Kang Yan

Learn More
The CPU–GPU communication bottleneck limits the performance improvement of GPU applications in heterogeneous GPGPU systems and usually is handled by data reuse optimization. This paper analyzes data reuse through DAG abstraction and obtains rules showing that the run-time data reuse optimization can effectively relieve the bottleneck. Based on the rules,(More)
The size and growth rate of lung nodules highly correlate with the chance of malignancy and they are the most important indicators for assessment of lung cancer treatment effect. Therefore, accurate segmentation of the lung nodules is greatly significant for the diagnosis and treatment of the lung cancers. In this paper, a novel method is introduced to(More)
For increasing the classification accuracy of chest DR images between normal and lesion images, and improving the deficiencies of poor generalization ability of traditional statistical theory, a kind of medical image classification method adapting small samples was proposed. In order to get the decision-making function, SVM classifier was applied to study(More)
A combined sintering aid mixture of B<inf>2</inf>O<inf>3</inf> and CuO for lead-free piezoelectric ceramics 0.95K<inf>0.5</inf>Na<inf>0.5</inf>NbO<inf>3</inf>-0.05BaTiO<inf>3</inf> (KNN-BT) is introduced. The effects of the mixture sintering aids of 0.6B<inf>2</inf>O<inf>3</inf>-0.4CuO on the sintering behavior, microstructure, and electrical properties for(More)
Stack filters are a class of slip window nonlinear digital filters that satisfy a weak superposition property known as the threshold decomposition and stacking property. They are suitable to parallel processing. Stack filters include many kinds of nonlinear filters in theory, being an important tool for nonlinear research. Beginning with stack filters's(More)