检索结果-内蒙古大学图书馆

Integrating Differential Evolution into gazelle optimization for advanced global optimization and engineering applications

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 434卷

作者： Biswas, Saptadeep Singh, Gyan Maiti, Binanda Ezugwu, Absalom El-Shamir Saleem, Kashif Smerat, Aseel Abualigah, Laith Bera, Uttam Kumar Natl Inst Technol Agartala Dept Math Agartala Tripura India North West Univ Unit Data Sci & Comp 11 Hoffman St ZA-2520 Potchefstroom South Africa King Saud Univ Coll Appl Studies & Community Serv Dept Comp Sci & Engn Riyadh 11362 Saudi Arabia Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Biosci Chennai 602105 India Appl Sci Private Univ Appl Sci Res Ctr Amman 11931 Jordan Al Al Bayt Univ Comp Sci Dept Mafraq 25113 Jordan

The gazelle optimization algorithm (GOA) is an innovative metaheuristic inspired by the survival tactics of gazelles in predator-rich environments. While GOA demonstrates notable advantages in solving unimodal, multimodal, and engineering optimization problems, it struggles with local optima and slow convergence in high-dimensional and non-convex scenarios. This paper proposes the Hybrid gazelle optimization algorithm with Differential Evolution (HGOADE), which combines Differential Evolution (DE) with GOA to leverage their complementary strengths for addressing limitations. HGOADE initializes a population of candidate solutions using GOA, then enhances these solutions through DE's mutation and crossover operations. The algorithm subsequently employs GOA's exploration and exploitation phases to refine the solutions. By integrating DE's robust exploration capabilities with GOA's dynamic search patterns, HGOADE aims to improve global and local search performance. The effectiveness of HGOADE is validated through experiments on benchmark functions from the CEC 2017, CEC 2020, CEC 2022 suite, comparing with ten established optimization techniques, including classical GOA, Salp Swarm algorithm (SSA), Grey Wolf Optimizer (GWO), Gravitational Search algorithm (GSA), Arithmetic optimization algorithm (AOA), Constriction Coefficient-Based Particle Swarm optimization Gravitational Search algorithm (CPSOGSA), Sine Cosine algorithm (SCA), Particle Swarm optimization (PSO), Biogeography-Based optimization (BBO), and DE. Additionally, the performance of HGOADE is assessed against prominent winners from CEC competitions, specifically CMA-ES, LSHADEcnEpSin, and LSHADESPACMA, using the CEC-2017 test suite. Statistical analyses using the Wilcoxon Rank Sum Test and Wilcoxon Signed- Rank Test, along with the Weighted Aggregated Sum Product Assessment (WASPAS) method, confirm that HGOADE significantly outperforms existing algorithms in terms of solution quality and convergence speed. HGO

关键词： gazelle optimization algorithm Differential Evolution Exploration and exploitation Brownian motion L & eacute vy flight Engineering design optimization Weighted Aggregated Sum Product Assessment (WASPAS) method Multi-criteria decision making

来源：评论

学校读者我要写书评

暂无评论

Secure Routing in Mobile Ad Hoc Networks with Hybrid Tasmanian gazelle optimization

引用

IETE JOURNAL OF RESEARCH 2025年

作者： Anand, M. Vijay Krishnamurthy, Anand Kannan, Anusha Govindarajan, Nagappan Saveetha Engn Coll Autonomous Dept Comp Sci & Engn Thandalam Tamilnadu India Rajalakshmi Engn Coll Autonomous Dept Comp Sci & Engn Thandalam TamilNadu India Vellore Inst Technol Sch Comp Sci & Engn Chennai Tamilnadu India

In dynamic wireless networks like Mobile Ad Hoc Networks (MANETs), where nodes communicate without a fixed infrastructure, ensuring secure and efficient communication is crucial due to inherent vulnerabilities such as malicious attacks and energy constraints. To address this issue, this study introduces a novel approach that combines Tasmanian Devil optimization (TDO) and gazelle optimization algorithm (GOA), termed Hybrid Tasmanian gazelle optimization (HTGO). This approach is designed to enhance energy-efficient routing and secure communication in MANETs. The HTGO method combines the strengths of local exploration from the TDO and global exploitation from the GOA which increases the overall performance in cluster head selection. The system optimizes routing paths by considering various factors such as energy consumption, communication cost, trust, and network load. Additionally, the study integrates fuzzy logic-based trust evaluation to increase security by detecting malicious nodes during data transmission. The system is implemented and tested on a simulation platform, with performance evaluated using key metrics such as Packet Delivery Ratio (PDR), energy consumption, network lifespan, delay, Packet Loss Ratio (PLR), and detection rate of malicious nodes. Experimental results show that HTGO outperforms existing methods by achieving longer network lifetime, higher PDR, lower energy consumption, and a reduced delay. It also demonstrates superior security with a detection rate of 93% for malicious nodes, highlighting its effectiveness in both energy optimization and secure communication in MANETs. This study contributes to more secure and energy-efficient routing in MANETs, which provides an ideal solution for dynamic and vulnerable wireless network environments.

关键词： Energy-efficient routing Fuzzy logic gazelle optimization algorithm Mobile ad hoc networks Tasmanian devil optimization

来源：评论

学校读者我要写书评

暂无评论

gazelle optimization and conditional variational auto encoder for telecom user service recommendation based on churn analysis

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 267卷

作者： Haridasan, Vani Hariharanath, K. Muthukumaran, Kavitha Sri Sivasubramaniya Nadar Coll Engn Dept Management Studies Chennai Tamil Nadu India

Customer churn analysis in telecommunication industry is a very essential factor to be achieved and it makes direct impact to retaining customers and generating income. Various current approaches are utilized to enhancing the customer experience in telecommunication-network service with churn analysis. But those approaches has lots of challenges such as acquisition cost will be high within the networks and also the satisfaction level of recommending the network for the customers was not in a rapid-flow. To-overcome these concerns, Conditional Variational Auto Encoder (CVAE) is developed to enhance the customer experience in telecommunication-network by predicting the churn-customers. The text's was gathered and pre-processed using tokenization, stemming, stop word removal, spell correction, handling negation, character normalization and lemmatization. Subsequently, Contrastive information extraction with Generation Transformer(CGT) is used to extract features. Appropriate Features are chosen by using t-DSNE (t-Distributed Stochastic Neighbor Embedding). Optimal number of components are selected using GOA. Finally, CVAE is used for predicting churn customers and recommend the high priority network to the user. From the experiment analysis, the proposed approach attains an accuracy of 97.2%, a precision value of up to 94.5%, and a specificity range of 98.1% for service recommendation. Whereas accuracy of 96.45, precision of 93.5% and specificity of 96% is achieved for churn prediction. Thus, the suggested-method is the better choice for enhancing the customer experience in telecommunications-network.

关键词： Churn analysis Conditional variational auto encoder Contrastive information extraction with generative transformer t -Distributed stochastic neighbors embedding gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Deep learning based Enhanced Data Aggregation with Multi-Objective optimization method in Wireless Sensor Networks

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2025年第3期18卷 1-17页

作者： Thiyagarajan, N. Shanmugasundaram, N. KGiSL Inst Technol Dept Elect & Commun Engn Coimbatore Tamil Nadu India Sri Eshwar Coll Engn Dept Elect & Commun Engn Coimbatore Tamil Nadu India

Nowadays, Wireless Sensor Networks (WSNs) play a significant role in data collection and dissemination in various applications. In hierarchically clustered WSN models, the cluster heads (CHs) consume more energy due to the additional workload of receiving, aggregating, and transmitting data from their member nodes to the sink. The CH selection is important in extending the lifetime of WSNs by conserving energy expenditure at sensor nodes. Therefore, this paper proposes a Deep Learning based Enhanced Data Aggregation with Multi-Objective optimization method in Wireless Sensor Network. The gazelle optimization algorithm (GOA) is employed for the energy-efficient cluster-head selection with the incorporation of a well-defined fitness function constructed with intra-cluster proximity, sink proximity, and the residual energy. A single candidate optimizer (SCO) is introduced to select the most suitable routes from the CH to the sink node, considering factors such as energy and proximity. To enhance the efficiency of data aggregation (DA), a novel approach is introduced using a Self-Attention-Based Provisional Variational-Auto-Encoder Generative-Adversarial-Network (SPVAGAN). The proposed framework demonstrates its effectiveness in Energy Consumption (Ec), Packet Delivery Ratio (PDR), End-to-End Delay (E2ED), Communication Overhead (CoH), and Data Accuracy over the other models.

关键词： gazelle optimization algorithm Single Candidate Optimizer Wireless Sensor Network Cluster Head

来源：评论

学校读者我要写书评

暂无评论

AI-DeepFrothNet: Continuous monitoring and tracking of froth flotation working condition by root cause analysis and optimized predictive control

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Abouda, Khalid A. Xu, Degang Idress, Wail M. Elmaki, Hager M. Mazhar, Tehseen Aoun, Muhammad Ghadi, Yazeed Yasin Shahzad, Tariq Hamam, Habib Cent South Univ Sch Automat Changsha 410083 Hunan Peoples R China Alzaiem Alazhari Univ Fac Engn Elect Engn Dept Khartoum 13311 Sudan Omdurman Islamic Univ Dept Elect & Elect Engn Omdurman 14415 Sudan Natl Coll Business Adm & Econ Sch Comp Sci Lahore 54000 Pakistan Ghazi Univ Dept Comp Sci & IT Dera Ghazi Khan 32200 Punjab Pakistan Mir Chakra Khan Rind Univ Technol Dept Comp & IT Dera Ghazi Khan 32200 Punjab Pakistan Al Ain Univ Coll Engn Abu Dhabi 12555 U Arab Emirates COMSATS Univ Islamabad Dept Comp Sci Sahiwal Campus Sahiwal 57000 Pakistan Univ Moncton Fac Engn Moncton NB E1A3E9 Canada Univ Johannesburg Sch Elect Engn Dept Elect & Elect Engn Sci ZA-2006 Johannesburg South Africa Govt Punjab Sch Educ Dept Dept Comp Sci & Informat Technol Layyah 31200 Pakistan Bridges Acad Excellence Spectrum Tunis Tunisia Int Inst Technol & Management IITG Ave Grandes EcolesBP 1989 Libreville Gabon

Achieving optimal working conditions in froth flotation is critical for maximizing mineral recovery. Traditional manual observation methods are limited by subjectivity and the inability to adapt to changing production environments. Many existing approaches do not provide a clear picture of the flotation behavior's root cause, which directly impacts the grade recovery rate. In this study, we proposed an AI-DeepFrothNet solution to address the prevailing challenges. The proposed work utilized a Putrefaction Enrichment and Tuning Network (PETNET) to eliminate and adjust the noise in the Red, Green, and Blue (RGB) images. Using a Skipped Attention Gated Recurrent Unit (SkA-GRU) for RGB to Hyper Spectral Image (HSI) conversion ensured the preservation of the local and global features. The pre-processed frames were subjected to frame-byframe analysis using the You Look Only Once-V7 (YOLO-V7). To identify a root cause, the proposed research utilized a Multi-Agent Deep Q Learning (MA-DQL) solution, in which three agents were involved in analyzing the different conditions and properties of the froth layer. To ensure the quality and stability of the mineral outcome, the optimized controller comprehended the root cause control variables and optimized their values using the gazelle optimization algorithm (GOA) logic. The proposed work demonstrated superior performance compared to existing methods and achieved 93 % accuracy, 96 % precision, 95 % recall, and 87 % F1 score, outperforming other methods.

关键词： Ai-deepfrothnet Hyper spectral image You look only one-v7 Multi-agent deep q learning gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A bio-inspired optimal feature with convolutional GhostNet based squeeze excited deep-scale capsule network for intrusion detection

引用

COMPUTERS & SECURITY 2025年 150卷

作者： Ammannamma, Tamminina Chakravarthy, A. S. N. Jawaharlal Nehru Technol Univ Dept Comp Sci & Engn Kakinada 533003 Andhra Pradesh India

Intrusion detection plays a significant part in ensuring information security, and its primary purpose is to correctly detect multiple attacks on the network. Due to the high Internet usage, the vulnerability in the network is also increasing. The messages sent over the network are attacked by intruders, and therefore, it is necessary to identify the intrusion in the network. The proposed study introduces a bio-inspired feature selection-based technique for intrusion detection using a convolutional Ghost-Net-based deep-scale capsule network. First, inputs are collected from three different datasets: CICIDS, NBIoT, and UNSW NB15. After data collection, the data is pre-processed to improve classification accuracy. The pre-processing phase includes various phases such as data cleaning, min-max normalization, and imputation of missing values. Then, the pre-processed data is provided for the next step of feature selection to reduce the feature dimensionality problem and computational complexity. Feature selection is performed utilizing a modified gazelle optimization algorithm (Mod-GO). Finally, the network intruders are classified based on the selected characteristics using a hybridized network called Convolutional GhostNet-based Squeeze Excited Deep-Scale Capsule Network (CGN_SEDSCapsNet). Then, to improve the efficiency of the proposed classifier, the Enhanced Artificial Humming Bird (EAH) algorithm is used to optimize the parameters. Thus, the output of the network detects the intrusion. The proposed method is verified experimentally, and the performance metrics are analyzed. The simulation is performed with the Python tool. Experimental verification proves the proposed CGN_SEDSCapsNet model offers better accuracy than existing techniques.

关键词： gazelle optimization algorithm Convolutional GhostNet capsule network Intrusion Classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing beyond 5G connectivity and security: optimizing user-to-multiple AP associations with hybrid deep learning and innovative optimization techniques

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-40页

作者： Nooh, Sameer Abdullah King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Syst Jeddah 21589 Saudi Arabia

The investigation of sophisticated methods to maximize user-to-multiple access point (AP) associations has been spurred by the unwavering need for fast, dependable connectivity in Beyond 5G (B5G) networks. This paper proposed a novel approach for selecting optimal AP by combining state-of-the-art deep learning (DL) architectures such as Alex Net, ResNet50, and Darknet53 with an innovative hybrid optimization algorithm. The adaptive feature of the FOX-inspired optimization algorithm is combined with the efficiency of the standard gazelle optimization algorithm in this study. Combining these two optimization strategies guarantees a balanced trade-off between exploration and exploitation, leading to selecting APs that optimize network performance while adjusting to changing environmental conditions. This strategy not only improves connectivity but also advances wireless network evolution, establishing the way for effective and flexible B5G communication systems. The optimization of user-to-multiple AP associations in B5G networks presents a comprehensive challenge that this research attempts to handle through the smooth integration of cutting-edge optimization methods with DL approaches.

关键词： 5G connectivity User-to-multiple access point Deep learning Security DarkNet 53 gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Design tools to stabilize and to synchronize fractional-order energy resources system based on fractional-order control approaches: a review

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2025年第4期47卷 1-31页

作者： Soukkou, Ammar Soukkou, Yassine Haddad, Sofiane Lekouaghet, Badis Benghanem, Mohamed Jijel Univ Fac Sci & Technol Renewable Energy Lab Jijel 18000 Algeria Res Ctr Ind Technol CRTI Algiers 16014 Algeria Islamic Univ Madinah Fac Sci Phys Dept Madinah Saudi Arabia

In this work, a review of fractional-order calculus (F-oC), fractional-order systems (F-oSs), fractional-order chaotic and hyperchaotic systems (F-oCHSs) as a special case of F-oSs is considered. Modeling, simulation and control using the concept of F-oC, as advanced control technique, of F-oCHSs and stability analysis strategies are addressed. As a case study, the paper proposes a stable feedback control strategy based on the so called fractional-order PD controller (F-oPDC) with an adequate knowledge base for synchronization and/or stabilization a large class of F-oCHSs. The stability analysis is performed using Lyapunov stability theories and a recent stability hypothesis and assumptions of F-oSs. The 'optimal' knowledge base of the proposed F-oPDC, while meeting design requirements, is obtained based on a nature-inspired optimization method named gazelle optimization algorithm inspired from the 'gazelles' survival ability in their predator-dominated environment. Accordingly, the proposed design approach offers a good compromise between simplicity of implementation, faster convergence speed, higher tracking precision, robustness to uncertainties and energy efficiency, computational time, stability and accuracy for the case of controlling F-oCHSs. Ultimately, results of simulations are presented to illustrate both the feasibility and efficacy of the proposed strategy, by taking the fractional-order energy resources demand-supply (FoER-DS) hyperchaotic system as an example.

关键词： Fractional-order systems Fractional-order chaotic and hyperchaotic systems Lyapunov stability theory PD-based feedback control Multiobjective optimization gazelle optimization algorithm Stabilization and synchronization Energy resources demand-supply hyperchaotic system

来源：评论

学校读者我要写书评

暂无评论

Enhancing power quality in distribution networks using three-phase unified power quality conditioner (UPQC)

引用

ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY 2025年 1-23页

作者： Kumar, M. Jagadeesh Chandrasekar, P. Bhat, B. Anand Gupta, Sachin Sri Sairam Inst Technol Dept Elect & Elect Engn Chennai India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept Elect & Elect Engn Chennai India Nitte Deemed Be Univ NMAM Inst Technol Dept Elect & Elect Engn Karkala 574110 Karnataka India Lovely Profess Univ Sch Elect & Elect Engn Dept Robot & Control Phagwara Punjab India

One of the primary technical difficulties in distributed generation power systems is the problem of power quality (PQ). Furthermore, PQ has been greatly decreased in distributed generation networks due to harmonics and voltage sag compensation, which has an impact on system stability. The hybrid technique of power quality in distribution networks utilizing three-phase unified power quality conditioner is proposed in this work as a means of improving power quality in power distribution networks. The main objective of the proposed approach is to lessen voltage and current harmonics and voltage-swell and voltage-sag. The gazelle optimization algorithm is used to optimize control parameters, while the spiking deep residual network refines control strategies. Together, they enhance PQin UPQC systems by adapting to dynamic conditions, reducing power loss, and mitigating voltage instability and harmonic distortion. By then, the proposed method's performance is implemented into execution on the MATLAB platform, and it is contrasted with other existing methods. The proposed technique displays superior outcome in all approaches like salp swarm algorithm, cuckoo search algorithm, and latent semantic analysis. From the outcomes, it is concluded that the proposed method reduces the total harmonic distortion is 1(%), power loss is 82.85 KW is low and the computation time is 0.4 s it is lower than compared with other existing methods.

关键词： Active power filter unified power quality conditioner gazelle optimization algorithm Proportional integral controller Total harmonic distortion Power quality Voltage-sag Voltage-swell

来源：评论

学校读者我要写书评

暂无评论

Automatic modulation classification scheme for next-generation cellular networks using optimized adaptive multi-scale dual attention network

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2025年第3期18卷 1-18页

作者： Dinesh, G. Priya, W. Deva Shirley, C. P. Vignesh, T. SRM Inst Sci & Technol Dept Computat Intelligence Sch Comp Chennai Tamil Nadu India Saveetha Inst Med & Tech Sci SIMATS Univ Saveetha Sch Engn Dept Comp Sci & Engn Chennai Tamil Nadu India Karunya Inst Technol & Sci Dept Comp Sci & Engn Coimbatore Tamil Nadu India Panimalar Engn Coll Dept Comp Sci & Business Syst Chennai Tamil Nadu India

In the automatic modulation classification (AMC) is a major role on the appropriate detection of suspicious and unnecessary signals actions to perform complete safe communication in next-generation cellular networks. Traditional AMC schemes often struggle with the complexity and variability inherent in modern communication environments. This paper proposes a novel Automatic Modulation Classification method for Next-Generation Cellular Networks using Optimized Adaptive Multi-Scale Dual Attention Network (AMC-NGCN-AMSDAN). Initially, the input signal data are taken from HisarMod2019.1 dataset. Coherence Shock Filtering (CSF) is used to maintain various kinds of modulation systems and tunes the modulation data range. Then the spectral features are extracted by Multi-level Haar Wavelet Features Fusion Network (MHWFN). After that, Adaptive Multi-Scale Dual Attention Network (AMSDAN) is used to categorize the modulation schemes, like Analog, FSK, PAM, PSK, and QAM. Finally, the gazelle optimization algorithm (GOA) is proposed to optimize the AMSDAN weight parameter. The AMC-NGCN-AMSDAN method attains 22.75%, 25.52%, 27.22% higher accuracy and 22.25%, 27.22%, 22.32% lesser computational time compared to the existing models, like Artificial intelligence-driven real-time AMC for next-generation cellular networks (AIDRT-AMC-NGCN), Robust AMC utilizing Convolutional Deep Neural Network with Scalogram Information (AMC-CDNN-SI), and Deep Learning-dependent Robust AMC for Next-Generation Networks (DL-AMC-NGN) respectively.

关键词： Automatic modulation classification Adaptive multi-scale dual attention network Coherence shock filtering gazelle optimization 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：