检索结果-内蒙古大学图书馆

Harnessing variable reduction approach with deep recurrent neural network for student's academic performance analysis

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 118卷 393-405页

作者： Katib, Iyad Ragab, Mahmoud King Abdulaziz Univ Fac Comp & Informat Technol Jeddah 21589 Saudi Arabia

Predicting student performance aids the educational stakeholders in making interventions and taking proactive decisions for developing education quality and addressing the ever-evolving demands of society. Deep learning (DL) methods, particularly recurrent neural networks (RNN) and convolutional neural networks (CNN) have shown great potential in predicting student performance based on different factors like study habits, attendance, and past academic records. These models can learn complex patterns and relationships by processing large datasets, enabling accurate prediction of future educational outcomes. This predictive ability could help educators intervene early and offer targeted support for the student at risk of underperforming, eventually enhancing the overall academic success rate. Simultaneously, the feature selection (FS) for predicting student performance assists in establishing strategic plans for the educational performance enhancement of students and plays a vital role in improving predictive accuracy. There are many FS techniques for predicting student performance, but the study shows several merits and demerits of existing FS techniques in selecting optimum features. This article develops a new variable reduction with an optimal deep recurrent neural network (VR-ODRNN) approach for student performance and course outcome analysis. The VR-ODRNN model aims to examine the student data to identify course grades obtained by the students. Primarily, min-max normalization is used to scale the input data uniformly. For variable reduction, the VR-ODRNN model utilizes a coot optimization algorithm (COA) to choose an optimal subset of features. Besides, the student's performance is predicted by using the DRNN. Finally, the hyperparameter selection of the DRNN approach is performed by employing the Dwarf Mongoose Gannet optimization algorithm (DMGOA). The simulation analysis of the VR-ODRNN model is examined using the student performance dataset from the Kaggle

关键词： Educational Data Mining coot optimization algorithm Feature Selection Student Performance Hyperparameter Selection

来源：评论

学校读者我要写书评

暂无评论

An innovative interval grey model for construction waste forecasting

引用

APPLIED MATHEMATICAL MODELLING 2024年 126卷 22-51页

作者： Xu, Yan Lin, Tong Du, Pei Wang, Jianzhou Ocean Univ China Sch Math Sci Qingdao 266100 Peoples R China Jiangnan Univ Sch Business Wuxi 214122 Peoples R China Dongbei Univ Finance & Econ Qingdao Financial Res Inst Qingdao 266100 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China Jiangnan Univ Food Safety Res Base Jiangsu Prov Wuxi 214122 Peoples R China

Nowadays, construction waste has become a global challenge that needs to be addressed, and its accurate prediction is crucial for subsequent treatment and policy development. However, current popular big data methods struggle to be effectively applied due to sample size limits. Meanwhile, the key issues of data uncertainty and time-delayed nature must be considered, the former of which can be addressed by interval prediction. Therefore, a novel interval time-delayed threeparameter discrete grey model for construction waste prediction is proposed in this study, whose time-delayed coefficient is optimized via optimization algorithms. Moreover, the relevant mathematical derivation and proof of this model are also described and discussed in detail in the research. Two case studies of the construction waste dataset are used to examine the effectiveness of the proposed model. Through a series of comparisons with other state-of-the-art models, the results show that the proposed model can improve the prediction performance with excellent prediction results. Meanwhile, this study also presents scenario analysis and discussions of the construction waste prediction results during the 14th Five-Year Plan period, and finds that the current policies and measures are difficult to achieve the future planning goals, and further policy development and implementation of measures are imminent.

关键词： construction waste forecasting interval grey models coot optimization algorithm scenario analysis

来源：评论

学校读者我要写书评

暂无评论

Design of an Iterative Dual Metaheuristic VARMAx Model Enhancing Efficiency of Time Series Predictions

引用

IEEE ACCESS 2024年 12卷 128071-128084页

作者： Boddu, Yuvaraja Manimaran, A. Arunkumar, B. Ramkumar, D. VIT AP Univ Sch Adv Sci Dept Math Amaravati 522237 Andhra Pradesh India VIT AP Univ Sch Comp Sci & Engn Amaravati 522237 Andhra Pradesh India

Traditional methods, while effective to a degree, often grapple with limitations such as reduced accuracy, specificity, and higher prediction delays, particularly in high-stakes fields like stock market analysis, forest cover monitoring, and medical disease prediction. To address these shortcomings, this study introduces an innovative approach: the design of an iterative dual metaheuristic VARMAx (Vector Autoregressive Moving Average with exogenous inputs) model. This model leverages the robustness of Grey Wolf Optimizer (GWO) to enhance the Vector Autoregressive (VAR) component and employs the coot optimization algorithm to optimize the Moving Average (MA) aspect of the VARMAx process. The rationale behind selecting these specific metaheuristic algorithms lies in their proven efficiency in exploring and exploiting the solution space, which is crucial for achieving accurate time series predictions. The proposed model demonstrates a significant leap in performance metrics when tested across various datasets encompassing stock market trends, forest cover changes, and medical disease forecasts. Compared to existing methodologies, the iterative dual metaheuristic VARMAx model exhibits a 2.9% increase in prediction precision when compared with Fuzzy C Means (FCM), and Empirical Mode Decomposition (EMD) Methods, a 3.5% rise in accuracy when compared with Variational Model Decomposition (VMD) & EMD Methods, a 2.5% improvement in recall when compared with VMD & FCM, a 3.2% enhancement in the Area Under the Curve (AUC), and a notable 3.4% boost in specificity when compared with VMD, FCM & EMD Methods. Moreover, it significantly reduces the delay in predictions by 4.9%. These metrics not only underscore the model's efficacy but also highlight its potential in delivering timely and reliable forecasts, which are critical in decision-making processes. The models ability also verified with two statistical tests called Model confidence set and Diebold Mariano test procedures at 5%

关键词： Predictive models Autoregressive processes Metaheuristics Time series analysis Accuracy Prediction algorithms Forecasting optimization methods Time series prediction metaheuristic algorithms VARMAx model grey wolf optimizer coot optimization algorithm scenarios

来源：评论

学校读者我要写书评

暂无评论

Developing a machine learning-based model using optimization algorithms to estimate the released synthetic gas and solid yield in the gasification process

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2025年第6期8卷 1-20页

作者： Wang, Xiaohe Changchun Coll Elect Technol Dept Gen Educ Changchun 130114 Jilin Peoples R China

Gasification is an important procedure because it efficiently transforms a variety of carbon-containing substances like coal, biomass, and waste into valuable products such as syngas, hydrogen, and synthetic fuels. The effectiveness of the gasification procedure relies on important factors that need to be taken into account. Thus, in the present study, a machine learning (ML) technique was used based on initial data from 312 experiments in order to predict the production rate of raw gases and solids in the gasification process. Over the modeling stage, as the novelty of the research, metaheuristic optimization algorithms as successors were coupled to the Decision Tree (DT) as the main model to tune the performance of the model, leading to simulate gasification efficiently compared to the single model. Raw gases and solids generated at the end of gasification depend on various factors, including input materials and thermodynamic parameters, e.g., temperature. By applying the developed hybrid models with optimizers coot optimization algorithm (COA) and Gradient-based optimizer (GBO), it becomes feasible to create a framework quantifying the influence of the variables on the production of gases and solids. Several assessing criteria were employed to evaluate the performance of developed models. By investigating the results of modeling, hybrid models were found at a higher level of modeling in terms of coefficient of determination with the average calculated R2 of around 98%, while for a single model of 96%. Generally, the developing approach of the bare single AI-based models can be used to simulate thermodynamic operations to give experts more understanding of processes working efficiently.

关键词： Gasification process Biomass Energy production Biochar yield Decision tree coot optimization algorithm Gradient-based optimizer

来源：评论

学校读者我要写书评

暂无评论

Enhancing prediction of elemental composition through machine learning decision tree models for biomass gasification optimization

引用

CHEMICAL PRODUCT AND PROCESS MODELING 2024年第5期19卷 737-760页

作者： Xu, Peng Zhang, Jidong Zhengzhou Coll Finance & Econ Sch Informat Engn Zhengzhou 450054 Henan Peoples R China

The worldwide transition to cleaner, sustainable energy sources, prompted by population growth and industrialization, responds to uncertain fossil fuel prices and environmental concerns, highlighting the substantial benefits of renewable energy in reducing greenhouse gas emissions and addressing climate change. Derived from non-fossilized organic materials, biomass emerges as a significant and sustainable contributor to renewable energy. Its diverse nature is complemented by a range of conversion technologies, encompassing combustion, pyrolysis, gasification, and liquefaction, providing versatile avenues for biomass energy transformation. Gasification, the transformative process of converting organic matter into combustible gases under controlled oxygen levels, is accomplished through direct oxygen supply or pyrolysis. This method yields a dependable gaseous fuel versatile for heating, industrial processes, power generation, and liquid fuel production. Machine learning employs advanced statistical techniques for modeling across diverse industries, showcasing particular efficacy in optimizing thermochemical processes by precisely identifying the optimal operating conditions required for achieving desired product properties. These models utilize proximate biomass data to predict the elemental compositions of N2 and H2. Assessment of both single and two hybrid models indicated that the introduced optimizers significantly enhanced the estimation of N2 and H2 when combined with Decision Tree (DT), with Decision Tree Coupled with Artificial Hummingbird algorithm (DTAH) proving particularly effective. Notably, DTAH demonstrated outstanding performance with remarkable R2 values of 0.990 for N2 and 0.992 for H2. Additionally, the minimal Root Mean Square Error (RMSE) values of 1.291 and 1.550 for N2 and H2 predictions respectively underscore the precision of DTAH, establishing it as a suitable choice for practical real-world applications.

关键词： machine learning biomass gasification decision tree coot optimization algorithm Artificial Hummingbird algorithm

来源：评论

学校读者我要写书评

暂无评论

Discussion on adaptive neuro-fuzzy inference system-based models for predicting ultimate bearing capacity of rock-socketed piles

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第6期7卷 5743-5757页

作者： Cai, Fan Hubei Univ Technol Sch Civil Engn Architecture & Environm Wuhan 430068 Hubei Peoples R China

The ultimate bearing capacity (Qu\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${Q}_{u}$$\end{document}) of rock-socketed piles is determined by the combined end-bearing resistance at side resistance and the pile tip along the pile shaft. This research innovatively addresses the complex challenge of assessing pile tip-bearing capacity in rock formations, a task that traditionally relies on intricate numerical models often inaccessible for routine engineering. By establishing an Adaptive Neuro-Fuzzy Inference System (ANFIS) model and hybrid models incorporating the Flying Fox Optimizer (FFO) and coot optimization algorithm (COA), this study offers a novel approach to accurately calculating the Qu\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${Q}_{u}$$\end{document} of rock-socketed piles, making the process more efficient and practical for engineers. According to similar research, a number of factors were chosen as inputs to combine the impacts of soil and rock layers, including Uniaxial compressive strength of pile (UCS), total length (p\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p$$\end{document}) to diameter (D), the length of the soil layer (Ls\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${L}_{s}$$\end{document}) to socket length (Lr\documen

关键词： Ultimate bearing capacity Rock-socketed piles Adaptive neuro-fuzzy inference systems Flying fox optimizer coot optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Applying machine learning for biomass gasification prediction: enhancing efficiency and sustainability

引用

CHEMICAL PRODUCT AND PROCESS MODELING 2024年第5期19卷 713-735页

作者： Tai, Chang Xiong, Shasha Henan Mech & Elect Vocat Coll Zhengzhou 451191 Peoples R China

In the contemporary era, marked by the increasing significance of sustainable energy sources, biomass gasification emerges as a highly promising technology for converting organic materials into valuable fuel, offering an environmentally friendly approach that not only mitigates waste but also addresses the growing energy demands. However, the effectiveness of biomass gasification is intricately tied to its predictability and efficiency, presenting a substantial challenge in achieving optimal operational parameters for this complex process. It is at this precise juncture that machine learning assumes a pivotal role, initiating a transformative paradigm shift in the approach to biomass gasification. This article delves into the convergence of machine learning and the prediction of biomass gasification and introduces two innovative hybrid models that amalgamate the Support Vector Regression (SVR) algorithm with coot optimization algorithm (COA) and Walrus optimization algorithm (WaOA). These models harness nearby biomass data to forecast the elemental compositions of CH4 and C2Hn, thereby enhancing the precision and practicality of biomass gasification predictions, offering potential solutions to the intricate challenges within the domain. The SVWO model (SVR optimized with WaOA) is an effective tool for predicting these elemental compositions. SVWO exhibited outstanding performance with notable R2 values of 0.992 for CH4 and 0.994 for C2Hn, emphasizing its exceptional accuracy. Additionally, the minimal RMSE values of 0.317 for CH4 and 0.136 for C2Hn underscore the precision of SVWO. This accuracy in SVWO's predictions affirms its suitability for practical, real-world applications.

关键词： gasification biomass support vector regression coot optimization algorithm Walrus optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimation of pile-bearing capacity applying hybrid auto-regressed models based on regression decision tree

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第3期7卷 2225-2239页

作者： Li, Yunpeng Dong, Shenghuan Jian, Yingbin Mei, Yuqian Shijiazhuang Railway Vocat & Tech Coll Acad Affairs Off Shijiazhuang 050062 Peoples R China Shijiazhuang Railway Tech Coll Integrat Ctr Sci & Technol Ind & Educ Shijiazhuang 050062 Peoples R China Shijiazhuang Railway Vocat & Tech Coll Personnel Dept Shijiazhuang 050062 Peoples R China

The utilization of machine learning (ML) approaches for predicting pile bearing capacity (PBC) has been a focal point in various research endeavors. Nevertheless, the inherent limitations of some ML methods, specifically their challenges in identifying global minima and their dilatory convergence rate, constitute the principal drawbacks when employing this methodology. This present investigation was dedicated to the development of an ML-based predictive model that has been enriched through optimization algorithms. Models were developed employing a Regression Decision Tree (DT) along with two optimizers, including the Artificial Hummingbird algorithm (AHA) and coot optimization algorithm (COA). The inputs encompassed mean cohesion, mean friction angle, mean soil-specific weight, mean pile-soil friction angle, flap number, pile area, and pile length. At the same time, the model's output was defined as the ultimate bearing capacity of the piles. The relationship between input parameters and the output was determined. The outcomes of this study demonstrated a significant alignment between the PBC predictions generated by the Regression Decision Tree optimized with Artificial Hummingbird algorithm (DTAH) and the actual measured bearing capacities. The high coefficient of determination and low Root Mean Square Error values, specifically 0.998 and 89.29 (KN), respectively, for the testing datasets, underscore the value of employing optimized DT models as robust, efficient, and pragmatic tools for predicting PBC, offering substantial advantages in the field of civil and geotechnique engineering.

关键词： Pile bearing capacity Machine learning methods Regression Decision Tree Hybrid models Artificial Hummingbird algorithm coot optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An explanatory machine learning model for forecasting compressive strength of high-performance concrete

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第1期7卷 543-555页

作者： Yan, Guifeng Wu, Xu Zhang, Wei Bao, Yuping Nantong Inst Technol Dept BIM Res Nantong 226002 Jiangsu Peoples R China

High-performance concrete (HPC) is one of the concrete types with high strength, good performance, and high durability, which has been considered in the structural industry. Testing and sampling this type of concrete to determine its mechanical properties is daunting and complex. In addition, human and environmental factors were significant in the preparation of samples, which was also time-consuming and energy-consuming. Artificial intelligence (AI) can be used to eliminate and reduce these factors. This article intends to use the machine learning (ML) method to forecast one of the HPC mechanical properties: compressive strength (CS). The experimental data set used from the published article includes 168 samples, of which 70% (118) of the sample belonged to training and 30% (50) to the testing phase. Least square support vector regression (LSSVR) is one of the ML models used for forecasting in this article. In addition, meta-heuristic algorithms have been utilized to obtain the target to improve the accuracy and reduce the error. algorithms include Honey Badger algorithm (HBA), coot optimization algorithm (COA), and generalized normal distribution optimization (GNDO). Combining the algorithms with the introduced model forms a hybrid format evaluated by metrics in the training and testing phases. By evaluating the hybrid models, it has been determined that they can forecast with high accuracy and are reliable. In general, the LSHB hybrid model obtained the highest R2 and the lowest error compared to other models.

关键词： High-performance concrete Compressive strength Least square support vector regression Honey Badger algorithm coot optimization algorithm Generalized normal distribution optimization

来源：评论

学校读者我要写书评

暂无评论

coot-SVR model: estimation of the capillary water absorption of building stones

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第2期7卷 993-1005页

作者： Li, Yuchen Caofeidian Coll Technol Coll Engn Tangshan 063000 Hebei Peoples R China

The examination of a rock's capillary water absorption (CWA) entails extensive and time-intensive procedures and experiments. However, the use of machine learning prediction technologies has the potential to reduce both the cost and time associated with this process. This research proposes the use of support vector regression (SVR) models to effectively accomplish the forecasting objectives of the design. The study further emphasizes the identification of optimal SVR parameters by integrating the coot optimization algorithm (COOA) and Salp Swarm optimization (SSA) techniques. The novelty of this study lies in the combination of SVR with optimization algorithms, the application of machine learning for CWA prediction in rocks, the improved performance of the hybridized approach, and the comparative analysis demonstrating the superiority of the proposed COOA-SVR system over existing methods. The empirical results indicate that both the COOA-SVR and SSA-SVR techniques perform well in the process of CWA forecasting. Specifically, the R-2 values obtained for the training and testing phases are 0.981 and 0.9714, respectively. By evaluating the RMSE index, COOA-SVR could gain roughly half its value with respect to SSA-SVR model, by reducing from 18.4557 to 9.253 g/m(2)/s(0.5) in the train part.

关键词： Building stones Capillary water absorption Estimation Support vector regression coot optimization algorithm Salp swarm optimization

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：