检索结果-内蒙古大学图书馆

Ensemble learning predicts glass-forming ability under imbalanced datasets

COMPUTATIONAL MATERIALS SCIENCE 2025年 248卷

作者： Cheng, Duan-jie Liang, Yong-chao Pu, Yuan-wei Chen, Qian Guizhou Univ Coll Adv Optoelect Mat & Technol Sch Big Data & Informat Engn Guiyang 550025 Peoples R China

With the development of artificial intelligence, machine learning (ML) is widely used to predict glass-forming ability (GFA). However, GFA experimental data usually exhibits a long-tailed distribution, and the similarity between the enhanced dataset and the original dataset is unclear. In terms of modeling, although model fusion provides better prediction results than individual learners, it also faces the risk of overfitting. Therefore, two preprocessing methods designed for regression problems WEighted Relevance-based Combination Strategy (WERCS) and Synthetic Minority Over-sampling technique with Gaussian Noise (SMOGN) are employed. The best strategy is selected by Pairwise correlation difference (PCD). Based on the screening results, this paper further proposes a multi-layer stacking ensemble learning model (MLS) for predicting GFA. Considering model accuracy and diversity together, the base model and meta-model combinations are optimized by bayesian optimization algorithm (BOA). The results show that MLS achieves R2 = 0.79 in prediction accuracy, which is better than other models and criteria discussed in this paper. In addition, the generalization ability of the MLS model is verified in the Cu-Mg-Ca alloy system. To explain the MLS model, SHapley Additive exPlanation (SHAP) is introduced. With the help of MLS and SHAP methods, the formation law of bulk metallic glasses (BMGs) is revealed, and the BMGs of Zr-Cu-Al-Ag series alloys are successfully designed.

关键词： Glass-forming ability Data Enhancement Ensemble learning bayesian optimization algorithm Design of bulk metallic glasses

来源：评论

学校读者我要写书评

暂无评论

Holographic memory-based bayesian optimization algorithm (HM-BOA) in dynamic environments

引用

Science China(Information Sciences) 2013年第9期56卷 110-126页

作者： KAEDI Marjan GHASEM-AGHAEE Nasser AHN Chang Wook Department of Information technology Engineering University of Isfahan Department of Computer Engineering University of Isfahan Department of Computer Engineering Sungkyunkwan University

This paper presents a new evolutionary dynamic optimization algorithm, holographic memory-based bayesian optimization algorithm (HM-BOA), whose objective is to address the weaknesses of sequential memory-based dynamic optimization approaches. To this end, holographic associative neural memory is applied to one of the recent successful memory-based evolutionary methods, DBN-MBOA (memory-based BOA with dynamic bayesian networks). Holographic memory is appropriate for encoding environmental changes since its stimulus and response data are represented by a vector of complex numbers such that the phase and the magnitude denote the information and its confidence level, respectively. In the learning process in HM-BOA, holographic memory is trained by probabilistic models at every environmental change. Its weight matrix contains abstract information obtained from previous changes and is used for constructing a new probabilistic model when the environment changes. The unique features of HM-BOA are: 1) the stored information can be generalized, and 2) a small amount of memory is required for storing the probabilistic models. Experimental results adduce grounds for its effectiveness especially in random environments.

关键词： dynamic optimization bayesian optimization algorithm holographic memory dynamic bayesian networks.

来源：评论

学校读者我要写书评

暂无评论

bayesian algorithm optimized deep model for multi-signal fault identification of hydraulic pumps

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 121卷 465-483页

作者： Tang, Shengnan Jiang, Yixuan Zhou, Tao Zhu, Yong Lim, Kian Meng Jiangsu Univ Inst Adv Mfg & Modern Equipment Technol Sch Mech Engn Zhenjiang 212013 Peoples R China Zhejiang Univ State Key Lab Fluid Power & Mechatron Syst Hangzhou 310013 Peoples R China Natl Univ Singapore Dept Mech Engn Singapore 117575 Singapore Jiangsu Univ Natl Res Ctr Pumps Zhenjiang 212013 Peoples R China LEO Grp Co Ltd Wenling 317500 Peoples R China

Hydraulic pump (HP) supplies the power for a hydraulic transmission system. It is critical for the fault diagnosis of HP to guarantee the healthy operation of systems. The rapid progress of artificial intelligence and measuring technique empowers data-driven methods. Diagnosis methods based on machine learning are limited in timeconsuming parameter adjustment. Moreover, current methods based on one measured signal achieve fault diagnosis only by using limited feature information. To address the two problems, this research proposes an intelligent fault diagnosis method for HP. First, original signals from multiple sources are obtained using multiple sensors. Due to the effective solution of frequency aliasing and the good robustness to the background noise of the signals, an intelligent method combining an improved deep model and synchrosqueezing wavelet transform is further established. The introduction of bayesian algorithm completes the adaptive selection of main parameters and contributes to reduce the computing time. The optimal model is selected by updating hyperparameter groups and evaluating the performance. The optimized diagnostic model presents good convergence and stability. The diagnostic accuracies achieve 96.69 %, 97.58 %, and 99.89 % for three signals. The proposed diagnostic method presents the effectiveness in mining fault characteristic information and intelligent identification of common fault types.

关键词： Hydraulic pump Intelligent defect identification Deep model bayesian optimization algorithm Synchrosqueezing wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Prediction of compressive strength of multiple types of fiber-reinforced concrete based on optimized machine learning models

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 152卷

作者： Zhao, Ning Zhang, Haonan Xie, Peilun Chen, Xiaowei Wang, Xuewei Sichuan Agr Univ Sch Civil Engn Chengdu 611830 Peoples R China Southeast Univ Sch Civil Engn Nanjing 211189 Peoples R China

The accurate prediction of compressive strength of fiber-reinforced concrete (FRC) is essential for its design optimization and performance assessment, as it can significantly reduce testing costs. However, the high variability of FRC's compressive strength poses considerable prediction challenges. Current research has predominantly focused on developing prediction models for single-type FRC, while the prediction of compressive strength across multiple types of FRC remains a critical and unresolved issue in the field. To address this gap, this study proposes a novel hybrid approach integrating Deep Neural Networks (DNN), Generalized Regression Neural Networks (GRNN), and Extreme Gradient Boosting (XGBoost) with optimization techniques-Particle Swarm optimization (PSO), bayesian optimization (BO), and Bald Eagle Search (BES). A comprehensive dataset of 386 peer-reviewed compressive strength measurements was utilized, with K-means++ algorithm ensuring balanced training and testing set distributions. Hyperparameter optimization for DNN, GRNN, and XGBoost was conducted by combining PSO, BO, and BES with five-fold cross-validation. Results demonstrate strong model performance, with the BES-XGBoost model achieving the highest accuracy, exhibiting deviations of approximately 15 % between actual and predicted values. Additionally, Shapley Additive Explanations (SHAP) and partial dependence plots were employed to analyze the feature importance on compressive strength and the coupling effects of fiber characteristics. The proposed approach not only provides enhanced prediction accuracy for multiple types of FRC but also delivers valuable insights for FRC proportioning design, advancing the field of FRC performance evaluation.

关键词： Fiber-reinforced concrete Neural network Compressive strength prediction Particle swarm optimization algorithm bayesian optimization algorithm Bald eagle search optimizer

来源：评论

学校读者我要写书评

暂无评论

Hybrid machine learning modeling of nitrogen removal from wastewater using gas-liquid-solid circulating fluidized bed riser

引用

CHEMICAL ENGINEERING RESEARCH & DESIGN 2024年 207卷 295-307页

作者： Razzak, Shaikh Abdur Sultana, Nahid Hossain, S. M. Zakir Rahman, Muhammad Muhitur Yuan, Yue Hossain, Mohammad Mozahar Zhu, Jesse King Fahd Univ Petr & Minerals Dept Chem Engn Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Interdisciplinary Res Ctr Refining & Adv Chem Dhahran Saudi Arabia Imam Abdulrahman Bin Faisal Univ Coll Comp Sci & Informat Technol Dept Comp Sci Dammam Saudi Arabia Univ Bahrain Coll Engn Dept Chem Engn Zallaq Bahrain King Faisal Univ Dept Civil & Environm Engn Al Hufuf Saudi Arabia Western Univ Dept Chem & Biochem Engn London ON Canada

Municipal wastewater generally contains high amounts of nitrogen (N), approximately 23-28 mg/L of total Kjeldahl Nitrogen (TKN), which causes eutrophication and pollution of groundwater. This article reports the generation of empirical models for estimating the nitrogen removal efficacy of two outputs (NH4-N 4-N and NO3-N) 3-N) from the anoxic riser of a highly efficient municipal wastewater treatment system involving a gas-liquid-solid circulating fluidized bed (GLSCFB) bioreactor. To identify the important variables and discard irrelevant ones, the ReliefF algorithm is applied initially. Out of 10 independent variables, this method indicates that only three, such as flow rate, total Kjeldahl Nitrogen (TKN), and downer effluent of NO3-N, are meaningful for anoxic nitrogen removal. Then, a hybrid bayesian optimization algorithm and Support Vector Regression (BOA-SVR) is implemented, considering only the essential variables. In this regard, real-life laboratory data are utilized to develop the models. The BOA approach and k-fold cross-validation technique are explicitly applied to optimize the model's hyperparameters and avoid overfitting. The established models provided sufficiently accurate predictions via their comparisons to the experimental observations. Besides, the BOA-SVR model outperforms the classical multiple linear regression (MLR). The BOA-SVR models' forecasted results for both the predicted amount of NH4-N 4-N and NO3-N 3-N are favorably compared with the laboratory trials (R2> 2 > 99 %). A comprehensive evaluation is further conducted to validate the performance of this model by calculating the root mean square error, mean absolute percentage error, fractional bias, and computational efficiency. Gaussian white noise is used to add three distinct noise levels (20 %, 40 %, and 60 %) to the testing data to evaluate the model's robustness. Moreover, the plots of relative deviations and residuals were dispersed across the zero-reference line with moderate

关键词： Nitrogen Removal Municipal Wastewater Twin Fluidized Bed Bioreactor Feature Selection bayesian optimization algorithm SVR Model

来源：评论

学校读者我要写书评

暂无评论

Forecasting the hydropower unit vibration based on adaptive variational mode decomposition and neural network

引用

APPLIED SOFT COMPUTING 2024年 150卷

作者： Lu, Zhaoheng Tao, Ran Xiao, Ruofu Li, Puxi China Agr Univ Coll Water Resources & Civil Engn Beijing 100083 Peoples R China China Agr Univ Beijing Engn Res Ctr Safety & Energy Saving Techno Beijing 100083 Peoples R China State Key Lab Hydropower Equipment Harbin 150046 Peoples R China

The feature extraction, diagnosis and prediction of vibration and fault are important to maintain the stable operation of units with the large-scale popularization of virtual power plants in hydropower plants. Therefore, more accurate and suitable state detection methods and forecasting models for complex conditions are needed. VMD is limited by the presetting of mode number, penalty factor and initial center frequency, which greatly reduces the accuracy of the algorithm. In this study, IAVMD algorithm is proposed. The initial center frequencies and the mode number can be determined by the scale space plane and the energy loss coefficient. The numerical model of penalty factor is constructed based on center frequency differences. Finally, the mode numbers are combined and adjusted by autocorrelation and other methods. Through comparative analysis of simulation signal and experimental signal, IAVMD shows great improvements in complex signals. At the same time, it is proved that the forecasting model combining IAVMD with BO and LSTM has significantly improved the prediction accuracy. Through comparative analysis, the results prove that the prediction model constructed by this method has higher accuracy.

关键词： Variational mode decomposition Signal analysis Operation status detection bayesian optimization algorithm Long short-term memory network

来源：评论

学校读者我要写书评

暂无评论

Research on mine water source classifications based on BO-CatBoost

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2024年第10期196卷 876-876页

作者： Li, Han Yang, Zhenwei Lv, Hang Wang, Man Zhang, Bo Yan, Hengrui Zhang, Hongyu Henan Polytech Univ Inst Resources & Environm Jiaozuo 454000 Peoples R China Collaborat Innovat Ctr Coal Work Safety & Clean Hi Jiaozuo 454000 Peoples R China China Pingmei Shenma Holding Grp Co Ltd Pingdingshan 467000 Henan Peoples R China

Mine water surge is one of the main safety risks in coal mines. This research offers a novel mine water source identification model (BO-CatBoost) to successfully avoid and control mine sudden water catastrophes by properly identifying the sources of mine water. First, the classification model is trained and built using the Categorical Boosting (CatBoost) algorithm. The Gaussian process bayesian optimization (BO) algorithm is used to optimize parameters, and the optimal parameter combination is integrated into the CatBoost algorithm to build the BO-CatBoost mine water source identification model, which further improves the accuracy of mine water source identification. The model was also applied to the Pingdingshan mine to verify the practicality of the model. Then, 29 groups of unknown water sources in Pingdingshan were selected as validation samples for the model and compared with the conventional CatBoost, Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (Xgboost) models. The comparison results demonstrate that the accuracy of LightGBM, Xgboost, CatBoost, and BO-CatBoost models can reach 69%, 79.3%, 79.3%, and 100% respectively, and the RMSE is 0.947, 0.643, 0.719, and 0.0 respectively. The comprehensive analysis shows that, when it comes to mine water source detection, the BO-CatBoost model performs noticeably better than other models in terms of discriminative accuracy and generalization capacity. Lastly, the multi-output prediction and decision-making process of the BO-CatBoost water source identification model is visualized by the interpretability analysis performed with the SHAP approach. The research demonstrates that the BO-CatBoost model can more precisely and impartially identify mine water sources, offering fresh concepts for mine water source detection.

关键词： Mine water source Pingdingshan coalfield CatBoost SHAP bayesian optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

State of health estimation for lithium-ion batteries with bayesian optimized Gaussian process regression

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING 2024年

作者： Ye, Li-hua He, Zhou Ke, Cheng-long Cheng, Xing Zhao, Xu Zhang, Zi-xing Shi, Ai-ping Jiangsu Univ Sch Automot & Transportat Engn 301 Xuefu Rd Zhenjiang Jiangsu Peoples R China

The estimation of the state of health (SOH) of lithium-ion batteries is of great importance to ensure the safe and stable operation of a lithium-ion battery management system (BMS). Accurate estimation of SOH can effectively prevent unnecessary losses of lithium-ion batteries due to failures. Therefore, a bayesian-optimized Gaussian process regression (BO-GPR) method is proposed for SOH estimation. Firstly, the ageing characteristics reflecting the SOH of the battery are extracted from the charge/discharge time and incremental capacity (IC) curve, and the correlation between the health characteristics and the SOH is analysed by means of grey correlation (GRA). On the other hand, a bayesian optimization algorithm is used to automatically find the optimal hyperparameters of the GPR model and trained using the battery dataset to obtain the SOH estimating model. To validate the effectiveness of the method, the datasets provided by NASA and Oxford are used as experimental objects and compared with different data-driven models to verify the accuracy and reliability of the proposed model. The experimental results show that the method proposed in this paper has a high accuracy in the estimation of the SOH, with the maximum average estimation error being within 1%.

关键词： Lithium-ion battery state of health bayesian optimization algorithm Gaussian process regression

来源：评论

学校读者我要写书评

暂无评论

A Novel Malware Detection Model in the Software Supply Chain Based on LSTM and SVMs

引用

APPLIED SCIENCES-BASEL 2024年第15期14卷 6678页

作者： Zhou, Shuncheng Li, Honghui Fu, Xueliang Jiao, Yuanyuan Inner Mongolia Agr Univ Coll Comp & Informat Engn Hohhot 010018 Peoples R China

With the increasingly severe challenge of Software Supply Chain (SSC) security, the rising trend in guarding against security risks has attracted widespread attention. Existing techniques still face challenges in both accuracy and efficiency when detecting malware in SSC. To meet this challenge, this paper introduces two novel models, named the bayesian optimization-based Support Vector Machine (BO-SVM) and the Long Short-Term Memory-BO-SVM (LSTM-BO-SVM). The BO-SVM model is constructed on an SVM foundation, with its hyperparameters optimized by bayesian optimization. To further enhance its accuracy and efficiency, the LSTM-BO-SVM model is proposed, building upon BO-SVM and employing LSTM networks for pre-classification. Extensive experiments were conducted on two datasets: the balanced ClaMP dataset and the unbalanced CICMalDroid-2020 dataset. The experimental results indicate that the BO-SVM model is superior to other models in terms of accuracy;the accuracy of the LSTM-BO-SVM model on the two datasets is 98.2% and 98.6%, respectively, which is 2.9% and 2.2% higher than that of the BO-SVM on these two datasets.

关键词： software supply chain malware detection long short-term memory network bayesian optimization algorithm support vector machine

来源：评论

学校读者我要写书评

暂无评论

A rolling bearing fault diagnosis technique based on recurrence quantification analysis and bayesian optimization SVM

引用

APPLIED SOFT COMPUTING 2024年 156卷

作者： Wang, Bing Qiu, Wentao Hu, Xiong Wang, Wei Shanghai Maritime Univ Shanghai 201306 Peoples R China

A rolling bearing fault diagnosis technique is proposed based on Recurrence Quantification Analysis (abbreviated as RQA) and bayesian optimized Support Vector Machine (abbreviated as RQA-Bayes-SVM). Firstly, analyzing the vibration signal with recurrence plot and the nonlinear feature parameters are extracted with RQA, constructing a feature matrix describing the fault mode and fault degree comprehensively. Finally, bayesian optimization algorithm is introduced for searching the best penalty factor C and kernel function parameter g of SVM and establishing an optimal Bayes-SVM model. Bearing datasets from CWRU is imported for diagnosis on fault mode and fault degree. The results show that the technique presents a good performance on fault mode diagnosis as well as fault degree distinction. Compared with common k-Nearest Neighbor (abbreviated as KNN) and Random Forest (abbreviated as RF) diagnosis models, Bayes-SVM has the best accuracy and stability, which indicates a potential value for engineering applications.

关键词： Rolling bearing RQA Fault diagnosis SVM bayesian 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：