检索结果-内蒙古大学图书馆

Introducing a Novel Hybrid Machine Learning Model and Developing its Performance in Estimating Water Quality Parameters

引用

WATER RESOURCES MANAGEMENT 2022年第10期36卷 3901-3927页

作者： Kadkhodazadeh, Mojtaba Farzin, Saeed Semnan Univ Fac Civil Engn Dept Water Engn & Hydraul Struct Semnan *** Iran

For the first time, a novel hybrid machine learning model named the least-squares support vector machine-arithmetic optimization algorithm (LSSVM-AOA) was proposed. The performance of LSSVM-AOA was checked on six benchmark data sets (BDSs) to showcase its applicability. After testing the performance of the novel hybrid machine learning model, its performance in electrical conductivity (EC) and total soluble solids (TDS) estimating was developed at six stations in the Karun river basin. For this purpose, effective parameters were selected by the principal component analysis (PCA) method. The results of the technique for order of preference by similarity to ideal solution (TOPSIS) method showed that the LSSVM-AOA has promising results in modeling BDSs and estimating water quality parameters (WQPs) in comparison with classical and hybrid algorithms (artificial neural network (ANN), adaptive neural fuzzy inference system (ANFIS), LSSVM, LSSVM-particle swarm optimization (LSSVM-PSO) and LSSVM-whale optimization algorithm (LSSVM-WOA)). The average values of correlation coefficient (R) in EC and TDS estimates were 0.969 and 0.950, respectively. Eventually, the Monte Carlo method (MCM) showed that the LSSVM-AOA has the lowest uncertainty among other algorithms.

关键词： New hybrid algorithm LSSVM arithmetic optimization algorithm Water quality parameters Benchmark data set TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Bi-directional Long-term Short-term Memory Classification Method of Diabetes Datasets

引用

ENGINEERING LETTERS 2022年第4期30卷 1603页

作者： Li, Xu-Dong Wang, Jie-Sheng Hao, Wen-Kuo Zhao, Xiao-Rui Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan 114051 Peoples R China

As a underlying disease, diabetes has become more and more common worldwide. The patients presented with persistent and long-term hyperglycemia. If the cause of diabetes is not identified and not treated in time, many complications will occur. Because the identification process is complicated, patients choose a medical center to visit a diagnostic center to consult a doctor. This study will focus on how to design a classification model to accurately determine whether a patient has diabetes. Therefore, this paper combines the trigonometric function pedigree arithmetic optimization algorithm (AOA) with the bi-directional long short-term memory (Bi-LSTM) neural network. Based on two kinds of neural networks, 10 diabetes classification methods based on heuristic algorithm training network parameters are designed. Simulation experimental results demonstrate that the trigonometric function pedigree arithmetic optimization algorithm to improve the parameters of the Bi-LSTM network can significantly improve the classification accuracy. Finally, the Bi-LSTM classification model based on tanAOA has the best classification utility, and the classification accuracy is better than other classification methods.

关键词： diabetes data classification arithmetic optimization algorithm bi-directional long-term short-term memory

来源：评论

学校读者我要写书评

暂无评论

Novel hybrid AOA and ALO optimized supervised machine learning approaches to predict the compressive strength of admixed concrete containing fly ash and micro-silica

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2022年第4期5卷 391-402页

作者： Zhu, Weixiang Huang, Lihua Zhang, Zhijun Zhejiang Guangsha Vocat & Tech Univ Construct Sch Civil Engn Architecture Dongyang 322100 Peoples R China Zhejiang Guangsha Vocat & Tech Univ Construct Sch Management Engn Dongyang 322100 Peoples R China Southwest China Architectural Design & Res Inst C Chengdu 610042 Peoples R China

Detecting the impact of admixtures like fly ash and micro-silica on the mechanical property of concrete, especially the compressive strength (CS), earned a lot of attention not only in the concrete industry but also in future extended research and analysis. In this study, two innovative methods of hybrid support vector regression optimized by arithmetic optimization algorithm and Antlion optimization algorithm named AOSVR and ALSVR were developed to generate accurately a trustable relationship between the feeding input (eight ingredients) of the model and the target values that optimizers by finding key variables of SVR lead to model precisely. These models applied to perform a prediction process of CS values for 170 High-Performance Concrete (HPC) samples. It can be concluded that the coefficient of determination values showed 0.9872 and 0.9850 for AOSVR and ALSVR, respectively. Moreover, the hybrid AOSVR model outperformed the most premier accuracy in the prediction of CS. Also, using these hybrid models helps diminish the cost of concrete testing and further the analysis of concrete mechanical characterization.

关键词： High-performance concrete Micro-silica arithmetic optimization algorithm Antlion optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of thermal conductivity of granitic rock: an application of arithmetic and salp swarm algorithms optimized ANN

引用

EARTH SCIENCE INFORMATICS 2022年第4期15卷 2303-2317页

作者： Lawal, Abiodun Ismail Kwon, Sangki Kim, Minju Aladejare, Adeyemi Emman Onifade, Moshood Inha Univ Yong Hyun Dong Dept Energy Resources Engn Incheon South Korea Fed Univ Technol Akure Dept Min Engn Akure Nigeria Univ Oulu Oulu Min Sch Oulu Finland Univ Nambia Dept Civil & Min Engn POB 3624 Ongwediva Namibia

Thermal conductivity (TC) is an important rock property as it determines its energy transfer potential. Compared with other rock properties like uniaxial comprehensive strength (UCS), it is rarely investigated. Hence, novel arithmetic and Salp swarm optimized artificial neural network (ANN) models are used to predict the thermal conductivity of granitic rock based on the results of non-destructive tests. Fifty (50) core samples were obtained from the study location and tested in the laboratory. The results obtained from the laboratory investigations were used to perform the ordinary ANN and the optimized ANN models. The outcomes showed that the performances of the optimized ANN models are better than the ordinary ANN model. The results were also compared with the multiple linear regression model (MLR) although the predictive strength of the MLR model is extremely low. The proposed models were mathematically transformed into simple mathematical models, and a graphic user interface (GUI) prepared with the Visual basic programming language was developed. The proposed models can be practically implemented for TC prediction.

关键词： Thermal conductivity Energy transfer arithmetic optimization algorithm Salp swarm

来源：评论

学校读者我要写书评

暂无评论

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid algorithm

引用

PROCESSES 2024年第1期12卷 221页

作者： Li, Shuai Jin, Nan Dogani, Azadeh Yang, Yang Zhang, Ming Gu, Xiangyun 76 Chongmingdao East Rd Qingdao 266000 Peoples R China Ferdowsi Univ Mashhad Fac Agr Dept Agr Econ Mashhad *** Iran

The reliable operation of industrial equipment is imperative for ensuring both safety and enhanced production efficiency. Machine learning technology, particularly the Light Gradient Boosting Machine (LightGBM), has emerged as a valuable tool for achieving effective fault warning in industrial settings. Despite its success, the practical application of LightGBM encounters challenges in diverse scenarios, primarily stemming from the multitude of parameters that are intricate and challenging to ascertain, thus constraining computational efficiency and accuracy. In response to these challenges, we propose a novel innovative hybrid algorithm that integrates an arithmetic optimization algorithm (AOA), Simulated Annealing (SA), and new search strategies. This amalgamation is designed to optimize LightGBM hyperparameters more effectively. Subsequently, we seamlessly integrate this hybrid algorithm with LightGBM to formulate a sophisticated fault warning system. Validation through industrial case studies demonstrates that our proposed algorithm consistently outperforms advanced methods in both prediction accuracy and generalization ability. In a real-world water pump application, the algorithm we proposed achieved a fault warning accuracy rate of 90%. Compared to three advanced algorithms, namely, Improved Social Engineering Optimizer-Backpropagation Network (ISEO-BP), Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN), and Grey Wolf Optimizer-Light Gradient Boosting Machine (GWO-LightGBM), its Root Mean Square Error (RMSE) decreased by 7.14%, 17.84%, and 13.16%, respectively. At the same time, its R-Squared value increased by 2.15%, 7.02%, and 3.73%, respectively. Lastly, the method we proposed also holds a leading position in the success rate of a water pump fault warning. This accomplishment provides robust support for the timely detection of issues, thereby mitigating the risk of production interruptions.

关键词： fault warning LightGBM hybrid algorithm hyperparameter optimization arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 241卷

作者： Zhang, Lijie Janosik, Dominik Changchun Univ Sci & Technol Sch Comp Sci Changchun 130000 Peoples R China Slovak Univ Technol Bratislava Radlinskeho 11 Bratislava 81368 Slovakia

The focus of this paper is to improve short-term load forecasting for electric power. To achieve this goal, the study explores and evaluates hybrid models, specifically using the CatBoost and XGBoost algorithms, which are optimized with different optimizers. The study incorporates hourly electricity load data and also includes tem-perature data to enhance the precision of the forecasting models. Statistical metrics are then used to assess the performance of these models. The study evaluates the performance of the hybrid models on both training and testing datasets. It finds that the CatBoost-arithmetic optimization algorithm hybrid model outperforms the other models in the training dataset. However, in the testing dataset, the XGBoost-arithmetic optimization algorithm hybrid model demonstrates superior performance compared to the CatBoost models. The study con-ducts an importance and sensitivity analysis to understand which variables have the most significant impact on the target variable, which is likely electricity load. The results of this analysis reveal that temperature is the most influential variable affecting the target variable. Additionally, the month variable is identified as having a notable impact on load forecasting. These findings suggest that employing hybrid models, particularly those optimized with appropriate algorithms, can significantly improve the accuracy of short-term load forecasting. Moreover, the study highlights the importance of incorporating temperature data into these models, as temperature is a key driver of electricity load patterns.

关键词： Short-term load forecasting Hybrid machine learning models CatBoost and XGBoost models arithmetic optimization algorithm Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Assessing groundwater behavior and future trends in the Ardabil Aquifer: A comparative study of groundwater modeling system and categorical gradient boosting hybrid model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期255卷

作者： Bairami, Milad Khajavi, Hamed Rastgoo, Amir K N Toosi Univ Technol Dept Civil Engn Tehran Iran

Rapid population growth and rising demand have led to increased groundwater extraction, underscoring the importance of effective water resource management. While groundwater models are practical tools, their reliance on extensive hydrogeological and hydrological data can pose challenges when such data is unavailable or inaccessible. In this study, two modeling approaches were employed for the prediction and characterization of groundwater behavior in Ardabil Plain from October 2010 to March 2021. Initially, groundwater behavior was modeled using Modflow. Subsequently, the groundwater behavior was modeled within the same time frame using the hybrid CatBoost-AOA model. Groundwater levels were then determined using these two models until the year 2031. The CatBoost-AOA hybrid method showed the highest agreement (correlation coefficient: 0.9977). Modflow and CatBoost models predicted a decline of 0.77 and 0.85 m, respectively, until 2031. This study aims to guide sustainable development planning, with CatBoost-AOA providing a simplified and efficient alternative for accurately forecasting groundwater fluctuations.

关键词： Groundwater Modeling system Categorical Gradient Boosting Ardabil plain Groundwater level Modflow arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing short-term wind speed prediction based on an outlier-robust ensemble deep random vector functional link network with AOA-optimized VMD

引用

ENERGY 2024年 296卷

作者： Zhang, Chu Li, Zhengbo Ge, Yida Liu, Qianlong Suo, Leiming Song, Shihao Peng, Tian 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

Wind speed prediction is a crucial aspect in the utilization of wind energy. In this paper, a wind speed prediction model based on an outlier-robust ensemble deep random vector functional link network (ORedRVFL) and arithmetic optimization algorithm-optimized variational mode decomposition (AOA-VMD) is designed. First, the penalty factor and the number of mode decompositions of VMD are optimized using the AOA algorithm and the original data are decomposed using the optimized VMD. Then the decomposed data is predicted using the ensemble deep random vector functional link network (edRVFL) model. The edRVFL uses rich intermediate features for the final decision, which can make the final result closer to the real data. In order to strengthen the anti-interference ability to the outliers, this paper robustly improves the edRVFL model, and the improved model is called ORedRVFL. ORedRVFL reduces the impact of outliers by introducing regularization and norm to balance the relationship between training error and weights. The experiments have proved that the model proposed in this paper outperforms other models in terms of anti-interference ability and prediction accuracy.

关键词： Ensemble deep random vector functional link network Anti-interference ability Wind speed prediction arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Deep Learning Model for Forecasting Ultra-Short-Term Time Series Wind Speeds for Wind Turbines

引用

PROCESSES 2023年第11期11卷 3247页

作者： Yang, Jianzan Pang, Feng Xiang, Huawei Li, Dacheng Gu, Bo Powerchina Guiyang Engn Corp Ltd Guiyang 550081 Peoples R China North China Univ Water Resources & Elect Power Sch Elect Engn Zhengzhou 450011 Peoples R China

Accurate forecasting of ultra-short-term time series wind speeds (UTSWS) is important for improving the efficiency and safe and stable operation of wind turbines. To address this issue, this study proposes a VMD-AOA-GRU based method for UTSWS forecasting. The proposed method utilizes variational mode decomposition (VMD) to decompose the wind speed data into temporal mode components with different frequencies and effectively extract high-frequency wind speed features. The arithmetic optimization algorithm (AOA) is then employed to optimize the hyperparameters of the model of the gated recurrent unit (GRU), including the number of hidden neurons, training epochs, learning rate, learning rate decay period, and training data temporal length, thereby constructing a high-precision AOA-GRU forecasting model. The AOA-GRU forecasting model is trained and tested using different frequency temporal mode components obtained from the VMD, which achieves multi-step accurate forecasting of the UTSWS. The forecasting results of the GRU, VMD-GRU, VMD-AOA-GRU, LSTM, VMD-LSTM, PSO-ELM, VMD-PSO-ELM, PSO-BP, VMD-PSO-BP, PSO-LSSVM, VMD-PSO-LSSVM, ARIMA, and VMD-ARIMA are compared and analyzed. The calculation results show that the VMD algorithm can accurately mine the high-frequency components of the time series wind speed, which can effectively improve the forecasting accuracy of the forecasting model. In addition, optimizing the hyperparameters of the GRU model using the AOA can further improve the forecasting accuracy of the GRU model.

关键词： variational mode decomposition arithmetic optimization algorithm gated recurrent unit ultra-short-term forecasting time series wind speed

来源：评论

学校读者我要写书评

暂无评论

Application of AOA algorithm for optimal placement of electric vehicle charging station to minimize line losses

引用

ELECTRIC POWER SYSTEMS RESEARCH 2023年第PartA期214卷

作者： Kathiravan, K. Rajnarayanan, P. N. Theni Kammavar Sangam Coll Technol Dept Elect & Elect Engn Koduvilarpatti PO Virapandi Tamilnadu India

The conventional transportation system uses fossil fuels and it emits greenhouse gases which affect the envi-ronment. A new kind of transportation must be created immediately because of the growing population. Electric Vehicles (EVs) have less impact on environmental pollution and they will become the base for future transport systems. The battery's specific energy is very low and it needs frequent charging. The long-distance trans-portation using EVs needs charging stations and it leads to placing Electric Vehicle Charging Station (EVCS) in the power grid. The placement of EVCS in the grid increases network losses which have an adverse impact on the grid. In this research work, network loss minimization by the optimum placement of EVCS along with Distributed Generation (DG) is considered. The proposed approach has been validated on the IEEE 33 bus system. The analysis was carried out using the Loss Sensitivity Factor (LSF) approach considering the variable network pa-rameters in the Radial Distribution Network (RDN). The EVCS optimal placement was resolved by arithmetic optimization algorithm (AOA). The results are compared with Particle Swarm optimization (PSO) and Harris Hawks optimization (HHO) approaches. The findings show that the optimal placement of EVCS along with DGs reduces network losses considerably.

关键词： Integrated electric vehicle charging station with distributed generation Loss sensitivity factor Real power loss arithmetic optimization algorithm Radial network

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

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

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：