Search

Background: The detection of Alzheimer's Disease (AD) in its formative stages, especially in Mild Cognitive Impairments (MCI), has the potential of helping the clinicians in understanding the condition. The literature review shows that the classification of MCI-converts and MCI-non-converts has not been explored profusely and the maximum classification accuracy reported is rather low. Thus, this paper proposes a Machine Learning approach for classifying patients of MCI into two groups one who converted to AD and the others who are not diagnosed with any signs of AD. The proposed algorithm is also used to distinguish MCI patients from controls (CN). This work uses the Structural Magnetic Resonance Imaging data.Methods: This work proposes a 3-D variant of Local Binary Pattern (LBP), called LBP-20 for extracting features. The method has been compared with 3D-Discrete Wavelet Transform (3D-DWT). Subsequently, a combination of 3D-DWT and LBP-20 has been used for extracting features. The relevant features are selected using the Fisher Discriminant Ratio (FDR) and finally the classification has been carried out using the Support Vector Machine.Results: The combination of 3D-DWT with LBP-20 results in a maximum accuracy of 88.77. Similarly, the proposed combination of methods is also applied to distinguish MCI from CN. The proposed method results in the classification accuracy of 90.31 in this data.Conclusion: The proposed combination is able to extract relevant distribution of microstructures from each component, obtained with the use of DWT and thereby improving the classification accuracy. Moreover, the number of features used for classification is significantly less as compared to those obtained by 3D-DWT. The performance of the proposed method is measured in terms of accuracy, specificity and sensitivity and is found superior in comparison to the existing methods. Thus, the proposed method may contribute to effective diagnosis of MCI and may prove advantageous in clinical settings. [ABSTRACT FROM AUTHOR]

Nonparametric Discriminant Analysis (NDA) possesses inherent advantages over Linear Discriminant Analysis (LDA) such as capturing the boundary structure of samples and avoiding matrix inversion. In this paper, we present a novel method for constructing an updated Nonparametric Discriminant Analysis (NDA) model for face recognition. The proposed method is applicable to scenarios where bursts of data samples are added to the existing model in random chunks. Also, the samples which degrade the performance of the model need to be removed. For both of these problems, we propose incremental NDA (INDA) and decremental NDA (DNDA) respectively. Experimental results on four publicly available datasets viz. AR, PIE, ORL and Yale show the efficacy of the proposed method. Also, the proposed method requires less computation time in comparison to batch NDA which makes it suitable for real time applications. [ABSTRACT FROM AUTHOR]

With the advent of microarray technology, it is possible to measure gene expression levels of thousands of genes simultaneously. This helps us diagnose and classify some particular cancers directly using DNA microarray. Highdimensionality and small sample size of microarray datasets has made the task of classification difficult. These datasets contain a large number of redundant and irrelevant genes. For efficient classification of samples there is a need of selecting a smaller set of relevant and non-redundant genes. In this paper, we have proposed a two stage algorithm for finding a set of discriminatory genes responsible for classification of high dimensional microarray datasets. In the first stage redundancy is reduced by grouping correlated genes into clusters and selecting a representative gene from each cluster. Maximal information compression index is used to measure similarity between genes. In the second stage a wrapper based forward feature selection method is used to obtain a set of discriminatory genes for a given classifier. We have investigated three different techniques for clustering and four classifiers in our experiments. The proposed algorithm is tested on six well known publicly available datasets. Comparison with the other state-of-the-art methods show that our proposed algorithm is able to achieve better classification accuracy with less number of genes. [ABSTRACT FROM AUTHOR]