检索结果-南通市图书馆

Computers, Materials & Continua 2019年第7期61卷 103-117页

作者： Yang Yu Zeyu Xiong Yueshan Xiong Weizi Li HPCL School of Computer ScienceNational University of Defense TechnologyChangsha410073China Department of Computer Science University of North Carolina at Chapel HillNorth Carolina 27599USA

Logistic regression is often used to solve linear binary classification problems such as machine vision,speech recognition,and handwriting recognition.However,it usually fails to solve certain nonlinear multi-classification problem,such as problem with non-equilibrium samples.Many scholars have proposed some methods,such as neural network,least square support vector machine,AdaBoost meta-algorithm,etc.These methods essentially belong to machine learning categories.In this work,based on the probability theory and statistical principle,we propose an improved logistic regression algorithm based on kernel density estimation for solving nonlinear multi-classification.We have compared our approach with other methods using non-equilibrium samples,the results show that our approach guarantees sample integrity and achieves superior classification.

关键词： Logistic regression multi-classification kernel function density estimation non-equilibrium

Classifier for centrality determination with zero-degree calorimeter at the cooling-storage-ring external-target experiment

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2023年第11期34卷 168-173页

作者： Biao Zhang Li‑Ke Liu Hua Pei Shu‑Su Shi Nu Xu Ya‑Ping Wang Key Laboratory of Quark and Lepton Physics(MOE)and Institute of Particle Physics Central China Normal UniversityWuhan 430079China

The zero-degree calorimeter(ZDC)plays a crucial role toward determining the centrality in the Cooling-Storage-Ring External-target Experiment(CEE)at the Heavy Ion Research Facility in Lanzhou.A boosted decision tree(BDT)multi-classification algorithm was employed to classify the centrality of the collision events based on the raw features from ZDC such as the number of fired channels and deposited energy.The data from simulated^(238)U+^(238)U collisions at 500 MeV∕u,generated by the IQMD event generator and subsequently modeled using the GEANT4 package,were employed to train and test the BDT model.The results showed the high accuracy of the multi-classification model adopted in ZDC for centrality determination,which is robust against variations in different factors of detector geometry and response.This study demon-strates the good performance of CEE-ZDC in determining the centrality in nucleus-nucleus collisions.

关键词： ZDC Boosted decision trees multi-classification IQMD Centrality determination

Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第9期76卷 3763-3781页

作者： Sayyid Kamran Hussain Ali Haider Khan Malek Alrashidi Sajid Iqbal Qazi Mudassar Ilyas Kamran Shah Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering Faculty of Computer ScienceLahore Garrison UniversityLahore54000Pakistan Department of Computer Science Applied CollegeUniversity of TabukTabukSaudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl Hofuf31982Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl HofufSaudi Arabia

As ocular computer-aided diagnostic(CAD)tools become more widely accessible,many researchers are developing deep learning(DL)methods to aid in ocular disease(OHD)diagnosis.Common eye diseases like cataracts(CATR),glaucoma(GLU),and age-related macular degeneration(AMD)are the focus of this study,which uses DL to examine their identification.Data imbalance and outliers are widespread in fundus images,which can make it difficult to apply manyDL algorithms to accomplish this analytical assignment.The creation of efficient and reliable DL algorithms is seen to be the key to further enhancing detection performance.Using the analysis of images of the color of the retinal fundus,this study offers a DL model that is combined with a one-of-a-kind concoction loss function(CLF)for the automated identification of OHD.This study presents a combination of focal loss(FL)and correntropy-induced loss functions(CILF)in the proposed DL model to improve the recognition performance of classifiers for biomedical data.This is done because of the good generalization and robustness of these two types of losses in addressing complex datasets with class imbalance and outliers.The classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy(ACU),recall(REC),specificity(SPF),Kappa,and area under the receiver operating characteristic curve(AUC)as the evaluation metrics.The testing shows that the method is reliable and efficient.

关键词： Deep learning multi-classification focal loss CNN eye disease

A New Process Industry Fault Diagnosis Algorithm Based on Ensemble Improved Binary-Tree SVM

维普期刊数据库评论

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 Electronics 2015年第2期24卷 258-262页

作者： WANG Anna SHA Mo LIU Limei CHU Maoxiang College of Information Science and Engineering Northeastern University

Support vector machine(SVM) is an effective tool in deal with small sample, nonlinear and high dimension classification problems. In this paper, an improved pre-treatment binary-tree SVM is proposed to solve fault diagnosis. Furthermore an ensemble method is presented to establish ensemble SVM. Here the improved SVM is used as weak learning machine. The new ensemble SVM can improve the performance of single binary-tree SVM.At the end, the new algorithm is applied to fault diagnosis of blast furnace faults and the Tennessee Eastman process(TEP). The experiments results show that the improved binary-tree SVM algorithm has an excellent performance on diagnosis speed and accuracy.

关键词： multi-classification Binary-tree SVM Ensemble-learning Fault diagnosis

EEG Based Eye Movements multi-classification Using Convolutional Neural Network

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

EEG Based Eye Movements Multi-Classification Using Convoluti...

第40届中国控制会议

作者： Haodong Zhuang Banghua Yang Bo Li Peng Zan BaiHeng Ma Xia Meng School of Mechatronic Engineering and Automation Research Center of Brain Computer EngineeringShanghai University Science and Technology on Electro-optic Control Laboratory China National Clinical Research Center for Neurological Diseases

Several studies stated that more natural and direct interactive control methods are needed in pilot training especially in case of emergency. The expression of intention based on biological signal is a natural way. Eye movement plays an important role in human interaction with the environment which is suitable as a control instruction. Eye movement signals have certain temporal feature in Electroencephalogram（EEG） signals. We collected the eye movement signals by an EEG headset with dry electrodes with high performance. At the same time, deep learning has shown great success in EEG signal processing. In this work, a shallow 2D-Convolutional Neural Network（CNN） structure is proposed to classify the eye movements in 4 directions of upward, downward, leftward and rightward in EEG signals, which are used as 4 kinds of commands to control virtual aircraft.The data are fed to the network through the simulation training experiment designed by us. The average accuracy of the 4 eye movement directions was 88.13%, 86.59%, 87.78% and 87.85% respectively. Among the 10 subjects, the highest accuracy was 92.71%, the lowest was 84.88%, and the total average accuracy was 87.59%, which proves the effectiveness of the scheme.

关键词： EEG Eye movement Machine learning multi-classification

multi-Purpose Forensics of Image Manipulations Using Residual-Based Feature

在线全文

cnki会议

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第12期65卷 2217-2231页

作者： Anjie Peng Kang Deng Shenghai Luo Hui Zeng Southwest University of Science and Technology Mianyang621010China Binghamton University State University of New YorkNewYork13902USA

The multi-purpose forensics is an important tool for forge image detection.In this paper,we propose a universal feature set for the multi-purpose forensics which is capable of simultaneously identifying several typical image manipulations,including spatial low-pass Gaussian blurring,median filtering,re-sampling,and JPEG compression.To eliminate the influences caused by diverse image contents on the effectiveness and robustness of the feature,a residual group which contains several high-pass filtered residuals is introduced.The partial correlation coefficient is exploited from the residual group to purely measure neighborhood correlations in a linear way.Besides that,we also combine autoregressive coefficient and transition probability to form the proposed composite feature which is used to measure how manipulations change the neighborhood relationships in both linear and non-linear way.After a series of dimension reductions,the proposed feature set can accelerate the training and testing for the multi-purpose forensics.The proposed feature set is then fed into a multi-classifier to train a multi-purpose detector.Experimental results show that the proposed detector can identify several typical image manipulations,and is superior to the complicated deep CNN-based methods in terms of detection accuracy and time efficiency for JPEG compressed image with low resolution.

关键词： Digital image forensics partial correlation auto-regression multi-classification

A multi-classification Algorithm of Semi-Supervised Support Vector Data Description Based on Pairwise Constraints

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Multi-Classification Algorithm of Semi-Supervised Support ...

2013年中国智能自动化学术会议

作者： Ying Zhao Guan-jun Wang Department of Computer Science and Technology China University of Mining and Technology

A constraint-based semi-supervised support vector machine classification learning algorithm is proposed based on support vector data description algorithm with pairs of semi-supervised learning thinking combined.multiple hyperspheres are constructed by constraints for the k-classification problems,so that the original problem converted to a k-classification problem.The algorithm to get positive constraints label and negative constraints label by calculating the degree -membership of unlabeled samples,then multiple hyperspheres constructed based on the multi-classification algorithm.Finally,simulation experiments on artificial datasets and UCI datasets to verify the effectiveness of the algorithm.

关键词： SVDD Semi-supervised learning multi-classification Pairwise constraints

一种基于多分类语义分析和个性化的语义检索方法

在线全文

cnki会议

学校读者我要写书评

暂无评论

东南大学学报（自然科学版） 2014年第2期44卷 261-265页

作者：马应龙李鹏鹏张敬旭华北电力大学控制与计算机工程学院北京102206 甘肃省电力公司兰州730030

为了进一步提升语义检索的精度和改善用户体验,提出了一种基于多分类语义分析和个性化的语义检索方法.首先,利用改进的多分类语义分析方法实现目标文档的向量化,并建立词向量库;然后,利用支持向量机对文档进行分类,并结合文档类别生成... 详细信息

为了进一步提升语义检索的精度和改善用户体验,提出了一种基于多分类语义分析和个性化的语义检索方法.首先,利用改进的多分类语义分析方法实现目标文档的向量化,并建立词向量库;然后,利用支持向量机对文档进行分类,并结合文档类别生成标签索引.在检索时,根据词向量库的引导,使用用户历史检索记录和个人信息优化检索结果.实验结果显示,基于该方法的系统的检索精度、平均DCG和nDCG指标值分别达到0.7,7.267和0.890,较基于Lucene方法和Yahoo Directory方法所得结果的均值分别高出31%,36%和19%.在时间复杂度上,每次检索的平均耗时为0.669 s,较Lucene方法仅增加了0.326 s.由此可见,该方法提高了检索的精度和综合相关度,且额外的时间消耗较少.

关键词：语义检索多分类语义分析词向量库个性化算法 multi-classification semantic analysis (MSA) term vector database (TVDB )

Customer’ Credit Sale Risk classification Based on Support Vector Machine and Rough Sets

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Customer’ Credit Sale Risk Classification Based on Support ...

2010 3rd IEEE International Conference on Computer Science and Information Technology—ICCSIT 2010

作者： Yuping Wu School of Economic and Management Henan Polytechnic University n Jiaozuo 454000 P. R. China

Aiming at the shortages of the existing data-miningmodel for classification of customer’s credit sale risk, a new classification model based on rough sets and support vector machine presents is put forward in this paper. First, the theory of rough set is applied to pick up and reduce the index attributes. Then, the training samples are sent to the support vector machine to train and learn. After that, the sorts of the customers’ credit sale risk in test samples are differentiated.The test results indicate that the new classification model based on rough sets and support vector machine shows higherforecast precision than the traditional ones and it is moreefficient and practical.

关键词： credit sale rough set SVM multi-classification statistical learning theory

Fault Diagnosis for Electrohydraulic Servo Valve Based on Support Vector Machine

在线全文

cnki会议

学校读者我要写书评

暂无评论

Fault Diagnosis for Electrohydraulic Servo Valve Based on Su...

2012年计算机应用与系统建模国际会议

作者： Li Shiqiang Jiang Tongmin Li Xiaoyang school of reliability and system engineering beihang university

Fault diagnosis for hydraulic components has features of nonlinearity and high dimensional pattern identification, so it’s difficult to do it accurately with small sample using some common methods. Aimed at this problem, fault analysis for electro-hydraulic servo valve is carried on and the thought of symptom parameters reflecting the running status is illustrated.firstly. Then combining with function in the toolbox of MATLAB, the function to carry out multi-classification fault diagnosis based on Directed Acyclic Graph (DAG) Support Vector Machine (SVM) theory is built. At last, an example of fault diagnosis t is taken to test and verify the effectiveness of this method.

关键词： multi-classification fault diagnosis Support Vector Machine （SVM） Directed Acyclic Graph （DAG） electro-hydraulic servo valve