Feature Subset Selection For Classification Research Articles

Enhanced textural analysis for endometrial tuberculosis identification from ultrasound images

Endometrial Tuberculosis (ETB) is a major observation in Infertility due to Female Genital Tuberculosis (FGTB). Transvaginal ultrasound (TVUS) images are used to initiate the diagnostic procedure. An effective computational method to identify and classify ETB from TVUS images is presented in this paper. The images from female patients have been collected from medical centers in India. A composite co-occurrence model is proposed; where a Non-Subsampled Contourlet Transformation (NSCT) enhances the textural appearances of the images before feature extraction. Since original TVUS are inherently ill defined; the transformation highlights the directional, multi- scale spectral texture features for discriminatory analysis. Experimental results show that the textural features extracted from these transformed images are more discriminative. The proposed approach achieved an F-score of 0.821and a sensitivity of 0.801 for the dataset in hand. A dimensionality reduction of 66.6% is achieved by Entropy based Normalized Mutual Information ranking and subsequent feature subset selection for classification.

Feature subset selection for classification of malignant and benign breast masses in digital mammography

Computer-aided diagnosis of breast cancer is becoming increasingly a necessity given the exponential growth of performed mammograms. In particular, the breast mass diagnosis and classification arouse nowadays a great interest. Texture and shape are the most important criteria for the discrimination between benign and malignant masses. Various features have been proposed in the literature for the characterization of breast masses. The performance of each feature is related to its ability to discriminate masses from different classes. The feature space may include a large number of irrelevant ones which occupy a lot of storage space and decrease the classification accuracy. Therefore, a feature selection phase is usually needed to avoid these problems. The main objective of this paper is to select an optimal subset of features in order to improve masses classification performance. First, a study of various descriptors which are commonly used in the breast cancer field is conducted. Then, selection techniques are used in order to determine the most relevant features. A comparative study between selected features is performed in order to test their ability to discriminate between malignant and benign masses. The database used for experiments is composed of mammograms from the MiniMIAS database. Obtained results show that Gray-Level Run-Length Matrix features provide the best result.

Sequence Features and Subset Selection Technique for the Prediction of Protein Trafficking Phenomenon in Eukaryotic Non Membrane Proteins

Protein trafficking or protein sorting is the mechanism by which a cell transports proteins to the appropriate position in the cell or outside of it. This targeting is based on the information contained in the protein. Many methods predict the subcellular location of proteins in eukaryotes from the sequence information. However, most of these methods use a flat structure to perform prediction. In this work, we introduce ensemble methods to predict locations in the eukaryotic protein-sorting non membrane pathway hierarchically. We used features that were extracted exclusively from full length protein sequences with feature subset selection for classification. Sequence driven features, sequence mapped features and sequence autocorrelation features were tested with ensemble learners and classifier performances were compared with and without feature subset selection technique. This study shows the new features extracted from full length eukaryotic protein sequences are effective at capturing biological features among compartments in eukaryotic non membrane pathways at two levels. Feature subset selection techniques helped to reduce the time taken for building the classification model.

Searching for interacting features in subset selection1

The evolving and adapting capabilities of robust intelligence are best manifested in its ability to learn. Machine learning enables computer systems to learn, and improve performance. Feature selection facilitates machine learning (e.g., classification) by aiming to remove irrelevant features. Feature (attribute) interaction presents a challenge to feature subset selection for classification. This is because a feature by itself might have little correlation with the target concept, but when it is combined with some other features, they can be strongly correlated with the target concept. Thus, the unintentional removal of these features may result in poor classification performance. It is computationally intractable to handle feature interactions in general. However, the presence of feature interaction in a wide range of real-world applications demands practical solutions that can reduce high-dimensional data while preserving feature interactions. In this paper, we take up the challenge to design a special data structure for feature quality evaluation, and to employ an information-theoretic feature ranking mechanism to efficiently handle feature interaction in subset selection. We conduct experiments to evaluate our approach by comparing with some representative methods, perform a lesion study to examine the critical components of the proposed algorithm to gain insights, and investigate related issues such as data structure, ranking, time complexity, and scalability in search of interacting features.

Feature subset selection for classification of histological images

Classification of histological images is considered in this paper. The task is to distinguish different classes of tumours of the central nervous system on the basis of features extracted from microscopic slides. The number of extracted features is relatively high and some of them seem to be irrelevant for classification of the images. Thus, the main objective of this study is to select such a feature subset that improves the predictive accuracy of the classifier. The wrapper approach is chosen to obtain this aim, where a search for the good subset of features is made using a non-parametric case-base classifier. To guide a search process, a forward beam selection algorithm is introduced. It sequentially adds relevant features in a parallel way for the most promising subsets. It is shown that the proposed approach gives good predictive accuracy for the considered histopathological problem.