Entity

Time filter

Source Type

Langfang, China

Guo L.,Hebei University of Technology | Hu M.,Hebei University of Technology | Zhao L.,Harvard University | Zhao L.,XinAoMDT Technology Co. | And 2 more authors.
BioTechnology: An Indian Journal | Year: 2013

In the brain Magnetic Resonance (MR) images, the nasopharynx part is highly irregular. It is difficult to accurately segment this part. Owing to its powerful capacity in solving non-linearity problems, One-class Support Vector Machine (SVM) method has been widely used as a segmentation tool. However, the conventional one-class SVMs assume that each feature of the samples has the same importance degree for the segmentation result, which is not necessarily true in real applications. In addition, oneclass SVM parameters also affect the segmentation result. In this study, Immune Algorithm (IA) was introduced in searching for the optimal feature weights and the parameters simultaneously. An Immune Feature Weighted SVM (IFWSVM) method was used to segment the nasopharynx in MR images. Theoretical analysis and experimental results showed that the IFWSVM had better performance than the conventional methods. © 2013 Trade Science Inc. - INDIA. Source


Zhang B.,Tsinghua University | Liu S.,CAS Institute of High Energy Physics | Liu F.,Tsinghua University | Zhang X.,XinAoMDT Technology Co. | And 4 more authors.
Journal of Biomedical Optics | Year: 2011

Simultaneous positron emission tomography (PET) and fluorescence tomography (FT) for in vivo imaging of small animals is proposed by a dual-modality system. This system combines a charge-coupled device-based nearinfrared fluorescence imaging with a planar detector pairbased PET. With [ 18F]-2-fluoro-2-deoxy-d-glucose radioactive tracer and the protease activated fluorescence probe, on the one hand, the simultaneous metabolic activity and protease activity in tumor region are revealed by the PET and FT, respectively. On the other hand, the protease activity both on the surface layer and the deep tissue of the tumor is provided by the fluorescence reflection imaging and FT, respectively. ©2011 Society of Photo-Optical Instrumentation Engineers (SPIE). Source


Guo L.,Hebei University of Technology | Zhao L.,Harvard University | Zhao L.,XinAoMDT Technology Co. | Wu Y.,Hebei University of Technology | And 3 more authors.
IEEE Transactions on Magnetics | Year: 2011

Tumor detection using medical images plays a key role in medical practices. One challenge in tumor detection is how to handle the nonlinear distribution of the real data. Owing to its ability of learning the nonlinear distribution of the tumor data without using any prior knowledge, one-class support vector machines (SVMs) have been applied in tumor detection. The conventional one-class SVMs, however, assume that each feature of a sample has the same importance degree for the classification result, which is not necessarily true in real applications. In addition, the parameters of one-class SVM and its kernel function also affect the classification result. In this study, immune algorithm (IA) was introduced in searching for the optimal feature weights and the parameters simultaneously. One-class immune feature weighted SVM (IFWSVM) was proposed to detect tumors in MR images. Theoretical analysis and experimental results showed that one-class IFWSVM has better performance than conventional one-class SVM. © 2011 IEEE. Source


Guo L.,Hebei University of Technology | Li Y.,Hebei University of Technology | Miao D.,Hebei University of Technology | Zhao L.,Harvard University | And 3 more authors.
IEEE Transactions on Magnetics | Year: 2011

In the brain MR images, the boundary of each encephalic tissue is highly irregular. Traditional 3-D reconstruction algorithms are challenged. Owing to its powerful capacity in solving nonlinearity problems, the sphere-shaped support vector machines (SSSVMs) is applied in the 3-D reconstruction. Selecting parameters for SSSVM and the kernel function, however, is a complicated issue. Appropriate parameters can make the model more flexible and help to obtain more accurate data description. In this study, immune algorithm (IA) is used in searching for the optimal parameters. Immune SSSVM (ISSSVM) is proposed to reconstruct the 3-D encephalic tissues in MR images. As shown by the experiment of this study, each encephalic tissue can be reconstructed efficiently, and satisfied accuracy and visual effect can be obtained. © 2011 IEEE. Source


Guo L.,Hebei University of Technology | Wu Y.,Hebei University of Technology | Zhao L.,Harvard University | Zhao L.,XinAoMDT Technology Co. | And 3 more authors.
IEEE Transactions on Magnetics | Year: 2011

The classification of mental tasks is one of key issues of EEG-based brain computer interface (BCI). Differentiating classes of mental tasks from EEG signals is challenging because EEG signals are nonstationary and nonlinear. Owing to its powerful capacity in solving nonlinearity problems, support vector machine (SVM) method has been widely used as a classification tool. Traditional SVMs, however, assume that each feature of a sample contributes equally to classification accuracy, which is not necessarily true in real applications. In addition, the parameters of SVM and the kernel function also affect classification accuracy. In this study, immune feature weighted SVM (IFWSVM) method was proposed. Immune algorithm (IA) was then introduced in searching for the optimal feature weights and the parameters simultaneously. IFWSVM was used to multiclassify five different mental tasks. Theoretical analysis and experimental results showed that IFWSVM has better performance than traditional SVM. © 2011 IEEE. Source

Discover hidden collaborations