检索结果-内蒙古大学图书馆

Design of a Novel PID Controller Based on Machine Learning algorithm for a Micro-Thermoelectric Cooler of the Polymerase Chain Reaction Device

引用

IEEE ACCESS 2024年 12卷 61959-61977页

作者： Arikusu, Yilmaz Seryar Bayhan, Nevra Manisa Celal Bayar Univ Dept Elect Engn TR-45400 Manisa Turkiye Istanbul Univ Cerrahpasa Dept Elect & Elect Engn TR-34320 Istanbul Turkiye

The combined use of Extreme Gradient Boosting (xgboost) algorithm, one of the machine learning (ML) methods, and a generalization of Hermite-Biehler theorem to obtain a novel PID controller that will ensure robustly stable and optimized operation of a micro thermoelectric cooler (Micro-TEC), which is the main part of a Polymerase chain reaction (PCR) device, is a unique approach of our study compared to previous studies. Therefore, we first established a mathematical model of the micro-TEC by making real-time measurements and then, a new data set was created to find the optimum parameter values of PID controller, and finally, xgboost Hyperparameters with GridSearchCV was used for the first time to predict PID controller parameters. The xgboost algorithm achieved 97% training success and 91% test success in estimating the parameters of the PID controller. Moreover, the novel controller developed using the xgboost algorithm in this study has an impressive speed of 3 seconds. Additionally, our proposed method was compared with various metaheuristic optimization algorithms in terms of error percentage. The error percentages of xgboost, the equilibrium optimization, the particle swarm optimization and the artificial bee colony optimization algorithms were found to be 0.4%, 1.1%, 3.7% and 11.1%, respectively. It is observed the settling times of micro-TEC with ML-PID controller for all five PCR cycles are 4.86, 44, 83.4, 123 and 162.5 seconds, respectively, and the overshoot values are below 5%. The proposed method gave the smallest settling time, error and overshoot percentages compared to these metaheuristic optimization algorithms.

关键词： Temperature control Machine learning algorithms Polymers Stability analysis Prediction algorithms Power system stability Thermoelectric materials xgboost algorithm GridSearchCV thermoelectric cooler machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Using Learning algorithm for Parkinson's Disease Detection with Handwritten Sketches'

引用

CYBERNETICS AND SYSTEMS 2024年第8期55卷 2388-2404页

作者： Shrivastava, Anurag Chakkaravarthy, Midhun Shah, Mohd Asif Lincoln Univ Coll LUC Dept Elect & Commun Engn Kota Baharu Kelantan Malaysia Lincoln Univ Coll Fac Comp Sci & Multimedia Kota Baharu Kelantan Malaysia Kebri Dehar Univ ECE Somali Ethiopia

The degenerative neurological condition known as Parkinson's disease is distinguished by tremors, stiffness, and difficulties with walking, balance, and motor coordination. Parkinson's disease is a progressive condition. Identifying whether this guy suffers from Parkinson's disease is the purpose of this puzzle. Early detection and effective treatment of Parkinson's disease can significantly improve the quality of life for those affected. This highlights the significance of early disease detection. The objective of this initiative is to facilitate the identification of Parkinson's disease through the use of hand-drawn graphics. Three unique Machine Learning algorithms are used in this article. The adaptability of the model has been demonstrated through the usage of a variety of designs, including but not limited to spirals, waves, cubes, and triangles. Experiment results showed that datasets 89.7% correct, and proposed xgboost algorithm is 98.75% accurate.

关键词： K-NN NB Parkinson's Disease (PD) Machine Learning xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Tool wear state recognition and prediction method based on laplacian eigenmap with ensemble learning model

引用

ADVANCED ENGINEERING INFORMATICS 2024年 60卷

作者： Xie, Yang Gao, Shangshang Zhang, Chaoyong Liu, Jinfeng Jiangsu Univ Sci & Technol Sch Mech Engn Zhenjiang 212000 Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Intelligent Mfg Equipment & Technol Wuhan 430074 Peoples R China

Accurate prediction of tool wear status plays a critical role in the digital manufacturing industry, and its health level directly affects machining quality, production costs, and overall productivity. In response to the problems of the high dimensionality of extracted features from tool wear characterization sensors, redundant information, and large individual model errors and biases, a novel method for tool wear status identification and prediction that fuses downscaling dimensionality and ensemble models is proposed. First, a multi-algorithm feature filtering based on Random Forest (RF) and extreme gradient boosting (xgboost) is utilized, and the laplacian eigenmaps (LE) algorithm is combined to perform fusion downscaling on the filtered features. Then, the parameters of the xgboost algorithm are optimized using grid search (GS). Finally, the performance of the proposed method is evaluated by different tool wear experiments for both regression and classification using model prediction accuracy evaluation metrics (R-squared values and f1 values) and prediction time. The experimental results show that for different tools wear experimental data, the R-squared values of the regression model are higher than 0.98, the f1 values of the classification model are above 0.96, and the prediction speed is improved by an order of magnitude compared with other models. The results are analyzed to verify the effectiveness and applicability of the proposed method, which can provide technical support for the automated machining process.

关键词： Tool wear Laplacian eigenmaps Features fusion xgboost algorithm Ensemble method

来源：评论

学校读者我要写书评

暂无评论

Understanding the relationship between rural morphology and photovoltaic (PV) potential in traditional and non-traditional building clusters using shapley additive exPlanations (SHAP) values

引用

APPLIED ENERGY 2025年 380卷

作者： Liu, Jiang Peng, Changhai Zhang, Junxue Southeast Univ Sch Architecture Nanjing 210096 Peoples R China Southeast Univ Key Lab Urban & Architectural Heritage Conservat Minist Educ Nanjing Peoples R China Jiangsu Univ Sci & Technol Sch Civil Engn & Architecture Zhenjiang 212100 Peoples R China

Rural areas have a large quantity of rooftops and facades appropriate for installing PV panels. However, the unclear impact of rural morphology on PV potential hinders their effective utilization. To address this challenge, this study examined 300 clusters of traditional and non-traditional rural buildings in Nanjing. 17 morphological indicators were identified, representing plot shape, built density, building form, and terrain variation. The annual PV power generation and Levelized cost of electricity (LCOE) were simulated. Using an explainable machine learning framework (xgboost algorithm combined with SHAP values), we explored the relationship between rural building morphology and PV potential. The results revealed that mean building height (BH) and floor area ratio (FAR) are key factors for PV power generation, while only BH is crucial for LCOE. As BH and FAR increase, PV generation declines, while LCOE rises. Particularly, BH has a stronger influence on technical potential in traditional clusters, whereas FAR plays a comparable role in non-traditional ones. Using these indicators, rural clusters can be categorized into three typologies for technical potential: low BH-low FAR, high BHlow FAR, and high BH-high FAR, and two for economic potential: low BH and high BH, with mean values being 176.1, 134, 121.5 kWh/m2/y, and 0.5, 0.53 CHY/kWh, respectively. A demonstration conducted outside Nanjing showed that our findings can be applied to the broader Yangtze River Delta region with a maximum error of less than 15 %. This study provides insights to inform rural PV policy-making and system planning, which are essential for China's low-carbon energy transition.

关键词： Rural morphology PV potential xgboost algorithm SHAP value Impact analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Abnormal Ship Brightness Temperature Detection Based on Infrared Image Edge-Enhanced Segmentation Network

引用

APPLIED SCIENCES-BASEL 2025年第7期15卷

作者： Hong, Xiaobin Chen, Guanqiao Chen, Yuanming Cai, Ruimou South China Univ Technol Sch Mech & Automot Engn Guangzhou 510641 Peoples R China South China Univ Technol Sch Civil Engn & Transportat Guangzhou 510641 Peoples R China Guangzhou Shipyard Int Co Ltd Guangzhou 511462 Peoples R China

Infrared imaging is based on thermal radiation and does not rely on visible light, allowing for it to operate normally at night and in low-light conditions. This characteristic is beneficial for regulatory authorities to monitor ships. Existing infrared image segmentation methods face challenges such as the absence of color information, blurred edges, weak high-frequency details, and low contrast due to the imaging principles. Consequently, the segmentation accuracy for small-sized ship targets and edges is low, influenced by the indistinct features of infrared images and the weak difference between the background and targets. To address these issues, this paper proposes an infrared image ship segmentation algorithm called the Infrared Image Edge-Enhanced Segmentation Network (IERNet) to extract ship temperature information. By using pseudo-color infrared images, the sensitivity to edges is enhanced, improving the edge features of ships in infrared images. The Sobel operator is used to obtain edge feature maps, and the Convolutional Block Attention Module (CBAM) extracts key feature information. In the Fusion Unit, edge features guide the extraction of infrared ship features in the backbone network, resulting in feature maps rich in edge information. Finally, a specialized loss function with edge weights supervises the fusion features. An eXtreme Gradient Boosting (xgboost) machine learning model is then established to predict the ship image brightness temperature threshold, using engine brightness threshold, water area brightness threshold, boundary brightness threshold, and temperature gradient as predictive elements. In terms of image segmentation, our algorithm achieves a segmentation performance of 89.17% mIoU. Regarding the xgboost model's performance, it achieves high goodness of fit and small error values on both the training and testing sets, demonstrating its good performance in predicting ship temperature. The model achieves over 70% goodness of fit, and

关键词： infrared image ship image segmentation blurred edges small targets xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine learning-aided biochar design for the adsorptive removal of emerging inorganic pollutants in water

引用

SEPARATION AND PURIFICATION TECHNOLOGY 2025年 362卷

作者： Ullah, Habib Khan, Sangar Zhu, Xiaoying Chen, Baoliang Rao, Zepeng Wu, Naicheng Idris, Abubakr M. Zhejiang Univ Innovat Ctr Yangtze River Delta Haining 311400 Zhejiang Peoples R China Zhejiang Univ Dept Environm Sci Hangzhou 310058 Zhejiang Peoples R China Ningbo Univ Dept Geog & Spatial Informat Tech Ningbo 315211 Peoples R China King Khalid Univ Coll Sci Dept Chem Abha 62529 Saudi Arabia

The escalating presence of emerging inorganic pollutants (EIPs) including vanadium (V), antimony (Sb), thallium (Tl), mercury (Hg), fluoride (F- ), and rare earth elements (REEs) in aquatic environments poses a significant threat to water quality and human health. Therefore, remediation of EIPs contaminated water is of pressing concern. Biochar adsorption offers a promising, environmentally benign, and cost-effective approach for EIP removal. However, inconsistent experimental methodologies and varying research objectives in previous studies hinder the selection of optimal biochar for specific EIP. Developing biochar materials with high adsorption capacity is crucial for effectively removing EIPs from water. However, the optimization of biochar designing using advanced artificial intelligence (AI) methodologies has not been thoroughly reviewed. This study employed a dataset of 528 data points from 61 biochar samples, collected from adsorption experiments conducted between 2014 and 2024, encompassing 24 variables related to various EIPs. To predict adsorption capacity and elucidate adsorption mechanisms, Random Forest (RF), Support Vector Regression (SVR), xgboost, and CatBoost machine learning algorithms were applied. The xgboost model outperformed the others, achieving a coefficient of determination (R2) of 0.96 and a lower root mean squared error (RMSE) of 0.4. Feature importance and SHAP value analysis identified reaction pH, initial concentration and pyrolysis temperature as key predictors of adsorption efficiency. Future predictions from the xgboost model indicate that reaction pH, initial concentration pyrolysis temperature and biochar pH, are critical factors influencing EIP adsorption. This research offers novel insights into EIPs adsorption and establishes a framework for designing sustainable biochar-based adsorbents for wastewater treatment.

关键词： Machine learning (ML) Inorganic water pollution Adsorption Biochar xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Tolerance allocation of mechanical assemblies including thermal deformation: A machine learning - based method

引用

JOURNAL OF THERMAL STRESSES 2025年第1期48卷 64-81页

作者： Soroush, Hossien Khodaygan, Saeed Nik, Javad Hemati Sharif Univ Technol Mech Engn Dept Tehran Iran

Tolerance allocation is one of the prominent tools to achieve the optimal manufacturing cost and the best performance for mechanical assemblies. Variations in dimensions and geometry shape due to different working temperatures for various components within an assembly can make initially assigned tolerances ineffective. Therefore, it is necessary to consider the component's deformation caused by thermal gradients during the tolerance design. In this paper, a new method is presented for optimal tolerance allocation of mechanical assemblies under thermal deformation. First, the system's temperature working conditions and tolerance design goals are specified, followed by the finite element simulation of the assembly at the desired working temperature. Then, the assembly equation is determined according to the complexity of the problem by using analytical methods and some machine learning (ML) algorithms such as xgboost. The optimal tolerance design is formulated into a constrained multi-objective optimization problem. Then, to obtain the Pareto front of optimal tolerances, the multi-objective optimization is solved by the NSGA-II algorithm. Finally, to illustrate the capability of the proposed method, two case studies are considered, and obtained results from the presented method and conventional approaches are compared.

关键词： Finite element simulation NSGA-II algorithm thermal deformation thermal gradients tolerance allocation xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Online payments fraud prediction using optimized genetic algorithm based feature extraction and modified loss with XG boost algorithm for classification

引用

SWARM AND EVOLUTIONARY COMPUTATION 2025年 95卷

作者： Lingeswari, R. Brindha, S. St Peters Inst Higher Educ & Res Dept Comp Applicat Chennai Tamilnadu India St Peters Inst Higher Educ & Res Dept Comp Sci & Applicat Chennai Tamilnadu India

Online payment fraud become a pressing concern in the digital age, necessitating robust predictive models to identify fraudulent transactions effectively. This research proposes a novel approach that leverages an Optimized Genetic algorithm (GA) for feature extraction and a Modified Loss function in conjunction with the xgboost algorithm for classification. The first step involves the application of a GA to optimize feature selection. Genetic algorithms mimic the process of natural selection, iteratively evolving a population of potential feature subsets to maximize the predictive power of the model. This optimization process helps identify the most relevant features for fraud detection, reducing dimensionality and enhancing model efficiency. Next, a Modified Loss function is introduced to the xgboost algorithm. Traditional loss functions aim to minimize prediction errors, but they may not be directly suited for fraud detection, where the focus is on correctly classifying fraudulent transactions. The Modified Loss function is tailored to prioritize the identification of fraudulent cases, thus improving the model's ability to differentiate between legitimate and fraudulent limitations transactions. The proposed approach is evaluated using real-world online payment transaction datasets, and its performance is compared to traditional methods. Experimental results demonstrate the superiority of the optimized genetic algorithm-based feature extraction and the Modified Loss with xgboost algorithm for classification in terms of fraud detection accuracy, precision, and recall. By improving the accuracy and efficiency of fraud detection systems, this methodology can help financial institutions and e-commerce platforms protect their customers from fraudulent activities while reducing false positives.

关键词： Online payments fraud Genetic algorithm Feature extraction Modified loss function Classification xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

xgboost assisted in identifying the structural damage behavior of fiber-reinforced concrete during the soundless demolition process through electrical resistance changes

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 478卷

作者： Tian, Weichen Qiu, Ruipeng Tang, Zhen Zhong, Yiwei Liu, Xianglong Wang, Xingang Zou, Fubing Li, Ruisen Nanchang Univ Sch Infrastruct Engn Nanchang 330031 Peoples R China Nanchang Univ Jiangxi Prov Key Lab Adv Civil Engn Mat & Green In Nanchang 330031 Peoples R China Nanchang Univ Engn Res Ctr Watershed Carbon Neutralizat Minist Educ Nanchang 330031 Peoples R China Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China Qingdao Agr Univ Coll Civil Engn & Architecture Qingdao 266109 Peoples R China

Real-time and accurate feedback of structural state during concrete demolition period is significant to promise the safe and controllable construction process. In this work, soundless demolition technology (SDT) was used to demolish carbon fibers reinforced concrete (CFRC). The electrical resistance and crack widths of SDT processed CFRC were recorded with varying water to agent ratios (w/a) and fiber fractions. Results demonstrated that the carbon fibers (CFs) contents showed insignificant influence on the compressive strength at 240 days, while exhibited remarkable advantage on reducing the electrical resistance and resisting the cracking induced by the internal expansion force. Collectively, the competition between the material's resistance and expansion force determines the demolition process, and the increase in CFs contributes to improving the material's resistance, while higher w/a weakened the expansion force. Moreover, the electrical resistance exhibited a specific decreasethen-increase trend during the demolition process, which was related to the "squeeze effect" induced by the expansion force. A strong relationship was observed between electrical resistance and crack width, and the xgboost model was established to elucidate the effects of different variables on the crack width with high accuracy (R2=0.994), the hyperparameters were determined based on the grid search and 10-fold cross-validation method, and the model was further verified by the SHAP indicators.

关键词： Soundless demolition technology Fiber-reinforced concrete Electrical resistance change xgboost algorithm SHAP

来源：评论

学校读者我要写书评

暂无评论

A machine learning method based on TPE-xgboost model for TRIP/TWIP near-β titanium alloy design

引用

MATERIALS TODAY COMMUNICATIONS 2024年 41卷

作者： Wang, Zheng Zhang, Haoyu Wang, Shengyuan Cheng, Jun Wang, Chuan Zhou, Ge Zhang, Siqian Chen, Lijia Shenyang Univ Technol Sch Mat Sci & Engn Shenyang 110870 Liaoning Peoples R China Shenyang Univ Technol Shenyang Key Lab Adv Struct Mat & Applicat Shenyang 110870 Liaoning Peoples R China Northwest Inst Nonferrous Met Res Shaanxi Key Lab Biomed Met Mat Xian 710016 Peoples R China Liaoning Univ Coll Light Ind Shenyang 110036 Liaoning Peoples R China

The traditional design method for TRIP/TWIP near-beta titanium alloys is time-consuming and expensive. This paper proposes a machine-learning design method for a near-beta titanium alloy that uses the Tree-structured Parzen Estimator (TPE) algorithm to optimize the hyperparameter space of xgboost for improved model prediction accuracy in TRIP/TWIP. The model predicts the mechanical properties and plasticity mechanisms of the alloy based on its composition, key empirical parameters derived from the composition, and solution treatment temperature. The test results of the TPE-xgboost model showed that when predicting the ultimate tensile strength (UTS), the adjusted determination coefficient (Adjusted R-2), root mean square error (RMSE), and mean absolute error (MAE) values were 0.9264, 39.63 MPa and 44.83 MPa, respectively. When predicting elongation (El), the Adjusted R-2, RMSE, and MAE values are 0.9134, 1.97 %, and 1.89 %, respectively. When predicting the plastic mechanisms of the alloy, the F1-score, Recall, Precision, Accuracy, and Area Under the ROC Curve (AUC) were 0.74, 0.75, 0.80, 0.78, and 0.83, respectively. A near-beta titanium alloy, Ti-8V-4Mo-3.5Al-3Cr-2Zr (wt%), along with an associated heat treatment process, has been developed using this model. The experimental results have demonstrated that the model accurately predicts the strength, elongation, and plasticity mechanisms of the alloys. The TRIP/TWIP effects occur due to {332}<113> twinning and secondary alpha" martensite formation during tensile deformation. This study offers an alternative approach for designing TRIP/TWIP near-beta titanium alloys.

关键词： Machine learning Near-beta titanium alloy TRIP TWIP xgboost 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：