|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Weighted Multi-source TrAdaBoost显示文摘 | CHENG Yuhu CAO Ge WANG Xuesong PAN Jie | 2013 | Chinese Journal of Electronics2013，22，3： | 5 |
| 2 | Dimensionality Reduction for Hyperspectral Data Based on Sample-Dependent Repulsion Graph Regularized Auto-encoder显示文摘To achieve high classification accuracy of hyperspectral data, a dimensionality reduction algorithm called Sample-dependent repulsion graph regularized auto-encoder(SRGAE) is proposed. Based on the sample-dependent graph, by applying the repulsion force to the samples from different classes but nearby, a sampledependent repulsion graph is built to make the samples from the same class will be pro jected to samples that are close-by and the samples from different classes will be pro jected to samples that are far away. The sampledependent repulsion graph can avoid the neighborhood parameter selection problem existing in the nearest neighborhood graph. By integrating advantages of deep learning and graph regularization technique, the SRGAE can maintain the learned deep features are consistent with the inherent manifold structure of the original hyperspectral data. Experimental results on two real hyperspectral data show that, when compared with some popular dimensionality reduction algorithms, the proposed SRGAE can yield higher classification accuracy. | WANG Xuesong KONG Yi CHENG Yuhu | 2017 | Chinese Journal of Electronics2017，26，6： | 4 |
| 3 | THE DISTRIBUTION OF PREFERENTIAL PATHS AND ITS RELATION TO THE SOIL CHARACTERISTICS IN THE THREE GORGES AREA,CHINA显示文摘To study the characteristics of the distribution of the preferential paths and the affecting factors in the Three Gorges area, four soil profiles were dug to observe the distribution of preferential paths in the Quxi watershed in the Yangtze River basin. The Morisita exponential test method was used to examine the distribution type of preferential paths. The physical properties and infiltration characteristics of the soil were also measured to evaluate their relationship to preferential paths. The results showed that in this area, preferential paths clustered and mainly distributed in the 80-100 cm soil layer, and along the interface between the weathered layer and semi-weathered layer. There were more non-capillary pores in the 83-110 cm layer than in the other layers. It can be derived that most non-capillary pores in this layer were preferential paths caused by geological processes and rotten plant roots. The percentage of coarse soil particles increased with the depth of the soil layer. In the deeper soil layer, the coarse soil particles helped the formation of preferential paths. The fastest steady infiltration rate was observed in the of 83-110cm layer, which is inferred to be due to the greater number of preferential paths. | Hongjiang ZHANG Jinhua CHENG Yuhu SHI Yun CHENG | 2007 | International Journal of Sediment Research2007，22，1： | 4 |
| 4 | A Quick Convex Hull Building Algorithm Based on Grid and Binary Tree显示文摘A quick convex hull building algorithm using grid and binary tree is proposed for the minimum convex buidling of planar point set. Grids are used to assess and eliminate those interior points wihtout any contribution to convex hull building and points are sought in the boundary grid only so as to enhance the efficiency of algorithm. The minimum convex bull is built by taking such advantages of binary tree as quick, convenient and applicable for various point sets with different distributions, so as to resolve the description problem of concave point. The time complexity of the algorithm is low because of grid pretreatment. As the results of comparative expriment of random point and actual picture show, the proposed algorithm can obtain the best profile of 2D planar picture with minimum time, which is applicable for describing the shape of irregular convex-concave objects. | GAO Yang CHENG Yuhu WANG Xuesong | 2015 | Chinese Journal of Electronics2015，24，2： | 4 |
| 5 | Fault diagnosis using a probability least squares support vector classification machine显示文摘Coal mines require various kinds of machinery. The fault diagnosis of this equipment has a great impact on mine production. The problem of incorrect classification of noisy data by traditional support vector machines is addressed by a proposed Probability Least Squares Support Vector Classification Machine (PLSSVCM). Samples that cannot be definitely determined as belonging to one class will be assigned to a class by the PLSSVCM based on a probability value. This gives the classification results both a qualitative explanation and a quantitative evaluation. Simulation results of a fault diagnosis show that the correct rate of the PLSSVCM is 100%. Even though samples are noisy, the PLSSVCM still can effectively realize multi-class fault diagnosis of a roller bearing. The generalization property of the PLSSVCM is better than that of a neural network and a LSSVCM. | GAO Yang, WANG Xuesong, CHENG Yuhu, PAN Jie School of Information and Electrical Engineering, China University of Mining & Technology, Xuzhou 221116, China | 2010 | Mining Science and Technology2010，20，6： | 4 |
| 6 | Identification of Overlapping Protein Complexes Using Structural and Functional Information of PPI Network显示文摘An identification algorithm of overlapping protein complexes is put forward by simultaneously considering the topological structural and biological functional information of Protein-protein interaction(PPI) network.Main works include: constructing the edge weight of weighted PPI network on the basis of structural and functional information of PPI network to more accurately describe the correlation between protein vertices; improving the Newman algorithm to make it applicable to weighted PPI network and thus to identify overlapping protein complexes; and providing the denoising criteria based on the structural and function information of PPI network: connections which have no contribution to the high aggregation of PPI network or which are among proteins of independent functions are judged to be false positive connections. The experimental results on the dataset of saccharomyces cerevisiae PPI network show that the proposed algorithm has higher identification accuracy and matching rate when compared with the current representative identification algorithms of protein complexes. | WANG Xuesong CHENG Yuhu SUN Weifang | 2015 | Chinese Journal of Electronics2015，24，3： | 4 |
| 7 | An Ensemble Classifier Based on Selective Independent Component Analysis of DNA Microarray Data显示文摘 | WANG Xuesong WANG Xuesong GU Yangyang GU Yangyang CHENG Yuhu CHENG Yuhu ZHANG Zheng ZHANG Zheng | 2009 | Chinese Journal of Electronics2009，18，4： | 3 |
| 8 | Domain Adaptation Network Based on Autoencoder显示文摘The domain adaptation uses labeled source domain data to train a classifier to be used in the target domain with no or small amount of labeled data. Usually there exists discrepancy in terms of marginal and conditional distributions for both source and target domains,which is of critical importance to minimize the distribution discrepancy between domains. As a classical model in deep learning, the autoencoder is capable of realizing distribution matching and enhancing classification accuracy by extracting more abstract and effective features from data. A Domain adaptation network based on autoencoder(DANA) is proposed. The DANA structure consists of a couple of encoding layers: a feature extraction layer and a classification layer. For the feature extraction layer,the marginal distributions of source and target domains are matched by using the nonparametric maximum mean discrepancy measurement. For the classification layer, the softmax regression model is applied to encode the label information of source domains meanwhile to match the conditional distribution. Experimental results on ImageNet,Corel and Leaves datasets have shown the enhanced classification accuracy by our proposed algorithm compared with the classical methods. | WANG Xuesong MA Yuting CHENG Yuhu | 2018 | Chinese Journal of Electronics2018，27，6： | 3 |
| 9 | Hyperspectral Image Classification Based on Unsupervised Heterogeneous Domain Adaptation CycleGan显示文摘Aiming at the difficulty of obtaining sufficient labeled Hyperspectral image(HSI)data and the inconsistent feature distribution of different HSIs,a novel Unsupervised heterogeneous domain adaptation CycleGan(UHDAC)is proposed by using CycleGan to capture the transferable features in the absence of similar data.On the one hand,the two-way mapping is used to find the internal relationship between the source and target domain data,while the two-way adversary is used to constrain the source and target domain features,realizing the alignment of feature distributions.On the other hand,the CORAL loss function is introduced to minimize the distance between the second-order statistical difference between the source and target domain features,so as to solve the insufficient constraint of mapping relationship caused by the low consistency of HSI data structure in different domains.Experiments on three real HSI datasets show that UHDAC can effectively realize the unsupervised classification of target domain HSI with high classification accuracy by using the labeled HSI data in the source domain. | WANG Xuesong LI Yiran CHENG Yuhu | 2020 | Chinese Journal of Electronics2020，29，4： | 3 |
| 10 | Real-Time Wind Power Forecast Error Estimation Based on Eigenvalue Extraction by Dictionary Learning显示文摘Because of the fluctuation and uncertainty characteristics of wind power, it is difficult to achieve a perfect wind power forecast. The forecast error may lead to an imbalance between the load demand and power supply. The object of recent research on forecast error is to achieve the probability distribution of forecast error based on the statistics of historical data. This statistical error achieved from a probability distribution cannot reveal the real-time condition of wind power. A real-time forecast Error estimate method based on dictionary learning(EEDL) was proposed. In EEDL, several coefficients that have strong relevance to the forecast error are computed.The dictionary learning method is used to extract the eigenvalues of forecast error from these coefficients. Based on the eigenvalues, a real-time error estimation model was built to obtain the forecast error. EEDL was compared to the estimation method based on a Probability distribution function(PDF). The performance of EEDL was also compared to the error estimation method based on a PDF while using different forecast techniques. | HAN Li LI Mingze WANG Xuesong CHENG Yuhu | 2019 | Chinese Journal of Electronics2019，28，2： | 3 |
| 11 | Joint Feature Representation and Classifier Learning Based Unsupervised Domain Adaption ELM显示文摘In the problem of unsupervised domain adaption Extreme learning machine(ELM), the output layer parameters need to have both classification and domain adaptation functions, which often cannot be simultaneously fully utilized. In addition, traditional matching method based on data probability distribution cannot find the common subspace of source and target domains under large difference between domains. In order to alleviate the pressure of double functions of classifier parameters, the entire ELM learning process is mainly divided into two stages: feature representation and adaptive classifier learning, thus a joint feature representation and classifier learning based unsupervised domain adaption ELM model is proposed. In the feature representation stage, the source and target domain data are projected to their respective subspace while minimizing the difference in probability distribution between the two domains. In the adaptive classifier learning stage, the smooth manifold regularization term of target domain is used to improve the parameter adaptive ability.Experiments on six different types of datasets show that the proposed model has higher cross-domain classification accuracy. | WANG Xuesong ZHAO Jijuan CHENG Yuhu YU Qiang | 2021 | Chinese Journal of Electronics2021，30，1： | 3 |
| 12 | Protein Function Prediction Based on Active Semi-supervised Learning显示文摘In our study,the active learning and semisupervised learning methods are comprehensively used for label delivery of proteins with known functions in Proteinprotein interaction(PPI) network so as to predict the functions of unknown proteins.Because the real PPI network is generally observed with overlapping protein nodes with multiple functions,the mislabeling of overlapping protein may result in accumulation of prediction errors.For this reason,prior to executing the label delivery process of semi-supervised learning,the adjacency matrix is used to detect overlapping proteins.As the topological structure description of interactive relation between proteins,PPI network is observed with party hub protein nodes that play an important role,in co-expression with its neighborhood.Therefore,to reduce the manual labeling cost,party hub proteins most beneficial for improvement of prediction accuracy are selected for class labeling and the labeled party hub proteins are added into the labeled sample set for semisupervised learning later.As the experimental results of real yeast PPI network show,the proposed algorithm can achieve high prediction accuracy with few labeled samples. | WANG Xuesong CHENG Yuhu LI Lijing | 2016 | Chinese Journal of Electronics2016，25，4： | 2 |
| 13 | Multi-source Local Color Transfer Based on Texture Similarity显示文摘In order to realize automatic region matching between source and target images, a multi-source local color transfer algorithm based on texture similarity is proposed. The source and target images are segmented into a set of regions using an image segmentation algorithm. It computes the texture features of each region through the gray level co-occurrence matrix and then constructs corresponding texture feature vectors. The authors measure the relevance between the target and source regions by computing the Euclidean distance between corresponding texture feature vectors. The source region having the largest relevance with the target region is selected as the transfer source. Complete the color transfer by performing color space transformation and linear conversion on color values. Experimental results concerning on multi-source local color transfer and gray image colorization verify the validity of the proposed algorithm. | WANG Xuesong CAO Ge CHENG Yuhu | 2014 | Chinese Journal of Electronics2014，23，4： | 2 |
| 14 | Qualitative Analysis of Gene Regulatory Networks Based on Angular Discretization显示文摘 | WANG Xuesong LIU Qingfeng CHENG Yuhu LI Lijing | 2011 | Chinese Journal of Electronics2011，20，4： | 2 |
| 15 | A Bayesian Reinforcement Learning Algorithm Based on Abstract States for Elevator Group Scheduling Systems显示文摘 | CHENG Yuhu WANG Xuesong ZHANG Yiyang | 2010 | Chinese Journal of Electronics2010，19，3： | 2 |
| 16 | Value approximation with least squares support vector machine in reinforcement learning system显示文摘 | Xuesong Wang Xilan Tian Yuhu Cheng | 2007 | Joturnal of Computational and Theoretical Nanoscience2007，4，78： | 1 |
| 17 | A Fuzzy Actor-critic Reinforcement Learning Network 显示文摘 | Wang Xuesong Cheng Yuhu Yi Jianqiang | 2007 | Info- rmation Sciences2007，177，18： | 1 |
| 18 | Supervised Penalty Matrix Decomposition for Tumor Differentially Expressed Genes Selection显示文摘A reliable and precise recognition of the differentially expressed genes of tumor is crucial to treat the cancer effectively. The small number of differentially expressed genes in a huge gene expression dataset determines the important role of sparse methods, such as Penalty matrix decomposition(PMD), among the feature selection methods. The sparse methods always have the drawback: they do not take advantage of known class labels of gene expression data. A novel supervised-sparse method named as Supervised PMD(SPMD) is proposed by adding the class information into PMD via the total scatter matrix. The brief idea of our method used to select the differentially expressed genes is given as follows.The total scatter matrix is obtained according to the gene expression data with class label. The obtained total scatter matrix is decomposed by PMD to acquire the sparse vectors. The non-zero items in sparse vectors are selected as the differentially expressed genes. The Gene ontology(GO) enrichment of functional annotation of the selected genes is detected by Topp Fun. Experiments on synthetic data and two real tumor gene expression datasets show that the proposed SPMD is quite promising to select the differentially expressed genes. | LIU Jian CHENG Yuhu WANG Xuesong CUI Xiaoluo | 2018 | Chinese Journal of Electronics2018，27，4： | 1 |
| 19 | A novel cis‐AB allele derived from a unique 796C>A mutation in exon 7 of ABO gene显示文摘 | Cheng‐HwaiTzeng Ying‐JuChen Jau‐YiLyou Pei‐ShanChen Hsueng‐MeiLiu Hui‐YuHu Jeong‐ShiLin Lung‐ChihYu | 2004 | Transfusion2004，，1： | 1 |
| 20 | Missing Value Estimation for Gene Expression Profile Data显示文摘 | WANG Xuesong LIU Qingfeng CHENG Yuhu | 2012 | Chinese Journal of Electronics2012，21，4： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员