Search

Multiple kernel k‐means clustering (MKKC) can efficiently incorporate multiple base kernels to generate an optimal kernel. Many existing MKKC methods all need two‐step operation: learning clustering indicator matrix and performing clustering on it. However, the optimal clustering results of two steps are not equivalent to those of original problem. To address this issue, in this paper we propose a novel method named one‐step multiple kernel k‐means clustering based on block diagonal representation (OS‐MKKC‐BD). By imposing a block diagonal constraint on the product of indicator matrix and its transpose, this method can encourage the indicator matrix to be block diagonal. Then the indicator matrix can produce explicit clustering indicator, so as to implement one‐step clustering, which avoids the disadvantage of two‐step operation. Furthermore, a simple kernel weighting strategy is used to obtain an optimal kernel, which boosts the quality of optimal kernel. In addition, a three‐step iterative algorithm is designed to solve the corresponding optimization problem, where the Riemann conjugate gradient iterative method is used to solve the optimization problem of the indicator matrix. Finally, by extensive experiments on eleven real data sets and comparison of clustering results with 10 MKC methods, it is concluded that OS‐MKKC‐BD is effective. [ABSTRACT FROM AUTHOR]

In this paper, the heat transfer characteristics of a 2D gas–solid spout fluidized bed with a hot gas jet are investigated using computational fluid dynamics-discrete element method. The initial temperature of the background gas and particles in the spouted bed was set to 300 K. The particle temperature distribution after injection of 500 K gas from the bottom, center of the bed, is presented. The simulation results indicate well heat transfer behavior in the bed. Then, statistical analysis is conducted to investigate the influence of inlet gas velocity and particle thermal conductivity on the heat transfer at particle scale in detail. The results indicate that the particle mean temperature and convective heat transfer coefficient (HTC) linearly increase with the increase in inlet gas velocity, while the conductive HTC and the uniformity of particle temperature distribution are dominated by the particle thermal conductivity. The conductive and convective heat transfer play different roles in the spout fluidized bed. These results should be useful for the further research in such flow pattern and the optimization of operating such spouted fluidized beds. [ABSTRACT FROM AUTHOR]

Objective: The aim of the present study is to investigate Chinese handwriting on mobile touch devices, considering the effects of three characteristics of the human finger (type, length, and width) and three characteristics of Chinese characters (direction of the first stroke, number of strokes, and structure).Background: Due to the popularity of touch devices in recent years, finger input for Chinese characters has attracted more attention from both industry and academia. However, previous studies have no systematical consideration on the effects of human finger and Chinese characters on Chinese handwriting performance.Method: An experiment was reported in this article to illustrate the effects of the human finger and Chinese characters on the Chinese handwriting performance (i.e., input time, accuracy, number of protruding strokes, mental workload, satisfaction, and physical fatigue).Results: The experiment results indicated that all six factors have significant effects on Chinese handwriting performance, especially on the input time, accuracy, and number of protruding strokes.Conclusion: Finger type, finger length, finger width, direction of the first stroke, number of strokes, and character structures are significantly influencing Chinese handwriting performance. These factors should be taken into more consideration in future research and the practical design for Chinese handwriting systems. [ABSTRACT FROM AUTHOR]