检索结果-内蒙古大学图书馆

9th International Conference on computer science and Engineering, UBMK 2024

作者： sarikaya, Burcu sönmez Bahtiyar, Şerif Istanbul Technical University Cyber Security and Privacy Research Lab SPFLab Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350365887

Intrusion Detection systems (IDs) have been significant for Unmanned Aerial Vehicles (UAVs) since high connectivity is essential for such vehicles. Recently, machine learning-based defense mechanisms have contributed to detecting intrusions. Data are crucial to better results with machine learning algorithms. However, security data is not freely distributed so there is a lack of security-related data about UAVs that can be processed with machine learning. In this research, we create synthetic security data for UAVs using Generative Adversarial Networks (GANs) that can be utilized to develop machine learning-based IDs systems. We propose employing Conditional Tabular Generative Adversarial Networks (CTGANs), Gaussian copulas, and Variational AutoEncoders (VAEs) to generate syn-thetic jamming attacks from the widely-used UAV attack dataset. We experimentally evaluated the performance of each model by using many metrics, such as Kullback-Leibler decomposition. Experimental results show that the distribution of CTGAN synthetic data is similar to the distribution of real data. Finally, we created a machine learning-based IDs and applied it to each dataset to validate the success rate of intrusion detection with newly generated synthetic data. It was observed that CTGAN-generated data decreased the IDs accuracy by approximately 25%, while Gaussian copula-generated data resulted in a 20% decrease, and VAE-generated data led to a 1% reduction, all relative to the accuracy achieved with real data. These findings suggest that synthetic data generation holds significant potential for enhancing the security frameworks of UAVs. The experimental results demonstrate that the CTGAN model is particularly effective in producing synthetic data that challenges traditional intrusion detection mechanisms, thereby contributing to the development of more robust IDs capabilities. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

research on Optimization of Underground Pipe Gallery Remote Antenna Deployment and Resource Allocation based on Machine learning 7

Research on Optimization of Underground Pipe Gallery Remote ...

引用

7th IEEE International Conference on computer and Communication Engineering Technology, CCET 2024

作者： Guo, Tian Zhao, Yang Ma, Boxiang Ma, Xianwei Ding, Yiming Li, Jinghan Bai, Wei State Grid Beijing Electric Power Company Beijing China State Grid Smart Grid Research Institute Co. Ltd. Beijng China

ISBN: (纸本)9798350355673

With the continuous advancement of the construction of the Internet of Things (IoT) in China's power sector and the increasing number of cable channels, the demand for cable channel monitoring is becoming increasingly urgent. There is a pressing need for low-cost, high-efficiency digital operation and maintenance methods to support this demand. Currently, there is no mature wireless sensor network solution suitable for cable channels. Therefore, it is necessary to develop a customized low-power wireless sensor network system that supports coverage enhancement and flexible topology networking, forming an application deployment plan for wireless sensor network systems in cable channels and laying the foundation for the construction of digital cable channels. To address this, our paper proposes a wireless sensor network model for cable channels. This model comprises convergence nodes, remote radio units, and equipment within the cable channels, aiming to maximize the total system throughput. To solve this problem, we use deep reinforcement learning methods in machine learning. Through theoretical analysis and numerical simulations, we verify that this method performs better in terms of total system throughput compared to other benchmark methods. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Linux log anomaly behavior prediction method based on XGBoost 4

Linux log anomaly behavior prediction method based on XGBoos...

引用

4th International symposium on computer Technology and Information science, IsCTIs 2024

作者： Wang, Ruini Jiangsu Automation Research Institute Electronic Equipment Business Unit Lianyungang China

ISBN: (纸本)9798350354560

To solve the problem that abnormal behavior in Linux logs is difficult to identify effectively, this paper proposes a method for predicting abnormal behavior in Linux logs based on XGBoost algorithm. By analyzing the historical log data, the method uses the efficient gradient lifting decision tree mechanism of XGBoost algorithm, and realizes the efficient learning rate and regularization strategy through multiple rounds of iterative optimization, effectively coping with the data imbalance and improving the model generalization ability. Experiments show that this model can significantly improve the accuracy and real-time of anomaly detection, and effectively distinguish between normal and abnormal log behaviors. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Label-Efficient Time series Representation learning: A Review

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6027-6042页

作者： Eldele, Emadeldeen Ragab, Mohamed Chen, Zhenghua Wu, Min Kwoh, Chee-Keong Li, Xiaoli Institute for Infocomm Research The Centre for Frontier AI Research Agency for Science Technology and Research 138632 Singapore Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Institute for Infocomm Research Agency for Science Technology and Research 138632 Singapore

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semisupervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross domain based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field. © 2024 IEEE.

关键词： supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Intelligent Classroom based on CAD Multi-Valued Color Image segmentation Algorithm

引用

computer-Aided Design and Applications 2023年第S3期20卷 16-28页

作者： Wang, Nanlan Li, Jianqi Balaji, Prasanalakshmi Vaiyapuri, Thavavel Verma, Amit School of Computer and Electrical Engineering Hunan university of Arts and Science Hunan Changde415000 China International Education Center Philippine Christian University Manila1772 Philippines Department of Computer Science King Khalid University Saudi Arabia Department of Computer Sciences College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Saudi Arabia Department of CSE University Centre for Research & Development Chandigarh University Punjab Mohali140413 India

In order to solve the problem that the efficiency of smart classroom is not high enough, a multi valued color image segmentation algorithm based on CAD is proposed to optimize the smart classroom. This paper explores the notion of smart education as well as a conceptual framework to enable children to receive excellent education and to spark their interest through creative learning. Firstly, CAD software is used to improve software design efficiency and optimize product technology;secondly, the core technology of the smart classroom is improved by using the national value color image segmentation algorithm, and compared with the smart classroom without the multi value color image segmentation algorithm;Finally, the utilization efficiency of the improved smart classroom is counted. It is proved that the smart classroom based on CAD multi valued color image segmentation algorithm can give greater play to the role of smart classroom, reduce the teaching pressure of teachers by 20% and improve the learning efficiency of students by 20%. The intelligent classroom has a higher degree of informatization and more powerful functions, which is of great help to promote classroom communication and improve communication efficiency. The smart classroom is easier to run and adapt thanks to the optimization of the CAD multi threshold color picture segmentation algorithm, which considerably improves the system's work efficiency and capability. However, the smart classroom also has its own shortcomings, which are mainly reflected in the high investment cost, the complex design of the system and the high maintenance cost in the later stage. With the optimization of CAD multi valued color image segmentation algorithm, the smart classroom is easier to operate and adjust, which greatly enhances the work efficiency and ability of the system. © 2023 CAD solutions, LLC.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

A Machine learning-based Observational Constraint Correction Method for seasonal Precipitation Prediction

引用

Advances in Atmospheric sciences 2025年第1期42卷 36-52页

作者： Bofei ZHANG Haipeng YU Zeyong HU Ping YUE Zunye TANG Hongyu LUO Guantian WANG shanling CHENG Key Laboratory of Cryospheric Science and Frozen Soil Engineering Nagqu Plateau Climate and Environment Observation and Research Station of Tibet Autonomous RegionNorthwest Institute of Eco-Environment and ResourcesChinese Academy of SciencesLanzhou 730000China University of the Chinese Academy of Sciences Beijing 100049China Key Open Laboratory of Arid Climate Change and Disaster Reduction of CMA Key Laboratory of Arid Climate Change and Reducing Disaster of Gansu ProvinceInstitute of Arid MeteorologyChina Meteorological AdministrationLanzhou 730000China School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China

seasonal precipitation has always been a key focus of climate *** a dynamic-statistical combined method,the existing observational constraint correction establishes a regression relationship between the numerical model outputs and historical observations,which can partly predict seasonal ***,solving a nonlinear problem through linear regression is significantly *** study implements a nonlinear optimization of an existing observational constrained correction model using a Light Gradient Boosting Machine(LightGBM)machine learning algorithm based on output from the Beijing National Climate Center Climate system Model(BCC-CsM)and station observations to improve the prediction of summer precipitation in *** model was trained using a rolling approach,and LightGBM outperformed Linear Regression(LR),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost).Using parameter tuning to optimize the machine learning model and predict future summer precipitation using eight different predictors in BCC-CsM,the mean Anomaly Correlation Coefficient(ACC)score in the 2019–22 summer precipitation predictions was 0.17,and the mean Prediction score(Ps)reached *** Ps score was improved by 7.87%and 6.63%compared with the BCC-CsM and the linear observational constraint approach,*** observational constraint correction prediction strategy with LightGBM significantly and stably improved the prediction of summer precipitation in China compared to the previous linear observational constraint solution,providing a reference for flood control and drought relief during the flood season(summer)in China.

关键词： observational constraint LightGBM seasonal prediction summer precipitation machine learning

来源：评论

学校读者我要写书评

暂无评论

A Modified Oppositional Chaotic Local search strategy based Aquila Optimizer to Design an Effective Controller for Vehicle Cruise Control system

引用

Journal of Bionic Engineering 2023年第4期20卷 1828-1851页

作者： serdar Ekinci Davut Izci Laith Abualigah Raed Abu Zitar Department of Computer Engineering Batman University72100BatmanTurkey Center for Engineering Application and Technology Solutions Ho Chi Minh City Open UniversityHo Chi MinhVietnam Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman19328Jordan Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl Al-Bayt UniversityMafraq25113Jordan Faculty of Information Technology Middle East UniversityAmman11831Jordan Applied Science Research Center Applied Science Private UniversityAmman11931Jordan School of Computer Sciences Universiti Sains Malaysia11800PenangPulau PinangMalaysia Sorbonne Center of Artificial Intelligence Sorbonne University-Abu DhabiAbu DhabiUnited Arab Emirates

In this work,we propose a real proportional-integral-derivative plus second-order derivative(PIDD2)controller as an efficient controller for vehicle cruise control systems to address the challenging issues related to efficient *** this regard,this paper is the first report in the literature demonstrating the implementation of a real PIDD2 controller for controlling the respective *** construct a novel and efficient metaheuristic algorithm by improving the performance of the Aquila Optimizer via chaotic local search and modified opposition-based learning strategies and use it as an excellently performing tuning *** also propose a simple yet effective objective function to increase the performance of the proposed algorithm(CmOBL-AO)to adjust the real PIDD2 controller's parameters *** show the CmOBL-AO algorithm to perform better than the differential evolution algorithm,gravitational search algorithm,African vultures optimization,and the Aquila Optimizer using well-known unimodal,multimodal benchmark ***2019 test suite is also used to perform ablation experiments to reveal the separate contributions of chaotic local search and modified opposition-based learning strategies to the CmOBL-AO *** the vehicle cruise control system,we confirm the more excellent performance of the proposed method against particle swarm,gray wolf,salp swarm,and original Aquila optimizers using statistical,Wilcoxon signed-rank,time response,robustness,and disturbance rejection *** also use fourteen reported methods in the literature for the vehicle cruise control system to further verify the more promising performance of the CmOBL-AO-based real PIDD2 controller from a wider *** excellent performance of the proposed method is also illustrated through different quality indicators and different operating ***,we also demonstrate the good performing capability of the CmOBL-AO algorithm for real traffic *** show

关键词： Aquila optimizer Chaotic local search Modified opposition-based learning Real PIDD^(2)controller Vehicle cruise control system Bionic engineering

来源：评论

学校读者我要写书评

暂无评论

Artificial visual-tactile perception array for enhanced memory and neuromorphic computations

引用

InfoMat 2024年第3期6卷 81-94页

作者： Jiaqi He Ruilai Wei shuaipeng Ge Wenqiang Wu Jianchao Guo Juan Tao Ru Wang Chunfeng Wang Caofeng Pan CAS Center for Excellence in Nanoscience Beijing Key Laboratory of Micro-nano Energy and SensorBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBeijingthe People's Republic of China School of Nanoscience and Engineering University of Chinese Academy of SciencesBeijingthe People's Republic of China Guangdong Research Center for Interfacial Engineering of Functional Materials College of Materials Science and EngineeringShenzhen UniversityShenzhenthe People's Republic of China

The emulation of human multisensory functions to construct artificial perception systems is an intriguing challenge for developing humanoid robotics and cross-modal human–machine *** by human multisensory signal generation and neuroplasticity-based signal processing,here,an artificial perceptual neuro array with visual-tactile sensing,processing,learning,and memory is *** neuromorphic bimodal perception array compactly combines an artificial photoelectric synapse network and an integrated mechanoluminescent layer,endowing individual and synergistic plastic modulation of optical and mechanical information,including short-term memory,long-term memory,paired pulse facilitation,and“learning-experience”*** or superimposed visual and tactile stimuli inputs can efficiently simulate the associative learning process of“Pavlov's dog”.The fusion of visual and tactile modulation enables enhanced memory of the stimulation image during the learning process.A machine-learning algorithm is coupled with an artificial neural network for pattern recognition,achieving a recognition accuracy of 70%for bimodal training,which is higher than that obtained by unimodal *** addition,the artificial perceptual neuron has a low energy consumption of~20 *** its mechanical compliance and simple architecture,the neuromorphic bimodal perception array has promising applications in largescale cross-modal interactions and high-throughput intelligent perceptions.

关键词： artificial intelligent systems mechanoluminescence neuromorphic computing optoelectronic synapse visual-tactile perception

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Machine learning-based Heuristic Algorithm for Buffer Management and project scheduling Optimization 1

引用

science, Engineering Management and Information Technology First International Conference, sEMIT 2022

作者： Zohrehvandi, shakib soltani, Roya Lefebvre, Dimitri Zohrehvandi, Mehrnoosh Tenera, Alexandra New Technologies Department Center for European Studies Kharazmi University Tehran Iran Department of Industrial Engineering Faculty of Engineering Khatam University Tehran Iran Department of Industrial Engineering Science and Research Branch Islamic Azad University Tehran Iran GREAH Le Havre Normandy University 75 Rue Bellot Le Havre76600 France UNIDEMI Universidade NOVA de Lisboa Caparica Portugal

ISBN: (数字)9783031403958

ISBN: (纸本)9783031403941

One of the main problems that project managers face is that in most cases the projects won’t be completed according to predetermined schedules and therefore prolonged delays and losses occur during the project implementation phase. This study aims to propose a predictive buffer management algorithm (PBMA) based on machine learning technology to predict project buffer size and control project buffer consumption in construction projects to be not more than predetermined schedules and consequently prevent delays in projects’ completion times. The proposed machine-learning-based heuristic algorithm falls into the category of supervised machine learning algorithms and consists of two main stages. In the first stage, the project critical chain is identified and the appropriate project buffer size is specified. In the second stage, the consumption of the project buffer is monitored and controlled in the project implementation stage. To evaluate the performance of the proposed PBMA, it is coded in MATLAB software and implemented using the data taken from a hypothetical project. The results show that the use of the proposed PBMA improves the productivity of projects, and therefore the projects can be completed according to predetermined schedules. The resulted values for the longest path of the project’s critical activities, the duration of the project’s critical chain, the buffer duration of the project, and the duration of the project plan are respectively 60, 30, 15, and 45 days. The proposed PBMA can be applied to a variety of projects. © The Author(s), under exclusive license to springer Nature switzerland AG 2023.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Federated learning on Internet of Things:Extensive and systematic Review

引用

computers, Materials & Continua 2024年第5期79卷 1795-1834页

作者： Meenakshi Aggarwal Vikas Khullar sunita Rani Thomas AndréProla shyama Barna Bhattacharjee sarowar Morshed shawon Nitin Goyal Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpuraPunjab140401India Department of CSE&IT BPS Mahila VishwavidyalayaKhanpur KalanSonipatHaryana131305India Engineering Research&Innovation Group Universidad Europea del AtlánticoC/Isabel Torres 21Santander39011Spain Department of Project Management Universidad Internacional IberoamericanaAreciboPR00613USA Department of Project Management Universidade Internacional do CuanzaEstrada Nacional 250Bairro KaluapandaCuito-BiéAngola Department of Computer Science and Engineering University of Science and Technology Chittagong(USTC)Chattogram4202Bangladesh Deptartment of EEE University of Science and Technology Chittagong(USTC)Chattogram4202Bangladesh Department of Computer Science and Engineering School of Engineering and TechnologyCentral University of HaryanaMahendragarhHaryana123031India

The proliferation of IoT devices requires innovative approaches to gaining insights while preserving privacy and resources amid unprecedented data ***,FL development for IoT is still in its infancy and needs to be explored in various areas to understand the key challenges for deployment in real-world *** paper systematically reviewed the available literature using the PRIsMA guiding *** study aims to provide a detailed overview of the increasing use of FL in IoT networks,including the architecture and challenges.A systematic review approach is used to collect,categorize and analyze FL-IoT-based *** was performed in the IEEE,Elsevier,Arxiv,ACM,and WOs databases and 92 articles were finally *** measures were published in English and with the keywords“FL”and“IoT”.The methodology begins with an overview of recent advances in FL and the IoT,followed by a discussion of how these two technologies can be *** be more specific,we examine and evaluate the capabilities of FL by talking about communication protocols,frameworks and *** then present a comprehensive analysis of the use of FL in a number of key IoT applications,including smart healthcare,smart transportation,smart cities,smart industry,smart finance,and smart *** key findings from this analysis of FL IoT services and applications are also ***,we performed a comparative analysis with FL IID(independent and identical data)and non-ID,traditional centralized deep learning(DL)*** concluded that FL has better performance,especially in terms of privacy protection and resource *** is excellent for preserving privacy becausemodel training takes place on individual devices or edge nodes,eliminating the need for centralized data aggregation,which poses significant privacy *** facilitate development in this rapidly evolving field,the insights presented are intended to help practitioners and re

关键词： Internet of Things federated learning PRIsMA framework of FL applications of FL data privacy communication

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：