Liangfeng Xu

Learn More
An adaptive facial expression recognition method based on component and global features is presented in this paper. The facial component features are highlighted for purpose of improving facial expression percent correct rate. Firstly, eyebrows, eyes, nose and mouth are divided from a facial expression image and then the component features would be gotten(More)
Considering the instability of link quality, a new routing algorithm for WMN, namely ASA, based on Ant Colony Optimization algorithm(ACO) and simulated annealing algorithm(SA) was presented. This algorithm not only combined the adaptation, robustness and distributed, decentralized merit of ACO but also used SA to remedy the weakness of ant algorithm and(More)
Because of the limitation of Monogenic waves' extraction from expression texture, this thesis proposes an adaptive facial expression feature fusion method based on MBP (monogenic binary pattern) and Histogram of HMOG (monogenic orientated gradients). To begin with our method, we get information of orientation, phase and magnitude component from filtered(More)
Pancreatic cancer is characterized as a type of gastrointestinal tumor with a poor prognosis and high degree of malignancy. CIITA gene was found highly methylated in pancreatic carcinoma cell line PANC-1 and responsible for the low expression of MHC-II that may lead to immune evasion. Here, we tried to prepare pancreatic cancer vaccine with PANC-1 cells via(More)
PURPOSE The organ or tumor activity is not uniform due to inhomogeneous expression/distributions of receptors/antigens and the nonuniform vascularization of the tumor tissue. However, most patient-specific three-dimensional Monte-Carlo methods for radionuclide dosimetry have dealt with quasi-homogeneous activity distributions. A voxel-by-voxel activity(More)
In order to overcome the one-sidedness and limitations of a single subspace in feature extraction and classification, we propose a face recognition method that extracts features in double complementary space and utilize multi-decision for classification. In the feature extraction stage, we use ICA and LPE algorithm as the first layer in complementary space(More)
The Lyman–Kutcher–Burman (LKB) normal tissue complication probability (NTCP) model is often used to estimate the damage level to normal tissue. However, it does not manifestly involve the influence of radiosensitivity parameters. This work replaces the generalized mean equivalent uniform dose (gEUD) with the equivalent uniform dose (EUD) in the LKB model to(More)
PURPOSE To evaluate the influence of energy spectra, mesh sizes, high Z element on dose and PVDR in Microbeam Radiation Therapy (MRT) based on 1-D analogy-mouse-head-model (1-D MHM) and 3-D voxel-mouse-head-phantom (3-D VMHP) by Monte Carlo simulation. METHODS A Microbeam-Array-Source-Model was implemented into EGSnrc/DOSXYZnrc. The microbeam size is(More)