检索结果-内蒙古大学图书馆

Internet of Things Enabled DDoS Attack Detection Using Pigeon Inspired Optimization algorithm with Deep Learning Approach

引用

Computers, Materials & Continua 2024年第9期80卷 4047-4064页

作者： Turki Ali Alghamdi Saud S.Alotaibi Department of Computer Science and Artificial Intelligence College of ComputingUmm Al-Qura UniversityMakkah21955Saudi Arabia

Internet of Things(IoTs)provides better solutions in various fields,namely healthcare,smart transportation,home,*** Denial of Service(DoS)outbreaks in IoT platforms is significant in certifying the accessibility and integrity of IoT *** learning(DL)models outperform in detecting complex,non-linear relationships,allowing them to effectually severe slight deviations fromnormal IoT activities that may designate a DoS *** uninterrupted observation and real-time detection actions of DL participate in accurate and rapid detection,permitting proactive reduction events to be executed,hence securing the IoT network’s safety and ***,this study presents pigeon-inspired optimization with a DL-based attack detection and classification(PIODL-ADC)approach in an IoT *** PIODL-ADC approach implements a hyperparameter-tuned DL method for Distributed Denial-of-Service(DDoS)attack detection in an IoT ***,the PIODL-ADC model utilizes Z-score normalization to scale input data into a *** handling the convolutional and adaptive behaviors of IoT,the PIODL-ADCmodel employs the pigeon-inspired optimization(PIO)method for feature selection to detect the related features,considerably enhancing the recognition’s ***,the Elman Recurrent Neural Network(ERNN)model is utilized to recognize and classify DDoS ***,reptile search algorithm(RSA)based hyperparameter tuning is employed to improve the precision and robustness of the ERNN method.A series of investigational validations is made to ensure the accomplishment of the PIODL-ADC *** experimental outcome exhibited that the PIODL-ADC method shows greater accomplishment when related to existing models,with a maximum accuracy of 99.81%.

关键词： Internet of things denial of service deep learning reptile search algorithm feature selection

来源：评论

学校读者我要写书评

暂无评论

Optimizing signal smoothing using HERS algorithm and time fractional diffusion equation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartF期238卷

作者： Jayaraj, Amutha Praba Gounder, Kuppuswamy Nallappa Rajagopal, Jeetendra Nandha Engn Coll Dept Math Erode 638052 Tamil Nadu India Kalaignar Karunanidhi Inst Technol Dept Mech Engn Coimbatore Tamil Nadu India Kongu Engn Coll Dept Math Perundurai Tamil Nadu India

Signal processing is often affected by various sources of noise that can distort or modify the signals. Removing these noises from the original signal is a crucial step in signal processing, and researchers have proposed several approaches to address this issue. However, achieving an optimized solution remains a challenge. In this study, we introduce a novel approach called the Hybrid Ebola-based reptile search (HERS) model based on Time Fractional Diffusion Equation (TFDE). The TFDE is a conventional diffusion equation used for preserving the peak smoothness of spectra signals. In our proposed technique, we consider the processing spectrum of the signal as the reference signal, which serves as the design for the diffusion equation. By applying the diffusion function, we achieve signal peak preservation and smoothing, referred to as the filtering of diffusion. One potential challenge with the time fractional order diffusion equation is its susceptibility to variations in the time step size. To address this, we employ the HERS algorithm to select an optimal time step size that enables efficient signal smoothing. To validate the effectiveness of the proposed technique, we conduct simulations and compare the results with conventional techniques such as the wavelet model, Savitzky-Golay, and regularization techniques. The per-formance evaluation confirms the superiority of our proposed HERS-TFDE approach in noise removal and signal smoothing. This research aims to contribute to the development of an optimized solution for noise removal in signal processing, leveraging the Hybrid Ebola reptile search algorithm and TFDE. The findings have the po-tential to enhance various signal-processing applications where noise reduction is critical.

关键词： Diffusion equation Spectrum signal Peal preserving smoothing signal Ebola search algorithm Diffusion filtering reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimally enhanced fractional-order cascaded integral derivative tilt controller for improved load frequency control incorporating renewable energy sources and electric vehicle

引用

SOFT COMPUTING 2023年第20期27卷 15247-15267页

作者： Raj, Utkarsh Shankar, Ravi NIT Patna Dept Elect Engn Patna India

This article discusses the intermittent nature of renewable energy sources and electric vehicles for improved load frequency control mechanism of interconnected power system. This research also looks at the impact of communication latency on system stability and sustainability. The mathematical modelling and analysis of the studied proposed system, a two-area interconnected hybrid power system, includes a thermal plant, hydro plant, and gas plant in each area. Moreover, both control areas also incorporate sporadic solar and wind power plants as well as electric vehicles for case study purposes. A novel cascade fractional-order integral-derivative and tilt controller has been designed for the analysed system. A new modified Quasi-Opposition reptile search algorithm (QORSA) is also proposed to optimise the different parameters of controller. To demonstrate its superiority, the QORSA is compared with some recent prominent meta-heuristic algorithms. Furthermore, the effectiveness and efficacy of the proposed control approach has been analysed in comparison with existing controllers as well as some other research work under diverse conditions like step and random disturbances. The comprehensive results studies show the overall better and improved dynamic performance analysis for anticipated hybrid power system. Finally, the proposed methodology is validated through real-time experimental analysis by means of Opal-RT platform for its practical feasibility.

关键词： Load frequency control Renewable energy sources Electric vehicle TID controller reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic optimization based- ensemble learners for the carbonation assessment of recycled aggregate concrete

引用

APPLIED SOFT COMPUTING 2024年 159卷

作者： Golafshani, Emadaldin Mohammadi Behnood, Ali Kim, Taehwan Ngo, Tuan Kashani, Alireza Univ New South Wales Sch Civil & Environm Engn Sydney NSW 2052 Australia Univ Mississippi Dept Civil Engn University MS 38677 USA Univ Melbourne Infrastruct Engn Dept Melbourne Vic 3010 Australia

This study addresses the enhanced prevalence of carbonation, a process accelerating steel reinforcement corrosion in recycled aggregate concrete (RAC) compared to natural aggregate concrete. Traditional carbonation depth assessment methods in RAC are noted for being labor-intensive, costly, and requiring specialized expertise. There is a noted deficiency in the application of machine learning techniques for accurately predicting carbonation depth in RAC, a gap this study aims to fill. Utilizing the extreme gradient boosting (XGBoost) technique, recognized for its efficacy in ensemble machine learning, this study innovates in modeling carbonation depth in RAC. It emphasizes the criticality of hyperparameter optimization of the XGBoost algorithm for maximizing model accuracy. To achieve this, three novel metaheuristic optimization algorithms, including reptile search algorithm (RSA), Aquila optimizer (AO), and arithmetic optimization algorithm (AOA), were introduced as global optimizers for tunning the XGBoost hyperparameters. The study was underpinned by a comprehensive database compiled from extensive literature, facilitating the development of an accurate RAC carbonation depth model. Through rigorous evaluations, including sensitivity analyses, the Wilcoxon signed-rank test, and runtime comparisons, the synthesized models demonstrated exceptional accuracy, with coefficients of determination exceeding 0.95. The XGBoost-AO algorithm, in particular, showcased superior performance, with the XGBoost-RSA algorithm providing efficient predictions considering runtime. SHapley Additive exPlanations (SHAP) interpretation highlighted environmental conditions as significant carbonation depth influencers. A userfriendly graphical user interface was developed, enhancing the practical utility of the findings for predicting carbonation depth progression in RAC over time. This research significantly advances the predictive accuracy for carbonation depth in RAC, contributing to the

关键词： Recycled aggregate concrete Carbonation depth XGboost ensemble technique Equilibrium optimizer Arithmetic optimization algorithm reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting

引用

ARTIFICIAL INTELLIGENCE REVIEW 2024年第3期57卷 45-45页

作者： Pavlov-Kagadejev, Marijana Jovanovic, Luka Bacanin, Nebojsa Deveci, Muhammet Zivkovic, Miodrag Tuba, Milan Strumberger, Ivana Pedrycz, Witold Min & Met Inst Bor Zeleni Bulevar 35 Bor 19210 Serbia Singidunum Univ Tech Fac Danijelova 32 Belgrade 11000 Serbia Singidunum Univ Fac Informat & Comp Danijelova 32 Belgrade 11000 Serbia Natl Def Univ Turkish Naval Acad Dept Ind Engn TR-34942 Tuzla Istanbul Turkiye Univ Coll London UCL Bartlett Sch Sustainable Construct London WC1E 6BT England Lebanese Amer Univ Dept Elect & Comp Engn Byblos Lebanon Univ Alberta Fac Engn Dept Elect & Comp Engn 9211 116St NW Edmonton AB T6G 1H9 Canada Polish Acad Sci Syst Res Inst Warsaw Poland Istinye Univ Fac Engn & Nat Sci Dept Comp Engn Istanbul Turkiye

Power supply from renewable energy is an important part of modern power grids. Robust methods for predicting production are required to balance production and demand to avoid losses. This study proposed an approach that incorporates signal decomposition techniques with Long Short-Term Memory (LSTM) neural networks tuned via a modified metaheuristic algorithm used for wind power generation forecasting. LSTM networks perform notably well when addressing time-series prediction, and further hyperparameter tuning by a modified version of the reptile search algorithm (RSA) can help improve performance. The modified RSA was first evaluated against standard CEC2019 benchmark instances before being applied to the practical challenge. The proposed tuned LSTM model has been tested against two wind production datasets with hourly resolutions. The predictions were executed without and with decomposition for one, two, and three steps ahead. Simulation outcomes have been compared to LSTM networks tuned by other cutting-edge metaheuristics. It was observed that the introduced methodology notably exceed other contenders, as was later confirmed by the statistical analysis. Finally, this study also provides interpretations of the best-performing models on both observed datasets, accompanied by the analysis of the importance and impact each feature has on the predictions.

关键词： Long short-term memory networks Metaheuristics optimization reptile search algorithm Shapley additive explanations Wind power generation

来源：评论

学校读者我要写书评

暂无评论

Securing Consumer Electronics Devices: A Blockchain-Based Access Management Approach Enhanced by Deep Learning Threat Modeling for IoT Ecosystems

引用

IEEE ACCESS 2024年 12卷 110671-110680页

作者： Asiri, Mashael M. Alfraihi, Hessa Said, Yahia Othman, Kamal M. Salama, Ahmed S. Marzouk, Radwa King Khalid Univ Appl Coll Mahayil Dept Comp Sci Abha 61421 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia Northern Border Univ Coll Engn Dept Elect Engn Ar Ar 91431 Saudi Arabia Umm Al Qura Univ Coll Engn & Islamic Architecture Dept Elect Engn Mecca 24211 Saudi Arabia Future Univ Egypt Fac Engn & Technol Dept Elect Engn New Cairo 11845 Egypt

Securing user electronics devices has become a significant concern in the digital period, and a forward-thinking solution covers the fusion of blockchain (BC) technology and deep learning (DL) methods. Blockchain improves device safety by transforming access management, storing credentials on a tamper-resistant ledger, mitigating the risk of unauthorized access and giving a robust defence against malevolent actors. Integrating DL into this framework also raises safety measures, as it permits devices to inspect and regulate to develop attacks distinctly. DL models accurately recognize intricate designs and anomalies, allowing the technique to distinguish and threaten possible attacks in real time. The fusion of BC and DL not only improves the reliability of user electronics but also establishes a dynamic and adaptive safety system, enhancing consumer confidence in the safety of their devices. Therefore, this study presents a BC-Based Access Management with DL Threat Modeling (BCAM-DLTM) technique for securing consumer electronics devices in the IoT ecosystems. The BCAM-DLTM technique mainly follows a two-phase procedure: access management and threat detection. Moreover, BC technology can be applied to the access management of consumer electronics devices. Besides, the BCAM-DLTM technique applies a deep belief networks (DBNs) model for proficiently identifying threats. To enhance the recognition results of the DBN model, the hyperparameter tuning procedure uses the reptile search algorithm (RSA). The experimental outcome study of the BCAM-DLTM approach employs the NSLKDD dataset. The comprehensive results of the BCAM-DLTM approach portrayed a superior accuracy outcome of 99.63% over existing models in terms of distinct metrics.

关键词： Biological system modeling Safety Consumer electronics Internet of Things Computational modeling Threat modeling Ecosystems Blockchains Deep learning search methods Evidence theory Blockchain deep learning reptile search algorithm deep belief network

来源：评论

学校读者我要写书评

暂无评论

An evolutionary algorithm-based approach for efficient design of Wiener spline non-linear adaptive filter and its experimental validation

引用

EVOLVING SYSTEMS 2024年第6期15卷 2111-2134页

作者： Janjanam, Lakshminarayana Saha, Suman Kumar Kar, Rajib Sasi Inst Technol & Engn Dept Elect & Commun Engn Tadepalligudem 534101 Andhra Pradesh India Natl Inst Technol Dept Elect & Commun Engn Raipur 492010 Chhattisgarh India Natl Inst Technol Dept Elect & Commun Engn Durgapur 713209 West Bengal India

Wiener spline adaptive filters (WSAFs) are newly proposed non-linear adaptive filters consisting of a linear filter that is succeeded by the non-linear spline network. Recently, the WSAFs have efficiently been modelled for non-linear practical systems with computational complexity using advanced versions of least mean square algorithms. However, the existing WSAFs fail to mitigate the noise effectively when the systems are highly non-linear. Moreover, they furnish poor estimates with slow convergence, and the exactness of results relies on the decent setting of some initial state parameters such as bounds of learning rates, filter selection, nonlinearity selection, etc. In this work, an evolutionary algorithm (EA) is employed to design WSAF while conquering the above issues successfully. In this technique, the EA simultaneously updates linear filter coefficients and the control points of the spline function by using the well-formulated cost function. As a result, further enhancement is guaranteed in estimation accuracy, convergence quality, steady-state accuracy and filter stability compared to other reported works. This work simulates several benchmark WSAFs using an efficient newly developed EA called reptile search algorithm (RSA). As compared with other employed state-of-the-art algorithms, the mean squared deviation (MSD) between the real and estimated parameters and the output mean squared error (MSE) metric results of the proposed RSA-based WSAF are as low as 1.01E-07 and 2.07E-08, respectively, and also the quality of fitness (QF) is 99.79%. Moreover, the significant MSE results of -52.47 dB and -47.77 dB, respectively, are achieved through the proposed RSA-based WSAF design for practical plants such as liquid-saturated heat exchangers (LSHE) and cascade tanks. Further, the corresponding proposed model is also implemented on the TMS320C6713 digital signal processor hardware to verify the feasibility of the proposed scheme in the real-time scenario.

关键词： Wiener spline adaptive filter Non-linear system identification reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing transient response performance of automatic voltage regulator system by using a novel control design strategy

引用

ELECTRICAL ENGINEERING 2023年第4期105卷 1993-2005页

作者： Can, Oezay Andic, Cenk Ekinci, Serdar Izci, Davut Recep Tayyip Erdogan Univ Dept Elect & Automat Rize Turkiye Istanbul Tech Univ Dept Elect Engn Istanbul Turkiye Batman Univ Dept Comp Engn Batman Turkiye Middle East Univ MEU Res Unit Amman Jordan

The terminal voltage of the synchronous generator must be kept between determined values by a closed-loop control system called automatic voltage regulator (AVR). To enhance the performance of the AVR system, this study introduces a new type of controller design. In this context, a novel controller named fractional order (FO) proportional-integral-derivative plus second-order derivative (FOPIDD2) has been proposed for the first time, and an optimization method known as the reptile search algorithm (RSA) has been utilized in order to tune the six parameters of FOPIDD2 controller. The performance of the proposed RSA-FOPIDD2 controller is compared with twenty-two studies employing a variety of controllers such as PID, PIDA, FOPID, and PIDD2 and published within the last three years. The results of the comparison show that the proposed controller provides improved performance for the AVR system when compared to other methods.

关键词： reptile search algorithm Automatic voltage regulator Optimization Controller design

来源：评论

学校读者我要写书评

暂无评论

Parameter Extraction of Photovoltaic Cells and Modules by INFO algorithm

引用

IEEE ACCESS 2022年 10卷 87022-87052页

作者： Demirtas, Mehmet Koc, Kezban Gazi Univ Fac Technol Dept Elect & Elect Engn TR-06560 Ankara Turkey

This study presents the extraction of unknown parameters of various photovoltaic (PV) cells and modules by using the weighted mean of vectors (INFO) algorithm. The parameter estimation of PV cells and modules is one of the most important issues in the design of effective PV power systems. Since the PV parameters are highly nonlinear and complex in nature, the estimation of these parameters also becomes a challenging optimization problem for designers. The main challenge is to obtain the most accurate estimation. In order to solve the problem in a unique way, the state-of-the-art metaheuristic algorithms that have not been tried so far in parameter extraction are chosen. The selected ones are the INFO optimization algorithm, the artificial hummingbird algorithm (AHA), the artificial ecosystem-based optimization (AEO) algorithm, the runge kutta (RUN) optimizer, and lastly the reptile search algorithm (RSA). The motivation here is to test as many algorithms as possible to reach to the most accurate solution. In addition, the gray wolf optimizer (GWO), the frequently used one in literature due to its superiority in parameter extraction applications, is selected to validate the results of the evaluated algorithms through comparison against the GWO. Moreover, the performances of these algorithms are compared with evaluation metrics consisting of minimum, mean, maximum, standard deviation, and statistical tests using Wilcoxon signed-rank test and Friedman test. At the end of the study, it is demonstrated that the INFO, statistically, produces the highest accuracy and reliable results. Due to its statistical success compared to other algorithms, the INFO is used to extract the parameters of a commercially available PV cells and modules. It is clearly shown that the parameters extracted by the INFO closely match the parameters provided by the manufacturer's datasheet, which points out the superiority of the INFO algorithm in PV modeling.

关键词： Optimization Integrated circuit modeling Adaptation models Computational complexity Sociology Parameter extraction Resistance Ecosystems Artificial ecosystem-based optimization algorithm artificial hummingbird algorithm diode model Friedman test grey wolf optimizer parameter extraction reptile search algorithm runge kutta optimizer weighted mean of vectors Wilcoxon signed rank test

来源：评论

学校读者我要写书评

暂无评论

Enhancing Online Food Service User Experience Through Advanced Analytics and Hybrid Deep Learning for Comprehensive Evaluation

引用

IEEE ACCESS 2024年 12卷 70999-71009页

作者： Alshahrani, Hussain Mengash, Hanan Abdullah Maashi, Mashael Kouki, Fadoua Mahmud, Ahmed Al Duhayyim, Mesfer Shaqra Univ Coll Comp & Informat Technol Dept Comp Sci Shaqra 111111 Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci POB 84428 Riyadh 11671 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Dept Software Engn Riyadh 11543 Saudi Arabia King Khalid Univ Appl Coll Muhail Aseer Dept Financial & Banking Sci Abha 61413 Saudi Arabia Future Univ Egypt Res Ctr New Cairo 11835 Egypt Prince Sattam Bin Abdulaziz Univ Coll Comp Engn & Sci Dept Comp Sci Al Kharj 16273 Saudi Arabia

User experience (UX) analysis of Online Food Delivery Services (OFDS) involves features like order placement efficacy, delivery tracking reliability, ease of navigation, menu visibility, and payment process simplicity. By examining these factors, OFDS offers can optimize its platforms to improve user satisfaction, streamline ordering procedures, minimize friction points, and improve customer retention. We can gain valued visions into customer opinions and preferences by connecting sentiment analysis, recommendation systems, feature extractors, and XAI platforms. Then, this information can be employed to develop the superiority of service, personalize UX, and finally develop customer fulfilment and platform victory. This paper presents a reptile search algorithm with a Hybrid DL-based UX Detection (RSAHDL-UXD) approach on OFDSs. The RSAHDL-UXD approach utilizes data preprocessing and a word2vec-based word embedding process. For UX recognition, sliced multi-head self-attention slice recurrent neural network (SMH-SASRNN) methodology is employed. Finally, the hyperparameter tuning procedure was executed using RSA. To validate the upgraded performance of the RSAHDL-UXD methodology, a wide array of models was executed on manifold online food services datasets. The experimental outcomes stated that the RSAHDL-UXD model highlighted the superior accuracy of 98.57% and 93.33% on the Swiggy and Zomato datasets, respectively.

关键词： Online food delivery services deep learning artificial intelligence reptile search algorithm hyperparameter tuning

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：