Jaroslaw Kurek

Support vector machine for fault diagnosis of the broken rotor bars of squirrel-cage induction motor

The paper presents an automatic computerized system for the diagnosis of the rotor bars of the induction electrical motor by applying the support vector machine. Two solutions of diagnostic system have been elaborated. The first one, called fault detection, discovers only the case of the fault occurrence. The second one (complex diagnosis) is able to find which bars have been damaged. The most important problem is concerned with the generation and selection of the diagnostic features, on the basis of which the recognition of the state of the rotor bars is done. In our approach, we use the spectral information of the motor current, voltage and shaft field of one phase registered in an instantaneous form. The selected features form the input vector applied to the support vector machine, used as the classifier. The results of the numerical experiments are presented and discussed in the paper.

Texture characterization based on the Kolmogorov-Smirnov distance

We have developed new Kolmogorov-Smirnov method of description of the texture images.We have checked the performance of the proposed descriptor on the set of soil images.We have compared our solution to well known Haralick description of the texture. The paper proposes the new numerical descriptor of the texture based on the Kolmogorov-Smirnov (KS) statistical distance. In this approach to feature generation we consider the distribution of the pixel intensity placed in equal circular distances from the central point. In this statistical analysis each pixel of the image takes the role of the central point and KS statistics is estimated for the whole image. We determine the KS distance of pixel intensity corresponding to the coaxial rings of the increasing distance from the center. The slope of the linear regression function applied for approximating the characteristics presenting KS distance versus the geometrical distance of these rings, forms the proposed statistical descriptor of the image. We show the application of this numerical description for recognition of the set of images of soil of different type and show that it behaves very well as the diagnostic feature, better than texture Haralick features.

Multistage classification by using logistic regression and neural networks for assessment of financial condition of company

The paper presents the new approach to the automatic assessment of the financial condition of the company. We develop the computerized classification system applying WOE representation of data, logistic regression and Support Vector Machine (SVM) used as the final classifier. The applied method is a combination of a classical binary scoring approach and Support Vector Machine classification. The application of this method to the assessment of the financial condition of companies, classified into five classes, has shown its superiority with respect to classical approaches.

False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification

BACKGROUND AND OBJECTIVEnThe aim of computer-aided-detection (CAD) systems for mammograms is to assist radiologists by marking region of interest (ROIs) depicting abnormalities. However, the confusing appearance of some normal tissues that visually look like masses results in a large proportion of marked ROIs with normal tissues. This paper copes with this problem and proposes a framework to reduce false positive masses detected by CAD.nnnMETHODSnTo avoid the error induced by the segmentation step, we proposed a segmentation-free framework with particular attention to improve feature extraction and classification steps. We investigated for the first time in mammogram analysis, Hilberts image representation, Kolmogorov-Smirnov distance and maximum subregion descriptors. Then, a feature selection step is performed to select the most discriminative features. Moreover, we considered several classifiers such as Random Forest, Support Vector Machine and Decision Tree to distinguish between normal tissues and masses. Our experiments were carried out on a large dataset of 10168 ROIs (8254 normal tissues and 1914 masses) constructed from the Digital Database for Screening Mammography (DDSM). To simulate practical scenario, our normal regions are false positives asserted by a CAD system from healthy cases.nnnRESULTSnThe combination of all the descriptors yields better results than each feature set used alone, and the difference is statistically significant. Besides, the feature selection steps yields a statistically significant increase in the accuracy values for the three classifiers. Finally, the random forest achieves the highest accuracy (81.09%), outperforming the SVM classifier (80.01%)) and decision tree (79.12%), but the difference is not statistically significant.nnnCONCLUSIONSnThe accuracy of discrimination between normal and abnormal ROIs in mammograms obtained with the proposed gray level texture features sets are encouraging and comparable to these obtained with multiresolution features. Combination of several features as well as feature selection steps improve the results. To improve false positives reduction in CAD systems for breast cancer diagnosis, these features could be combined with multiresolution features.

Detection of ‘Orange Skin’ Type Surface Defects in Furniture Elements with the Use of Textural Features

The accuracy of detecting the orange skin surface defect in lacquered furniture elements was tested. Textural features and an SVM classifier were used. Features were selected from a set of 50 features with the bottom-up feature selection strategy driven by the Fisher measure. The features selected were the Kolmogorow-Smirnow-based features, some of the Hilbert curve-based features, some of the maximum subregions features and also some of the thresholding-based features. The Otsu thresholding and percolation-based features were all rejected. The images of size (300,times ,300) pixels cut from the original, larger images were treated as objects. There were three quality classes: very good, good and bad. In the cross-validation process where the testing sets consisted of 90 and the training sets of 910 objects the accuracies ranged from 90% to 98% and the average accuracy was 94%. The tests revealed that more research should be done on the choice of features for this problem.

Novel methods of image description and ensemble of classifiers in application to mammogram analysis

Abstract The paper proposes new advanced methods of image description and an ensemble of classifiers for recognition of mammograms in breast cancer. The non-negative matrix factorization and many other advanced methods of image representation, not exploited in the field of mammogram recognition, are developed and checked in the role of diagnostic features. Final image recognition is done by using an ensemble of classifiers. The new approach to the integration of an ensemble is proposed. It applies the weighted majority voting with the weights determined from the optimization task defined on the basis of the area under curve of ROC. The results of numerical experiments performed on large data base “Digital Database for Screening Mammography” containing more than 10,000 mammograms have confirmed superior accuracy in recognition of abnormal from the normal cases. The presented results of class recognition exceed the best achievements for this base reported in the actual publications.

Deep learning and non-negative matrix factorization in recognition of mammograms

This paper presents novel approach to the recognition of mammograms. The analyzed mammograms represent the normal and breast cancer (benign and malignant) cases. The solution applies the deep learning technique in image recognition. To obtain increased accuracy of classification the nonnegative matrix factorization and statistical self-similarity of images are applied. The images reconstructed by using these two approaches enrich the data base and thanks to this improve of quality measures of mammogram recognition (increase of accuracy, sensitivity and specificity). The results of numerical experiments performed on large DDSM data base containing more than 10000 mammograms have confirmed good accuracy of class recognition, exceeding the best results reported in the actual publications for this data base.

Deep learning in assessment of drill condition on the basis of images of drilled holes

This paper presents novel approach to drill condition assessment using deep learning. The assessment regarding level of the drill wear is done on the basis of the drilled hole images. Two states of the drill are taken into account: the sharp enough to continue production and worn out. The decision is taken on the basis of the shape of hole and also the level of hole shredding. In this way the drill condition is associated with the problem of image analysis and classification. Novel approach to this classification task in the form of deep learning has been applied in solving this problem. The important advantage of this method is great simplification of the recognition procedure, since any handy craft prepared features are not needed and the focus may be concentrated on the most interesting aspects of data mining and machine learning. The obtained results belong to the best in comparison to other approaches to the problem solution.

Transfer learning in recognition of drill wear using convolutional neural network

The paper presents an application of transfer learning using convolutional neural network (CNN) in recognition of the drill state on the basis of hole images drilled in the laminated chipboard. Three classes are recognized: red, yellow and green, which correspond with 3 stages of drill state. Red class indicates the drill, which is worn out and should be replaced immediately in drilling process. Yellow class corresponds to the state in which warning should be sent to the operator to check manually state of the drill. The last class corresponds to the green state indicating good condition of drill, enabling further use in production. The important advantage of transfer learning approach is possibility of training classification model using only small portion of data. This is in contrast to the classical deep learning methods of convolutional neural networks, which require very large data base to achieve acceptable accuracy of class recognition. The results of numerical experiments in drill state recognition have confirmed suitability of this novel method to accurate class recognition at small population of available learning data.

Automatic recognition of drill condition on the basis of images of drilled holes

This paper presents an automatic algorithm to recognize the condition of drills on the basis of analysis of the drilling hole images. The algorithm includes the image preprocessing leading to extraction of the diagnostic features, which are used as the input attributes for the classification system. The condition of drill is classified into two groups: the useful one (the sharp enough state) and worn out (useless in production).