Wyniki wyszukiwania - BazTech

1

Semi-supervised vs. supervised learning for mental health monitoring: A case study on bipolar disorder

Casalino Gabriella, Castellano Giovanna, Hryniewicz Olgierd, Leite Daniel, Opara Karol, Radziszewska Weronika, Kaczmarek-Majer Katarzyna

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 3

419--428

EN

Acoustic features of speech are promising as objective markers for mental health monitoring. Specialized smartphone apps can gather such acoustic data without disrupting the daily activities of patients. Nonetheless, the psychiatric assessment of the patient’s mental state is typically a sporadic occurrence that takes place every few months. Consequently, only a slight fraction of the acoustic data is labeled and applicable for supervised learning. The majority of the related work on mental health monitoring limits the considerations only to labeled data using a predefined ground-truth period. On the other hand, semi-supervised methods make it possible to utilize the entire dataset, exploiting the regularities in the unlabeled portion of the data to improve the predictive power of a model. To assess the applicability of semi-supervised learning approaches, we discuss selected state-of-the-art semi-supervised classifiers, namely, label spreading, label propagation, a semi-supervised support vector machine, and the self training classifier. We use real-world data obtained from a bipolar disorder patient to compare the performance of the different methods with that of baseline supervised learning methods. The experiment shows that semi-supervised learning algorithms can outperform supervised algorithms in predicting bipolar disorder episodes.

2

A Comparative Analysis of Image Segmentation Using Classical and Deep Learning Approach

Plaksyvyi Arsen, Skublewska-Paszkowska Maria, Powroźnik Paweł

Advances in Science and Technology. Research Journal

|

2023

|

Vol. 17, no 6

127--139

EN

Segmentation is one of the image processing techniques, widely used in computer vision, to extract various types of information represented as objects or areas of interest. The development of neural networks has influenced image processing techniques, including creation of new ways of image segmentation. The aim of this study is to compare classical algorithms and deep learning methods in RGB image segmentation tasks. Two hypotheses were put forward: 1) “The quality of segmentation applying deep learning methods is higher than using classical methods for RGB images”, and 2) “The increase of the RGB image resolution has positive impact on the segmentation quality”. Two traditional segmentation algorithms (Thresholding and K-means) were compared with deep learning approach (U-Net, SegNet and FCN 8) to verify RGB segmentation quality. Two resolutions of images were taken into consideration: 160x240 and 320x480 pixels. Segmentation quality for each algorithm was estimated based on four parameters: Accuracy, Precision, Recall and Sorensen-Dice ratio (Dice score). In the study the Carvana dataset, containing 5,088 high-resolution images of cars, was applied. The initial set was divided into training, validation and test subsets as 60%, 20%, 20%, respectively. As a result, the best Accuracy, Dice score and Recall for images with resolution 160x240 were obtained for U-Net, achieving 99.37%, 98.56%, and 98.93%, respectively. For the same resolution the highest Precision 98.19% was obtained for FCN-8 architecture. For higher resolution, 320x480, the best mean Accuracy, Dice score, and Precision were obtained for FCN-8 network, reaching 99.55%, 99.95% and 98.85%, respectively. The highest results for classical methods were obtained for Threshold algorithm reaching 80.41% Accuracy, 58.49% Dice score, 67.32% Recall and 52.62% Precision. The results confirm both hypotheses.

3

Diagnosing faults in the timing system of a passenger car spark ignition engine using the bayes classifier and entropy of vibration signals

Czech Piotr

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2022

|

z. 116

83--98

EN

Today's systems for diagnosing the technical condition of machines, including vehicles, use very advanced methods of acquiring and processing input data. Presently, work is being conducted globally to solve related problems. At the moment, it is not yet possible to create a single procedure that would enable the construction of a properly functioning diagnostic system, regardless of the selected object to be diagnosed. Hence, there is a need to conduct further research into the possibility of using already developed methods, as well as their modification to other diagnostic cases. This article presents the results of research related to the use of the Bayes classifier for diagnosing the technical condition of passenger car engine components. Damage to the exhaust valve of a spark ignition engine was diagnosed. The source of information on the technical condition was vibration signals recorded at various measuring points and under different operating conditions of the car. To describe the nature of changes in the vibration signals, the entropy measures were determined for the decomposed signal using the discrete wavelet transform is proposed.

4

A cloud-based urban monitoring system by using a quadcopter and intelligent learning techniques

Khanmohammadi Sohrab, Samadi Mohammad

Journal of Automation Mobile Robotics and Intelligent Systems

|

2022

|

Vol. 16, No. 2

11--19

EN

The application of quadcopter and intelligent learning techniques in urban monitoring systems can improve flexibility and efficiency features. This paper proposes a cloud-based urban monitoring system that uses deep learning, fuzzy system, image processing, pattern recognition, and Bayesian network. The main objectives of this system are to monitor climate status, temperature, humidity, and smoke, as well as to detect fire occurrences based on the above intelligent techniques. The quadcopter transmits sensing data of the temperature, humidity, and smoke sensors, geographical coordinates, image frames, and videos to a control station via RF communications. In the control station side, the monitoring capabilities are designed by graphical tools to show urban areas with RGB colors according to the predetermined data ranges. The evaluation process illustrates simulation results of the deep neural network applied to climate status and effects of the sensors’ data changes on climate status. An illustrative example is used to draw the simulated area using RGB colors. Furthermore, circuit of the quadcopter side is designed using electric devices.

5

Noise robust illumination invariant face recognition via bivariate wavelet shrinkage in logarithm domain

Chen Guang Yi, Krzyżak Adam, Duda Piotr, Cader Andrzej

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

Vol. 12, No. 3

169--180

EN

Recognizing faces under various lighting conditions is a challenging problem in artificial intelligence and applications. In this paper we describe a new face recognition algorithm which is invariant to illumination. We first convert image files to the logarithm domain and then we implement them using the dual-tree complex wavelet transform (DTCWT) which yields images approximately invariant to changes in illumination change. We classify the images by the collaborative representation-based classifier (CRC). We also perform the following sub-band transformations: (i) we set the approximation sub-band to zero if the noise standard deviation is greater than 5; (ii) we then threshold the two highest frequency wavelet sub-bands using bivariate wavelet shrinkage. (iii) otherwise, we set these two highest frequency wavelet sub-bands to zero. On obtained images we perform the inverse DTCWT which results in illumination invariant face images. The proposed method is strongly robust to Gaussian white noise. Experimental results show that our proposed algorithm outperforms several existing methods on the Extended Yale Face Database B and the CMU-PIE face database.

6

Performance of artificial neural networks in an inverse problem of laser beam diagnostics

Pietrak Karol, Muszyński Radosław, Marek Adam, Łapka Piotr

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 1

art. no. e140100

EN

The presented results are for the numerical verification of a method devised to identify an unknown spatio-temporal distribution of heat flux that occurs at the surface of a thin aluminum plate, as a result of pulsed laser beam excitation. The presented identification of boundary heat flux function is a part of the newly proposed laser beam profiling method and utilizes artificial neural networks trained on temperature distributions generated with the ANSYS Fluent solver. The paper focuses on the selection of the most effective neural network hyperparameters and compares the results of neural network identification with the Levenberg–Marquardt method used earlier and discussed in previous articles. For the levels of noise measured in physical experiments (0.25–0.5 K), the accuracy of the current parameter estimation method is between 5 and 10%. Design changes that may increase its accuracy are thoroughly discussed.

7

Channel based epilepsy seizure type detection from electroencephalography (EEG) signals with machine learning techniques

Tuncer Erdem, Bolat Emine Doğru

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 2

575--595

EN

Epileptic seizures result from disturbances in the electrical activity of the brain, classified as focal, generalized, or unknown. Failure to correctly classify epileptic seizures may result in inappropriate treatment and continuation of seizures. Therefore, automatic detection of generalized, focal, and other epileptic seizures from EEG signals is important. In this research article, Focal-Generalized classification method is proposed that compares traditional classification algorithms and deep learning methods. Two different classifications: four-class (Case (I) Complex Partial Seizure (CPSZ) (C4-T4 Onset)-CPSZ (FP2-F8 Onset)-CPSZ (T5-O1 Onset)- Absence Seizure (ABSZ)) and two-class (Case (II) CPSZ-ABSZ) problems are considered. This study includes preprocessing of scalp Electroencephalogram (EEG) data, feature extraction with discrete wavelet method, feature selection using Correlation-based Feature Selection (CFS) method, and classification of data with classifier algorithms (K-Nearest Neighbors (Knn), Support Vector Machine (SVM), Random Forest (RF) and Long Short-Term Memory (LSTM). The proposed method was applied on 23 subjects in the Temple University Hospital (TUH) scalp EEG data set, and a classification success rate of 95,92% for case (I) and 98,08% for case (II) was successfully achieved with deep learning architecture LSTM.

8

Road safety for cyclists based on the calories needed

Bosurgi Gaetano, Pellegrino Orazio, Wachnicka Joanna, Okraszewska Romanika

Transport Problems

|

2021

|

T. 16, z. 1

113--126

EN

Cyclists are a vulnerable group of road users, especially when no separate infrastructure for cyclists is provided. Then, road factors such as distance and altitude differences can indirectly affect cyclists' safety. Therefore, the authors proposed a procedure based on the geometric characteristics of the road that can determine riding difficulties for cyclists. The proposed procedure can be used both by the public authorities who manage cyclists' safety and as a method of classifying the road network for cycling. The proposed procedure, based on the use of pattern recognition techniques, analyses data from a sample of nine riders who travelled on rural roads within the Municipality of Messina (Italy) to classify the roads according to their cycling difficulty. For each rider, duration, distance, road slope, altitude difference and spent calories have been measured and analysed. The collected data were used for the development of a model capable of predicting the cyclist’s physical effort as a function of the road alignment itself. Knowing the effort required to cycle along a route can contribute to a more complete assessment of road classification, commonly defined according to motor vehicles. Moreover, it may constitute a measure determining the safety of cycling by encouraging cyclists to travel along roads compatible with their physical abilities.

9

Graph-based segmentation with homogeneous hue and texture vertices

Ngo Lua, Han Jae-Ho

Optica Applicata

|

2021

|

Vol. 51, nr 4

541--549

EN

This work presents an automated segmentation method, based on graph theory, which processes superpixels that exhibit spatially similarities in hue and texture pixel groups, rather than individual pixels. The graph shortest path includes a chain of neighboring superpixels which have minimal intensity changes. This method reduces graphics computational complexity because it provides large decreases in the number of vertices as the superpixel size increases. For the starting vertex prediction, the boundary pixel in first column which is included in this starting vertex is predicted by a trained deep neural network formulated as a regression task. By formulating the problem as a regression scheme, the computational burden is decreased in comparison with classifying each pixel in the entire image. This feasibility approach, when applied as a preliminary study in electron microscopy and optical coherence tomography images, demonstrated high measures of accuracy: 0.9670 for the electron microscopy image and 0.9930 for vitreous/nerve-fiber and inner-segment/outer-segment layer segmentations in the optical coherence tomography image.

10

Rozpoznawanie wzorców : projektowanie, ewaluacja zastosowania

Rybak Łukasz, Dudczyk Janusz

Elektronika : konstrukcje, technologie, zastosowania

|

2021

|

Vol. 62, nr 11

12--15

PL

Artykuł stanowi przegląd literatury dotyczącej procesu rozpoznawania wzorców. We wstępie pracy zdefiniowano terminy istotne w kontekście rozważań opisanych w kolejnych sekcjach artykułu oraz określono cel, którym było dokonanie przeglądu istotnych zagadnień ściśle związanych z procesem rozpoznawania wzorców. Następnie scharakteryzowano poszczególne etapy wspomnianego procesu podkreślając zależności pomiędzy nimi. W kolejnej sekcji artykułu opisano istotne problemy występujące na etapie ewaluacji systemu rozpoznawania wzorców. Szczegółowo przedstawiono popularną metodę stosowaną do ich rozwiązywania. Następnie przywołano szereg prac, w których autorzy stosowali proces rozpoznawani wzorców do wielu rzeczywistych problemów.

EN

The article contains a literature review concerning the pattern recognition process. The terms, important in the context of the considerations described in the following sections of the article, were defined in the introduction. Moreover the purpose of the article was stated. The aim was to review significant issues closely related to the pattern recognition process. Then, the each stage of the above-mentioned process were characterized, emphasizing the relationships between them. The next section of the article describes the significant problems that occur at the stage of pattern recognition system evaluation. The popular method used to solve them was presented in detail. Subsequently, a series of papers were referenced in which the authors applied the pattern recognition process to many real-world problems.

11

Rgb-D face recognition using LBP-DCT algorithm

Kumar Sunil B L, Kumari Sharmila M

Applied Computer Science

|

2021

|

Vol. 17, no 3

73--81

EN

Face recognition is one of the applications in image processing that recognizes or checks an individual's identity. 2D images are used to identify the face, but the problem is that this kind of image is very sensitive to changes in lighting and various angles of view. The images captured by 3D camera and stereo camera can also be used for recognition, but fairly long processing times is needed. RGB-D images that Kinect produces are used as a new alternative approach to 3D images. Such cameras cost less and can be used in any situation and any environment. This paper shows the face recognition algorithms’ performance using RGB-D images. These algorithms calculate the descriptor which uses RGB and Depth map faces based on local binary pattern. Those images are also tested for the fusion of LBP and DCT methods. The fusion of LBP and DCT approach produces a recognition rate of 97.5% during the experiment

12

Optimized Method based on Lattice Sequences for Multidimensional Integrals in Neural Networks

Todorov Venelin, Dimov Ivan, Fidanova Stefka

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

243--246

EN

In this work we investigate advanced stochastic methods for solving a specific multidimensional problem related to neural networks. Monte Carlo and quasi-Monte Carlo techniques have been developed over many years in a range of different fields, but have only recently been applied to the problems in neural networks. As well as providing a consistent framework for statistical pattern recognition, the stochastic approach offers a number of practical advantages including a solution to the problem for higher dimensions. For the first time multidimensional integrals up to 100 dimensions related to this area will be discussed in our numerical study.

13

Discrimination of faults in induction machine based on pattern recognition and neural networks techniques

Lakrout Abdelkader, Bendjebbar Mokhtar, Henini Noureddine

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 10

55--61

EN

The work presented in this paper is a contribution in the theme of monitoring and diagnosing of faults in the three-phase squirrel cage induction machine. The proposed approach is based on the pattern recognition methods and the artificial intelligence techniques. For so doing, measurements of the stator currents are carried out on a machine subject to various faults such as: short-circuit in the stator windings, bar breakage, bearing failure and eccentricity fault. These acquisitions are classified in databases in order to process them and calculate their Power Spectral Density (PSD). Then, another database is formed of the digital data of the PSD images of the currents associated with the type of fault. After that, a process of learning and classification by artificial neural networks was developed. The test results show the efficiency, robustness and correctness of the proposed approach for the discrimination of faults of electrical or mechanical origin affecting the machine.

PL

Praca przedstawiona w tym artykule stanowi wkład w temat monitorowania i diagnozowania uszkodzeń w trójfazowej maszynie indukcyjnej klatkowej. Proponowane podejście opiera się na metodach rozpoznawania wzorców i technikach sztucznej inteligencji. W tym celu pomiary prądów stojana są przeprowadzane na maszynie podlegającej różnym usterkom, takim jak: zwarcie w uzwojeniach stojana, pęknięcie pręta, uszkodzenie łożyska i błąd mimośrodowości. Przejęcia te są klasyfikowane w bazach danych w celu ich przetworzenia i obliczenia ich gęstości widmowej mocy (PSD). Następnie tworzona jest kolejna baza danych z cyfrowymi danymi obrazów PSD prądów związanych z rodzajem uszkodzenia. Następnie opracowano proces uczenia się i klasyfikacji przez sztuczne sieci neuronowe. Wyniki testu pokazują skuteczność, niezawodność i poprawność proponowanego podejścia do rozróżnienia wad pochodzenia elektrycznego lub mechanicznego mających wpływ na maszynę.

14

Deep learning approach for open switch fault diagnosis in matrix frequency converter

Sabour Mustapha

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 11

155--160

EN

This document proposes a new method for detecting and locating open circuit faults in a matrix frequency converter (MC) based on the technique of pattern recognition by neural networks. The converter input and output current signals are used for this purpose. For this, a database of current signals under healthy conditions and defective for different operating conditions was established. After transforming these signals into a Concordia lair, a process of deep learning by a convolutional neural network was carried out. To verify the robustness of our proposed approach, a simulation of a MC system with a defective power electronic switch supplying an asynchronous motor controlled by DTC-SVM under different conditions of torque and speed was developed. The diagnostic results demonstrate the feasibility and effectiveness of the proposed method. It made it possible to locate the faulty switch precisely and quickly.

PL

Zaproponowano nową metodę wykrywania i lokalizowania uszkodzeń obwodu otwartego w przekształtniku matrycowym (MC) w oparciu o technikę rozpoznawania wzorców przez sieć neuronową. W tym celu wykorzystywane są sygnały wejściowe i wyjściowe prądu przekształtnika. Utworzono bazę danych sygnałów prądowych w warunkach znamionowych i z uszkodzeniem dla różnych warunków pracy. Po przekształceniu tych sygnałów w środowisku Concordia przeprowadzono proces głębokiego uczenia się przez splotową sieć neuronową. Aby zweryfikować Wiarygodność naszego proponowanego podejścia, opracowano model symulacyjny układu MC z uszkodzonym łącznikiem energoelektronicznym zasilającym silnik asynchroniczny sterowany metodą DTC-SVM z róznymi wartościami momentu i prędkości obrotwej. Wyniki diagnostyczne pokazują wykonalność i skuteczność proponowanej metody.

15

Recognition of species and genera of bacteria by means of the product of weights of the classifiers

Plichta Anna

International Journal of Applied Mathematics and Computer Science

|

2020

|

Vol. 30, no. 3

463--473

EN

In microbiology, computer methods are applied in the analysis and recognition of laboratory-acquired microscopic images concerning, for example, bacterial cells or other microorganisms. Proper recognition of the species and genera of bacteria is a key stage in the microbiological diagnostics process, because it allows a quick start of the appropriate therapy. The original method proposed in the paper concerns the automatic recognition of selected species and genera of bacteria presented in digital images. The classification was made on the basis of the analysis of the physical characteristics of bacterial cells using the product of classifier confidence weights. The end result of the classification process is the classification list, sorted in descending order according to the weights of the classifiers. In addition to the correct classification, a list of other possible results of the analysis is obtained. The method thus allows not only the classification, but also an analysis of the confidence level of the selection made. The proposed method can be used to recognize not only bacterial cells, but also other microorganisms, for example, fungi that exhibit similar morphological characteristics. In addition, the use of the method does not require the application of specialized computer equipment, which widens the scope of applications regardless of the laboratory IT infrastructure, not only in microbiological diagnostics, but also in other diagnostic laboratories.

16

Chessboard and Chess Piece Recognition With the Support of Neural Networks

Czyżewski Maciej A., Laskowski Artur, Wasik Szymon

Foundations of Computing and Decision Sciences

|

2020

|

Vol. 45, No. 4

257--280

EN

Chessboard and chess piece recognition is a computer vision problem that has not yet been efficiently solved. Digitization of a chess game state from a picture of a chessboard is a task typically performed by humans or with the aid of specialized chessboards and pieces. However, those solutions are neither easy nor convenient. To solve this problem, we propose a novel algorithm for digitizing chessboard configurations. We designed a method of chessboard recognition and pieces detection that is resistant to lighting conditions and the angle at which images are captured, and works correctly with numerous chessboard styles. Detecting the board and recognizing chess pieces are crucial steps of board state digitization. The algorithm achieves 95% accuracy (compared to 60% for the best alternative) for positioning the chessboard in an image, and almost 95% for chess pieces recognition. Furthermore, the subprocess of detecting straight lines and finding lattice points performs extraordinarily well, achieving over 99.5% accuracy (compared to the 74% for the best alternative).

17

The concept of an intelligent system of an outfit completion

Semianchuk Sofiia, Shestakevych Tetiana

ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes

|

2020

|

Vol. 9, No 2

30--36

EN

The article considers the main criteria for the selection and formation of the wardrobe, which is one of the areas of application of methods and means for image classification. Typical software solutions for the task are analyzed, and the Analytic Hierarchy Process was used to analyze such applications. To improve the wardrobe selection process, the concept of an intelligent information system based on the use of convolutional neural networks was proposed.

18

Classification of epileptic EEG signals using PSO based artificial neural network and tunable-Q wavelet transform

George S. Thomas, Subathra M. S. P., Sairamya N. J., Susmitha L., Joel Premkumar M.

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 2

709--728

EN

Epilepsy is a widely spread neurological disorder caused due to the abnormal excessive neural activity which can be diagnosed by inspecting the electroencephalography (EEG) signals visually. The manual inspection of EEG signals is subjected to human error and is a tedious process. Further, an accurate diagnosis of generalized and focal epileptic seizures from normal EEG signals is vital for the supervision of pertinent treatment, life advancement of the subjects, and reduction in cost for the subjects. Hence the development of automatic detection of generalized and focal epileptic seizures from normal EEG signals is important. An approach based on tunable-Q wavelet transform (TQWT), entropies, Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) is proposed in this work for detection of epileptic seizures and its types. Two EEG databases namely, Karunya Institute of Technology and Sciences (KITS) EEG database and Temple University Hospital (TUH) database consisting of normal, generalized and focal EEG signals is used in this work to analyze the performance of the proposed approach. Initially, the EEG signals are decomposed into sub-bands using TQWT and the non-linear features like log energy entropy, Shannon entropy and Stein's unbiased risk estimate (SURE) entropy is computed from each sub-band. The informative features from the computed feature vectors are selected using PSO and fed into ANN for the classification of EEG signals. The proposed algorithm for KITS database achieved a maximum accuracy of 100% for four experimental cases namely, (i) normal-focal, (ii) normal-generalised, (iii) normal-focal + generalised and (iv) normal-focal-generalised. The TUH database achieved an accuracy of 95.1%, 97.4%, 96.2% and 88.8% for the four experimental cases. The proposed approach is promising and able to discriminate the epileptic seizure types with satisfactory classification performance.

19

Review of Printed Fabric Pattern Segmentation Analysis and Application

Kumah Charles, Raji Rafiu King, Pan Ruru

Autex Research Journal

|

2020

|

Vol. 20, no. 4

530--538

EN

Image processing of digital images is one of the essential categories of image transformation in the theory and practice of digital pattern analysis and computer vision. Automated pattern recognition systems are much needed in the textile industry more importantly when the quality control of products is a significant problem. The printed fabric pattern segmentation procedure is carried out since human interaction proves to be unsatisfactory and costly. Hence, to reduce the cost and wastage of time, automatic segmentation and pattern recognition are required. Several robust and efficient segmentation algorithms are established for pattern recognition. In this paper, different automated methods are presented to segregate printed patterns from textiles fabric. This has become necessary because quality product devoid of any disturbances is the ultimate aim of the textile printing industry.

20

The regularization method in the classification task according to given examples

Kwiatkowski Włodzimierz

Przegląd Teleinformatyczny

|

2019

|

T. 7, Nr 3-4 (49)

3--13

EN

The article considers the problem of classification based on the given examples of classes. As a feature vector, a complete characteristic of object is assumed. The peculiarity of the problem being solved is that the number of examples of the class may be less than the dimension of the feature vector, and also most of the coordinates of the feature vector can be correlated. As a consequence, the feature covariance matrix calculated for the cluster of examples may be singular or ill-conditioned. This disenable a direct use of metrics based on this covariance matrix. The article presents a regularization method involving the additional use of statistical properties of the environment.

PL

W artykule rozpatrywany jest problem klasyfikacji na podstawie wskazanych przykładów klas. Jako wektor cech przyjmuje się kompletną charakterystykę obiektów. Osobliwość rozwiązywanego zadania wynika z tego, że liczba przykładów klasy może być mniejsza od wymiaru wektora cech, a także wektor cech może zawierać współrzędne skorelowane. W konsekwencji macierz kowariancji cech obliczana dla klastra przykładów może być osobliwa albo źle uwarunkowana. Uniemożliwia to bezpośrednie stosowanie metryk bazujących na tej macierzy kowariancji. W artykule została przedstawiona metoda regularyzacji polegająca na dodatkowym wykorzystaniu statystycznych właściwości środowiska.