Comparison of text feature selection policies and using an adaptive framework

Text categorization is the task of automatically assigning unlabeled text documents to some predefined category labels by means of an induction algorithm. Since the data in text categorization are high-dimensional, often feature selection is used for reducing the dimensionality. In this paper, we make an evaluation and comparison of the feature selection policies used in text categorization by employing some of the popular feature selection metrics. For the experiments, we use datasets which vary in size, complexity, and skewness. We use support vector machine as the classifier and tf-idf weighting for weighting the terms. In addition to the evaluation of the policies, we propose new feature selection metrics which show high success rates especially with low number of keywords. These metrics are two-sided local metrics and are based on the difference of the distributions of a term in the documents belonging to a class and in the documents not belonging to that class. Moreover, we propose a keyword selection framework called adaptive keyword selection. It is based on selecting different number of terms for each class and it shows significant improvement on skewed datasets that have a limited number of training instances for some of the classes.     

Investigation of the Effect of Ni Amount on the Wear Performance of A356 Cast Aluminum Alloys

Metallurgist - This study investigates the effect of artificial aging treatment on wear performance of A356 alloy containing different amounts of Ni. Within the scope of the study, A356/Ni alloys...     

Effects of Li Substitution in Bi-2223 Superconductors

The effects of Li substitution on the properties of high temperature superconductor Bi₁₇Pb_0.3Sr₂C₂Cu_3−x Li _x O _y were investigated. The samples were prepared by substituting Li (x=0.00–0.20) with changing ratios by a solid state reaction method. The samples were characterized by X-ray diffraction, DC electrical resistivity, AC magnetic susceptibility, and scanning electronic microscopy (SEM). The X-ray diffraction studies were done at room temperature and the lattice constants of the material were determined by indexing all the peaks observed. This study shows that there are two coexisting phases; high-T _c (2223) phase and low-T _c (2212) phase. The lattice structure of the material belongs to the orthorhombic unit cell. The volume fraction was estimated from the intensities of Bi-(2223) and Bi-(2212) phases. The sample with 20 wt% of added Li showed the higher volume fraction of Bi-(2223) phase formed (81%) compared to the other samples. The DC electrical resistivity of all the samples decreased as the wt% of Li increased. Both the onset critical temperatures T _c (onset) and zero electrical resistivity critical temperatures T _c (R=0) of the samples were determined from the DC electrical resistivity measurements. The observed value of the onset critical T _c (onset) temperature was 110 K agreeing well with the magnetic susceptibility measurements. We obtained T _c onset at 112 K from AC magnetic susceptibility measurements.      

Adsorption of lead and copper on bentonite and grapeseed activated carbon in single- and binary-ion systems

In this study, bentonite originating from Turkey (Eski?ehir province) and activated carbon obtained from grapeseed were used as adsorbents for the removal of lead (Pb²⁺) and copper (Cu²⁺) ions from aqueous solutions. Experiments were performed in single- and binary-ion systems at constant temperature of 298 K and pH value of 5. In order to describe the adsorption mechanism Langmuir, Freundlich and Temkin isotherms were used. The total adsorption capacity values of adsorbents were compared. It was observed that the total adsorption capacity values were changed depending on the type of adsorbent used, type of metal ion and interaction between metal ions.     

Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines

This paper presents a new approach for the classification of the power system disturbances using support vector machines (SVMs). The proposed approach is carried out at three serial stages. Firstly, the features to be form the SVM classifier are obtained by using the wavelet transform and a few different feature extraction techniques. Secondly, the features exposing the best classification accuracy of these features are selected by a feature selection technique called as sequential forward selection. Thirdly, the best appropriate input vector for SVM classifier is rummaged. The input vector is started with the first best feature and incrementally added the chosen features. After the addition of each feature, the performance of the SVM is evaluated. The kernel and penalty parameters of the SVM are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. Finally, both the noisy and noiseless signals are applied to the classifier given above stages. Experimental results indicate that the proposed classifier is robust and has more high classification accuracy with regard to the other approaches in the literature for this problem.     

Implementation of a single-phase matrix converter induction motor drive

This paper presents an implementation of a single-phase matrix converter for a variable speed single-phase induction motor. The paper analyzes the characteristics of a single-phase ac–ac converter drive with particular emphasis on the harmonic content, input voltage utilization and variable speed performance of the motor. Both square and sinusoidal wave modulation signals in PWM generation have been used to demonstrate the effect of the modulating signal on the input voltage utilization and output harmonic content. Simulation and experimental results for an R–L and induction motor loads are presented. Promising results illustrate that a good performance of a single-phase induction motor fed by a matrix converter is achievable.     

Clustering of high throughput gene expression data

High throughput biological data need to be processed, analyzed, and interpreted to address problems in life sciences. Bioinformatics, computational biology, and systems biology deal with biological problems using computational methods. Clustering is one of the methods used to gain insight into biological processes, particularly at the genomics level. Clearly, clustering can be used in many areas of biological data analysis. However, this paper presents a review of the current clustering algorithms designed especially for analyzing gene expression data. It is also intended to introduce one of the main problems in bioinformatics – clustering gene expression data – to the operations research community.     

Iterative performance improvement of fuzzy control systems for three tank systems

This paper suggests the performance improvement of fuzzy control systems (FCSs) for three tank systems using iterative feedback tuning (IFT). The stable design of Takagi–Sugeno–Kang fuzzy controllers is guaranteed by means of a stability theorem based on LaSalle’s global invariant set theorem formulated for a class of multi input-multi output (MIMO) nonlinear processes. An IFT algorithm characterized by setting the step size to guarantee the FCS stability is proposed. The theoretical approaches are applied in a case study that deals with the IFT-based stable design of fuzzy controllers dedicated to the level control of a cylindrical three tank system as a representative MIMO system. A set of experimental results for a laboratory setup illustrates the performance improvement.     

Medical application of information gain based artificial immune recognition system (AIRS): Diagnosis of thyroid disease

In this paper, we have made medical application of a new artificial immune system named the information gain based artificial immune recognition system (IG-AIRS) which minimizes the negative effects of taking into account all attributes in calculating Euclidean distance in shape–space representation which is used in many artificial immune systems. For medical data, thyroid disease data set was applied in the performance analysis of our proposed system. Our proposed system reached 95.90% classification accuracy with 10-fold CV method. This result ensured that IG-AIRS would be helpful in diagnosing thyroid function based on laboratory tests, and would open the way to various ill diagnoses support by using the recent clinical examination data, and we are actually in progress.     

A new feature selection method on classification of medical datasets: Kernel F-score feature selection

In this paper, we have proposed a new feature selection method called kernel F-score feature selection (KFFS) used as pre-processing step in the classification of medical datasets. KFFS consists of two phases. In the first phase, input spaces (features) of medical datasets have been transformed to kernel space by means of Linear (Lin) or Radial Basis Function (RBF) kernel functions. By this way, the dimensions of medical datasets have increased to high dimension feature space. In the second phase, the F-score values of medical datasets with high dimensional feature space have been calculated using F-score formula. And then the mean value of calculated F-scores has been computed. If the F-score value of any feature in medical datasets is bigger than this mean value, that feature will be selected. Otherwise, that feature is removed from feature space. Thanks to KFFS method, the irrelevant or redundant features are removed from high dimensional input feature space. The cause of using kernel functions transforms from non-linearly separable medical dataset to a linearly separable feature space. In this study, we have used the heart disease dataset, SPECT (Single Photon Emission Computed Tomography) images dataset, and Escherichia coli Promoter Gene Sequence dataset taken from UCI (University California, Irvine) machine learning database to test the performance of KFFS method. As classification algorithms, Least Square Support Vector Machine (LS-SVM) and Levenberg–Marquardt Artificial Neural Network have been used. As shown in the obtained results, the proposed feature selection method called KFFS is produced very promising results compared to F-score feature selection.