检索结果-南通市图书馆

Prediction of Shear Bond Strength of Asphalt Concrete Pavement Using Machine Learning Models and grid search Optimization Technique

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 691-712页

作者： Quynh-Anh Thi Bui Dam Duc Nguyen Hiep Van Le Indra Prakash Binh Thai Pham Civil Engineering Department University of Transport Technology54 Trieu KhucThanh XuanHanoi100000Vietnam DDG(R)Geological Survey of India Gandhinagar382010India

Determination of Shear Bond strength(SBS)at interlayer of double-layer asphalt concrete is crucial in flexible pavement *** study used three Machine Learning(ML)models,including K-Nearest Neighbors(KNN),Extra Trees(ET),and Light Gradient Boosting Machine(LGBM),to predict SBS based on easily determinable input ***,the grid search technique was employed for hyper-parameter tuning of the ML models,and cross-validation and learning curve analysis were used for training the *** models were built on a database of 240 experimental results and three input variables:temperature,normal pressure,and tack coat *** validation was performed using three statistical criteria:the coefficient of determination(R2),the Root Mean Square Error(RMSE),and the mean absolute error(MAE).Additionally,SHAP analysis was also used to validate the importance of the input variables in the prediction of the *** show that these models accurately predict SBS,with LGBM providing outstanding ***(Shapley Additive explanation)analysis for LGBM indicates that temperature is the most influential factor on ***,the proposed ML models can quickly and accurately predict SBS between two layers of asphalt concrete,serving practical applications in flexible pavement structure design.

关键词： Shear bond asphalt pavement grid search optimization machine learning

The grid search Algorithm of Tectonic Stress Tensor Based on Focal Mechanism Data and Its Application in the Boundary Zone of China, Vietnam and Laos

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Earth Science 2016年第5期27卷 777-785页

作者： Yongge Wan Shuzhong Sheng Jichao Huang Xiang Li Xin Chen Institute of Disaster Prevention Sanhe 065201 China Earthquake Administration of the Guangxi Autonomous Region Nanning 530022 China

Stress field plays a key role in geodynamics. In this study, an algorithm to determine the stress tensor and its confidence range from focal mechanism data by using grid search method was proposed. The experiment uses artificial focal mechanism data which were generated by extensional, compression and strike-slip stress regime and different level of noise, shows that the precision of the estimated stress tensor based on this algorithm is greatly improved compared with traditional algorithms. This algorithm has three advantages：（1） The global optimal solution of the stress tensor is determined by fine grid search of 1o×1o×1o×0.01 and local minimum value is avoided; （2） precision of focal mechanism data can be considered, i.e., different weight of the focal mechanism data contributes differently to the process of determining stress tensor; （3） the confidence range of the determined stress tensor can be obtained by using F-test. We apply this algorithm in the boundary zone of China, Vietnam and Laos, and obtain the stress field with SSE-NNW compressive stress direction and NEE-SWW extensional stress direction. The stress ratio is 0.6, which shows that the eigen values of the stress tensor are nearly in arithmetic sequence. The stress field in this region is consistent with the left-lateral strike slip of the Dienbien-Lauangphrabang arc fault. The result will be helpful in studying the geological dynamic process in this region.

关键词： stress tensor grid search focal mechanism uncertainty.

维普期刊数据库

A Rapid grid search Method for Solving Dynamic Programming Problems in Economics

在线全文

学校读者我要写书评

暂无评论

Frontiers of Economics in China-Selected Publications from Chinese Universities 2013年第2期8卷 260-271页

作者： Hui He Hao Zhang School of Economics and Key Laboratory of Mathematical Economics Shanghai Universityof Finance and Economics Shanghai 200433 China School of Labor and Human Resources Renmin University of China Beijing 100872 China

We introduce a rapid grid search method in solving dynamic program- ming problems in economics. Compared to mainstream grid search methods, by us- ing local information of the Bellman equation, this method can significantly increase the efficiency in solving dynamic programming problems by reducing the grid points searched in the control space.

关键词： dynamic programming Bellman equation grid search concavity search-ing efficiency

Least Squares Mutual Information for grid search CEEMD:A Suitable Vibration Signal Analysis Method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Least Squares Mutual Information for Grid Search CEEMD:A Sui...

Tumor Classification of Gene Expression Data by Fuzzy Hybrid Twin SVM

第37届中国控制会议

作者： Xu Bo Zhou Fengxing Yan Bao Kang Li Huipeng Liu Yi Yan Dan Wuhan University of Science and Technology Huanggang Normal University Huazhong University of Science and Technology

Empirical mode decomposition（EMD） is an adaptive nonlinear,non-stationary signal analysis and processing *** applications of EMD are primarily restricted by "mode mixing," or information coupling between IMFs（Intrinsic mode function,IMF） such that the result of EMD decomposition cannot correctly reflect the real physical *** summarizing existing analysis and processing methods,this paper proposes an algorithm of integrating the least square mutual information（with grid search for CEEMD decomposition）,and the aliasing frequency to be amended（ensuring orthogonality between various IMF components to further suppress mode mixing,reduce the number of IMF components,and improve computational efficiency）.The validity of the proposed method is verified through simulation *** method is then used to extract the fault characteristic frequency of a rolling bearing micro-fault *** results demonstrate that the proposed algorithm can obtain more accurate fault frequency characteristics with a lower total lumped number,fewer IMF components,and lower computational costs relative to traditional methods.

关键词： mode mixing CEEMD least-squares mutual information grid search rolling bearing micro-fault

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第1期31卷 99-106页

作者： DUAN Hua FENG Tong LIU Songning ZHANG Yulin SU Jionglong College of Mathematics and Systems Science Shandong University of Science and Technology School of AI and Advanced Computing XJTLU Entrepreneur College (Taicang) Xi'an Jiaotong-Liverpool University

A new classification model, the fuzzy hybrid twin support vector machine(TWSVM), namely FHTWSVM, is proposed by combining the fuzzy TWSVM and the hypersphere support vector machine(SVM).The hypersphere SVM is utilized for generating the hyperspheres for the positive and negative class with the smallest possible radius, so that the hyperspheres can contain as many samples as possible. The samples which the hyperspheres cover form a new sample set. Furthermore a distance-based fuzzy function is utilized to calculate the fuzzy factors for the samples. Finally FHTWSVM is used to train all samples with the parameters optimized by grid search. This method can maximize intra-class clustering for noise removal and reduce the influence of *** demonstrate the superiority of the performance of FHTWSVM over other classifiers, e.g., KNN, RF,Bayesian, TWSVM, Ada Boost and XGBoost, a series of experiments is conducted using eight gene expression datasets. The evaluation results show that the proposed approach can improve the classification performance as well as reduce prediction errors for the datasets.

关键词： biology computing support vector machines grid search fuzzy TWSVM hypersphere support vector machine hypersphere SVM intra-class clustering pattern classification fuzzy hybrid twin SVM FHTWSVM tumor classification tumours fuzzy hybrid twin support vector machine learning (artificial intelligence) distance-based fuzzy function fuzzy set theory pattern clustering search problems gene expression data

Master event based backazimuth estimation and its application to downhole microseismic monitoring

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2022年第6期19卷 2675-2682页

作者： Xiao-Bo Meng Hai-Chao Chen Feng-Lin Niu Yi-Jing Du Department of Geophysics Chengdu University of TechnologyChengduSichuan610059China Unconventional Petroleum Research Institute and State Key Laboratory of Petroleum Resources and ProspectingChina University of PetroleumBeijing102249China Department of Earth Environmental and Planetary SciencesRice UniversityHoustonTX77005USA Petro China Research Institute of Petroleum Exploration and Development Beijing100083China

Microseismic monitoring provides a valuable tool for evaluating the effectiveness of hydraulic fracturing ***,robust detection and accurate location of microseismic events are challenging due to the low signal to noise ratio(SNR)of their signals on *** a downhole monitoring setting,P-wave polarization direction measured from 3-component records is usually considered as the backazimuth of the microseismic event,i.e.,the direction of the *** direction and arrival time difference between the P and S waves is used to locate the seismic *** SNR is low,an accurate estimate of event backazimuth becomes very challenging with the traditional covariance matrix *** we propose to employ a master event and use a grid search method to find the backazimuth of a target event that maximizes the dot product of the two backazimuthal vectors of the master and target *** compared the backazimuths measured with the proposed grid-search and the conventional covariance-matrix methods using a large synthetic *** found that the grid-search method yields more accurate backazimuth estimates from low SNR records when measurements are made at single geophone *** array data are combined,the proposed method also has some advantage over the covariance-matrix method,especially when the number of geophones is *** also applied the method to a microseismic dataset acquired by a hydraulic fracturing project at a shale play site in southwestern China and found that the relocated microseismic events tend to align along existing faults more tightly than those in the original catalog.

关键词： Hydraulic fracturing Microseismic event Back azimuth Master event grid search Covariance-matrix

维普期刊数据库

An Early Stopping-Based Artificial Neural Network Model for Atmospheric Corrosion Prediction of Carbon Steel

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第12期65卷 2091-2109页

作者： Phyu Hnin Thike Zhaoyang Zhao Peng Liu Feihu Bao Ying Jin Peng Shi National Center for Materials Service Safety University of Science and Technology BeijingBeijing100083China Department of Computer Engineering and Information Technology Yangon Technological UniversityYangon11181Myanmar

The optimization of network topologies to retain the generalization ability by deciding when to stop overtraining an artificial neural network(ANN)is an existing vital challenge in ANN prediction *** larger the dataset the ANN is trained with,the better generalization the prediction can *** this paper,a large dataset of atmospheric corrosion data of carbon steel compiled from several resources is used to train and test a multilayer backpropagation ANN model as well as two conventional corrosion prediction models(linear and Klinesmith models).Unlike previous related works,a grid search-based hyperparameter tuning is performed to develop multiple hyperparameter combinations(network topologies)to train multiple ANNs with mini-batch stochastic gradient descent optimization algorithm to facilitate the training of a large *** that,one selection strategy for the optimal hyperparameter combination is applied by an early stopping method to guarantee the generalization ability of the optimal network *** correlation coefficients(R)of the ANN model can explain about 80%(more than 75%)of the variance of atmospheric corrosion of carbon steel,and the root mean square errors(RMSE)of three models show that the ANN model gives a better performance than the other two models with acceptable *** influence of input parameters on the output is highlighted by using the fuzzy curve analysis *** result reveals that TOW,Cl-and SO2 are the most important atmospheric chemical variables,which have a well-known nonlinear relationship with atmospheric corrosion.

关键词： Atmospheric corrosion prediction early stopping fuzzy curve grid search hyperparameter tuning multilayer neural network

Fast approximate maximum likelihood period estimation from incomplete timing data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2013年第2期26卷 435-441页

作者： Ye Haohuan Liu Zheng Jiang Wenli College of Electronic Science & Engineering National University of Defense Technology

To estimate the period of a periodic point process from noisy and incomplete observations, the classical periodogram algorithm is modified. The original periodogram algorithm yields an estimate by performing grid search of the peak of a spectrum, which is equivalent to the periodogram of the periodic point process, thus its performance is found to be sensitive to the chosen grid spacing. This paper derives a novel grid spacing formula, after finding a lower bound of the width of the spectral mainlobe. By employing this formula, the proposed new estimator can determine an appropriate grid spacing adaptively, and is able to yield approximate maximum likelihood estimate （MLE） with a computational complexity of O（n2）. Experimental results prove that the proposed estimator can achieve better trade-off between statistical accuracy and complexity, as compared to existing methods. Simulations also show that the derived grid spacing formula is also applicable to other estimators that operate similarly by grid search.

关键词： grid search Maximum likelihood period estimation Periodic point process Periodogram Pulse repetition frequency

维普期刊数据库

SVM Model Selection Using PSO for Learning Handwritten Arabic Characters

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2019年第9期61卷 995-1008页

作者： Mamouni El Mamoun Zennaki Mahmoud Sadouni Kaddour Département Informatique Universitédes Sciences et de la Technologie d’Oran Mohamed Boudiaf USTO-MB BP 1505 El M’naoeur31000OranAlgérie

Using Support Vector Machine(SVM)requires the selection of several parameters such as multi-class strategy type(one-against-all or one-against-one),the regularization parameter C,kernel function and their *** choice of these parameters has a great influence on the performance of the final *** paper considers the grid search method and the particle swarm optimization(PSO)technique that have allowed to quickly select and scan a large space of SVM parameters.A comparative study of the SVM models is also presented to examine the convergence speed and the results of each *** is applied to handwritten Arabic characters learning,with a database containing 4840 Arabic characters in their different positions(isolated,beginning,middle and end).Some very promising results have been achieved.

关键词： SVM PSO handwritten Arabic grid search character recognition