检索结果-南通市图书馆

A Unique Relative Entropy-Based Symmetrical Co-occurrence Matrix Thresholding with Statistical Spatial Information

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第3期24卷 622-626页

作者： fan jiulun ZHANG Hong School of Electronic Engineering Xidian University School of Telecommunication and Information Engineering Xi’an University of Posts and Telecommunications

Thresholding based on gray-gray cooccurrence matrix is a local thresholding technique. Relative entropy is usually used to gauge the relative difference of uncertainties in two physical systems, and the relative entropy-based asymmetrical co-occurrence matrix thresholding has been applied successfully. We propose to construct symmetrical co-occurrence matrix with the statistical spatial information from the mean values in object and background regions of an image. In this way, a unique relative entropy-based symmetrical co-occurrence matrix thresholding method is derived. Computer-simulation results demonstrated the higher adaptability and efficiency of the proposed method, as compared with square distance based symmetrical co-ocurrence matrix thresholding, Otsu’s and relative entropy methods.

关键词： Image segmentation Symmetrical cooccurrence matrix Relative entropy thresholding Region mean value

L_(2,1)-norm robust regularized extreme learning machine for regression using CCCP method

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2023年第2期30卷 61-72页

作者： Wu Qing Wang fan fan jiulun Hou Jing School of Automation Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Telecommunication and Information Engineering&School of Artificial Intelligence Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Humanities and Foreign Languages Xi'an University of Posts and TelecommunicationsXi'an 710121China

As a way of training a single hidden layer feedforward network(SLFN),extreme learning machine(ELM)is rapidly becoming popular due to its ***,ELM tends to overfitting,which makes the model sensitive to noise and *** solve this problem,L_(2,1)-norm is introduced to ELM and an L_(2,1)-norm robust regularized ELM(L_(2,1)-RRELM)was proposed.L_(2,1)-RRELM gives constant penalties to outliers to reduce their adverse effects by replacing least square loss function with a non-convex loss *** light of the non-convex feature of L_(2,1)-RRELM,the concave-convex procedure(CCCP)is applied to solve its *** convergence of L_(2,1)-RRELM is also given to show its *** order to further verify the effectiveness of L_(2,1)-RRELM,it is compared with the three popular extreme learning algorithms based on the artificial dataset and University of California Irvine(UCI)*** each algorithm in different noise environments is tested with two evaluation criterions root mean square error(RMSE)and *** results of the simulation indicate that L_(2,1)-RRELM has smaller RMSE and greater fitness under different noise *** analysis shows that L_(2,1)-RRELM has better generalization performance,stronger robustness,and higher anti-noise ability and fitness.

关键词： extreme learning machine(ELM) non-convex loss L_(2,1)-norm concave-convex procedure(CCCP)

Cancelable palmprint template generating algorithm based on adaptive threshold

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2019年第1期26卷 1-11页

作者： Min Xiangshen fan jiulun Zhang Xuefeng Department of Communications and Information Engineering Xi'an University of Posts and Telecommunications

Aiming at the problem of low recognition rate and poor security in the process of palmprint identity authentication,a cancelable palmprint template generating algorithm is proposed,which is based on local Gabor directional pattern with adaptive threshold by mean(m LGDP),difference local Gabor directional pattern with adaptive threshold by mean(m DLGDP)and feature fusion of *** this method,the feature code of the image is segmented and the feature vectors are extracted and *** the Bloom filter is used to achieve many-toone mapping and the location scrambling of palmprint ***,the scrambling result matrix and the user key are irreversibly transformed by the convolution operation to obtain a revocable template of the palmprint *** theoretical and experimental results analysis show that,in the case of key loss,the method of feature fusion can enhance the diversity of the original palmprint template effectively,improve the recognition rate efficiently,and have better security.

关键词： cancelable palmprint template Gabor adaptive threshold feature fusion

Application of smoothing technique on twin support vector hypersphere

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2020年第3期27卷 31-41页

作者： Wu Qing Gao Xiaofeng fan jiulun Zhang Hengchang School of Automation Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Telecom munication and Information Engineering Xi'an University of Posts and TelecommunicationsXi'an 710121China

In order to improve the learning speed and reduce computational complexity of twin support vector hypersphere(TSVH),this paper presents a smoothed twin support vector hypersphere(STSVH)based on the smoothing *** can generate two hyperspheres with each one covering as many samples as possible from the same class ***,STSVH only solves a pair of unconstraint differentiable quadratic programming problems(QPPs)rather than a pair of constraint dual QPPs which makes STSVH faster than the *** considering the differentiable characteristics of STSVH,a fast Newton-Armijo algorithm is used for solving *** experiment results on normally distributed clustered datasets(NDC)as well as University of California Irvine(UCI)data sets indicate that the significant advantages of the proposed STSVH in terms of efficiency and generalization performance.

关键词： twin support vector hypersphere Newton-Armijo algorithm smoothing approximation function unconstraint differentiable optimization

Structural regularized twin support vector machine based on within-class scatter and between-class scatter

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2021年第4期28卷 39-52页

作者： Wu Qing Fu Yanlin fan jiulun Ma Tianlu School of Automation Xi'an University of Posts and TelecommunicationsXi’an 710121China School of Telecommunication and Information Engineering Xi’an University of Posts and TelecommunicationsXi'an 710121China

Robust minimum class variance twin support vector machine(RMCV-TWSVM) presented previously gets better classification performance than the classical TWSVM. The RMCV-TWSVM introduces the class variance matrix of positive and negative samples into the construction of two hyperplanes. However, it does not consider the total structure information of all the samples, which can substantially reduce its classification accuracy. In this paper, a new algorithm named structural regularized TWSVM based on within-class scatter and between-class scatter(WSBS-STWSVM) is put forward. The WSBS-STWSVM can make full use of the total within-class distribution information and between-class structure information of all the samples. The experimental results illustrate high classification accuracy and strong generalization ability of the proposed algorithm.

关键词： generalization ability twin support vector machine within-class scatter between-class scatter

Color image encryption scheme based on chaotic systems

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2018年第2期25卷 39-48页

作者： Min Xiangshen fan jiulun Zhang Xuefeng Ren fang Department of Communications and Information Engineering Xi'an University of Posts and Telecommunications

To improve the security of the color image encryption scheme,a color image encryption scheme based on chaotic systems is proposed. Firstly, the proposed scheme sets the color image as a three-dimensional matrix which is scrambled by affine transformation. Second, the Logistic chaotic sequence applied to generate the control parameter and auxiliary key is used to encrypt the three-dimensionaL matrix. Here, we mainly focus on two methods for encryption processes. One is to generate a chaotic sequence by Logistic map and Henon map, which is used to perform XOR operation with the scrambled components R＇, G＇, B＇ respectively. The other one is to adopt a binary Logistic sequence to select the pixel position for the scrambled components R＇, G＇, B＇ image, and then applying the Henon map and Logistic map with the auxiliary key to perform the replacement encryption. Based on this, an encrypted image is synthesized. Simulation results show that the proposed image encryption scheme can implement better encryption and achieve higher security performance.

关键词： color image cncryption chaotic systems affine transformation Logistic map Henon map security performance

Vehicle color recognition based on smooth modulation neural network with multi-scale feature fusion

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第3期17卷 91-102页

作者： Mingdi HU Long BAI jiulun fan Sirui ZHAO Enhong CHEN School of Communications and Information Engineering&School of Artificial Intelligence Xi’an University of Posts&TelecommunicationsXi’an 710121China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China

Vehicle Color Recognition(VCR)plays a vital role in intelligent traffic management and criminal investigation ***,the existing vehicle color datasets only cover 13 classes,which can not meet the current actual ***,although lots of efforts are devoted to VCR,they suffer from the problem of class imbalance in *** address these challenges,in this paper,we propose a novel VCR method based on Smooth Modulation Neural Network with Multi-Scale Feature Fusion(SMNN-MSFF).Specifically,to construct the benchmark of model training and evaluation,we first present a new VCR dataset with 24 vehicle classes,Vehicle Color-24,consisting of 10091 vehicle images from a 100-hour urban road surveillance ***,to tackle the problem of long-tail distribution and improve the recognition performance,we propose the SMNN-MSFF model with multiscale feature fusion and smooth *** former aims to extract feature information from local to global,and the latter could increase the loss of the images of tail class instances for training with ***,comprehensive experimental evaluation on Vehicle Color-24 and previously three representative datasets demonstrate that our proposed SMNN-MSFF outperformed state-of-the-art VCR *** extensive ablation studies also demonstrate that each module of our method is effective,especially,the smooth modulation efficiently help feature learning of the minority or tail *** Color-24 and the code of SMNN-MSFF are publicly available and can contact the author to obtain.

关键词： vehicle color recognition benchmark dataset multi-scale feature fusion long-tail distribution improved smooth l1 loss

Least squares twin support vector machine with asymmetric squared loss

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2023年第1期30卷 1-16页

作者： Wu Qing Li Feiyan Zhang Hengchang fan jiulun Gao Xiaofeng School of Automation Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Telecommunication and Information Engineering Xi'an University of Posts and TelecommunicationsXi'an 710121China

For classification problems,the traditional least squares twin support vector machine(LSTSVM)generates two nonparallel hyperplanes directly by solving two systems of linear equations instead of a pair of quadratic programming problems(QPPs),which makes LSTSVM much faster than the original *** the standard LSTSVM adopting quadratic loss measured by the minimal distance is sensitive to noise and unstable to *** overcome this problem,the expectile distance is taken into consideration to measure the margin between classes and LSTSVM with asymmetric squared loss(aLSTSVM)is *** to the original LSTSVM with the quadratic loss,the proposed aLSTSVM not only has comparable computational accuracy,but also performs good properties such as noise insensitivity,scatter minimization and re-sampling *** experiments on synthetic datasets,normally distributed clustered(NDC)datasets and University of California,Irvine(UCI)datasets with different noises confirm the great performance and validity of our proposed algorithm.

关键词： classification least squares twin support vector machine asymmetric loss noise insensitivity

A Fixed Suppressed Rate Selection Method for Suppressed Fuzzy C-Means Clustering Algorithm

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics 2014年第8期5卷 1275-1283页

作者： jiulun fan Jing Li School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China School of Electronic Engineering Xidian University Xi’an China

Suppressed fuzzy c-means (S-FCM) clustering algorithm with the intention of combining the higher speed of hard c-means clustering algorithm and the better classification performance of fuzzy c-means clustering algorithm had been studied by many researchers and applied in many fields. In the algorithm, how to select the suppressed rate is a key step. In this paper, we give a method to select the fixed suppressed rate by the structure of the data itself. The experimental results show that the proposed method is a suitable way to select the suppressed rate in suppressed fuzzy c-means clustering algorithm.

关键词： Hard C-Means Clustering Algorithm Fuzzy C-Means Clustering Algorithm Suppressed Fuzzy C-Means Clustering Algorithm Suppressed Rate