Vol 29, No 3 (2019)

A brief outline of a report made November 12, 2018 at the Scientific Session of the Mathematical Science Branch of the Russian Academy of Sciences is presented in the paper. The report is orientated to an audience far from the problems on data mining. The report is an overview and presents the author’s personal considerations on the examined scientific field.

Cuckoo Search Algorithm (CSA) is one of the new swarm intelligence based optimization algorithms, which has shown an effective performance on many optimization problems. However, the effectiveness of CSA significantly depends on the exploration and exploitation potential and it may also possible to increase its efficiency when solving complex optimization problems. In this study, some mechanisms have been employed on CSA to increase its efficiency such as use of global best and individual best solutions to guide the other solutions, self-adaption techniques for parameters and so on. The modified CSA (i.e., MCSA) is successfully employed in clustering based classification domain. The experimental results and execution time prove its effectiveness over existing modified CSAs and other employed swarm intelligence algorithms. The proposed clustering model is also employed in color histopathological image segmentation domain and provides effective result.

The construction of a two-level decision scheme for recognition problems with many classes is proposed that is based on the development of the error-correcting output codes (ЕСОС) method. In the “classical” ЕСОС, a large number of partitions of the original classes into two macroclasses are constructed. Each macroclass is a union of some original classes. Each macroclass is assigned either 0 or 1. As a result, each original class is defined by a row of 0 and 1 (the stage of encoding) and a coding matrix is constructed. The stage of classification of an arbitrary new object consists in the solution of each dichotomic problem and application of a special decision rule (the stage of decoding). In this paper, new methods for weighting and taking into account codewords, modifying decision rules, and searching for locally optimal dichotomies are proposed, and various quality criteria for classification and the cases of extension of a codeword are considered.

The paper describes the adaptive method of estimating the parameters of the distribution of the useful signal under the assumption that the noise distribution can be pre-estimated. It is based on the method of moving separation of the finite normal mixtures and implemented for the estimating both signal-noise and signal distribution parameters. We assume that the probability distribution of the signal, signal with noise and “pure” noise can be presented in form of finite normal mixtures. Also, a method for change point detection based on testing the homogeneity hypothesis using the Kolmogorov criterion is proposed.

The study is devoted to mathematical and functional/physical interpretation of image analysis and processing operations used as sets of operations (ring elements) in descriptive image algebras (DIA) with one ring. The main result is the determination and characterization of interpretation domains of DIA operations: image algebras that make it possible to operate with both the main image models and main models of transformation procedures that ensure effective synthesis and realization of the basic procedures involved in the formal description, processing, analysis, and recognition of images. The applicability of DIAs in practice is determined by the realizability—the possibility of interpretation—of its operations. Since DIAs represent an algebraic language for the mathematical description of image processing, analysis, and understanding procedures using image transformation operations and their representations and models, the authors consider an algebraic interpretation. These procedures are formulated and implemented in the form of descriptive algorithmic schemes (DAS), which are correct expressions of the DIA language. The latter are constructed from the processing and transformation of images and other mathematical operations included in the corresponding DIA ring. The mathematical and functional properties of DIA operations are of considerable interest for optimizing procedures of processing and analyzing images and constructing specialized DAS libraries. Since not all mathematical operations have a direct physical equivalent, the construction of an efficient DAS for image analysis involves the problem of interpreting operations for DAS content. Research into this problem leads to the selection and study of interpretation domains of DIA operations. The proposed method for studying the interpretability of DIA operations is based on the establishment of correspondence between the content description of the operation function and its mathematical realization. The main types of interpretability are defined and examples given of the interpretability/uninterpretability of operations of a standard image algebra, which is a restriction of the DIA with one ring.

Developing an effective target appearance model is a challenging task in visual tracking under the influences of complicated appearance variations. Many tracking algorithms use a linear combination of previous tracking results to represent a target candidate. In existing target representations, all of the feature elements of a target candidate have the same coding vector. With such type of target representations, robust tracking is not satisfactory when drastic appearance variations occur. In this work, we present a novel appearance model for visual tracking. The proposed appearance model considers the similarity and the distinctiveness of the feature elements of a target candidate. The feature elements should share some similarity to jointly represent a target pattern. We exploit the distinctiveness of feature elements to represent the different importance by introducing a weighted regularization term in the appearance model. A more stable and discriminative target representation is obtained. Superior performance on challenging sequences against state-of-the-art trackers show the robustness of the novel appearance model and the proposed tracker.

Anemia is the blood disorder which develops in the condition of lack of healthy red blood cells or hemoglobin. According to the World Health Organization (WHO) nearly quarter of the human population suffers from anemia moreover, invasive detection of anemia is tedious and expensive. Initial screening for noninvasive detection of anemia is done by examining the color of eye conjunctiva and after that by accommodating the outcomes with an intrusive blood test. This paper aims to resolve this issues along with providing an optimal and fast solution for detecting the anemia using noninvasive methods. This process includes capturing the image of eyes and then manually extracting the eye conjunctiva and obtaining the region of interest (ROI). Once ROI is extracted, these images are processed to obtain the mean intensity values of red and green components of image pixels corresponding to ROI. Then a tuned machine learning algorithm is used to predict whether the patient is anemic or not. The model employed is run over 99 test subjects using k-Fold cross-validation and had achieved an accuracy of 93 percent. This study aims to develop an automated and cost-effective noninvasive technique.

In the present time, the development of medical images and the increasing use of digital images have played a crucial role in medical diagnosis. In this sense, the rapid growth of magnetic resonance images (MRI) technology increased the necessity to store, analyze and describe this amount of information more efficiently. By improving these processes, decision making for clinicians may reach a more accurate and a well-informed diagnosis. To achieve this aim, machine learning approaches have been considered as a complementary pillar of image processing. It has become essential to find efficient descriptors, which characterize the images such as texture, shape and color. Although there are many representations of known features, they are difficult to use in their unchanged forms. The proposed approach combines the global and local features. Global features are extracted using the combination of magnitude and phase features of the descriptor angular radial transform (ART). Local features are obtained through local binary pattern (LBP). Four most known machine-learning approaches are then applied (SVM, ANN, NB, KNN) on both features and the combination of both techniques yielded the best tumor detection performance.

Melanoma, starts growing in melanocytes, is less common but more serious and aggressive than any other types of skin cancers found in human. Melanoma skin cancer can be completely curable if it is diagnosed and treated in an early stage. Biopsy is a confirmation test of melanoma skin cancer which is invasive, time consuming, costly and painful. To prevent this problem, research regarding computerized analysis of skin cancer from dermoscopy images has become increasingly popular for last few years. In this research, we extract the pertinent features from dermoscopy images related to shape, size and color properties based on ABCD rule. Although ABCD features were used before, these features were mostly calculated to reflect asymmetry, compactness index as border irregularity, color variegation and average diameter. This paper proposes one asymmetry feature, three border irregularity features, one color feature and two diameter features as distinctive and pertinent. Implementation of our approach indicates that each of these proposed features is able to detect melanoma lesions with over 72% accuracy individually and the overall diagnostic system achieves 98% classification accuracy with 97.5% sensitivity and 98.75% specificity. Therefore, this method could assist dermatologist for making decision clinically.

Automatic evaluation of the retinal fundus image is regarded as one of the most important future tools for early detection and treatment of progressive eye diseases like glaucoma. Glaucoma leads to progressive degeneration of vision which is characterized by shape deformation of the optic cup associated with focal notching, wherein the degeneration of the blood vessels results in the formation of a notch along the neuroretinal rim. In this study, we have developed a methodology for automated prediction of glaucoma based on feature analysis of the focal notching along the neuroretinal rim and cup to disc ratio values. This procedure has three phases: the first phase segments the optic disc and cup by suppressing the blood vessels with dynamic thresholding; the second phase computes the neuroretinal rim width to detect the presence and direction of notching by the conventional ISNT rule apart from calculating the cup-to-disc ratio from the color fundus image (CFI); the third phase uses linear support vector based machine learning algorithm by integrating extracted parameters as features for classification of CFIs into glaucomatous or normal. The algorithm outputs have been evaluated on a freely available database of 101 images, each marked with decision of five glaucoma expert ophthalmologists, thereby returning an accuracy rate of 87.128%.

In Image De-fencing, segmentation and restoration of occluded fence region from the images are very challenging, when the desired object is occluded with an undesired object. This undesired object may be scattered in the whole image region. Existing algorithms can only detect single colored fences at a time from the digital images. This paper presents a multi-colored fence detection algorithm. Multi-threshold segmentation technique is used to segment the fence in the image. The segmented mask is amended by using morphological operations. To restore the fence occluded area in an image hybrid inpainting technique is used. Obtained results after experimentation are compared with the start-of-art image de-fencing technique.

The purpose of this work is to evaluate the efficacy of applying a model-based quantum clustering (QC) algorithm on thermograms of functional modes in WiFi circuits. As unsupervised clustering algorithm, it can work on clusters of any shape and does not require any prior information. QC proves its efficacy for many applications, it has been tested, in this work, and compared with other algorithms which suffer randomness according to initialization. The tests are conducted on thermograms of an electronic chip in different operation modes. The benefits of QC are confirmed through performance analysis of clustering algorithms. Robustness analysis is also conducted against white-Gaussian noise clustering and so on classification of actual WiFi circuit operation modes based on thermograms.