检索结果-内蒙古大学图书馆

Adaptive residual convolutional neural network for moiré image restoration

International Journal of Information Technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the zebra optimization algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

MMCNN-ZO: Modified multi-scale convolutional neural network-based zebra optimization for enhancing data encryption system

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2024年第2期17卷 924-943页

作者： Anuradha, M. Justus, J. Jean Sheela, L. Mary Immaculate SA Engn Coll Dept Comp Sci & Engn Chennai India St Josephs Coll Engn Dept Comp Sci & Engn Chennai India Pentecost Univ Dept Informat Technol Accra Ghana

Cloud computing (CC) is a rapidly growing technology that is deployed by various organizations due to the high level of scalability, elasticity, and virtualization it offers. However, security-related challenges arise due to insecure access control points. Security models in the cloud such as authentication, data recovery, confidentiality, accessibility, and data integrity. This includes the deployment model, barriers in cloud computing, cloud services, and security issues. Data security can be improved via the usage of encryption and decryption keys during transmission. However, the existing techniques often suffered from improved time consumption and complexity in handling more users. This paper mainly focuses on the data security issue with the outsourced sensitive data in the cloud server by designing a novel Modified Multi-scale Convolutional Neural Network-based zebra optimization (MMCNN-ZO) approach to improve the cloud data sharing system. The proposed MMCNN-ZO approach safeguards the crucial data effectively and outputs in the form of cipher text/image. Here, the weight functions of the MMCNN are tuned mechanically using the ZO algorithm for the enhanced encryption process. The decryption process is performed to obtain the data in user understandable format. These procedures make the proposed system effectively secure the data content by protecting against intrusions. The efficacy of the proposed MMCNN-ZO method is investigated using diverse evaluation indicators namely throughput, decryption, and encryption time. The proposed MMCNN-ZO algorithm achieved improvements in terms of throughput, encryption time, and decryption time of 7450 bits/sec, 4.82 ms, and 4.86 ms respectively compared to other existing methods of SVM, ANN, BPPSVC, and GBCRP. The experimental results inherit the better performances of the suggested MMCNN-ZO approach over other methods in terms of all metrics.

关键词： Cloud computing Encryption Modified multi-scale convolutional neural network zebra optimization algorithm Decryption

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of voltage profile improvement in AVR system using zebra optimization algorithms based on PID controller

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2023年 6卷

作者： Pazhanimuthu, C. Saravanan, G. Suresh, K.P. Kumar, R. Senthil Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Tamilnadu Coimbatore 641407 India Department of EEE Sri Krishna College of Technology Tamilnadu Coimbatore 641042 India School of Electrical Engineering Vellore Institute of Technology Tamilnadu Chennai 600127 India

Many problems are associated with dynamic changes in the power system, mainly because the number of switching loads has increased. These loads induce ineffective system behaviour, reduce the system voltage profile, and lead to improper voltage regulation. The proposed Automatic Voltage Regulator (AVR) system is intended to eliminate the above problem and preserve the system voltage at the generator terminal within the allowable range. In this work, Proportional-Integral-Derivative (PID) controllers are applied to enhance the dynamic behaviour of the AVR system. The zebra optimization algorithm (ZOA) and Osprey optimization algorithm (OOA) algorithms are implemented to optimize the system's transient response by modifying the gain of PID controller parameters, which include proportional, integral, and derivative parameters, to preserve a stable voltage profile. To achieve an optimal solution, the mathematical model of the proposed system is realized in the Internet of Things (IoT). The connected loads in the system can operate at the nominal voltage level through PID controller tuning using ZOA and OOA. The proposed system's performance is evaluated and verified with MATLAB R2023a. ZOA showed an improvement of 18.5 % with a peak overshoot of 0.01 % during the system-transient condition. Compared to conventional optimization algorithms implemented in AVR systems, ZOA provides faster responsiveness and enhanced system stability. © 2023 The Author(s)

关键词： AVR system Osprey optimization algorithm PID controller Power system optimization zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Load frequency control in power systems with high renewable energy penetration: A strategy employing PIλ(1+PDF) controller, hybrid energy storage, and IPFC-FACTS

引用

ALEXANDRIA ENGINEERING JOURNAL 2024年 106卷 337-366页

作者： Khan, Irfan Ahmed Mokhlis, Hazlie Mansor, Nurulafiqah Nadzirah Illias, Hazlee Azil Daraz, Amil Ramasamy, A. K. Marsadek, Marayati Afzal, Abdul Rahman Univ Malaya Fac Engn Dept Elect Engn Kuala Lumpur 50603 Malaysia NingboTech Univ Sch Informat Sci & Engn Ningbo 315100 Peoples R China Univ Tenaga Nas Inst Power Engn Kajang 43000 Selangor Malaysia Univ Business & Technol Dept Ind Engn Jeddah Saudi Arabia Middle East Univ Res Unit Amman Jordan

The high penetration of Renewable Energy Sources (RESs) in the modern power system poses a challenge to power system stability. This stability is affected by the stochastic, fluctuating output of RESs, which is influenced by weather conditions, and a lack of inertia resulting from reduced rotating mass. To address this issue, a new controller, referred to as Proportional-Fractional Integrator Plus Proportional-Derivative with Filter, PI lambda(1+PDF), is designed for Load Frequency Control (LFC) with the support of a Hybrid Energy Storage System (HESS) for power systems with high-RES penetration. The HESS comprises a Superconducting Magnetic Energy Storage System (SMES) and a Vanadium Redox Flow Battery (VRFB) coupled with an Interline Power Flow Controller Flexible AC Transmission Systems (IPFCFACTs) controller. The HESS, working in conjunction with the proposed LFC, injects virtual inertia and maintains power flow to expedite the frequency stability process. These systems are also integrated with Alternating Current (AC) and High Voltage Direct Current (HVDC) transmission lines to collectively enhance both the system's stability and the capacity of its transmission lines. To optimize the PI lambda(1+PDF) controller parameters, zebra optimization algorithm (ZOA) is employed utilizing an Integral Time Absolute Error (ITAE) objective function. The proposed controller is tested on a four-area power system integrated with a wind turbine, photovoltaic (PV) panels, a biodiesel generator, and a hydrogen aqua electrolyzer fuel cell, representing a high penetration of RESs in modern power systems. The results are compared with those obtained using Proportional-Integral-Derivative (PID) and Fractional Order Proportional Integral Derivative (FOPID) controllers. Sensitivity analysis and robustness tests are also performed to verify the stability of the power network by changing system parameters and under randomly chosen loading conditions. The proposed PI lambda (1+PDF) contr

关键词： Load frequency control zebra optimization algorithm Energy storage system IPFC FACTS Redox flow battery SMES

来源：评论

学校读者我要写书评

暂无评论

Parkinson's disease classification using nature inspired feature selection and recursive feature elimination

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第12期83卷 35197-35220页

作者： Chawla, Prabhleen Kaur Nair, Meera S. Malkhede, Dattakumar Gajanan Patil, Hemprasad Yashwant Jindal, Sumit Kumar Chandra, Avinash Gawas, Mahadev Anant Vellore Inst Technol Sch Elect Engn Vellore 632014 Tamil Nadu India Govt Goa State Higher Educ Council Directorate Higher Educ Alto Porvorim India

New progress in machine learning (ML) have paved the way for solving various existing complex problems, including in the medical field. In the proposed paper, we have investigated methods to detect Parkinson's Disease (PD) with Nature Inspired Feature Selection (NIFS) using the zebra optimization algorithm and Recursive Feature Elimination Cross Validation (RFECV). A vocal feature-based dataset has been used for PD Detection as it contains data relating to the vocal features of PD patients. It has been proven from research that vocal disorders are observed in the majority of individuals in the preliminary phases of this disease. The number of features has been reduced from 754, in the original dataset, to 40 using feature selection, and the classification results have been obtained for two cases, one being a 70:30 train test split and the other being tenfold cross-validation. We have implemented the proposed technique on 11 different classifiers. Out of these, the Gaussian Process classifier showed the best accuracy for both cases. The accuracy values obtained for cases one and two are 96% and 97.07%, respectively, one of the highest accuracy values obtained for similar research done by other researchers. Additionally, the generalization capability of the model obtained may be enhanced by including more data points in the dataset.

关键词： Nature Inspired Feature Selection Parkinson's disease Vocal features RFECV SMOTE zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal Model Reference Lead Compensator Design for Electric Vehicle Speed Control Using zebra optimization Technique

引用

JORDAN JOURNAL OF MECHANICAL AND INDUSTRIAL ENGINEERING 2023年第4期17卷 533-540页

作者： Mhmood, Ali H. Oleiwi, Bashra Kadhim Rakan, Amer B. Tikrit Univ Coll Petr Proc Engn Petr Syst Control Engn Dept Tikrit Iraq Univ Technol Iraq Control & Syst Engn Dept Baghdad Iraq

Electric vehicle systems are growing in popularity as a promising solution to the problems associated with traditional transportation systems, such as environmental pollution. Nonetheless, the task of devising control algorithms that effectively control electric vehicle systems continues to persist as a complex realm of research. This is due to the ongoing pursuit of refining the dynamic attributes of the system, a task that is riddled with challenges. The inherent instability exhibited by the system and the presence of undesirable behaviors further compound the intricacy of this endeavor, demanding careful attention and comprehensive analysis of the system's unstable roots. In this paper, an advanced control algorithm is proposed for controlling the speed of the electric vehicle system based on the lead compensation. In addition, the control algorithm is designed to include the utilization of model reference control to improve the time response properties of the closed-loop system. Then, the zebra optimization algorithm (ZOA) is used to optimally define the compensator parameters such that the reference model and system outputs be asymptotically identical with desirable steady-state error. Eventually, the simulation results show that the proposed optimal model reference lead compensator ensures stable and high-performance control of the electric vehicle system while maintaining simplicity and acceptable control action compared to other control approaches. This is substantiated by the noteworthy reductions it brings about: a staggering 90% decrease in rise time, a substantial 51% decrease in overshoot, and an impressive 99% reduction in cost value. In addition, the intervention of the proposed method completely eradicates steady-state errors, thus addressing a critical aspect of control system performance.

关键词： Electric vehicle system Speed control Lead compensator Model reference control zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Unconfined Compressive Strength prediction in geotechnical engineering: a novel approach using LSZO and LSWG optimization

引用

SMART SCIENCE 2024年

作者： Zhao, Kunpeng Zhao, Guanglei Henan Vocat Univ Sci & Technol Sch Architectural Engn Zhoukou 466000 Henan Peoples R China

The Unconfined Compressive Strength (UCS) measures a rock's ability to withstand axial loads without lateral support, crucial for engineering applications. Accurate prediction of UCS is critical for the stability and safety of various civil engineering projects, such as foundation design, mining, and tunneling. The ability to predict UCS reliably ensures better project planning and execution, ultimately enhancing the safety and efficiency of engineering applications. The paper aims to develop an innovative method for predicting the $UCS$UCS of rocks using a combination of the zebra Optimisation algorithm (ZOA) and the Wild Geese algorithm (WGA) integrated with the Least Square Support Vector Regression (LSSVR) predictive model. The novelty of the paper lies in the integration of ZOA and WGA optimizers with the LSSVR model to address the limitations of conventional methods, which often face challenges like slow achieving convergence and being stuck in local minima. The combination of these advanced algorithms results in significantly improved accuracy and convergence speed in UCS predictions, demonstrating a robust and reliable approach that advances the field of geotechnical engineering. The results show that combining ZOA and WGA optimizers with LSSVR enhances $UCS$UCS prediction accuracy and speed convergence. The LSZO models achieve a high level of precision, with a low RMSE value of 2.206 and an R2 value of 0.993. The safety and effectiveness of civil engineering projects are improved by this model, which provides a strong and trustworthy method for UCS prediction.

关键词： Least Square Support Vector Regression Wild Geese algorithm zebra optimization algorithm Unconfined Compressive Strength

来源：评论

学校读者我要写书评

暂无评论

Enhanced botnet detection in IoT networks using zebra optimization and dual-channel GAN classification

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-19页

作者： Shareef, S. K. Khaja Chaitanya, R. Krishna Chennupalli, Srinivasulu Chokkakula, Devi Kiran, K. V. D. Pamula, Udayaraju Vatambeti, Ramesh Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Informat Technol Hyderabad India SRKR Engn Coll Dept ECE Bhimavaram 534204 India Inst Aeronaut Engn Dept CSE Hyderabad India Nadimpalli Satyanarayana Raju Inst Technol Dept Comp Sci & Engn Visakhapatnam 531173 India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram India SRM Univ AP Dept Comp Sci & Engn Amaravati 522502 Andhra Pradesh India VIT AP Univ Sch Comp Sci & Engn Vijayawada 522237 India

The Internet of Things (IoT) permeates various sectors, including healthcare, smart cities, and agriculture, alongside critical infrastructure management. However, its susceptibility to malware due to limited processing power and security protocols poses significant challenges. Traditional antimalware solutions fall short in combating evolving threats. To address this, the research work developed a feature selection-based classification model. At first stage, a preprocessing stage enhances dataset quality through data smoothing and consistency improvement. Feature selection via the zebra optimization algorithm (ZOA) reduces dimensionality, while a classification phase integrates the Graph Attention Network (GAN), specifically the Dual-channel GAN (DGAN). DGAN incorporates Node Attention Networks and Semantic Attention Networks to capture intricate IoT device interactions and detect anomalous behaviors like botnet activity. The model's accuracy is further boosted by leveraging both structural and semantic data with the Sooty Tern optimization algorithm (STOA) for hyperparameter tuning. The proposed STOA-DGAN model achieves an impressive 99.87% accuracy in botnet activity classification, showcasing robustness and reliability compared to existing approaches.

关键词： Internet of things zebra optimization algorithm Graph attention network Sooty Tern optimization algorithm Node attention networks

来源：评论

学校读者我要写书评

暂无评论

Improved compressed sensing channel estimation algorithm for MIMO-OFDM systems 36

Improved compressed sensing channel estimation algorithm for...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Li, SiTong Yang, Yongli Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9798350387780;9798350387797

The signals in MIMO-OFDM systems have good sparsity characteristics, and the channel estimation problem can be transformed into a sparse signal recovery problem using compressed sensing theory. This paper proposes an adaptive compressed sampling matching and tracking algorithm based on zebra optimization (ZOA-CoSaMP), which utilizes the ZOA algorithm to optimize the atomic matching process of the CoSaMP algorithm. The generalized Jaccard coefficient is used for atomic secondary screening to improve the recovery accuracy, Simultaneously introducing a power function type variable step size strategy to achieve sparsity adaptation. Finally, it was demonstrated through experimental simulation that compared to the CoSaMP algorithm, this algorithm has better estimation accuracy.

关键词： compressive sensing mimo-ofdm channel estimation compressed sampling matching tracking zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimating the mechanical properties of high-performance concrete via automated and ensembled machine learning methods

引用

MATERIALS TODAY COMMUNICATIONS 2023年 37卷

作者： Liu, Xiaohua Zhang, Yu Lei, Song Yang, Shasha Xijing Univ Shaanxi Key Lab Safety & Durabil Concrete Struct Xian 710123 Shaanxi Peoples R China Xian Fengdong Real Estate Co Ltd Xian 710116 Shaanxi Peoples R China Yanan Univ Sch Petr Engn & Environm Engn Yanan 716000 Shaanxi Peoples R China

Environmentally friendly concrete is needed to reduce increased concrete consumption's environmental and climate impacts. One of the approaches to achieve this goal is using fly ash (FA) and silica fume (SF) in concrete mixes. The mentioned admixtures can enhance the workability and mechanical properties of concrete. Therefore, testing to predict the strength of concrete can be time-consuming and expensive. Thus, operating artificial intelligence methods, especially machine learning (ML), can simplify and speed up the procedure. Therefore, this investigation proposes to explore the possibility of using the ML models to predict the compressive strength (CS) and Slump (SL) of High-performance concrete (HPC). For this task, experimental results of HPC samples are used to develop the ML models, including Light Gradient Boosting Machine (LGBM) and Decision Tree (DT). In addition, some meta-heuristic algorithms have been used to improve the accuracy of presented models, which contain the zebra optimization algorithm and Tunicate Swarm algorithm. Extensive calculational tests were performed to assess the performance of the deemed models by using results achieved through experimental tests by statistical indicators. The LGZO model stands out from the other proposed models, exhibiting superior performance with impressively low RMSE values of 1.859 and 5.234 for CS and SL, respectively. These results prove the model's exceptional accuracy and robust predictive capability. Research findings suggest that utilizing predictive techniques instead of conducting costly and time-consuming tests could reduce costs and save time.

关键词： High-performance concrete compressive strength and slump Light gradient boosting machine Decision tree zebra optimization algorithm Tunicate swarm algorithm

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：