检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Zhichao Ding, Chuntao Wang, Shangguang Cheng, Ran Juefei-Xu, Felix Boddeti, Vishnu Naresh Sun Yat-sen University School of Software Engineering Zhuhai China Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing University of Posts and Telecommunications Key Laboratory of Networking and Switching Technology Beijing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China New York University New YorkNY United States Michigan State University Department of Computer Science and Engineering East LansingMI United States

ISBN: (纸本)9798350304855

Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interest from industry and academia. However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models. Existing approaches often require large floating-point operations (FLOPs) and substantial model parameter transmissions, presenting considerable challenges. To address these issues, this paper introduces a ground-station server-assisted framework. With the proposed framework, each layer of the CNN model contains only one learnable feature map (called the seed feature map) from which other feature maps are generated based on specific rules. The hyperparameters of these rules are randomly generated instead of being trained, thus enabling the generation of multiple feature maps from the seed feature map and significantly reducing FLOPs. Furthermore, since the random hyperparameters can be saved using a few random seeds, the ground station server assistance can be facilitated in updating the CNN model deployed on the LEO satellite. Experimental results on the ISPRS Vaihingen, ISPRS Potsdam, UAVid, and LoveDA datasets for semantic segmentation services demonstrate that the proposed framework outperforms existing state-of-the-art approaches. In particular, the SineFM-based model achieves a higher mIoU than the UNetFormer on the UAVid dataset, with 3.3 × fewer parameters and 2.2 × fewer FLOPs. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Predictive Caching of File System for Database Workload Management

Predictive Caching of File System for Database Workload Mana...

引用

AIML-Applications for engineering & Technology (ICAET), International Conference on

作者： Rohini Jadhav Veena Jadhav Prajakta Pawar Abhishek Kannaujia Abhishek Kumar Jayesh Gohil Department of Information Technology Bharati Vidyapeeth (Deemed to be University) College of Engineering Pune India Department of Computer Engineering Bharati Vidyapeeth (Deemed to be University) College of Engineering Pune India Department of Computer Engineering Bharati Vidyapeeth College of Engineering Lavale Pune India Principal Software Engineering Veritas

ISBN: (数字)9798350355611

ISBN: (纸本)9798350355628

The proactive caching technique known as “predictive caching” attempts to improve file system performance by anticipating and pre-fetching data that is likely to be requested in the future. Conventional caching strategies, such LRU (Least Recently Used) and LFU (Least Frequently Used), base their decision on which material to keep in the cache on historical access patterns. Although these methods work well in many situations, they could not completely take advantage of the temporal and geographical proximity of file system access patterns, which could result in less-than-ideal cache use. Utilizing machine learning algorithms, statistical analysis, or heuristics, predictive caching makes predictions about future access patterns based on past data, system status, file properties, or user activity. So we propose a predictive caching technique which reduce access latency and boost system performance by pre-fetching and storing pertinent data ahead of time in anticipation of incoming data accesses.

关键词： Machine learning algorithms File systems Statistical analysis Databases System performance Data systems Random forests

来源：评论

学校读者我要写书评

暂无评论

Which Combination of Test Metrics Can Predict Success of a software Project? A Case Study in a Year-Long Project Course

arXiv

引用

arXiv 2024年

作者： Filipovic, Marina Gilson, Fabian Computer Science and Software Engineering Te Whare Wānanga o Waitaha University of Canterbury Christchurch New Zealand

Context: Testing plays an important role in securing the success of a software development project. Various techniques of automated testing have been developed, including automated acceptance testing which represent the customer’s expectations where requirements can be translated into automated tests seamlessly. Prior studies have demonstrated beneficial effects of applying acceptance testing within a Behavioural-Driven Development method. Objectives: In this research, we investigate whether we can quantify the effects various types of testing have on functional suitability, i.e. the software conformance to users’ functional expectations. We explore which combination of software testing (automated and manual, including acceptance testing) should be applied to ensure the expected functional requirements are met, as well as whether the lack of testing during a development iteration causes a significant increase of effort spent fixing the project later on. Method: To answer those questions, we collected and analysed data from a year-long software engineering project course. Collected data per sprint included delivered story points, testing coverage metrics, and testing effort as per students work-logs. We combined manual observations and statistical methods, namely Linear Mixed-Effects Modelling, to evaluate the effects of coverage metrics as well as time effort on passed stories over 5 Scrum sprints. Results: The results suggest that a combination of a high code coverage for all of automated unit, acceptance, and manual testing has a significant impact on functional suitability. Similarly, but to a lower extent, front-end unit testing and manual testing can predict the success of a software delivery when taken independently. However, students time work-logs do not show statistically significant relationship between the time efforts and neither of the number of user stories delivered, nor the time spent fixing their software product in the following sprint. We observed

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Resource Management through Predictive Neural Networks and Reinforcement Learning

Enhancing Cloud Resource Management through Predictive Neura...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Lakshya Mohammad Ilham Hasan Khan Anish P Bajarange Software Engineering Delhi Technological University Delhi India Electrical Engineering Jamia Millia Islamia Delhi India Computer Science and Engineering Parul University Gujarat India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Prior strategies for scaling microservices encompassed various techniques, including diverse processing approaches and mathematical models. However, these methodologies often exhibited limitations in predictive accuracy and management complexity. This study employs Reinforcement Learning as an innovative alternative, particularly the Double Deep Q-Networks Algorithm. This approach autonomously monitors and evaluates essential scaling parameters, promptly triggering on-site actions when warranted. It adeptly balances the dual aspects of environment exploitation and exploration, optimizing computational resource usage while enhancing cost-effectiveness. Empirical evaluations substantiate the superiority of this approach in dynamically scaling cloud services with precision and resource optimization. By integrating LSTM and RNN predictive capabilities with Reinforcement Learning, this research contributes to efficient cloud resource management, a vital facet of contemporary cloud computing paradigms.

关键词： Cloud computing Neural networks Memory management Microservice architectures Reinforcement learning Prediction algorithms Mathematical models Resource management Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Semantically Robust Unsupervised Image Translation for Paired Remote Sensing Images

arXiv

引用

arXiv 2025年

作者： Fang, Sheng Li, Kaiyu Li, Zhe Zhao, Jianli Zhang, Xingli College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China School of Software Engineering Xi’an Jiaotong University Xi’an710049 China

Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed instead of multimodal outputs. In response to these problems, this paper proposes a new method, SRUIT (Semantically Robust Unsupervised Image-to-image Translation), which ensures semantically robust translation and produces deterministic output. Inspired by previous works, the method explores the underlying characteristics of bi-temporal Remote Sensing images and designs the corresponding networks. Firstly, we assume that bi-temporal Remote Sensing images share the same latent space, for they are always acquired from the same land location. So SRUIT makes the generators share their high-level layers, and this constraint will compel two domain mapping to fall into the same latent space. Secondly, considering land covers of bi-temporal images could evolve into each other, SRUIT exploits the cross-cycle-consistent adversarial networks to translate from one to the other and recover them. Experimental results show that constraints of sharing weights and cross-cycle consistency enable translated images with both good perceptual image quality and semantic preservation for significant differences. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Load Balancing Algorithm for Stable Pushing of Docker Images in Nginx 6

A Dynamic Load Balancing Algorithm for Stable Pushing of Doc...

引用

6th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2024

作者： Xi, Hajie Hu, Song Zhang, He Zhang, Shuang Weng, Jingnong Huang, Jian School of Computer Science and Engineering Beihang University Beijing China Research Institute of Highway Ministry of Transport State Key Lab of Transportation System Beijing China Transportation Comprehensive Enforcement Corps Beijing China School of Software Beihang University Beijing China

ISBN: (纸本)9798331541798

With the rapid development of artificial intelligence, a wide variety of deep learning models have emerged across various fields. Nevertheless, the quality of these models varies significantly, making the effective evaluation of model performance a pressing issue. In some open data competitions, remote evaluation based on Docker images has increasingly become a novel and reliable approach, providing a consistent environment to ensure the fairness of model evaluations. However, it imposes high demands on hardware resources, typically requiring dedicated resources for each participant to serve as Docker Registries for the pushing and management of Docker images. In this paper, we extend the load balancing module of the Nginx server by integrating Lua scripts and propose a Cache-based Dynamic Smooth Weighted Round-robin (CDSWRR) algorithm to optimize the pushing process of Docker images. By constructing a unified load balancing entry, the proposed approach simplifies the deployment of Docker Registry clusters. Experiments show that compared to weighted round-robin and IP hash algorithms of Nginx, the CDSWRR algorithm is able to ensure stable pushing of Docker images and reduce both response error rate and response time. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Script Module with Recording and Playback Function in CAE software

Design and Implementation of Script Module with Recording an...

引用

2023 International Conference on computer, Artificial Intelligence, and Control engineering, CAICE 2023

作者： Wang, Jingyu Fu, Chengjie Wang, Tiejun Wang, Yuntao Chen, Liangzhong School of Aeronautics and Astronautics Sichuan University Chengdu China Tianfu Engineering-Oriented Numerical Simulation & Software Innovation Center Sichuan University Chengdu China School of Computer Science Chengdu University of Information Technology Chengdu China College of Computer Science Sichuan University Chengdu China

ISBN: (纸本)9781510665040

In large-scale engineering experiments, such as hydrodynamics and aerodynamics experiments, computer aided software (CAE) is always used to manage a large number of parameters and experimental data to simulate the physical field through finite element analysis. To improve work efficiency, one of the most practical methods at present is to record user operations in the CAE software to script files with domain specific language (DSL), such as Python, and replay those script files to reproduce user operations. In this paper, a common script module ScriptEngine supporting the recording and playback function is introduced, and it can be embedded into any CAE software to automatically complete grid division, flow field calculation, pre-processing and post-processing by running the scripts. Furthermore, a demo program embedding ScriptEngine into an opensource FastCAE was developed and the results show that running the scripts recorded by ScriptEngine could obtain the same results as the user operations and ScriptEngine can be used as a common script module in any CAE software and other desktop software which needs the recording and playback function. © 2023 SPIE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection of Selfish Mining Attacks on Large-Scale Blockchain Networks

Efficient Detection of Selfish Mining Attacks on Large-Scale...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Fatemeh Erfan Martine Bellaiche Talal Halabi Department of Computer and Software Engineering Polytechnique Montréal Montréal QC Canada Department of Computer Science Université Laval Québec QC Canada

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Selfish mining attacks pose a significant and ongoing security threat to blockchain networks, including major platforms like Bitcoin and Ethereum. Understanding and effectively countering these attacks is crucial for maintaining the stability and integrity of these networks. This attack strategy involves a miner or a group of miners seeking to gain an advantage by delaying the immediate broadcasting of their mined blocks to the network. The selfish miners potentially mine more blocks in secret, increasing their rewards at the expense of other miners and the stability of the blockchain. Research has mainly focused on detecting this attack by analyzing data related to blocks and forks. This paper presents a new approach to efficiently detect selfish mining attacks in large-scale networks by analyzing various network indicators. To achieve this, we simulate a Bitcoin network and generate a dataset consisting of several features of individual miners and the overall network. We select the most reliable indicators by analyzing network features and reducing feature dimensions. Then, we employ random forest classification (RFC) to classify benign and selfish network behaviors. This approach not only achieves enhanced accuracy (99.96%), surpassing state-of-the-art methods utilizing deep learning, but also significantly reduces computational, storage, and temporal complexities. In doing so, it fortifies blockchain security more efficiently and accurately.

关键词： Deep learning Accuracy Computational modeling Bitcoin software quality Stability analysis software reliability Security Data mining Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion for Enhanced Parkinson's Disease Screening: Integrating Brain MRI, Hand Drawing, Facial Expressions, and Voice Analysis 5

Multimodal Fusion for Enhanced Parkinson's Disease Screening...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Warnakulasuriya, Naveen De Silva, Shalinika Madushika, Janani Gamage, Sadali Jayawardena, Sanath Karunasena, Anuradha Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Parkinson's disease (PD) profoundly impacts millions in Sri Lanka, emphasizing the importance of early detection for better patient outcomes. We introduce 'NeuraTrace PD,' an innovative application for early PD screening, combining brain MRI, hand-drawn image analysis, facial expression assessment, and voice analysis. For brain MRI analysis, we employed a Graph Convolutional Network (GCN), achieving an impressive accuracy of 91% and identifying distinct graph connectivity patterns using graph theory. We also use a deep Convolutional Neural Network (CNN) to reach 90% accuracy in analyzing hand-drawn images, while optimizing image resolution for efficiency and information retention. Facial expression analysis is a vital component, leveraging CNN and Constrained Local Models (CLM) to accurately extract Facial Action Units (FAUs), which contribute to a remarkable 95% accuracy using the XGBoost machine learning model. We introduce a Machine Learning (ML) algorithm and advanced signal processing to enhance voice feature analysis, offering a thorough understanding and classification of PD patients. It reaches 99% accuracy. In summary, our approach holds significant promise for advancing early PD diagnosis, ultimately improving the quality of life for those affected by this challenging condition. © 2023 IEEE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Intelligent environments with entangled quality properties

引用

Journal of Reliable Intelligent Environments 2022年第3期8卷 223-226页

作者： Rodríguez-Domínguez, Carlos Santokhee, Aditya Hornos, Miguel J. Research Group Software Engineering Department Higher Technical School of Computer and Telecommunication Engineering Campus de Aynadamar University of Granada Granada18071 Spain School of Digital Technologies Middlesex University Mauritius Flic en Flac Mauritius

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：