Wyniki wyszukiwania - BazTech

1

Badanie możliwości wykorzystania metod uczenia maszynowego do określenia przebiegu wydzieleń klas bonitacyjnych

Szkibiel Michał, Osińska-Skotak Katarzyna

Teledetekcja Środowiska

|

2024

|

T. 64

1--23

PL

W teledetekcji w ostatnich latach uzyskano duży postęp dzięki wprowadzeniu automatyzacji oraz zastosowaniu algorytmów sztucznej inteligencji. Nowe podejście pozwoliło wykryć zależności, które nie były widoczne dla człowieka i stał się możliwy analityczny opis rzeczywistości, który do tej pory głównie opierał się na intuicji. Jednym z wyzwań w zakresie teledetekcji gleb jest monitorowane stanu gleb w skali kraju oraz aktualizacja baz danych o glebach, w tym aktualizacja przebiegu wydzieleń klas bonitacyjnych. Celem niniejszych badań było sprawdzenie możliwości wykorzystania metod uczenia maszynowego do klasyfikacji gleb zgodnie z obowiązującą gleboznawczą klasyfikacją gruntów ornych z użyciem danych teledetekcyjnych i numerycznego modelu terenu (NMT). Jako dane źródłowe wykorzystano satelitarne obrazy optyczne Sentinel-2 i radarowe Sentinel-1 oraz cztery produkty pochodne NMT, opisujące cechy ważne z punktu widzenia klasyfikacji bonitacyjnej gleb. Klasyfikacje zostały przeprowadzone metodą lasów losowych i konwolucyjnych sieci neuronowych (CNN) na wybranym obszarze treningowym w różnych scenariuszach, a następnie wytrenowane modele zostały zweryfikowane na zestawie testowym. Niestety modele opisane lasami losowymi nie uzyskały dobrych wyników na zestawie testowym w przeciwieństwie do zestawu treningowego (skuteczność 70% vs 10%). Modele opisane przez CNN uzyskały wyniki podobne dla obu zestawów, lecz ich skuteczność była niska (40%).

EN

In recent years there was a large progress in remote sensing, thanks to applying automation and artificial intelligence algorithms. The new approach revealed relationships which were not visible for human operator and enabled analytical description of reality which was based on intuition so far. One of challenges of soil remote sensing is monitoring of soil condition in country scale and database actualisation including actualisation of soil valuation classes boundaries. The aim of the research was to find out possibilities of using machine learning methods for soil classification on arable land according to current Polish law with remote sensing data and digital elevation model (DEM). Used source data were optical satellite images of Sentinel-2 and radar of Sentinel-1, and four derived products of DEM describing significant features for soil valuation classification. Classification was done by random forests and convolutional neural networks (CNN) on selected training dataset in different scenarios and then trained models were verified on test dataset. Unluckily, models described by random forests were not successful on test dataset as much as on training dataset (accuracy 70% vs 10%). Models described by CNN had similar results for both datasets but the accuracy was low (40%).

2

Conditional mean embedding and optimal feature selection via positive definite kernels

Jorgensen Palle E.T., Song Myung-Sin, Tian James

Opuscula Mathematica

|

2024

|

Vol. 44, no. 1

79--103

EN

Motivated by applications, we consider new operator-theoretic approaches to conditional mean embedding (CME). Our present results combine a spectral analysis-based optimization scheme with the use of kernels, stochastic processes, and constructive learning algorithms. For initially given non-linear data, we consider optimization-based feature selections. This entails the use of convex sets of kernels in a construction of optimal feature selection via regression algorithms from learning models. Thus, with initial inputs of training data (for a suitable learning algorithm), each choice of a kernel K in turn yields a variety of Hilbert spaces and realizations of features. A novel aspect of our work is the inclusion of a secondary optimization process over a specified convex set of positive definite kernels, resulting in the determination of “optimal” feature representations.

3

Authorial approach to the detection of selected psychological traits based on handwritten texts

Woda Marek, Oliwa Grzegorz

International Journal of Electronics and Telecommunications

|

2024

|

Vol. 70, No. 1

145--152

EN

The study sought to use computer techniques to detect selected psychological traits based on the nature of the writing and to evaluate the effectiveness of the resulting software. Digital image processing and deep neural networks were used. The work is complex and multidimensional in nature, and the authors wanted to demonstrate the feasibility of such a topic using image processing techniques and neural networks and machine learning. The main studies that allowed the attribution of psychological traits were based on two models known from the literature, KAMR and DA. The evaluation algorithms that were implemented allowed the evaluation of the subjects and the assignment of psychological traits to them. The DA model turned out to be more effective than the KAMR model.

4

The Internet of Things and AI-based optimization within the Industry 4.0 paradigm

Mikołajewski Dariusz, Czerniak Jacek M., Piechowiak Maciej, Węgrzyn-Wolska Katarzyna, Kacprzyk Janusz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

Vol. 72, nr 1

art. no. e147346

EN

By reviewing the current state of the art, this paper opens a Special Section titled “The Internet of Things and AI-driven optimization in the Industry 4.0 paradigm”. The topics of this section are part of the broader issues of integration of IoT devices, cloud computing, big data analytics, and artificial intelligence to optimize industrial processes and increase efficiency. It also focuses on how to use modern methods (i.e. computerization, robotization, automation, machine learning, new business models, etc.) to integrate the entire manufacturing industry around current and future economic and social goals. The article presents the state of knowledge on the use of the Internet of Things and optimization based on artificial intelligence within the Industry 4.0 paradigm. The authors review the previous and current state of knowledge in this field and describe known opportunities, limitations, directions for further research, and industrial applications of the most promising ideas and technologies, considering technological, economic, and social opportunities.

5

Machine learning for two-phase gas-liquid flow regime evaluation based on raw 3D ECT measurement data

Wajman Radosław, Nowakowski Jacek, Łukiański Michał, Banasiak Robert

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

Vol. 72, nr 1

art. no. e148842

EN

This paper presents a study on applying machine learning algorithms for the classification of a two-phase flow regime and its internal structures. This research results may be used in adjusting optimal control of air pressure and liquid flow rate to pipeline and process vessels. To achieve this goal the model of an artificial neural network was built and trained using measurement data acquired from a 3D electrical capacitance tomography (ECT) measurement system. Because the set of measurement data collected to build the AI model was insufficient, a novel approach dedicated to data augmentation had to be developed. The main goal of the research was to examine the high adaptability of the artificial neural network (ANN) model in the case of emergency state and measurement system errors. Another goal was to test if it could resist unforeseen problems and correctly predict the flow type or detect these failures. It may help to avoid any pernicious damage and finally to compare its accuracy to the fuzzy classifier based on reconstructed tomography images – authors’ previous work.

6

Breast cancer diagnosis: A systematic review

Wen Xin, Guo Xing, Wang Shuihua, Lu Zhihai, Zhang Yudong

Biocybernetics and Biomedical Engineering

|

2024

|

Vol. 44, no. 1

119--148

EN

The second-leading cause of death for women is breast cancer. Consequently, a precise early diagnosis is essential. With the rapid development of artificial intelligence, computer-aided diagnosis can efficiently assist radiologists in diagnosing breast problems. Mammography images, breast thermal images, and breast ultrasound images are the three ways to diagnose breast cancer. The paper will discuss some recent developments in machine learning and deep learning in three different breast cancer diagnosis methods. The three components of conventional machine learning methods are image preprocessing, segmentation, feature extraction, and image classification. Deep learning includes convolutional neural networks, transfer learning, and other methods. Additionally, the benefits and drawbacks of different methods are thoroughly contrasted. Finally, we also provide a summary of the challenges and potential futures for breast cancer diagnosis.

7

Wybrane zagadnienia analizy szeregów czasowych

Adamski Krzysztof

Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki

|

2023

|

nr 29

7--104

PL

Artykuł obejmuje przegląd wybranych zagadnień związanych z analizą i predykcją szeregów czasowych zawierających dane z notowaniami giełdowymi. Przedstawiona została taksonomia szeregów czasowych oraz scharakteryzowane główne kierunki spotykane w analizie danych giełdowych. Szerzej opisane zostały wybrane narzędzia analizy technicznej. W kolejnych rozdziałach dokonany został przegląd wybranych metod uczenia maszynowego, zarówno metod algorytmicznych jak i metod wykorzystujących sieci neuronowe, przydatnych w analizie i predykcji szeregów czasowych.

EN

The article provides an overview of selected problems related to the analysis and prediction of time series containing stock market data. The taxonomy of time series is presented, and the main directions encountered in the analysis of financial data are characterized. Selected tools of technical analysis are described in more detail. Subsequent chapters provide a review of selected machine learning methods, divided into a section on algorithmic methods and a section on neural networks useful in the analysis and prediction of time series.

8

The Factors Disrupting the Evolution of Artificial Intelligence in Operational Risk Management in the Bangladeshi IT Sector - A Case Study

Ahmed Md Ferdous, Szczepański Marek

Zeszyty Naukowe Politechniki Poznańskiej. Organizacja i Zarządzanie

|

2023

|

Nr 87

9--31

EN

Despite the enormous potential and benefits of AI deployment or adoption, Bangladesh’s IT sector has yet to utilize AI for operational risk management (ORM). The main purpose of this research is to identify the primary barriers to AI deployment in operational risk management, as seen by professionals at the chosen company from the IT Sector in Bangladesh, and to interpret the findings under the TOE framework (Technology-Organization-Environment Framework). This study will provide a summary of the current state of artificial intelligence in operational risk management in Bangladeshi enterprises from the IT Sector, and identify the primary barriers to AI adoption in operational risk management in Bangladesh through an examination of Bangladeshi professionals' perceptions. The study's findings are determined using a quantitative approach. This article presents the findings of an online survey questionnaire conducted on IT professionals from a Bangladeshi IT organization. Results indicate that the internal culture and social components, transparency issues, insufficient financial investment, sufficient non-AI techniques, insufficient legal and ethical framework, bias, inaccuracy, feedback, and algorithm misuse are key challenges. Applying the TOE framework, the above have been classified into three categories of barriers: organizational, environmental, and technical.

PL

Pomimo niebywałego potencjału i korzyści płynących z implementacji sztucznej inteligencji w sektorze IT, Bangladesz nie zastosował jeszcze tej technologii w zarządzaniu ryzykiem operacyjnym. Podstawowym celem zaprezentowanych w tekście badań było określenie podstawowych barier uniemożliwiających wprowadzenie technologii AI w obszarze zarządzania ryzykiem operacyjnym na podstawie rozpoznań dokonanych przez przedstawicieli wybranych firm reprezentujących sektor IT w Bangladeszu. Wyniki badań zostały skonsultowane w ramach TOE (Technology-Organization-Environment Framework). Badanie niniejsze stanowi podsumowanie dotychczasowego wymiaru zastosowania sztucznej inteligencji w zarządzaniu ryzykiem w bangladeskich przedsiębiorstwach z branży IT. Ponadto artykuł zawiera – opartą na badaniach ankietowych, przeprowadzonych wśród przedstawicieli sektora IT z Bangladeszu – identyfikację podstawowych barier uniemożliwiających zastosowania sztucznej inteligencji w działaniach mających na celu określenie ryzyka operacyjnego. Metodologią badania były badania ilościowe, które wykazały, iż na drodze do zastosowania sztucznej inteligencji w przestrzeni określania ryzyka operacyjnego w branży IT w Bangladeszu leży szereg problemów. Wśród nich należy wymienić: kulturę wewnętrzną zarządzania, czynniki społeczne, problemy związane z transparentnością, niewystarczające inwestycje finansowe. Ponadto wskazać należy na istnienie innych technik zarządzania, które nie wykorzystują sztucznej inteligencji. W Bangladeszu nie funkcjonują wystarczające ramy prawne i etyczne, a w przedsiębiorstwach często panuje stronniczość, niedokładność, a same algorytmy bywają używane w nieprawidłowy sposób. Wymienione kluczowe wyzwania mogą zostać przyporządkowane do trzech kategorii: barier organizacyjnych, środowiskowych oraz technicznych.

9

Artificial intelligence in the chemical industry – risks and opportunities

Laska Mateusz, Karwala Izabela

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2023

|

z. 172

403--416

EN

Purpose: The aim of the article is to review the literature on the risks and opportunities of implementing Industry 4.0 - Artificial Intelligence solutions in the chemical industry. Design/methodology/approach: The review was carried out using available scientific articles, popular science publications, and media reports from the world's largest companies in the chemical industry. Findings: The analysis indicates that there are more benefits than risks arising from the implementation of Artificial Intelligence solutions in the chemical industry. Research limitations/implications: The frequent lack of specific economic indicators makes it difficult to clearly indicate the implementation potential of a specific solution in other companies in the chemical industry. Social implications: The implementation of AI in chemical industry companies can reduce environmental pollution, raw material consumption, and optimize production processes. Originality/value: The article, based on real data, is aimed at middle and senior management of companies in the chemical industry, presenting the advantages and disadvantages of implementing AI solutions in the chemical industry.

10

Automatyczne rozpoznawanie treści dokumentów ze wspomaganiem technik sztucznej inteligencji

Gulczyński Tomasz, Eljaszak Piotr

Wiadomości Elektrotechniczne

|

2023

|

R. 91, nr 10

24--27

PL

Przedsiębiorstwa i organizacje przetwarzają ogromne ilości dokumentacji papierowej, co angażuje pracowników do żmudnej i błędogennej pracy. Artykuł opisuje techniki, które można zastosować, aby zautomatyzować ten proces w celu wydobywania istotnych informacji z dokumentów takich jak podmiot i przedmiot umowy, terminy i daty, lokalizacja, dane techniczne obiektów i inne, specyficzne dla danego typu dokumentu. System iDoc stosuje elementy sztucznej inteligencji w rozpoznawaniu treści dokumentów, pozwala osiągnąć 10-krotne przyspieszenie przetwarzania przy zachowaniu wysokiej dokładności, a także umożliwia ręczną weryfikację danych.

EN

In today's business landscape, companies and organizations grapple with processing extensive volumes of paper documents, burdening their employees with tedious and error-prone tasks. This article presents innovative techniques for automating this process by efficiently extracting critical information from various documents, including contract subjects and objects, dates, deadlines, locations, technical data about devices, and other specific contents pertaining to distinct document types. Leveraging Artificial Intelligence, the iDoc system identifies document contents, enabling users to process data ten times faster while maintaining a high level of accuracy. By adopting iDoc, manual data processing becomes obsolete, while still allowing users to validate extracted information.

11

Deep Convolutional Neural Network Algorithm for Prediction of the Mechanical Properties of FSW Copper Welds from its Microstructure

Mishra Akshansh, Suman Asmita

Welding Technology Review

|

2023

|

R. 95

25--31

EN

Convolutional Neural Network (CNN) is a special type of Artificial Neural Network which takes input in the form of an image. Like Artificial Neural Network they consist of weights that are estimated during training, neurons (activation functions), and an objective (loss function). CNN is finding various applications in image recognition, semantic segmentation, object detection, and localization. The present work deals with the prediction of the welding efficiency of the Friction Stir Welded joints on the basis of microstructure images by carrying out training on 3000 microstructure images and further testing on 300 microstructure images. The loss function decreased for both training and testing set decreased with the increasing number of epochs. The obtained results showed an accuracy of 80 % on the validation dataset.

12

Application of unsupervised learning algorithms for analysis the vibrations of an oscillator forced by a random series of impulses

Ozga Agnieszka, Sulewski Marek

Vibrations in Physical Systems

|

2023

|

Vol. 34, nr 1

art. no. 2023121

EN

Paper discusses a mathematical model describing the vibrations of a linear oscillator forced by a random series of impulses. The study aims at checking how precisely the distributions of values of the impulses forcing the vibrations of an oscillator can be differentiated. The analysis was carried out in the MatLab environment with the use of hierarchical clustering algorithms of unsupervised machine learning, for samples generated from computer simulation. The time series are non-stationary. The studies showed that high precision could be achieved in distinguishing two very similar distributions forcing the vibrations, on the basis of an analysis of the two first moments calculated from the movement.

13

Prediction of ship's speed through ground using the previous voyage's drift speed

Yamane D., Kano T.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2023

|

Vol. 17 No. 1

129--137

EN

In recent years, 'weather routing' has been attracting increasing attention as a means of reducing costs and environmental impact. In order to achieve high-quality weather routing, it is important to accurately predict the ship's speed through ground during a voyage from ship control variables and predicted data on weather and sea conditions. Because sea condition forecasts are difficult to produce in-house, external data is often used, but there is a problem that the accuracy of sea condition forecasts is not sufficient and it is impossible to improve the accuracy of the forecasts because the data is external. In this study, we propose a machine learning method for predicting speed through ground by considering the actual values of the previous voyage’s drift speed for ships that regularly operate on the same route, such as ferries. Experimental results showed that this method improves the prediction performance of ship’s speed through ground.

14

Improving the credibility of the extracted position from a vast collection of job offers with machine learning ensemble methods

Drozda Paweł, Ropiak Krzysztof, Nowak Bartosz A., Talun Arkadiusz, Osowski Maciej

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2023

|

nr 26(1)

125--140

EN

The main aim of this paper is to evaluate crawlers collecting the job offers from websites. In particular the research is focused on checking the effectiveness of ensemble machine learning methods for the validity of extracted position from the job ads. Moreover, in order to significantly reduce the training time of the algorithms (Random Forests and XGBoost), granularity methods were also tested to significantly reduce the input training dataset. Both methods achieved satisfactory results in accuracy and F1 measures, which exceeded 96%. In addition, granulation reduced the input dataset by more than 99%, and the results obtained were only slightly worse (accuracy between 1% and 5%, F1 between 3% and 8%). Thus, it can be concluded that the considered methods can be used in the evaluation of job web crawlers.

15

A short technical review on Dgital Twins in smart manufacturing

Korkmaz Mehmet Erdi

Sustainable Production, Instrumentation and Engineering Sciences

|

2023

|

vol. 1, nr 1

1--7

EN

The most recent tendencies and breakthroughs in digital technologies have made it possible to implement a new model of manufacturing. By es-tablishing a digital twin of the real environment and basing their judg-ments on that twin, digital systems are able to monitor, optimize, and man-age the processes that they are applied to. This concept is predicated on the creation of a “Digital Twin” for each individual production source that contributes to the overall manufacturing process. In spite of the fact that different real-world applications of digital twin may involve different tech-nical and operational specifics, a significant amount of work was put in over the past few years to recognize and express principal properties, in addition to the primary challenges involved in the practical implementa-tion of digital twins within related industries. The purpose of this article is to review and analyze the fundamental principles, ideas, and technological solutions that comprise the Digital Twin vision for production processes. As a result, the objective of this review is to provide a synopsis of the state-of-the-art regarding digital twin concepts and to analyze their most recent status in terms of their potential application and implementation.

16

Reconstructing damaged data in AIS and other telecommunications systems: a survey

Szarmach Marta, Czarnowski Ireneusz

Scientific Journal of Gdynia Maritime University

|

2023

|

nr 127

15--26

EN

AIS (Automatic Identification System) is a telecommunication system created to enable ships to transmit information regarding their trajectories (such as their position, speed, course, etc.) to other ships and shore stations. With the use of AIS, collisions between ships can be avoided. Unfortunately, AIS suffers from some technical issues that lead to part of the transmitted data being damaged (incorrect or missing). This paper contains a review of machine learning based methods of reconstructing this damaged AIS data as well as examples of inspiration from other telecommunication systems for dealing with this kind of a problem. Finally, after analysing frameworks available in the relevant literature, a novel algorithm for AIS data reconstruction is briefly presented.

17

Zastosowanie uczenia maszynowego w lokalnych sieciach bezprzewodowych

Szott Szymon

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

7--14

PL

Pomocą w rozwiązaniu wyzwań stojących przed kolejnymi generacjami lokalnych sieci bezprzewodowych mogą okazać się metody oparte na uczeniu maszynowym (machine learning, ML). Celem niniejszego referatu jest przybliżenie tematyki zastosowania ML do poprawy wydajności sieci IEEE 802.11. Przedstawiono rodzaje uczenia maszynowego oraz przykłady zastosowań w sieciach Wi-Fi. Opisano działalność grupy IEEE 802.11 AIML TIG oraz wyznaczono przyszłe kierunki badań.

EN

Methods based on machine learning (ML) can prove to be helpful in addressing the challenges faced by future generations of wireless local area networks. The aim of this paper is to provide an overview of the application of ML to improve the performance of IEEE 802.11 networks. Various types of machine learning and examples of their applications in Wi-Fi networks are presented. The activities of the IEEE 802.11 AIML TIG are described and future research directions are outlined.

18

Zastosowanie algorytmów wielorękich bandytów do wyboru szybkości transmisji w sieciach IEEE 802.11ax

Wojnar Maksymilian, Ciężobka Wojciech

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

173--176

PL

Wybór szybkości transmisji jest kluczowym problemem sieci IEEE 802.11. Można traktować go jako zagadnienie wielorękich bandytów. W tej pracy zaimplementowano algorytmy wielorękich bandytów używając autorskiej biblioteki programistycznej. Przeprowadzono studium parametrów oraz testy działania rozwiązań w symulatorze ns-3. Wyniki pokazują, że zastosowanie omawianych algorytmów może znacząco poprawić wydajność gęstych sieci Wi-Fi.

EN

Data rate selection is a typical problem of Wi-Fi networks. We present this problem in IEEE 802.11 networks as a multi-armed bandit (MAB) problem. We implement MAB algorithms using our library for rapid prototyping of reinforcement learning algorithms. We conduct a parameter study and test the performance of the solutions in the ns-3 simulator. Our results show that using MAB algorithms can significantly improve the performance of dense Wi-Fi networks.

19

Unsupervised category learning in perceived video quality

Vejar Andres, Konaszyński Tomasz, Juszka Dawid, Leszczuk Mikołaj

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

329--332

EN

In video quality evaluation, the perceived quality is ranked by the participants using a categorical scale of five levels. To study the category learning dependency, the participants were divided into learners and no-learners, with respect to their classification accuracy. An analysis of the performance of the human unsupervised learning from machine learning models is presented in order to study the effects of category learning in the video assessment.

20

Uczenie maszynowe z ochroną prywatności danych

Sobolak Kamil, Chołda Piotr

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

113--116

PL

Porównano różne metody służące do zapewniania prywatności w przypadku przetwarzania danych z użyciem uczenia maszynowego. Wybrano najbardziej adekwatne metody: szyfrowanie homomorficzne, prywatność różnicowa, metoda uczenia federacyjnego. Efektywność przedstawionych algorytmów została ujęta ilościowo za pomocą powszechnie używanych metryk: funkcji kosztu dla jakości procesu uczenia, dokładności dla klasyfikacji i współczynnika determinacji dla regresji.

EN

Various methods for ensuring privacy in machine learning based data processing were compared. The most suitable methods have been selected: homomorphic encryption, differential privacy, and federated learning. The effectiveness of the presented algorithms was quantified using commonly used metrics: cost function for the quality of the learning process, accuracy for classification, and coefficient of determination for regression.