metric is greatly influenced by the alignment status of the input images, leading to its inability to reflect the fusion quality of aligned images. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

InsightCube: Accelerating Interactive Insight Discovery in Exploratory Data Analysis

InsightCube: Accelerating Interactive Insight Discovery in E...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Hanbing Zhang Yinan Jing Wei Zhang Zhenying He Kai Zhang X. Sean Wang Zhenqiang Chen Changchun Zhang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Transwarp Technology(Shanghai) Co. Ltd Shanghai China

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Exploratory data analysis (EDA) is usually human-in-the-loop and time tedious since identifying insights that show interesting characteristics and trends in data is laborious. Insight discovery helps users gain structured knowledge when understanding the dataset by categorizing interesting characteristics and trends into commonnesses and exceptions. However, existing insight discovery methods cannot interact with users when discovering insights. More importantly, the efficiency of insight discovery for these methods is low. In this paper, we propose a framework that supports and accelerates interactive insight discovery. We first divide the dataset into multiple subsets, and precompute the pattern snippets that include the distribution characteristics of subsets. Considering efficiency, we only pre-compute for subsets that cannot be further split. Then we design a novel cube structure, called InsightCube, to store precomputed pattern snippets. In order to accelerate insight discovery, we reuse the precomputed pattern snippets stored in InsightCube to infer the pattern of subsets that cannot be split. Furthermore, during insight discovery, we propose pruning strategies to accelerate the pattern inference for subsets that can be split. Experimental results on real-world datasets show that InsightCube improves the insight discovery efficiency by up to $2.5 \times$ compared to the state-of-the-art insight discovery method.

关键词： Data analysis Big Data Market research Human in the loop Optimization

来源：评论

学校读者我要写书评

暂无评论

Practical Strategies to Improve Test Efficiency

引用

Tsinghua Science and Technology 2007年第S1期12卷 250-254页

作者：丁志刚汪泓澄凌良合 Shanghai Development Center of Software Technology Shanghai Key Laboratory of Computer Software Evaluating and Testing

This paper introduces strategies to detect software bugs in earlier life cycle stage in order to improve test efficiency. Static analysis tool is one of the effective methods to reveal software bugs during software development. Three popular static analysis tools are introduced, two of which, PolySpace and Splint, are compared with each other by analyzing a set of test cases generatedd by the authors. PolySpace can reveal 60% bugs with 100% R/W ratio (ratio of real bugs and total warnings), while Splint reveal 73.3% bugs with 44% R/W ratio. And they are good at finding different categories of bugs. Two strategies are concluded to improve test efficiency, under the guideline that static analysis tools should be used in finding different categories of bugs according to their features. The first one aims at finding bugs as many as possible, while the second concentrates to reduce the average time on bug revelation. Experimental data shows the first strategy can find 100% bugs with 60% R/W ratio, the second one find 80% bugs with 66.7% R/W ratio. Experiment results prove that these two strategies can improve the test efficiency in both fault coverage and testing time.

关键词： static analysis PolySpace splint software bug

来源：评论

学校读者我要写书评

暂无评论

software Test Case Generation with Adequacy Analysis on Scenario-Based testing

引用

Journal of Donghua University(English Edition) 2011年第2期28卷 139-144页

作者：刘振宇杨根兴蔡立志 School of Computer Science Fudan University Shanghai Key Laboratory of Computer Software Evaluating and Testing

This paper studies the software scenario testing, which is commonly used in black-box testing at present. In the paper, the workflow model based on task-driven, which is very common in scenario testing, is analyzed. According to test adequacy criteria in scenario testing, the model is designed to correspond test cases in the light of logic block(LB). The final test cases that conform to the test adequacy criteria can be obtained through test case combination and test case reduction. In the last part of the paper, example of actual workflow is to design the efficient test case. Therefore the method is proved to be effective.

关键词： test case test adequacy system scenario software testing

来源：评论

学校读者我要写书评

暂无评论

FLSSM: A Federated Learning Storage Security Model with Homomorphic Encryption

arXiv

引用

arXiv 2025年

作者： Li, Yang Xia, Chunhe Li, Chang Li, Xiaojian Wang, Tianbo School of Computer Science and Engineering Beihang University Beijing100191 China Key Laboratory of Beijing Network Technology Beihang University Beijing100191 China Guangxi Collaborative Innovation Center Multi-Source Information Integration and Intelligent Processing Guangxi Normal University Guilin541004 China School of Computer Science and Technology Zhengzhou University of Light Industry Zhengzhou450000 China College of Computer Science and Information Technology Guangxi Normal University Guilin541004 China School of Cyber Science and Technology Beihang University Beijing100191 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China

Federated learning based on homomorphic encryption has received widespread attention due to its high security and enhanced protection of user data privacy. However, the characteristics of encrypted computation lead to three challenging problems: "computation-efficiency", "attack-tracing" and "contribution-assessment". The first refers to the efficiency of encrypted computation during model aggregation, the second refers to tracing malicious attacks in an encrypted state, and the third refers to the fairness of contribution assessment for local models after encryption. This paper proposes a federated learning storage security model with homomorphic encryption (FLSSM) to protect federated learning model privacy and address the three issues mentioned above. First, we utilize different nodes to aggregate local models in parallel, thereby improving encrypted models’ aggregation efficiency. Second, we introduce trusted supervise nodes to examine local models when the global model is attacked, enabling the tracing of malicious attacks under homomorphic encryption. Finally, we fairly reward local training nodes with encrypted local models based on trusted training time. Experiments on multiple real-world datasets show that our model significantly outperforms baseline models in terms of both efficiency and security metrics. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

PSO-Based Black-Box Lane Detection Adversarial Attack 2

PSO-Based Black-Box Lane Detection Adversarial Attack

引用

2nd International Conference on Artificial Intelligence, Human-computer Interaction and Robotics, AIHCIR 2023

作者： Fang, Hongtao Wang, Ruiyun Ma, Zeyu Chen, Mingang Shanghai Polytechnic University Shanghai Key Laboratory of Computer Software Testing and Evaluating shanghai China Shanghai Normal University Shanghai Key Laboratory of Computer Software Testing and Evaluating shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating shanghai China

ISBN: (纸本)9798350360363

Autonomous driving has achieved rapid development and promising performance by employing machine learning algorithms to automatically execute various maneuvers. Lane detection is one of the foremost tasks for vehicles, with a direct impact on driving decisions. Lane detection is a crucial component of autonomous driving, working in conjunction with lane centering control (LCC) and adaptive cruise control (ACC) to enable advanced driving assistance functions. At first thought, lane detection may seem immune to attacks. However, is this really the case? In this paper, we conduct experiments on lane detection modules and reveal their susceptibility to attacks exploiting hypersensitivity. Specifically, an excessively sensitive lane detector may mistake small markings for valid lanes, causing the vehicle to follow the wrong path. Through experiments, we demonstrate the vulnerability of lane detection models to adversarial attacks, even under black-box conditions where a change in one pixel can induce errors. We discuss the contrast between gradient-based and heuristic search-based optimization methods for black-box attacks and demonstrate the superiority of heuristic approaches for this task. Leveraging particle swarm optimization (PSO), we carry out lane detection attacks to address the research gap for black-box lane attacks. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Chemical reaction-inspired dual-population co-evolutionary algorithm for many-objective optimization

引用

Expert Systems with Applications 2025年 289卷

作者： Weichao Ding Mingshan Chen Wenbo Dong Fei Luo Chunhua Gu School of Information Science and Engineering East China University of Science and Technology 130 Meilong Road Shanghai 200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

Many-objective optimization problems (MaOPs) refer to the multi-objective problems with more than three conflicting objectives that need to be optimized simultaneously, which are prevalent but more challenging in scientific research and engineering applications. Existing many-objective optimization algorithms mainly make improvements in environmental selection strategies but rarely focus on the generation of offspring, and balancing convergence and diversity is still very difficult. To address these issues, this paper employs four basic collision operators in chemical reaction optimization to generate offspring and proposes a novel chemical reaction-inspired dual-population co-evolutionary algorithm (called DPCRO), which aims to further balance convergence and diversity to improve the quality of solutions in solving MaOPs. The proposed DPCRO consists of two independent and parallel populations, which are the uni-molecular evolutionary population (UE) and the bi-molecular evolutionary population (BE). UE adopts the uni-molecular collision operators for individual convergence optimization and provides convergence information for BE, while BE uses the bi-molecular collision operators for individual diversity optimization and provides diversity information for UE. These two populations work collaboratively to effectively balance their own convergence and diversity through collaborative interaction mechanisms. We conduct performance comparison experiments using multiple benchmark test problems with different characteristics. The experimental results show that the proposed algorithm not only enhances the performance of solving low-dimensional multi-objective problems, but also has strong competitiveness in addressing MaOPs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Web Application Test Based on Page Coverage Criteria

引用

Journal of Donghua University(English Edition) 2008年第3期25卷 291-296页

作者：蔡立志童维勤杨根兴 School of Computer Engineering and Science Shanghai University The Key Lab of Software Testing and Evaluating

software testing coverage criteria play an important role in the whole testing *** current coverage criteria for web applications are based on program or *** are not suitable for black-box test or intuitional to *** paper defines a kind of test criteria based on page coverage sequences only navigated by web application,including Page_Single,Page_Post,Page_Pre,Page_Seq2,Page_*** test criteria based on page coverage sequences made by interactions between web application and browser are being under consideration after *** order to avoid ambiguity of natural language,these coverage criteria are depicted using Z formal *** empirical result shows that the criteria complement traditional coverage and fault detection capability criteria.

关键词： web application coverage criteria browser interaction Z formal language

来源：评论

学校读者我要写书评

暂无评论

Application and method of quality management for small-size software project

Application and method of quality management for small-size ...

引用

IET International Conference on Information Science and Control Engineering 2012, ICISCE 2012

作者： Yang, Lin Liu, Zhenyu Cai, Lizhi Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

ISBN: (纸本)9781849196413

This paper studies the quality management method in small-size software project. In traditional method, test and evaluation are prerequisite methods to improve the project quality. The paper analyses characteristics and the disadvantages of project management in small-sized software project. Therefore, some quality activities should be considered in small-sized software project. The paper proposed lightweight quality planning, quality execution and quality monitoring activities in project management. Finally, the paper gives practical applications and proves method effective.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

evaluating software maintainability using fuzzy entropy theory

Evaluating software maintainability using fuzzy entropy theo...

引用

IEEE/International Association for computer and Information Science International Conference on computer and Information Science

作者： Cai, Lizhi Liu, Zhenyu Zhang, Juan Tong, Weiqin Yang, Genxing Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai 201112 China Shanghai Key Laboratory of Computer Software Evaluating and Testing China School of Computer Engineering and Science Shanghai University China

ISBN: (纸本)9780769541471

With the development of information technology, a large number of software products enter the maintenance phase. The maintainability of software products continues to attract people's attention. This paper proposes a new synthetic maintainability evaluation model basing on fuzzy entropy theory. In the model, the weight of different indexes is calculated by combining the entropy weight and expert weight. The entropy weight can be obtained through measuring the difference of membership degree of the index which reflects the consistency of the expert opinion. The evaluation result is more objective and reasonable. It provides a guideline to design a software product with high maintainability. © 2010 IEEE.

关键词： Entropy

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：