Jeng-Tzong Chen^1,2, Jia-Nan Ke¹, Huan-Zhen Liao¹

CMC-Computers, Materials & Continua, Vol.9, No.2, pp. 93-110, 2009, DOI:10.3970/cmc.2009.009.093

Abstract A null-field approach is employed to derive the Green's function for boundary value problems stated for the Laplace equation with circular boundaries. The kernel function and boundary density are expanded by using the degenerate kernel and Fourier series, respectively. Series-form Green's function for interior and exterior problems of circular boundary are derived and plotted in a good agreement with the closed-form solution. The Poisson integral formula is extended to an annular case from a circle. Not only an eccentric ring but also a half-plane problem with an aperture are demonstrated to see the validity of the present approach. Besides, a… More >

Chein-ShanLiu¹

CMC-Computers, Materials & Continua, Vol.13, No.3, pp. 219-234, 2009, DOI:10.3970/cmc.2009.013.219

Abstract The present paper reveals a new computational method for the illposed backward wave problem. The Fourier series is used to formulate a first-kind Fredholm integral equation for the unknown initial data of velocity. Then, we consider a direct regularization to obtain a second-kind Fredholm integral equation. The termwise separable property of kernel function allows us to obtain an analytical solution of regularization type. The sufficient condition of the data for the existence and uniqueness of solution is derived. The error estimate of the regularization solution is provided. Some numerical results illustrate the performance of the new method. More >

Chuanli Wang^1,2, En Zhu¹, Xinwang Liu¹, Jiaohua Qin², Jianping Yin^3,*, Kaikai Zhao⁴

CMC-Computers, Materials & Continua, Vol.61, No.1, pp. 409-421, 2019, DOI:10.32604/cmc.2019.06206

Abstract Multiple kernel clustering based on local kernel alignment has achieved outstanding clustering performance by applying local kernel alignment on each sample. However, we observe that most of existing works usually assume that each local kernel alignment has the equal contribution to clustering performance, while local kernel alignment on different sample actually has different contribution to clustering performance. Therefore this assumption could have a negative effective on clustering performance. To solve this issue, we design a multiple kernel clustering algorithm based on self-weighted local kernel alignment, which can learn a proper weight to clustering performance for each local kernel alignment. Specifically,… More >

Yang Yu¹, Zeyu Xiong^1,*, Yueshan Xiong¹, Weizi Li²

CMC-Computers, Materials & Continua, Vol.61, No.1, pp. 103-118, 2019, DOI:10.32604/cmc.2019.05154

Abstract 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,… More >

Ruikang Xing^1,*, Chenghai Li¹

CMC-Computers, Materials & Continua, Vol.60, No.2, pp. 767-780, 2019, DOI:10.32604/cmc.2019.04500

Abstract In clustering analysis, the key to deciding clustering quality is to determine the optimal number of clusters. At present, most clustering algorithms need to give the number of clusters in advance for clustering analysis of the samples. How to gain the correct optimal number of clusters has been an important topic of clustering validation study. By studying and analyzing the FCM algorithm in this study, an accurate and efficient algorithm used to confirm the optimal number of clusters is proposed for the defects of traditional FCM algorithm. For time and clustering accuracy problems of FCM algorithm and relevant algorithms automatically… More >

CMC-Computers, Materials & Continua, Vol.47, No.3, pp. 179-201, 2015, DOI:10.3970/cmc.2015.047.179

Abstract Discontinuous smoothed particle hydrodynamics (DSPH) method based on traditional SPH method, which can be used to simulate discontinuous physics problems near interface or boundary. Previous works showed that DSPH method has a good application prospect [Xu et al, 2013], but further verification and improvement are demanded. In this paper, we investigate the accuracy of DSPH method by some numerical models. Moreover, to improve the accuracy of DSPH method, first order and second order multidimensional RDSPH methods are proposed by following the idea of restoring particle consistency in SPH (RSPH) method which has shown good results in the improvement of particle… More >

L.H. Kuo¹, M.H. Gu², D.L. Young³, C.Y. Lin³

CMC-Computers, Materials & Continua, Vol.33, No.3, pp. 213-228, 2013, DOI:10.3970/cmc.2013.033.213

Abstract Coupled with the Houbolt method, a third order finite difference time marching scheme, the method of approximate particular solutions (MAPS) has been applied to solve wave equations. Radial basis function has played an important role in the solution process of the MAPS. To show the effectiveness of the MAPS, we compare the results with the well known Kansa's method, timemarching method of fundamental solutions (TMMFS), and traditional finite element methods. To validate the effectiveness and easiness of the MAPS, four numerical examples which including regular, smooth irregular, and non-smooth domains are given. More >