检索结果-内蒙古大学图书馆

Behaviour-diverse automatic penetration testing:a coverage-based deep reinforcement learning approach

Frontiers of computer science 2025年第3期19卷 15-24页

作者： Yizhou YANG Longde CHEN sha LIU Lanning WANG Haohuan FU Xin LIU Zuoning CHEN Zhongguancun Laboratory Beijing 100081China Zhejiang Lab Hangzhou 311121China National Research Centre of Parallel Computer Engineering and Technology Wuxi 214000China Faculty of Geographical Science Beijing Normal UniversityBeijing 100875China Department of Earth System Science Tsinghua UniversityBeijing 100084China

Reinforcement learning(RL)is gaining importance in automating penetration testing as it reduces human effort and increases ***,given the rapidly expanding scale of modern network infrastructure,the limited testing scale and monotonous strategies of existing RLbased automated penetration testing methods make them less effective in practical *** this paper,we present CLAP(Coverage-based Reinforcement learning to Automate Penetration Testing),an RL penetration testing agent that provides comprehensive network security assessments with diverse adversary testing behaviours on a massive *** employs a novel neural network,namely the coverage mechanism,to address the enormous and growing action spaces in large *** also utilizes a Chebyshev decomposition critic to identify various adversary strategies and strike a balance between *** results across various scenarios demonstrate that CLAP outperforms state-of-the-art methods,by further reducing attack operations by nearly 35%.CLAP also provides enhanced training efficiency and stability and can effectively perform pen-testing over large-scale networks with up to 500 ***,the proposed agent is also able to discover pareto-dominant strategies that are both diverse and effective in achieving multiple objectives.

关键词： network security penetration testing reinforcement learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of twelve transfer learning models for the prediction and crack detection in concrete dams,based on borehole images

引用

Frontiers of structural and Civil Engineering 2024年第10期18卷 1507-1523页

作者： Umer sadiq KHAN Muhammad IsHFAQUE saif Ur Rehman KHAN Fang Xu Lerui CHEN Yi LEI School of Computer and Information Science Hubei Engineering UniversityXiaogan 432000China Institute for AI Industrial Technology Research Hubei Engineering UniversityXiaogan 432000China College of Water Conservancy and Hydropower Engineering Hohai UniversityNanjing 210098China School of Computer Science and Engineering Central South UniversityChangsha 410083China College of Aviation Zhongyuan University of TechnologyZhengzhou 451191China School of Civil Engineering Central South UniversityChangsha 410083China

Disaster-resilient dams require accurate crack detection,but machine learning methods cannot capture dam structural reaction temporal patterns and *** research uses deep learning,convolutional neural networks,and transfer learning to improve dam crack *** deep-learning models are trained on 192 crack *** research aims to provide up-to-date detecting techniques to solve dam crack *** finding shows that the EfficientNetB0 model performed better than others in classifying borehole concrete crack surface tiles and normal(undamaged)surface tiles with 91%*** study’s pre-trained designs help to identify and to determine the specific locations of cracks.

关键词： concrete dam borehole closed-circuit television deep learning models crack detection water resources management management

来源：评论

学校读者我要写书评

暂无评论

research on concrete structure defect repair based on three-dimensional printing

引用

Frontiers of structural and Civil Engineering 2024年第5期18卷 731-742页

作者： Yang GU Wei LI Xupeng YAO Guangjun LIU School of Mechanical Engineering Tongji UniversityShanghai 201804China College of Civil Engineering Tongji UniversityShanghai 200092China Shanghai Engineering Research Center for Safety Intelligent Control of Building Machinery Shanghai 200032China

Quality assurance and maintenance play a crucial role in engineering construction,as they have a significant impact on project *** common issue in concrete structures is the presence of *** enhance the automation level of concrete defect repairs,this study proposes a computer vision-based robotic system,which is based on three-dimensional(3D)printing technology to repair *** system integrates multiple sensors such as light detection and ranging(LiDAR)and *** is utilized to model concrete pipelines and obtain geometric parameters regarding their ***,a convolutional neural network(CNN)is employed with a depth camera to locate defects in concrete ***,a method for coordinate transformation is presented to convert the obtained coordinates into executable ones for a robotic ***,the feasibility of this concrete defect repair method is validated through simulation and experiments.

关键词： concrete defect detection 3D printing deep learning point cloud data

来源：评论

学校读者我要写书评

暂无评论

Fine extraction of multi-crop planting area based on deep learning with sentinel- 2 time-series data

引用

Environmental science and Pollution research 2025年第19期32卷 11931-11949页

作者： Jiang, Jingmin Zhang, Jiahua Wang, Xue Zhang, shichao Kong, Delong Wang, Xiaopeng Ali, shawkat Ullah, Hidayat Space Information and Big Earth Data Research Center School of Computer Science and Technology Qingdao University Qingdao266071 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Accurate and timely access to the spatial distribution of crops is crucial for sustainable agricultural development and food security. However, extracting multi-crop areas based on high-resolution time-series data and deep learning still faces challenges. Therefore, this study aims to provide an effective model for multi-crop classification using high-resolution remote sensing time-series data. We designed two deep learning models based on convolutional neural network-long short-term memory (CNN-LsTM) and bidirectional long short-term memory (Bi-LsTM). The monthly synthetic time series of the normalized difference vegetation index (NDVI) from sentinel-2 data will be used as input features to extract the multi-crop planting area in shandong province’s northwestern, southwestern, and eastern regions. The results showed that deep learning models achieved higher accuracy compared to the random forest (RF) and extreme gradient boosting (XGBoost) models, with CNN-LsTM achieving the highest overall accuracy of 96.48%. At the county level, the coefficients of determination (R2) for the CNN-LsTM model were 0.91 for wheat, 0.88 for maize, and 0.73 for spring cotton. This study demonstrates that the CNN-LsTM model combined with monthly synthetic time-series NDVI provides a feasible approach for accurately mapping high-resolution multi-crop planting areas and also contributes significantly to decision support and resource management in agricultural production. © The Author(s), under exclusive licence to springer-Verlag GmbH Germany, part of springer Nature 2025.

关键词： Deep learning High-resolution Monthly synthetic time-series NDVI Multi-crop classification Remote sensing sentinel- 2

来源：评论

学校读者我要写书评

暂无评论

Designing Technology-based e-learning for Adult Education in the Philippine Agriculture sector: The PCAARRD Advanced learning Management system Experience

引用

sN computer science 2024年第5期5卷 620页

作者： Asilo, Eriza C. Laranas, Jesselle s. Decena, Fezoil Luz C. Institution Development Division Philippine Council for Agriculture Aquatic and Natural Resources Research and Development Laguna Los Banos Philippines

The pandemic has tested the resilience of organizations and consequently hastened the digital acceleration in many organizations. With the Philippine council for Agriculture, Forestry and Natural Resources research and Development (DOsT-PCAARRD), an e-learning modality was developed to disseminate relevant technologies that have been generated through its various research and development programs and projects. In developing the e-learning platform, the project adopted the ADDIE model of instructional design. This paper describes the process undertaken as PCAARRD transitioned from traditional classroom, face-to-face courses into an e-learning platform, adopting the ADDIE framework of instructional design and using Moodle as a learning management system. It also outlines the challenges and lessons learned from digitization, as well as recommendations and future directions for the program. Following the PCAARRD experience, the ADDIE model was an effective framework to use in e-learning development, primarily based on formative and summative evaluations. The success of e-learning can be considered a factor of various elements, including the learner, resource persons, the training course content, as well as the social interactions and ease of use of technology. The adoption of e-learning as a human capital investment continues to increase, which merits the evaluation of different organizational e-learning programs to introduce new insights or approaches in the delivery of adult learning for agriculture sector research and development. © The Author(s), under exclusive licence to springer Nature singapore Pte Ltd. 2024.

关键词： Adult education Agriculture research and development e-learning learning management system Online learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning Algorithm for Person Re-Identification based on Dual Network Architecture

引用

computers, Materials & Continua 2025年第5期83卷 2889-2905页

作者： Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen College of Information Engineering Harbin UniversityHarbin150086China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin UniversityHarbin150086China College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China Heilongjiang Forestry Intelligent Equipment Engineering Research Center Northeast Forestry UniversityHarbin150040China Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning *** this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal *** proposed approach can be classified into two main ***,the spatial attention feature map is formed by aggregating features in the spatial ***,the same operation is carried out on the channel dimension to formchannel attention ***,the receptive field size is adjusted adaptively tomitigate the changing person posture ***,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution *** experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading *** proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MsMT17,and DukeMTMC-reID ***,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 ***,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关键词： Person reidentification ReID computer vision self-attention spatial-temporal information

来源：评论

学校读者我要写书评

暂无评论

CollabGraph: A Graph-based Collaborative search summary Visualization

引用

IEEE TRANsACTIONs ON learning TECHNOLOGIEs 2023年第3期16卷 382-398页

作者： Ilkou, Eleni Tolmachova, Tetiana Fisichella, Marco Taibi, Davide Leibniz Univ Hannover L3S Res Ctr D-30167 Hannover Germany Natl Res Council Italy Inst Educ Technol I-90146 Palermo Italy

Currently, the search history in search engines is presented in a list view of some combination of enumerated results by title, URL, or search query. However, this classical list view is not ideal in collaborative search environments as it does not always assist users in understanding collaborators' search history results and the project's status. We present CollabGraph, a system for graph-based summary visualization in collaborative search learning environments. Our system differentiates from existing solutions by visualizing the summary of the collaboration results in a graph and having its core personal knowledge graphs (PKGs) for each user. Our research questions concentrate around the CollabGraph's usefulness, preference, and enhancement of participation of student's and teacher's feedback compared to the list view of search history results. We evaluate our approach with an online questionnaire in six different project-based searching as learning (saL) scenarios (Lss). The evaluation of users' experience indicates that the CollabGraph is useful, highly likeable, and could benefit users' participation and teacher's feedback by providing more precise insights into the project status. Our approach helps users better perceive about everyone's work, and it is a highly preferable feature alongside the list view. In addition, the results demonstrate that graph summary visualizations, such as the CollabGraph, are more suitable for closed-end scenarios and collaborative projects with many participants.

关键词： Collaborative e-learning platforms collaborative search group results personal knowledge graphs (PKGs) search history visualization searching as learning (saL) smart learning environment (sLE)

来源：评论

学校读者我要写书评

暂无评论

Age-of-Information-Aware Federated learning

引用

Journal of computer science & Technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index based Client selection(WICs)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of Information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

A deep transfer learning model for the deformation of braced excavations with limited monitoring data

引用

Journal of Rock Mechanics and Geotechnical Engineering 2025年第3期17卷 1555-1568页

作者： Yuanqin Tao shaoxiang Zeng Tiantian Ying Honglei sun sunjuexu Pan Yuanqiang Cai College of Civil Engineering Zhejiang University of TechnologyHangzhou310023China Engineering Research Center of Ministry of Education for Renewable Energy Infrastructure Construction Technology Hangzhou310023China

The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training *** address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(s2sCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been *** the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping *** illustrate the proposed methodology,an excavation project in Hangzhou,China is *** proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning *** the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent *** results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.

关键词： Braced excavation Wall deflections Transfer learning Deep learning Finite element simulation

来源：评论

学校读者我要写书评

暂无评论

Redefining Education: A Personalized AI Platform for Enhanced learning Experiences 2

Redefining Education: A Personalized AI Platform for Enhance...

引用

2nd International Workshop on Artificial INtelligent systems in Education, AIxEDU 2024

作者： schicchi, Daniele Taibi, Davide Institute for Education Technology National Research Council of Italy Palermo Italy

The PROsPETTIVA project aims to improve secondary education in sicily by integrating AI technologies to promote active learning and AI literacy among students and teachers. This paper provides an overview of the PROsPETTIVA platform, a web-based educational tool designed to offer personalized learning experiences using advanced Large Language Models (LLMs). The platform encourages controlled interactions with AI to prevent surface-level learning and promotes critical thinking by enabling students to engage with AI in a structured manner. By aligning with pedagogical objectives and incorporating teacher feedback, the project aims to establish a meaningful use of AI in education, supporting a deeper understanding of concepts and encouraging reflective engagement. The platform's features, such as summarization and simplification, have been carefully selected based on performance metrics to ensure a high-quality educational experience. Initial results suggest the potential of this approach in improving learning outcomes and reducing educational inequalities in the region. Future research will focus on refining the platform and expanding its functionalities based on user feedback. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Federated learning

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：