Wyniki wyszukiwania - BazTech

1

Algorytm ukrywania danych w obrazie oparty na klasyfikacji do wykrywania i rozpoznawania ukrytych informacji

Duszejko Paweł, Piotrowski Zbigniew

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

337--340

PL

W artykule przedstawiono innowacyjny algorytm ukrywania danych w obrazach oparty na klasyfikacji. Metoda pozwala na niezauważalne dla ludzkiego oka ukrycie danych, a jednocześnie zapewnia możliwość ich późniejszego wykrycia i rozpoznania bez konieczności posiadania klucza lub oryginalnego obrazu. Przeprowadzone eksperymenty potwierdzają skuteczność i niezawodność tej metody w porównaniu z innymi algorytmami. Proponowane rozwiązanie może się przyczynić do rozwoju takich dziedzin jak: bezpieczeństwo informacyjne, ochrona prywatności, autoryzacja i znakowanie wodne.

EN

The article presents an innovative algorithm for data hiding in images based on classification. The method allows imperceptible data hiding to the human eye while also providing the ability to later detect and recognise the hidden data without needing a key or the original image. The conducted experiments confirm the effectiveness and reliability of this method compared to other algorithms. The proposed solution can contribute to developing fields such as information security, privacy protection, authentication, and watermarking.

2

Improved competitive neural network for classification of human postures based on data from RGB-D sensors postures based on data from RGB-D sensors

Dutta Vibekananda, Cydejko Jakub, Zielińska Teresa

Journal of Automation Mobile Robotics and Intelligent Systems

|

2023

|

Vol. 17, No. 3

15--29

EN

The cognitive goal of this paper is to assess whether marker-less motion capture systems provide sufficient data to recognize human postures in the side view. The research goal is to develop a new posture classification method that allows for analysing human activities using data recorded by RGB‐D sensors. The method is insensitive to recorded activity duration and gives satisfactory results for the sagittal plane. An improved competitive Neural Network (cNN) was used. The method of pre- processing the data is first discussed. Then, a method for classifying human postures is presented. Finally, classification quality using various distance metrics is assessed. The data sets covering the selection of human activities have been created. Postures typical for these activities have been identified using the classifying neural network. The classification quality obtained using the proposed cNN network and two other popular neural networks were compared. The results confirmed the advantage of cNN network. The developed method makes it possible to recognize human postures by observing movement in the sagittal plane.

3

Recognition of sports exercises using inertial sensor technology

Krutz Pascal, Rehm Matthias, Schlegel Holger, Dix Martin

Applied Computer Science

|

2023

|

Vol. 19, no 1

152--163

EN

Supervised learning as a sub-discipline of machine learning enables the recognition of correlations between input variables (features) and associated outputs (classes) and the application of these to previously unknown data sets. In addition to typical areas of application such as speech and image recognition, fields of applications are also being developed in the sports and fitness sector. The purpose of this work is to implement a workflow for the automated recognition of sports exercises in the Matlab® programming environment and to carry out a comparison of different model structures. First, the acquisition of the sensor signals provided in the local network and their processing is implemented. Realised functionalities include the interpolation of lossy time series, the labelling of the activity intervals performed and, in part, the generation of sliding windows with statistical parameters. The preprocessed data are used for the training of classifiers and artificial neural networks (ANN). These are iteratively optimised in their corresponding hyper parameters for the data structure to be learned. The most reliable models are finally trained with an increased data set, validated and compared with regard to the achieved performance. In addition to the usual evaluation metrics such as F1 score and accuracy, the temporal behaviour of the assignments is also displayed graphically, allowing statements to be made about potential causes of incorrect assignments. In this context, especially the transition areas between the classes are detected as erroneous assignments as well as exercises with insufficient or clearly deviating execution. The best overall accuracy achieved with ANN and the increased dataset was 93.7 %.

4

Examining the Predictive Capability of Advanced Software Fault Prediction Models – An Experimental Investigation Using Combination Metrics

Sharma Pooja, Sangal Amrit Lal

e-Informatica Software Engineering Journal

|

2022

|

Vol. 16, nr 1

art. no. 220104

EN

Background: Fault prediction is a key problem in software engineering domain. In recent years, an increasing interest in exploiting machine learning techniques to make informed decisions to improve software quality based on available data has been observed. Aim: The study aims to build and examine the predictive capability of advanced fault prediction models based on product and process metrics by using machine learning classifiers and ensemble design. Method: Authors developed a methodological framework, consisting of three phases i.e., (i) metrics identification (ii) experimentation using base ML classifiers and ensemble design (iii) evaluating performance and cost sensitiveness. The study has been conducted on 32 projects from the PROMISE, BUG, and JIRA repositories. Result: The results shows that advanced fault prediction models built using ensemble methods show an overall median of $F$-score ranging between 76.50% and 87.34% and the ROC(AUC) between 77.09% and 84.05% with better predictive capability and cost sensitiveness. Also, non-parametric tests have been applied to test the statistical significance of the classifiers. Conclusion: The proposed advanced models have performed impressively well for inter project fault prediction for projects from PROMISE, BUG, and JIRA repositories.

5

Fuzzy sets in modelling patientʼs disease states in medical diagnostic support algorithms

Ameljańczyk Andrzej, Ameljańczyk Tomasz

Computer Science and Mathematical Modelling

|

2022

|

No. 15-16

45--51

EN

The article presents the concept of using fuzzy sets methodology in modelling patientʼs disease states for preliminary medical diagnosis. The preliminary medical diagnosis is based on the identified disease symptoms. The basis of the algorithm are descriptions of the patientʼs disease status and patterns of disease entities. These patterns were defined as fuzzy sets. The paper presents simple classifiers that allow he a preliminary diagnosis based on the analysis of fuzzy sets for the use of the general practitioner.

PL

W artykule przedstawiono koncepcję wykorzystania metodologii zbiorów rozmytych w modelowaniu stanów chorobowych pacjenta w algorytmach wstępnej diagnostyki medycznej. Wstępna diagnoza lekarska opiera się na rozpoznanych objawach choroby. Podstawą algorytmu są opisy stanu chorobowego pacjenta i wzorce jednostek chorobowych. Wzorce te zostały zdefiniowane jako zbiory rozmyte. W artykule przedstawiono proste klasyfikatory, które pozwalają na wstępną diagnozę na podstawie analizy zbiorów rozmytych do użytku lekarza pierwszego kontaktu.

6

Problem of soil science based cLassification of land in the context of updating land and building records

Budkowski Szczepan

Geomatics, Landmanagement and Landscape

|

2021

|

no. 3

83--91

EN

Pursuant to the Geodetic and Cartographic Law, the soil science based classification of land should be understood as the division of soils into valuation classes due to their productive quality, determined on the basis of soil genetic features. Pursuant to the above-mentioned Act, the task of the starosta (district administrator) is to maintain both the soil science classification of land, and the land and building records (cadastral records). The data that is the subject of the decision issued by the authority in the field of soil science classification of land constitute elements of the essential information set within land and building records, in accordance with Article 23 section 3 point 1 g of the Geodetic and Cartographic Law [PGiK]. The aim of this publication was to present the irregularities resulting from the failure to update land and building records, as well as from the lack of uniform administrative procedures in the field of soil science classification of land, which translates into the quality of the works performed. The research method used is the case study. The method was supported by the analysis of legislation in the above-mentioned subject matter.

PL

Zgodnie z ustawą Prawo Geodezyjne i Kartograficzne poprzez gleboznawczą klasyfikację gruntów należy rozumieć podział gleb na klasy bonitacyjne ze względu na ich jakość produkcyjną ustaloną na podstawie cech genetycznych gleb. Zgodnie z powyższą ustawą prowadzenie zarówno gleboznawczej klasyfikacji gruntów jak również ewidencji gruntów i budynków należy do zadań starosty. Dane będące przedmiotem wydawanej przez organ decyzji w zakresie gleboznawczej klasyfikacji gruntów są elementami zbioru informacji przedmiotowych ewidencji gruntów i budynków zgodnie z art. 23 ust.3 pkt 1 lit. g ustawy Prawo Geodezyjne i Kartograficzne [pgik]. Celem niniejszej publikacji było przedstawienie nieprawidłowości wynikających z braku aktualizacji ewidencji gruntów i budynków, a także braku jednolitych procedur administracyjnych w zakresie prac gleboznawczej klasyfikacji gruntów, które przekładają się na jakość wykonywanych prac. Stosowaną metodą badawczą jest studium przypadku. Metoda została wsparta analizą prawodawstwa w wyżej wymienionym zakresie.

7

Issues of the profession of a land classifier

Budkowski Szczepan

Geomatics, Landmanagement and Landscape

|

2021

|

no. 4

47--54

EN

From the legal point of view, the soil science classification is regulated by the Geodetic and Cartographic Law, where it is defined as the division of soils into valuation classes due to their production quality determined on the basis of the genetic characteristics of the soil. The executive act regulating the issue of soil science classification of land are the provisions included in the Regulation of the Council of Ministers of September 12, 2012 on soil science classification of land (Journal of Laws 2012, item 1246). The aim of the article was to present the problems resulting from the lack of regulation of the profession of land classifier and the lack of uniform administrative procedures regarding the selection of the classifier for the purposes of the classifications. The research method used is the case study. The method was supported by the analysis of legislation in the above-mentioned scope.

PL

Gleboznawcza klasyfikacja gruntów z punktu widzenia prawnego regulowana jest poprzez ustawę Prawo Geodezyjne i Kartograficzne, gdzie zdefiniowana jest jako podział gleb na klasy bonitacyjne ze względu na ich jakość produkcyjną ustaloną na podstawie cech genetycznych gleb. Aktem wykonawczym regulującym zagadnienie gleboznawczej klasyfikacji gruntów są przepisy zawarte w Rozporządzeniu Rady Ministrów z dnia 12 września 2012 r. w sprawie gleboznawczej klasyfikacji gruntów (Dz.U. 2012 poz.1246). Celem artykułu było przedstawienie problemów wynikających z braku uregulowania zawodu klasyfikatora gruntów oraz braku jednolitych procedur administracyjnych dotyczących wyboru klasyfikatora na potrzeby realizowanych prac klasyfikacyjnych. Stosowaną metodą badawczą jest studium przypadku. Metoda została wsparta analizą prawodawstwa w wyżej wymienionym zakresie.

8

The Huber's functions and their application to a classification problem

Gacki Henryk, Kulawik Agnieszka

Mathematica Applicanda

|

2020

|

Vol. 48, no. 2

99--114

EN

In the following paper a classification problem with two multivariate normally distributed classes is considered. The problem is solved in a case of an empirical real situation (a motors data) using the Karhunen-Loeve transform and classifying functions based on estimators for unknown parameters of a multivariate normal distribution. We consider the maximum likelihood estimator and a robust one. The robust estimator bases on the Huber's functions. The corresponding classifying functions (classifiers) are compared using the Leave-One-Out metod.

PL

W artykule rozważany jest problem klasyfikacji w przypadku dwóch klas o wielowymiarowym rozkładzie normalnym. Problem ten jest rozwiązywany na podstawie przykładu empirycznego (dane dotyczące silników) z wykorzystaniem transformacji Karhunena-Loevego oraz funkcji klasyfikujących bazujących na wybranych estymatorach nieznanych parametrów wielowymiarowego rozkładu normalnego. Rozważany jest zarówno klasyczny estymator - estymator największej wiarogodności, jak również estymator odporny, który opiera się o funkcje Hubera. Uzyskane klasyfikatory są porównywane za pomocą sprawdzianu krzyżowego - metoda Leave-One-Out.

9

Application of uninorms to aggregate uncertainty from many classifiers

Drygaś Paweł, Bazan Jan G., Pusz Piotr, Knap Maksymilian

Journal of Automation Mobile Robotics and Intelligent Systems

|

2019

|

Vol. 13, No. 4

85--90

EN

In this contribution we want to present the concept of uncertainty area of classifiers and an algorithm that uses uninorms to minimize the area of uncertainty in the pre‐ diction of new objects by complex classifiers.

10

Attribute selection for stroke prediction

Zdrodowska Małgorzata

Acta Mechanica et Automatica

|

2019

|

Vol. 13, no. 3

200--204

EN

Stroke is the third most common cause of death and the most common cause of long-term disability among adults around theworld. Therefore, stroke prediction and diagnosis is a very important issue. Data mining techniques come in handy to help determine the correlations between individual patient characterisation data, that is, extract from the medical information system the knowledge necessary to predict and treat various diseases. The study analysed the data of patients with stroke using eight known classification algorithms (J48 (C4.5), CART, PART, naive Bayes classifier, Random Forest, Supporting Vector Machine and neural networks Multilayer Perceptron), which allowed to build an exploration model given with an accuracy of over 88%. The potential features of patients, which may be factors that increase the risk of stroke, were also indicated.

11

Applying Machine Learning to Software Fault Prediction

Wójcicki B., Dabrowski R.

e-Informatica Software Engineering Journal

|

2018

|

Vol. 12, nr 1

199--216

EN

Introduction: Software engineering continuously suffers from inadequate software testing. The automated prediction of possibly faulty fragments of source code allows developers to focus development efforts on fault-prone fragments first. Fault prediction has been a topic of many studies concentrating on C/C++ and Java programs, with little focus on such programming languages as Python. Objectives: In this study the authors want to verify whether the type of approach used in former fault prediction studies can be applied to Python. More precisely, the primary objective is conducting preliminary research using simple methods that would support (or contradict) the expectation that predicting faults in Python programs is also feasible. The secondary objective is establishing grounds for more thorough future research and publications, provided promising results are obtained during the preliminary research. Methods: It has been demonstrated that using machine learning techniques, it is possible to predict faults for C/C++ and Java projects with recall 0.71 and false positive rate 0.25. A similar approach was applied in order to find out if promising results can be obtained for Python projects. The working hypothesis is that choosing Python as a programming language does not significantly alter those results. A preliminary study is conducted and a basic machine learning technique is applied to a few sample Python projects. If these efforts succeed, it will indicate that the selected approach is worth pursuing as it is possible to obtain for Python results similar to the ones obtained for C/C++ and Java. However, if these efforts fail, it will indicate that the selected approach was not appropriate for the selected group of Python projects. Results: The research demonstrates experimental evidence that fault-prediction methods similar to those developed for C/C++ and Java programs can be successfully applied to Python programs, achieving recall up to 0.64 with false positive rate 0.23 (mean recall 0.53 with false positive rate 0.24). This indicates that more thorough research in this area is worth conducting. Conclusion: Having obtained promising results using this simple approach, the authors conclude that the research on predicting faults in Python programs using machine learning techniques is worth conducting, natural ways to enhance the future research being: using more sophisticated machine learning techniques, using additional Python-specific features and extended data sets.

12

Feature projection k-NN classifier model for imbalanced and incomplete medical data

Porwik P., Orczyk T., Lewandowski M., Cholewa M.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

644--656

EN

Many datasets, especially various historical medical data are incomplete. Various qualities of data can significantly hamper medical diagnosis and are bottlenecks of medical support systems. Nowadays, such systems are often used in medical diagnosis. Even great number of data can be unsuitable when data is imbalanced, missing or corrupted. In some cases these troubles can be overcome by machine learning algorithms designed for predictive modeling. Proposed approach was tested on real medical data and some benchmarks dataset form UCI repository. The liver fibrosis disease from a medical point of view is difficult to treatment and has a significant social and economic impact. Stages of liver fibrosis are diagnosed by clinical observation and evaluations, coupled with a so-called METAVIR rating scale. However, these methods may be insufficient, especially in the recognition of phase of the disease. This paper describes a newly developed algorithm to non-invasive fibrosis stage recognition using machine learning methods – a classification model based on feature projection k-NN classifier. This solution allows extracting data characteristics from the historical data which may be incomplete and may contain imbalance (unequal) sets of patients. Proposed novel solution is based on peripheral blood analysis without using any specialized biomarkers, and can be successfully included to medical diagnosis support systems and might be a powerful tool for effective estimation of liver fibrosis stages.

13

Web–based framework for breast cancer classification

Bruździński T., Krzyżak A., Fevens T., Jeleń Ł.

Journal of Artificial Intelligence and Soft Computing Research

|

2014

|

Vol. 4, No. 2

149--162

EN

The aim of this work is to create a web-based system that will assist its users in the cancer diagnosis process by means of automatic classification of cytological images obtained during fine needle aspiration biopsy. This paper contains a description of the study on the quality of the various algorithms used for the segmentation and classification of breast cancer malignancy. The object of the study is to classify the degree of malignancy of breast cancer cases from fine needle aspiration biopsy images into one of the two classes of malignancy, high or intermediate. For that purpose we have compared 3 segmentation methods: k-means, fuzzy c-means and watershed, and based on these segmentations we have constructed a 25–element feature vector. The feature vector was introduced as an input to 8 classifiers and their accuracy was checked. The results show that the highest classification accuracy of 89.02 % was recorded for the multilayer perceptron. Fuzzy c–means proved to be the most accurate segmentation algorithm, but at the same time it is the most computationally intensive among the three studied segmentation methods.

14

Automated approach to classification of mine-like objects using multiple-aspect sonar images

Wang X., Liu X., Japkowicz N., Matwin S.

Journal of Artificial Intelligence and Soft Computing Research

|

2014

|

Vol. 4, No. 2

133--148

EN

In this paper, the detection of mines or other objects on the seabed from multiple side-scan sonar views is considered. Two frameworks are provided for this kind of classification. The first framework is based upon the Dempster–Shafer (DS) concept of fusion from a single-view kernel-based classifier and the second framework is based upon the concepts of multi-instance classifiers. Moreover, we consider the class imbalance problem which is always presents in sonar image recognition. Our experimental results show that both of the presented frameworks can be used in mine-like object classification and the presented methods for multi-instance class imbalanced problem are also effective in such classification.

15

Możliwości poprawy jakości kruszywa przez zastosowanie klasyfikatora pulsacyjnego typu KOMAG

Matusiak P., Kowol D.

Prace Naukowe Instytutu Górnictwa Politechniki Wrocławskiej. Studia i Materiały

|

2013

|

Vol. 136, nr 43

109--118

PL

Przedstawiono rozwój konstrukcji klasyfikatorów pulsacyjnych typu KOMAG stosowanych do pozyskiwania żwiru i piasku, z jednoczesnym wydzielaniem zanieczyszczeń organicznych i mineralnych. Zamieszczono wyniki badań laboratoryjnych optymalizujących działanie klasyfikatorów. Opisano czynniki procesowe wpływające na zwiększenie skuteczności wzbogacania w zależności od charakterystyki nadawy (kruszywa).

EN

Progress in development of design of KOMAG pulsating jigs used for utilization of gravel and sand together with separation of organic and mineral impurities is presented in the paper. Results of laboratory tests aiming at optimization of classifiers operation are given. Technological factors, which have an impact on increase of beneficiation efficiency depending on feed (aggregates) characteristics, are discussed.

16

A survey of old and new results for the test error estimation of a classifier

Anguita D., Ghelardoni L., Ghio A., Ridella S.

Journal of Artificial Intelligence and Soft Computing Research

|

2013

|

Vol. 3, No. 4

229--242

EN

The estimation of the generalization error of a trained classifier by means of a test set is one of the oldest problems in pattern recognition and machine learning. Despite this problem has been addressed for several decades, it seems that the last word has not been written yet, because new proposals continue to appear in the literature. Our objective is to survey and compare old and new techniques, in terms of quality of the estimation, easiness of use, and rigorousness of the approach, so to understand if the new proposals represent an effective improvement on old ones.

17

Analiza wybranych nieparametrycznych metod automatycznej klasyfikacji obiektów wielowymiarowych w aplikacji do nieniszczącej detekcji uszkodzeń

Giżewski T., Wac-Włodarczyk A., Goleman R., Czerwiński D.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 9b

234-237

PL

Artykuł przedstawia problematykę nieparametrycznych metod klasyfikacji w odniesieniu do numerycznego modelu obiektu fizycznego. Głównym tematem jest analiza skuteczności algorytmów pod kątem zastosowań w nieniszczącej detekcji uszkodzeń. Szczególną uwagę zwrócono na parametryzację modelu, jako czynnika istotnego przy minimalizacji kosztów procesu uczenia.

EN

The article presents the discussion on nonparametric classification methods in relation to the numerical model of a physical object. The main theme is the analysis of algorithms in applications to non-destructive testing of ferromagnetic materials. The particular attention was given to model parameterization as a significant factor in minimizing the cost of the learning process.

18

Klasyfikator pulsacyjny jako sprawdzone urządzenie do oczyszczania surowców mineralnych

Matusiak P., Kowol D.

Prace Naukowe Instytutu Górnictwa Politechniki Wrocławskiej. Studia i Materiały

|

2012

|

Vol. 134, nr 41

191-199

PL

Wymagania ochrony środowiska oraz kryteria efektywności wymuszają na producentach wysoką jakość kruszyw. Klasyfikator pulsacyjny jako wielokrotnie stosowane urządzenie pozwala na spełnienie tych wymagań. W artykule przedstawiono zasadę działania klasyfikatora pulsacyjnego, przedstawiono odmiany rozwiązań konstrukcyjnych oraz przykłady wdrożeń klasyfikatorów. Opisano możliwości zastosowania klasyfikatora z łożem zawiesinowym do rozdziału drobnoziarnistych surowców mineralnych.

EN

Regulations as regards environment protection and effectiveness criteria force the manufacturers to offer high-quality aggregates. Pulsatory jig as repeatedly used device enables meeting mentioned above requirements for minerals. Principle of pulsatory jig operation is presented in the paper. Versions of design solutions and examples of implementations of pulsatory jigs are given. Application possibilities of suspension classifier for separation of fine minerals are described.

19

Protein fold classification based on machine learning paradigm – a review

Stąpor K.

Bio-Algorithms and Med-Systems

|

2012

|

Vol. 8, no. 1

53--76

EN

Protein fold recognition using machine learning-based methods is crucial in the protein structure discovery, especially when the traditional sequence comparison methods fail because the structurally-similar proteins share little in the way of sequence homology. Many different machine learning-based fold classification methods have been proposed with still increasing accuracy and the main aim of this article is to cover all the major results in this field.

20

Diagnostics of DC machine based on analysis of acoustic signals with application of MFCC and classifier based on words

Głowacz A., Głowacz Z.

Archives of Metallurgy and Materials

|

2012

|

Vol. 57, iss. 1

179-183

EN

Technical diagnostics is concerned with the assessment of technical conditions of the machine through the study of properties of machine processes. Diagnostics is particularly important for factories and ironworks. In paper is presented method of diagnostics of imminent failure conditions of DC machine. This method is based on a study of acoustic signals generated by DC machine. System of sound recognition uses algorithms for data processing, such as Mel Frequency Cepstral Coefficient and classifier based on words. Software to recognize the sounds of DC machine was implemented on PC computer. Studies were carried out for sounds of faultless machine and machine with shorted coils. The results confirm that the system can be useful for diagnostics of dc and ac machines used in metallurgy.

PL

Techniczna diagnostyka zajmuje się oceną stanu technicznego maszyny poprzez badania własności procesów zachodzących w maszynie. Diagnostyka jest szczególnie ważna dla fabryk i hut. W artykule jest przedstawiona metoda diagnostyki stanów przedawaryjnych maszyny prądu stałego. Metoda ta oparta jest na badaniu sygnałów akustycznych generowanych przez maszynę prądu stałego. System rozpoznawania dźwięku wykorzystuje algorytmy przetwarzania danych, takich jak algorytm MFCC i klasyfikator oparty na słowach. Zaimplementowano oprogramowanie do rozpoznawania dźwięków maszyny prądu stałego na komputerze PC. Przeprowadzono badania sygnałów akustycznych maszyny bez uszkodzeń i maszyny ze zwartymi uzwojeniami. Wyniki badań potwierdzają, że system może być przydatny w diagnostyce maszyn prądu stałego i przemiennego używanych w hutnictwie.