检索结果-内蒙古大学图书馆

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

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

Novel distance-fitness learning scheme for ameliorating metaheuristic optimization

引用

ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 2025年 65卷

作者： Celik, Emre Houssein, Essam H. Abdel-Salam, Mahmoud Oliva, Diego Tejani, Ghanshyam G. Ozturk, Nihat Sharma, Sunil Kumar Baljon, Mohammed Duzce Univ Engn Fac Dept Elect & Elect Engn Duzce Turkiye Minia Univ Fac Comp & Informat Dept Comp Sci Al Minya Egypt Mansoura Univ Fac Comp & Informat Sci Mansoura 35516 Egypt Univ Guadalajara Dept Ingn Electrofoton Guadalajara Jalisco Mexico Saveetha Univ Saveetha Dent Coll & Hosp Saveetha Inst Med & Tech Sci Dept Res Analyt Chennai 600077 India Yuan Ze Univ Dept Ind Engn & Management Taoyuan 320315 Taiwan Gazi Univ Technol Fac Dept Elect & Elect Engn Ankara Turkiye Majmaah Univ Coll Comp & Informat Sci Dept Informat Syst Majmaah 11952 Saudi Arabia Majmaah Univ Coll Comp & Informat Sci Dept Comp Engn Majmaah 11952 Saudi Arabia Minia Natl Univ Al Minya Egypt

An important portion of metaheuristic algorithms is guided by the fittest solution obtained so far. searching around the fittest solution is beneficial for speeding up convergence, but it is detrimental considering local minima stagnation and premature convergence. A novel distance-fitness learning (DFL) scheme that provides better searchability and greater diversity is proposed to resolve these. The method allows search agents in the population to actively learn from the fittest solution, the worst solution, and an optimum distance-fitness (ODF) candidate. This way, it aims at approaching both the fittest solution and ODF candidate while at the same time moving away from the worst solution. The effectiveness of our proposal is evaluated by integrating it with the reptile search algorithm (RSA), which is an interesting algorithm that is simple to code but suffers from stagnating in local minima, converging too early, and a lack of sufficient global searchability. Empirical results from solving 23 standard benchmark functions, 10 Congresses on Evolutionary Computation (CEC) 2020 test functions, and 2 real-world engineering problems reveal that DFL boosts the capability of RSA significantly. Further, the comparison of DFL-RSA with popular algorithms vividly signifies the potential and superiority of the method over most of the problems in terms of solution precision.

关键词： Metaheuristic reptile search algorithm Distance-fitness learning Global optimization

来源：评论

学校读者我要写书评

暂无评论

Estimating the pile-bearing capacity utilizing a reliable machine-learning approach

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2025年第4期8卷 1-32页

作者： Hu, Juan Xia, Cunjing Wu, Jiahong Dong, Fenghui Zhejiang Shuren Univ Sch Urban Construct Hangzhou 310015 Zhejiang Peoples R China Shandong Univ Jinan 250100 Shandong Peoples R China Design & Res Inst Grp Co Ltd Guangdong Transportat Planning Guangzhou 510507 Peoples R China Nanjing Forestry Univ Coll Civil Engn Nanjing 210037 Peoples R China

Accurately estimating Pile Bearing Capacity (PBC) is crucial for safe, economical pile foundation construction, ensuring optimal material use and enhanced structural integrity. The study focuses on developing a framework using the Multi-Layer Perceptron (MLP) model to predict PBC. MLP is selected for its effectiveness in modeling complex, non-linear data links. To enhance the MLP's performance, two optimization algorithms, African Vulture Optimization (AVO) and reptile search algorithm (RSA), are integrated. These algorithms are selected for their ability to balance exploration and exploitation, helping the MLP avoid local minima and achieve global optima in complex optimization tasks. The proposed AI models achieved remarkable accuracy, with the MLPS2 (MLP + RSA in the second layer of MLP) and MLAV2 (MLP + AVO in the second layer of MLP) models attaining substantial Coefficient of Determination (R2) values of 0.995 and 0.988, alternatively. The MLPS2 model also obtained Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values of 126.70 KN and 102.80 KN, respectively. The MLAV2 model was demonstrated as the second-best model among the proposed frameworks, with an RMSE value of 203.04 KN. The developed AI predictive frameworks based on MLP and hybrid optimization techniques effectively enhance PBC estimations, paving the way for improved pile design and optimization.

关键词： Pile Pile bearing capacity Multilayer perceptron African Vulture Optimization reptile search algorithm

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

A comparative analysis of algorithms on concrete at elevated temperatures

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第6期7卷 6191-6205页

作者： Duan, Min Chongqing Coll Finance & Econ Coll Design Chongqing 402160 Peoples R China

Elevated temperatures have a substantial influence on the properties of the materials used in concrete manufacturing, leading to a noticeable decrease in the strength properties of the concrete. Attaining the intended compressive strength of concrete is a demanding and time-consuming pursuit. However, the use of supervised machine learning methods allows for an accurate initial prediction of the intended result. This work demonstrates the utilization of multi-layered perceptron (MLP), support vector regression (SVR), and least squared SVR (LSSVR) for predicting the compressive strength of concrete at elevated temperatures. The prediction models were enhanced by using the reptile search algorithm (RSA) and were trained on a dataset consisting of 207 data points. The investigation included a collection of nine input variables, namely water, cement, coarse aggregate, fine aggregate, fly ash, superplasticizers, silica fume, nano silica, and temperature. The results indicate that all the LSSR, SVRR and MLPR show great potential in accurately predicting the fc of concrete at elevated temperatures with acceptable values of the R2. Regarding the values related to the error-based metrics, the lowest values belonged to the LSSR model with a decline of about 50% with respect to the SVRR and MLPR networks. Turning to uncertainty analysis, it was obvious that in all three training, validating, and testing phases, MLPR resulted in the highest values of uncertainty, compared to SVRR. On the other hand, the most reliable model called LSSR introduced the smallest values of uncertainty at 6.028, 5.98, and 6.52, respectively, which depicted remarkable accuracy and dependability.

关键词： Concrete Elevated temperature Mechanical properties Estimation reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Elevating Student Performance Prediction using Extra-Trees Classifier and Meta-Heuristic Optimization algorithms

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第2期15卷 434-450页

作者： Li, Yangbo He, Mengfan Henan Inst Technol Dept Comp Sci & Technol Xinxiang 453003 Henan Peoples R China Henan Inst Technol Off President Xinxiang 453003 Henan Peoples R China

In the highly competitive landscape of academia, the study addresses the multifaceted challenge of analyzing voluminous and diverse educational datasets through the application of machine learning, specifically emphasizing dimensionality reduction techniques. This sophisticated approach facilitates educators in making data-informed decisions, providing timely guidance for targeted academic improvement, and enhancing the overall educational experience by stratifying individuals based on their innate aptitudes and mitigating failure rates. To fortify predictive capabilities, the study employs the robust Extra-Trees Classifier (ETC) model for classification tasks. This model is enhanced by integrating the Gorilla Troops Optimizer (GTO) and reptile search algorithm (RSA), cutting-edge optimization algorithms designed to refine decision-making processes and improve predictive precision. This strategic amalgamation underscores the research's commitment to leveraging advanced machine learning and bio-inspired algorithms to achieve more accurate and resilient student performance predictions in the mathematics course, ultimately aiming to elevate educational outcomes. Analyses of G1 and G3 showcase the efficacy of the ETRS model, demonstrating 97.5% Accuracy, F1-Score, and Recall in predicting the G1 values. Similarly, the ETRS model emerges as the premier predictor for G3, attaining 95.3% Accuracy, Recall, and F1-Score, respectively. These outcomes underscore the significant contributions of the proposed models in advancing precision and discernment in student performance prediction, aligning with the overarching goal of refining educational outcomes.

关键词： Student performance mathematics machine learning Extra-Trees Classifier Gorilla Troops Optimizer reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Research and application of a novel selective stacking ensemble model based on error compensation and parameter optimization for AQI prediction

引用

ENVIRONMENTAL REsearch 2024年 247卷 118176页

作者： Peng, Tian Xiong, Jinlin Sun, Kai Qian, Shijie Tao, Zihan Nazir, Muhammad Shahzad Zhang, Chu Huaiyin Inst Technol Fac Automat Huaian 223003 Peoples R China Huaiyin Inst Technol Jiangsu Permanent Magnet Motor Engn Res Ctr Huaian 223003 Peoples R China

With the ongoing process of industrialization, the issue of declining air quality is increasingly becoming a critical concern. Accurate prediction of the Air Quality Index (AQI), considered as an all-inclusive measure representing the extent of pollutants present in the atmosphere, is of paramount importance. This study introduces a novel methodology that combines stacking ensemble and error correction to improve AQI prediction. Additionally, the reptile search algorithm (RSA) is employed for optimizing model parameters. In this study, four distinct regional AQI data containing a collection of 34864 data samples are collected. Initially, we perform cross -validation on ten commonly used single models to obtain prediction results. Then, based on evaluation indices, five models are selected for ensemble. The results of the study show that the model proposed in this paper achieves an improvement of around 10% in terms of accuracy when compared to the conventional model. Thus, the model introduced in this study offers a more scientifically grounded approach in tackling air pollution.

关键词： Air pollution Stacking ensemble model Error correction reptile search 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：