Shengli Song

Learn More
Automatic target recognition (ATR) in synthetic aperture radar (SAR) images plays an important role in both national defense and civil applications. Although many methods have been proposed, SAR ATR is still very challenging due to the complex application environment. Feature extraction and classification are key points in SAR ATR. In this paper, we first(More)
Human cytomegalovirus (HCMV) is a well-studied β-herpesvirus virus, which adopts a variety of strategies to evade immune surveillance. It has been reported that in HCMV-infected cells, classical major histocompatibility (MHC) class I molecules are down-regulated, but the MHC class Ib molecule human leukocyte antigen (HLA)-E is normally expressed or even(More)
Named entity recognition (NER) is one of the fundamental problems in many natural language processing applications and the study on NER has great significance. Combining words segmentation and parts of speech analysis, the paper proposes a new NER method based on conditional random fields considering the graininess of candidate entities. The recognition(More)
The exact role of adult thymus in autoimmune disease state is poorly understood. We show here that thymus regulated experimental autoimmune encephalomyelitis (EAE), an animal model for multiple sclerosis, as evidenced by loss of spontaneous recovery in thymectomized EAE mice. There was progressive enrichment for CD4 single-positive Foxp3(+) regulatory T(More)
By using entropy and local neighborhood information, we present in this study a robust adaptive Gaussian regularizing Chan-Vese (CV) model to segment the myocardium from magnetic resonance images with intensity inhomogeneity. By utilizing the circular Hough transformation (CHT) our model is able to detect epicardial and endocardial contours of the left(More)
To improve particle swarm optimization (PSO) computing performance, the centroid of particle swarm is firstly introduced in standard PSO model to enhance interparticle cooperation and information sharing capabilities, then combining randomness and ergodicity of the strong chaotic motion and fast convergence of the simplex method, a novel particle swarm(More)
In this letter, we propose a novel ship detection method in synthetic aperture radar (SAR) imagery via variational Bayesian inference. First, we establish the ship detection probabilistic model which decomposes the SAR image as the sum of a sparse component associated with ships and a sea clutter component. Then, we introduce hierarchical priors of the(More)
An improved particle swarm optimization is used to train ridgelet neural network instead of the traditional gradient algorithms. Firstly, the model of ridgelet neural network and the traditional particle swarm optimization (PSO) algorithm are briefly described. Secondly, an improved particle swarm optimization with self-adaptation mutation factor is(More)
In order to avoid the disadvantages of CFAR detector and make full use of the polarimetric information, a novel method is proposed in this paper for detecting ships of polarimetric SAR images, based on tensor robust principle component analysis (tensor RPCA). This method is completely different from the traditional CFAR detector, and distribution model and(More)
According to the intelligent behavior of social population, the centroid of the individual best of particle swarm is firstly introduced in particle swarm optimization (PSO) model to enhance inter-particle cooperation and information sharing capabilities, then combining the mechanism of population migration algorithm (PMA), a novel PSO algorithm with(More)