检索结果-内蒙古大学图书馆

Robust Control for Uncertain Discrete-Time Linear Systems Using Reinforcement Learning With Discount Factor

IAENG International Journal of Applied Mathematics 2024年第12期54卷 2783-2791页

作者： Ding, Yuntian Yang, Yuxiao Yan, Zhilian Tai, Weipeng Research Institute of Information Technology Anhui University of Technology Ma’anshan243032 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215000 China School of Electrical & Information Engineering Anhui University of Technology Ma’anshan243032 China School of Computer Science and Technology Anhui University of Technology Ma’anshan243032 China

This paper focuses on robust control for uncertain discrete-time linear systems. We transform the robust control issure into an optimal control issure for an auxiliary system. The desired control gains are obtained by solving coupled algebraic Riccati equations. We propose a model-free off-policy reinforcement learning algorithm that incorporates a discount factor to get an approximate solution to the equation, using only measured data and eliminating the need for information about system dynamics. This algorithm requires adding probing noise to control inputs to maintain persistent excitation condition. We show that the probing noise does not introduce bias in the solution of the Bellman equation. The effectiveness of the proposed algorithm is verified through a simulation example, which analyzes the impact of the discount factor and the probing noise. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Feature Learning for Cross-Project Software Defect Prediction

引用

computers, Materials & Continua 2023年第10期77卷 161-180页

作者： Ahmed Abdu Zhengjun Zhai Hakim A.Abdo Redhwan Algabri Sungon Lee School of Software Northwestern Polytechnical UniversityXi’anChina School of Computer Science Northwestern Polytechnical UniversityXi’anChina Department of Computer Science Hodeidah UniversityPO Box 3114Al-HudaydahYemen Research Institute of Engineering and Technology Hanyang UniversityAnsanKorea Department of Robotics Hanyang UniversityAnsanKorea

Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for *** paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source *** proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive *** process involves graph construction,feature learning through graph embedding and LSTM,and defect *** evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.

关键词： Cross-project defect prediction graphs features deep learning graph embedding

来源：评论

学校读者我要写书评

暂无评论

Mitigating Denial Based Service Attacks in Heterogeneous Sensor Networks: Strategies and Solutions 11

Mitigating Denial Based Service Attacks in Heterogeneous Sen...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Desai, Jaynesh H Bagle, Neha S Rami, Khyati Verma, Shanti Bhagwan Mahavir University Department of Computer Applications Gujarat Surat India Sal Institute of Technology & Engineering Research Department of Computer Science Gujarat India L J University Department of Computer Applications Gujarat Ahmedabad India

ISBN: (纸本)9798350350357

With the development of heterogeneous sensory networks in various applications of domains for ensuring the security against denial based service (DoS) attacks will become a paramount. In this research study, a proposal of a novel system named SecureSenseGuard(SSG) for effectively detecting DoS attacks in heterogeneous sensor networks. SecureSenseGuard(SSG) leveraging the Decision Tree (DT) algorithm augmented with Recursive type Features Elimination (RFE) for achievinga robust and efficient attack detection. The proposed system may operate by first Collection of data from diverged sensors within the network. The data, representing various network attributes, are then preprocessed and fed into the DT algorithm for classifications process. RFE will be employed as a feature selection techniques to enhance the performance of DT algorithm by iterative process for removing less relevant features, thus improving in detection accuracy and reducing computational overhead. The proposed system SecureSenseGuard(SSG) will offer several advantages over existing approaches. By employing DT, it will provide interpretable and transparent decision rules for facilitating understanding and trust in the detection process. Moreover, the integration of RFE will enhance the system's scalability and adaptability for dynamic network environments. To evaluate the effectiveness of SecureSenseGuard(SSG) an extensive experiment may be conducted by using various ranges of datasets and synthetic attack scenarios. The Results demonstrate that SecureSenseGuard(SSG) achieved high detection rates. while maintaining a low false alarm rate, outperforming traditional approaches. Overall, SecureSenseGuard(SSG) may present a promising solution in mitigating DoS attacks in heterogeneous sensory networks by offering a balance between detection accuracy, interpretability, and computational efficiency. © 2024 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Developing Intelligent AI-Driven Systems for Automated Data science 1

Developing Intelligent AI-Driven Systems for Automated Data ...

引用

1st IEEE International Conference on Emerging research in Computational science, ICERCS 2023

作者： Komal, M. Shrimal, Gajendra Singh, Akhilendra Pratap Jebaraj, Solomon Dhingra, Lovish Reena, R. Vishwakarma Institute of Information Technology Department of Information Technology Pune India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Department of Computer Science and Information Technology Karnataka Bangalore India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

this article proposes the idea of applying smart synthetic intelligence (AI) structures to the automation of statistics technology. The AI structures are designed to study from records inputs to as it should be identify and procedure patterns, tendencies, and relationships within the statistics. Furthermore, those AI structures can be used to create computerized records technology fashions and practice them to datasets to be able to automate the records analysis procedure. The proposed AI gadget architecture is composed of numerous components, which might be accountable for extracting and extracting records, analyzing the statistics to decide styles and trends, and eventually, building models. The AI device structure contains superior strategies inclusive of deep gaining knowledge of, generative antagonistic networks, and reinforcement gaining knowledge of, so as to learn from a wide variety of records sources. Sooner or later, this newsletter discusses the capability advantages of the use of AI-pushed facts science automation and provides a few viable packages. © 2023 IEEE.

关键词： Reinforcement

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Multicast Protocols over ATM Networks 15

An Investigation of Multicast Protocols over ATM Networks

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Banerjee, Diptonil Vedantan, Kambam More, Priyanka Hemelatha, S. Kumar, Amit Vanaja, T. College of Engineering Teerthanker Mahaveer University Uttar Pradesh Moradabad India Karnataka Bangalore India Computer Engineering Vishwakarma Institute of InformationTechnology Pune India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore641021 India Centre for Interdisciplinary Research for Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India

ISBN: (纸本)9798350370249

The paper investigates the impact of the multicast method used over an asynchronous transfer mode (ATM) network in comparison to factor-to-factor solutions. The paper investigated mechanisms, multicast, and point-to-point (P2P) and in comparison their overall performance in phrases of throughput, total delay, and packet loss charge when beneath various community conditions. It turned into located that multicast had benefits in terms of total throughput and postpone while compared to P2P in phrases of cost of bandwidth for larger variety of receivers. Further, the multicast method had a lower packet loss charge than P2P in all situations. This paper concluded that no matter the complexity related multicast, because of its inherent blessings, is taken into consideration a better answer for multimedia programs that require a large number of receivers. Average, its miles counseled that multicast is the era of desire over ATM networks when the number of receivers growth. ©2024 IEEE |

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Predicting Dementia Risk Factors Based on Feature Selection and Neural Networks

引用

computers, Materials & Continua 2023年第5期75卷 2491-2508页

作者： Ashir Javeed Ana Luiza Dallora Johan Sanmartin Berglund Arif Ali Peter Anderberg Liaqat Ali Aging Research Center Karolinska InstitutetStockholm17165Sweden Department of Health Blekinge Institute of TechnologyKarlskrona37141Sweden School of Health Sciences University of SkövdeSkövdeSE 54128Sweden Department of Computer Science University of Science and Technology BannuBannu28100Pakistan Department of Electrical Engineering University of Science and Technology BannuBannu28100Pakistan

Dementia is a disorder with high societal impact and severe consequences for its patients who suffer from a progressive cognitive decline that leads to increased morbidity,mortality,and *** there is a consensus that dementia is a multifactorial disorder,which portrays changes in the brain of the affected individual as early as 15 years before its onset,prediction models that aim at its early detection and risk identification should consider these *** study aims at presenting a novel method for ten years prediction of dementia using on multifactorial data,which comprised 75 *** are two automated diagnostic systems developed that use genetic algorithms for feature selection,while artificial neural network and deep neural network are used for dementia *** proposed model based on genetic algorithm and deep neural network had achieved the best accuracy of 93.36%,sensitivity of 93.15%,specificity of 91.59%,MCC of 0.4788,and performed superior to other 11 machine learning techniques which were presented in the past for dementia *** identified best predictors were:age,past smoking habit,history of infarct,depression,hip fracture,single leg standing test with right leg,score in the physical component summary and history of TIA/*** identification of risk factors is imperative in the dementia research as an effort to prevent or delay its onset.

关键词： Dementia prediction feature selection genetic algorithm neural networks

来源：评论

学校读者我要写书评

暂无评论

DViTPolyp: Small Polyp Detection in Colonoscopy Videos based on Deep Vision Transformer 4

DViTPolyp: Small Polyp Detection in Colonoscopy Videos based...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Ma, Ming Xia, Likun Seo, Hyunseok Katz School of Science and Health Yeshiva University Dept. of Graduate Computer Science and Engineering New York United States College of Information Engineering Capital Normal University Beijing China Biomedical Research Institute Korea Institute of Science and Technology Seoul Korea Republic of

ISBN: (纸本)9798350395914

Early detection of colorectal polyps and removal play a crucial role in the prevention of colon cancer. computer-aided detection (CAD) methods can be employed to help endoscopists reduce the polyp miss-rates. Numerous automatic polyp detection methods have been explored. However, it is still challenging to automatically detect colon polyps in small size in colonoscopy videos. This paper presents a method termed DViTPolyp for detecting small colorectal polyp in colonoscopy videos. The proposed method leverages the power of the deep vision transformer as the detection head in the network to aggregate rich global features, and uses the re-attention mechanism to regenerate attention maps to capture the features from the backbone model and DViT block. Also, we propose to use a power regularized Intersection Over Union (IoU) as the loss function to further enhance the accuracy of detection. Experiments are conducted on a mix of several public polyp datasets. Comparative results show that our proposed method has a better performance than other methods. © 2024 IEEE.

关键词： colonoscopy videos loss function polyp detection vision transformer

来源：评论

学校读者我要写书评

暂无评论

Decoupling While Coupling: Towards More Accurate Stereo Image Sand Removal Beyond Certainty

Decoupling While Coupling: Towards More Accurate Stereo Imag...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

TizenRT OS Based Data Compression Algorithms for IoT Devices 4

TizenRT OS Based Data Compression Algorithms for IoT Devices

引用

4th IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2023

作者： Chamak, Tanmoy Roy Kaushik, Sachi Singhal, Shiven Dadheech, Aditya Anitha, Prof. A. Jenicka, Prof. S. Thapa, Vidisha School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Samsung Research Institute Karnataka Bangalore India

ISBN: (纸本)9798350306118

The paper investigates the integration and adaptation of the LZ4 compression algorithm within the context of TizenRT, in addition to existing algorithms Miniz and LZMA. TizenRT, a real-Time operating system tailored for Internet of Things (IoT) devices, presents unique challenges in balancing compression efficiency and resource constraints. The study evaluates the performance of LZ4 alongside Miniz and LZMA in terms of compression ratios, processing overhead, and memory utilization. Experimental results demonstrate the feasibility of LZ4's adoption in TizenRT, highlighting its potential to enhance data compression and decompression operations while adhering to the stringent requirements of IoT devices. The findings contribute to the optimization of data management strategies within the TizenRT ecosystem. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Security: Leveraging Isolation Forest for Malware Detection 2

Enhancing Network Security: Leveraging Isolation Forest for ...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Pawar, Janardan Adinath Avhankar, Madhavi Satish Gupta, Ashulekha Barve, Amit Patil, Harshal Maranan, Ramya Indira College of Commerce and Science Department of Computer Science Maharashtra Pune India Graphic Era Deemed to be University Department of Management Uttarakhand Dehradun India Parul University Parul Institute of Technology Faculty of Engineering and Technology Department of Computer Science and Engineering P.O. Limda Gujarat India Department of Computer Science and Engineering Maharashtra Pune India SIMATS Saveetha School of Engineering Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798350371314

In this work it has been shown that the growth of computer attacks continues to advance constantly, as well as the large number of vulnerability detection and protection tools that exist, therefore, not protecting a computer system allows easy access by intruders to the system, putting the confidentiality, integrity and availability of information at risk, in addition to increasing costs for performing corrective maintenance on damaged devices. Furthermore, studying the traffic flow of a network using the WireShark tool revealed instances of malware attacks, prompting the development of a proposed malware detection system for the network. To obtain the Dataset, all network statistics had to be forwarded to a host, where this host was connected to a Port Mirror. Once these statistics were obtained, they were captured thanks to the Netflow protocol, in order to have better management of the entire captured traffic flow. Isolation Forest shows an excellent probability of 92% and the model can distinguish between non-anomalous data and data that is malware which is superior than support vector machine (SVM). © 2024 IEEE.

关键词： Support vector machines

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：