Narrow Results

Protein structure classification is an important issue in understanding the associations between sequence and structure as well as possible functional and evolutionary relationships. Recently structural genomes initiatives and other high-throughput experiments have populated the biological databases at a rapid pace. In this paper, three types of classifiers, k nearest neighbors, class center and nearest neighbor and probabilistic neural networks and their homogenous ensemble for multiclass protein fold recognition problem are evaluated firstly, and then a heterogenous ensemble Voting System is designed for the same problem. The different features and/or their combinations extracted from the protein fold dataset are used in these classification models. The heterogenous classification results are then put into a voting system to get the final result. The experimental results show that the proposed method can improve prediction accuracy by 4%–10% on a benchmark dataset containing 27 SCOP folds.

In this paper, a new classification method (ADCC) for high-dimensional data is proposed. In this method, a decision cluster classification (DCC) model consists of a set of disjoint decision clusters, each labeled with a dominant class that determines the class of new objects falling in the cluster. A cluster tree is first generated from a training data set by recursively calling a variable weighting k-means algorithm. Then, the DCC model is extracted from the tree. Various tests including Anderson–Darling test are used to determine the stopping condition of the tree growing. A series of experiments on both synthetic and real data sets have been conducted. Their results show that the new classification method (ADCC) performed better in accuracy and scalability than existing methods like k-NN, decision tree and SVM. ADCC is particularly suitable for large, high-dimensional data with many classes.

As various genome sequencing projects have already been completed or are near completion, genome researchers are shifting their focus to functional genomics. Functional genomics represents the next phase, that expands the biological investigation to studying the functionality of genes of a single organism as well as studying and correlating the functionality of genes across many different organisms. Recently developed methods for monitoring genome-wide mRNA expression changes hold the promise of allowing us to inexpensively gain insights into the function of unknown genes. In this paper we focus on evaluating the feasibility of using supervised machine learning methods for determining the function of genes based solely on their expression profiles. We experimentally evaluate the performance of traditional classification algorithms such as support vector machines and k-nearest neighbors on the yeast genome, and present new approaches for classification that improve the overall recall with moderate reductions in precision. Our experiments show that the accuracies achieved for different classes varies dramatically. In analyzing these results we show that the achieved accuracy is highly dependent on whether or not the genes of that class were significantly active during the various experimental conditions, suggesting that gene expression profiles can become a viable alternative to sequence similarity searches provided that the genes are observed under a wide range of experimental conditions.

Magnetic resonance image (MRI) is an important tool to diagnose human diseases effectively. It is very important for research and clinical application to classify the normal and abnormal human brain MRI images automatically. In this paper, an accurate and efficient technique is proposed to extract features of MRIs and classify these images into normal and abnormal categories. We use two-dimensional multifractal detrended fluctuation analysis (2D MF-DFA) to obtain image features. These features are the local generalized Hurst exponents calculated by 2D MF-DFA. In this regard, the values of Hurst exponents are given as the training input vector and are taken to the classifiers. We use $k$-nearest neighbor ($k$-NN) and support vector machine (SVM) to classify a specific brain MRI as normal or glioma affected. For SVM, we apply the leave-one-out cross-validation method for experimental verification. The 2D MF-DFA-SVM system achieved accuracy, sensitivity, and specificity of $99.82\%$ ±$0.07$, $100\%$, and $99.81\%$ ±$0.09$, respectively. The 2D MF-DFA-$k$-NN system achieved accuracy, sensitivity, and specificity of $96\%$, $92.59\%$, and $100\%$, respectively. We find that when performing binary classification for brain MRIs, the SVM is superior to $k$-NN. In addition, our experimental results indicate that the proposed 2D MF-DFA-SVM achieved excellent outcomes compared to those of the previous works. The proposed system is a promising system to clinical use.

This paper proposes an intelligent classification technique to identify two categories of MRI volume data as normal and abnormal. The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to incorrect diagnosis when a large number of MRIs are analyzed. In this work, the textural features are extracted from the MR data of patients and these features are used to classify a patient as belonging to normal (healthy brain) or abnormal (tumor brain). The categorization is obtained using various classifiers such as support vector machine (SVM), radial basis function, multilayer perceptron and k-nearest neighbor. The performance of these classifiers are analyzed and a quantitative indication of how better the SVM performance is when compared with other classifiers is presented. In intelligent computer aided health care system, the proposed classification system using SVM classifier can be used to assist the physician for accurate diagnosis.

Patent classification is a large scale hierarchical text classification (LSHTC) task. Though comprehensive comparisons, either learning algorithms or feature selection strategies, have been fully made in the text categorization field, few work was done for a LSHTC task due to high computational cost and complicated structural label characteristics. For the first time, this paper compares two popular learning frameworks, namely, hierarchical support vector machine (SVM) and k-nearest neighbor (k-NN) that are applied to a LSHTC task. Our experimental results show that the latter outperforms the former for the LSHTC task, which is quite different from the existing results for normal text categorization tasks. In addition, this paper compares different similarity measures and ranking strategies in k-NN framework for LSHTC task. From our empirical study, conclusions can be drawn that k-NN is more appropriate for the LSHTC task than hierarchical SVM. BM25 outperforms other similarity measures and ListWeak gains a better performance than other ranking strategies. Our empirical results also indicate that using all the labels of the retrieved neighbors can remarkably improve classification performance over only using the first label of the retrieved neighbors.

The need to perform large hand-grasping strategies in daily life has promoted the development of robotic hands and prosthetic hands that mimic natural ones. This work presents a system for the detection of 10 basic hand grasps in healthy subjects based on single-channel transient-state Surface Electromyography (sEMG) signals. The studied grasps are large diameter, ring, knife index finger, writing tripod, power sphere, precision sphere, prismatic pinch, lateral, extension type, and parallel extension grasp. Signals were collected from 10 healthy volunteers using three sEMG electrodes connected to an Electromyography (EMG) shield using MATLAB as data acquisition software. The signals were classified using three different classifiers, i.e. $k$-Nearest Neighbors ($k$-NN), Diagonal Linear Discriminant Analysis (dl-DA), and Random Forest (RF). The used features were mean absolute value, integrated absolute value, variance, root mean square value, waveform length, Willison amplitude, slope sign change, zero crossing, autoregressive coefficients, and mean frequency. The results show that good classification accuracy is achieved when classifying a reduced number of grasps using a single-channel transient-state sEMG. The average accuracy for the different classifiers varied from 41.5% to 53.3% when classifying 10 grasps and from 78.4% to 91.9% when classifying five grasps using two features as a trainer. It is found that transient-state sEMG signals are efficient in the detection of different hand grasps, reducing the time to generate control signals and the number of channels.