检索结果-内蒙古大学图书馆

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Xiansen Chen Kun Xiao Lei Luo Yun Li Lirong Chen School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Guangdong Weichen Information Technology Co. Ltd Dongguan China

This paper proposes an anomaly detection algorithm based on Generative Adversarial Networks (GANs) for intrusion detection in Intelligent Connected Vehicles (ICVs). To address the imbalance between normal network traffic and attack traffic in vehicular networks, as well as the difficulty in collecting attack data, we train the neural network solely with normal traffic. We employ the Gini index to perform data dimensionality reduction, selecting 34 features with the highest purity of information and enhancing model training speed via normalization functions. Our algorithm combines the generative capabilities of GANs and the reconstructive power of autoencoders, detecting abnormal network data by learning the distribution of normal network data, thus eliminating the need to analyze packet payloads and safeguarding user privacy. We also develop a vehicular network traffic data collection scheme to collect network traffic data from ICVs. Experimental results indicate that our algorithm demonstrates high accuracy in detecting anomalous network traffic in ICVs, with an accuracy rate of 94.9%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Approaches for Reviewing Security-Related Aspects in Agile Requirements Specification of Web Applications

A Systematic Review of Approaches for Reviewing Security-Rel...

引用

computer Science, computer engineering, & Applied Computing (CSCE), Congress in

作者： Aqsa Munir Mohammed Assiri Saba Naveed Alam Muzna Khan Wasi Haider Butt Mamoona Humayun Department of Computer and Software Engineering College of Electrical and Mechanical Engineering (EME) National University of Science and Technology (NUST) Islamabad Pakistan Department of Computer Science College of Sciences and Humanities Aflaj Prince Sattam bin Abdulaziz University Saudi Arabia Department of Software Engineering College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Saudi Arabia Department of Information Systems College of Computer and Information Sciences Jouf University Al-Jouf Saudi Arabia

Imperfections in requirement specification can cause serious issues during software development life cycle. It might bring about inferior quality products due to missing attributes, for example, security. Specifically, Web Applications are considered as obvious target for getting significant information. Security aspects have gotten hard to manage in web applications because security requirements are not regularly seen appropriately and often details are missing which lead into ill-characterized security-related aspects. With the help of systemic literature review (SLR), we have identified 32 major research works which were published in period of year 2010 to 2020. We identified 38 security-related aspects of web applications and also 13 techniques and tools for security related aspects in agile requirement specification. We have also analyzed 22 challenges in reviewing security related aspects in agile development life cycle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Depth-Activated Saliency Detection for Uav Low-Altitude Outdoor Scenes

SSRN

引用

SSRN 2025年

作者： Zhu, Xian Zeng, Xiaoqin Cong, Yuhua Ma, Wei Liu, Qikai Wang, Qiuling Hohai University College of Computer and Software Engineering Nanjing China Nanjing University of Science and Technology Zijin College Nanjing China Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing China Nanjing Institute of Tourism and Hospitality Nanjing China

Saliency detection in UAV low-altitude outdoor scenes is critical for applications in environmental monitoring, disaster management, and autonomous navigation. However, challenges such as cluttered backgrounds, small or indistinct objects, and limited annotated datasets hinder the effectiveness of existing methods. To address these issues, we propose an innovative approach that integrates depth-activated feature modeling, multi-source pseudo-label generation, and uncertainty-aware optimization. The first component, the Depth-Activated Deformable Transformer (DADT), integrates global contextual modeling and depth-activated feature extraction to enhance foreground-background separation and improve saliency detection in complex environments. The second component employs a multi-source pseudo-label generation strategy, incorporating synthetic data and depth-guided refinement to enhance label diversity and improve small-object detection accuracy. Finally, an uncertainty-aware optimization strategy dynamically balances pseudo-label contributions, refining high-confidence regions while suppressing noise, thereby further improving boundary precision. Experimental results on UAV low-altitude datasets demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance and offering a robust solution for saliency detection in challenging outdoor scenarios. © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypes

TSEML: A task-specific embedding-based method for few-shot c...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ran Su Rui Shi Hui Cui Ping Xuan Chengyan Fang Xikang Feng Qiangguo Jin School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China School of Software Northwestern Polytechnical University Shaanxi China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University Guangdong China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Molecular subtyping of cancer is recognized as a critical and challenging upstream task for personalized therapy. Existing deep learning methods have achieved significant performance in this domain when abundant data samples are available. However, the acquisition of densely labeled samples for cancer molecular subtypes remains a significant challenge for conventional data-intensive deep learning approaches. In this work, we focus on the few-shot molecular subtype prediction problem in heterogeneous and small cancer datasets, aiming to enhance precise diagnosis and personalized treatment. We first construct a new few-shot dataset for cancer molecular subtype classification and auxiliary cancer classification, named TCGA Few-Shot, from existing publicly available datasets. To effectively leverage the relevant knowledge from both tasks, we introduce a task-specific embedding-based meta-learning framework (TSEML). TSEML leverages the synergistic strengths of a model-agnostic meta-learning (MAML) approach and a prototypical network (ProtoNet) to capture diverse and fine-grained features. Comparative experiments conducted on the TCGA FewShot dataset demonstrate that our TSEML framework achieves superior performance in addressing the problem of few-shot molecular subtype classification.

关键词： Metalearning Deep learning Knowledge engineering Medical treatment Benchmark testing Bioinformatics Cancer

来源：评论

学校读者我要写书评

暂无评论

Leaf Guard: Detecting the Diseases in Banana Leaf

Leaf Guard: Detecting the Diseases in Banana Leaf

引用

Advancements in Computing (ICAC), International Conference on

作者： K. Yathurshan S. Barathy G. Karini P. Sajitha Pradeep Abeygunawardhna Kaushalya Rajapakse Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka Faculty of Engineering| Electrical & Electronic Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

This research paper introduces “Leaf Guard,” a mobile app designed for disease detection and management in banana trees, specifically tailored for Sri Lanka's agricultural landscape. Through the amalgamation of image processing, deep learning, and customized chemical recommendations, this app proficiently identifies early-stage diseases, offering tailored remedies. Catering to farmers and agricultural experts, ‘Leaf Guard’ provides an intuitive tool, revolutionizing disease management and bolstering sustainable banana cultivation practices. By seamlessly integrating these cutting-edge technologies, this research significantly advances disease detection methods, paving the way for environmentally friendly and economical interventions. The study's findings not only enrich the realm of disease detection technology but also hold promise for future innovations, fostering sustainable approaches to enhance banana cultivation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global Stock Market Prediction Using Transformer-Based Deep Learning Techniques

Global Stock Market Prediction Using Transformer-Based Deep ...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： E. Gothai R. Thamilselvan P. Natesan K. Vignesh Department of Computer Technology Kongu Engineering College Perundurai Tamilnadu India Department of CSE Kongu Engineering College Perundurai Tamilnadu India Department of IT Kongu Engineering College Perundurai Tamilnadu India Department of CT MSc Software Systems Kongu Engineering College Perundurai Tamilnadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Deep learning approaches’ use in financial market forecasting has recently drawn a lot of attention from both investors and scholars. The Transformer framework, initially created for natural language processing, is used in this study to propose a revolutionary approach for forecasting the stock market indices of seven different economies: China, Canada, India, Japan, Russia, the United Kingdom, and the United States. The well-known Transformer architecture, which excels at capturing complex non-linear patterns, is modified to study the unique dynamics of each nation’s stock market. The model successfully determines the basic principles driving market behavior by using an encoder-decoder structure and a multi-head attention mechanism. The aforementioned indices are used in back-testing trials, which cover a variety of economic environments. The outcomes demonstrate that the Transformer performs better than conventional techniques, with Mean Squared Error (MSE) acting as a crucial evaluation criterion. Notably, the model shows promise for investors in these widely separated markets to receive excess profits. This study offers a thorough analysis of stock market forecasting, expanding its relevance to a wider global context. comprehension of how this strategy might adjust to various financial ecosystems is improved by the addition of seven unique economies. Future research may go more deeply into applications that are industry-specific and investigate potential extensions to additional international markets.

关键词： Deep learning Attention mechanisms Ecosystems computer architecture Transformers Natural language processing Stock markets Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning based Collaborative Computation Offloading in Vehicular Edge Networks

Multi-Agent Deep Reinforcement Learning based Collaborative ...

引用

International Conference on Distributed Computing Systems Workshop

作者： Hao Wang Huan Zhou Liang Zhao Xuxun Liu Victor C. M. Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology China Three Gorges University Yichang China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Recently, to cope with the long communication distance and unreliability of cloud-based computing architectures, mobile edge computing has emerged as a solution with great promise. This pattern extends cloud-based services towards the vehicular edge network and enables vehicular tasks to be offloaded to intermediate Roadside Units (RSUs) directly. However, as more and more tasks are offloaded to RSUs, the computation capacity of a single RSU becomes insufficient. Without edge cooperation, overall resource utilization and effectiveness are prone to being underutilized. To address this issue, this paper investigates a collaborative computation offloading scheme where adjacent RSUs can process offloaded tasks collaboratively rather than individually. First, we explore a vehicular edge network where the bilateral synergy between RSUs is leveraged. In particular, we incorporate a price-based incentive mechanism into the resource allocation process to promote overall resource utilization. Second, considering the time-varying system conditions and uncertain resource requirements, the optimization problem is approximated as a Markov Decision Process (MDP) and extended to a multi-agent system. Finally, we propose a Multi-agent Deep deterministic policy gradient-based computation Offloading and resource Allocation scheme (MDOA) to solve the corresponding problem. Simulation results show that the proposed MDOA can not only achieve a higher long-term utility of RSUs but also have better performance than other baselines in different scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lecture Centric Automated Distractor Generation for Post-Graduate software engineering Courses

A Lecture Centric Automated Distractor Generation for Post-G...

引用

Frontiers of Information technology (FIT)

作者： Rudeema Chughtai Farooque Azam Muhammad Waseem Anwar Wasi Haider But Muhammad Umar Farooq Department of Computer & Software Engineering College of Electrical & Mechanical Engineering (CEME) National University of Science & Technology (NUST) Islamabad Pakistan

ISBN: (纸本)9798350345940

Critical circumstances, natural disasters or pandemics like COVID 19 gave rise to the wide applicability of E-learning into education system. Efficient and fair online assessment is very important to utilize the inevitable benefits of E-learning.. In order to make it efficient, the trend of assessment has shifted from the subjective type to the objective type assessments which is mainly based on Multiple Choice Questions (MCQs), generation of MCQs is a tedious, tiresome and time consuming task. To cater this dire need, this study proposes an automated Multiple Choice Question (MCQ) generation by utilizing state of the art transformer based model T5 for the task of question generation and a lexicon based approach Sense2vec for the task of distractor generation. It also presented a domain specific lecture text based test data for performing evaluation on the task of domain specific lecture text based MCQ generation.

关键词： COVID-19 Electronic learning Pandemics Education Transformers Market research Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Neural Architecture Search Method with Multi-Dimensional Correlation Representation for Fault Diagnosis

A Neural Architecture Search Method with Multi-Dimensional C...

引用

Smart World Congress (SWC), IEEE

作者： Yumeng Liu Tingqi Wang Xu Zheng Ling Tian Hongan Wang Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

As deep learning has become more widely used for fault diagnosis, the shortcomings of model transferability and human model design costs are growing increasingly evident. The current work has tackled each of these two issues. Domain adaptation methods can provide transportability by mapping data to a common domain. For the consumption of manually constructed networks, Neural Architecture Search (NAS) is an intelligent solution that automatically select the ideal network structure. Unfortunately, there is little work to connect these two methodologies in fault diagnosis. Furthermore, these approaches are incapable in extracting internal correlations from instrumental signal data. In this paper, we propose a transferrable NAS fault diagnosis method, which maximizes savings in manual costs. We also integrate graph neural networks (GNN) in a stepwise manner into the NAS and domain adaptation to provide a multi-dimension correlation representation. Firstly, we structure the signal data into graph based on temporal relationships. Then, NAS designs automatically for selecting the optimal network structure and useful features. In NAS, graph encoder of GNN is used to establish internal relationships. Finally, domain adaptation provides transferability. At the same time, GNN’s weights in domain adaptation help to further mine data internal associations. We tested our method on two publicly available datasets and performed comparisons. The experimental results show the proposed method has superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of Using Continuous Integration (CI) and Continuous Delivery (CD) Deployment in DevOps to reduce the Gap between Developer and Operation

Effect of Using Continuous Integration (CI) and Continuous D...

引用

Information technology (ACIT)

作者： Abrar Mohammad Mowad Hamed Fawareh Mohammad A. Hassan Software Engineering Dept Faculty of Information Technology Zarqa University Computer Science Dept Faculty of Information Technology Zarqa University

ISBN: (数字)9798350320244

ISBN: (纸本)9798350320251

This paper focuses on how to use continuous integration (CI) and continuous Delivery (CD) methodology in DevOps to reduce the developer-operator gap. It also, shows how CI can be a CD bridge. The paper review DevOps and analyze strategies, methodologies, issues, and processes identified for the adoption and implementation of continuing practices. The result of our case studies shows the benefits, and advantages of using CI/CD in software development. Furthermore, this paper presents DevOps as a new model for reducing the gaps between development (Dev) and operations (ops). The Azure tool is used as DevOps CI/CD for the empowerment of continuous delivery of software to enable rapid and frequent releases, this enables rapid responses to changing customer requirements and thus it may be a decisive competitive advantage. This paper also measures the effectiveness of using CI/CD for reducing the time and effort in software development. We also, focus on the DevOps initiative to benefit of CI/CD and to effect of enhances flexibility in delivering the program with the expected quality on time to determine the areas that bridge the gap between Continuous Integration for Continuous Delivery. The methodology used in this paper by exploring and tracking a project developed by the company using the Azure software development tool. The experiment includes a project performance and evaluation.

关键词： Bridges Codes Source coding Pipelines Companies software Time measurement

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：