NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise removal.However,high computational load limits its wide application.Based on Principle Component Analysis(PC...NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise removal.However,high computational load limits its wide application.Based on Principle Component Analysis(PCA),Principle Neighborhood Dictionary(PND) was proposed to reduce the computational load of NLM.Nevertheless,as the principle components in PND method are computed directly from noisy image neighborhoods,they are prone to be inaccurate due to the presence of noise.In this paper,an improved scheme for image denoising is proposed.This scheme is based on PND and uses preprocessing via Gaussian filter to eliminate the influence of noise.PCA is then used to project those filtered image neighborhood vectors onto a lower-dimensional space.With the preproc-essing process,the principle components computed are more accurate resulting in an improved de-noising performance.A comparison with some NLM based and state-of-art denoising methods shows that the proposed method performs well in terms of Peak Signal to Noise Ratio(PSNR) as well as image visual fidelity.The experimental results demonstrate that our method outperforms existing methods both subjectively and objectively.展开更多
Brain arteriovenous malformation(BAVM) is frequently described as vascular malformation. Although computer tomography(CT), magnetic resonance imaging(MRI) and angiography can clearly detect lesions, there are no diagn...Brain arteriovenous malformation(BAVM) is frequently described as vascular malformation. Although computer tomography(CT), magnetic resonance imaging(MRI) and angiography can clearly detect lesions, there are no diagnostic biological markers of BAVM available. Current study demonstrated that micro RNA(mi RNA)showed a feasible marker for vascular disease. To find key correlations between these mi RNAs and the onset of BAVM, we carried out chip analysis of serum mi RNAs by identifying 18 potential markers of BAVM. We then constructed a principle component analysis and logistic regression(PCA-LR) model to analyze the 18 mi RNAs collected from 77 patients. Another 9 independent samples were used to test the resulting model. The results showed that mi RNAs hsa-mir-126-3p and hsa-mir-140 are important protective factors, while hsa-mir-338 is a dominating risk factor, all of which have stronger correlation with BAVM than others. We also compared the testing results using PCA-LR model with those using LR model. The comparison revealed that PCA-LR model is better in predicting the disease.展开更多
Serial Analysis of Gene Expression (SAGE) is a powerful tool to analyze whole-genome expression profiles. SAGE data, characterized by large quantity and high dimensions, need reducing their dimensions and extract feat...Serial Analysis of Gene Expression (SAGE) is a powerful tool to analyze whole-genome expression profiles. SAGE data, characterized by large quantity and high dimensions, need reducing their dimensions and extract feature to improve the accuracy and efficiency when they are used for pattern recognition and clustering analysis. A Poisson Model-based Kernel (PMK) was proposed based on the Poisson distribution of the SAGE data. Kernel Principle Component Analysis (KPCA) with PMK was proposed and used in feature-extract analysis of mouse retinal SAGE data. The computa-tional results show that this algorithm can extract feature effectively and reduce dimensions of SAGE data.展开更多
Principle component analysis （PCA） based chi-square test is more sensitive to subtle gross errors and has greater power to correctly detect gross errors than classical chi-square test. However, classical principal c...Principle component analysis （PCA） based chi-square test is more sensitive to subtle gross errors and has greater power to correctly detect gross errors than classical chi-square test. However, classical principal com- ponent test （PCT） is non-robust and can be very sensitive to one or more outliers. In this paper, a Huber function liked robust weight factor was added in the collective chi-square test to eliminate the influence of gross errors on the PCT. Meanwhile, robust chi-square test was applied to modified simultaneous estimation of gross error （MSEGE） strategy to detect and identify multiple gross errors. Simulation results show that the proposed robust test can reduce the possibility of type Ⅱ errors effectively. Adding robust chi-square test into MSEGE does not obviously improve the power of multiple gross error identification, the proposed approach considers the influence of outliers on hypothesis statistic test and is more reasonable.展开更多
基金Supported by the National Natural Science Foundation of China (No. 60776795,60736043,60902031,and 60805012)the Research Fund for the Doctoral Program of Higher Education of China (No. 200807010004,20070701023)the Fundamental Research Funds for the Central Universities of China (No. JY10000902028)
文摘NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise removal.However,high computational load limits its wide application.Based on Principle Component Analysis(PCA),Principle Neighborhood Dictionary(PND) was proposed to reduce the computational load of NLM.Nevertheless,as the principle components in PND method are computed directly from noisy image neighborhoods,they are prone to be inaccurate due to the presence of noise.In this paper,an improved scheme for image denoising is proposed.This scheme is based on PND and uses preprocessing via Gaussian filter to eliminate the influence of noise.PCA is then used to project those filtered image neighborhood vectors onto a lower-dimensional space.With the preproc-essing process,the principle components computed are more accurate resulting in an improved de-noising performance.A comparison with some NLM based and state-of-art denoising methods shows that the proposed method performs well in terms of Peak Signal to Noise Ratio(PSNR) as well as image visual fidelity.The experimental results demonstrate that our method outperforms existing methods both subjectively and objectively.
文摘Brain arteriovenous malformation(BAVM) is frequently described as vascular malformation. Although computer tomography(CT), magnetic resonance imaging(MRI) and angiography can clearly detect lesions, there are no diagnostic biological markers of BAVM available. Current study demonstrated that micro RNA(mi RNA)showed a feasible marker for vascular disease. To find key correlations between these mi RNAs and the onset of BAVM, we carried out chip analysis of serum mi RNAs by identifying 18 potential markers of BAVM. We then constructed a principle component analysis and logistic regression(PCA-LR) model to analyze the 18 mi RNAs collected from 77 patients. Another 9 independent samples were used to test the resulting model. The results showed that mi RNAs hsa-mir-126-3p and hsa-mir-140 are important protective factors, while hsa-mir-338 is a dominating risk factor, all of which have stronger correlation with BAVM than others. We also compared the testing results using PCA-LR model with those using LR model. The comparison revealed that PCA-LR model is better in predicting the disease.
基金Supported by the National Natural Science Foundation of China (No. 50877004)
文摘Serial Analysis of Gene Expression (SAGE) is a powerful tool to analyze whole-genome expression profiles. SAGE data, characterized by large quantity and high dimensions, need reducing their dimensions and extract feature to improve the accuracy and efficiency when they are used for pattern recognition and clustering analysis. A Poisson Model-based Kernel (PMK) was proposed based on the Poisson distribution of the SAGE data. Kernel Principle Component Analysis (KPCA) with PMK was proposed and used in feature-extract analysis of mouse retinal SAGE data. The computa-tional results show that this algorithm can extract feature effectively and reduce dimensions of SAGE data.
基金The National Natural Science Foundation of China(No 60504033)
文摘Principle component analysis （PCA） based chi-square test is more sensitive to subtle gross errors and has greater power to correctly detect gross errors than classical chi-square test. However, classical principal com- ponent test （PCT） is non-robust and can be very sensitive to one or more outliers. In this paper, a Huber function liked robust weight factor was added in the collective chi-square test to eliminate the influence of gross errors on the PCT. Meanwhile, robust chi-square test was applied to modified simultaneous estimation of gross error （MSEGE） strategy to detect and identify multiple gross errors. Simulation results show that the proposed robust test can reduce the possibility of type Ⅱ errors effectively. Adding robust chi-square test into MSEGE does not obviously improve the power of multiple gross error identification, the proposed approach considers the influence of outliers on hypothesis statistic test and is more reasonable.
