Wyniki wyszukiwania - BazTech

1

Multidecadal Wind-Wave Variability in Makassar Strait along ALKI 2: ERA-Interim Based Assessment Supports IKN Maritime Resilience

Pawara M.U., Arifuddin A.M.N., Apriansyah A., Mahmuddin F., Alamsyah A., Suardi S., Raditya M.Y.

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

|

2026

|

Vol. 20 No. 1

153--158

EN

This study investigates the multidecadal variability of wave and wind dynamics along the Indonesian ALKI 2 shipping lane in the Makassar Strait using ERA-Interim reanalysis data for 39 years (1979–2017). Seven observation points (K1–K7) were analyzed from northern Kalimantan to the southern strait. Key parameters include Significant Wave Height (SWH), Mean Wave Period (MWP), and 10-meter wind speed. The results reveal significant spatial and seasonal variability influenced by the monsoon system and local topographic effects. The northern points exhibit higher wave energy during DJF (December–February), while the southern points are more active in JJA (June–August), consistent with the prevailing seasonal winds. Trend analysis shows a weak but statistically significant increase in MWP at certain locations. These insights are critical for the development of maritime infrastructure and risk mitigation strategies associated with Indonesia’s new capital city (IKN Nusantara), located near this important shipping corridor.

2

Integrating Artificial Intelligence into Naval Capability Development

Ljulj A., Štambuk I., Slapničar V.

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

|

2026

|

Vol. 20 No. 1

173--185

EN

The rapid advancement of artificial intelligence (AI) is transforming naval capabilities, reshaping ship design, lifecycle management, operational decision-making, and autonomous maritime systems. Naval platforms are among the most complex engineered systems, characterised by long service lives, safety-critical functions, and demanding operational environments, making AI integration both strategically attractive and technically challenging. This paper presents an engineering-oriented review of AI applications in the naval domain, focusing on their role across the capability development lifecycle. To illustrate practical implementation, a Random Forest regression model is developed to support early-stage prediction of the block coefficient of naval ships. The review highlights significant opportunities associated with AI integration, including enhanced decision-making, improved design efficiency, and increased operational effectiveness. However, successful AI adoption requires technological advancement alongside organisational adaptation, strong governance, and sustained investment in human expertise. AI should therefore be understood not as a replacement for naval engineering expertise, but as a force multiplier that augments analytical capacity and accelerates innovation across the maritime domain.

3

Challenges in the Supply Chain Management Process for Offshore Wind Farms. A Scoping Review of Decision Support Tools Utilizing Discrete Event Simulation

Rybowski M.

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

|

2026

|

Vol. 20 No. 1

187--200

EN

Offshore wind energy (OWE) has become a key component of the global transition toward renewable energy; however, its supply chains remain highly complex due to harsh marine conditions, weather dependency, logistical constraints, and high capital intensity. In this context, decision support systems (DSSs) based on discrete event simulation (DES) are increasingly applied to improve planning and operational efficiency. This study aims to systematically identify offshore wind supply chain (OWSC) challenges addressed in the literature, evaluate the application of DES-based DSS, assess the methodological quality of existing studies, and highlight research gaps and future directions. A PRISMA-guided scoping review was conducted using a predefined protocol, covering English-language journal, conference, and technical publications from 2010 to 2025. Following database searches, deduplication, and screening, 30 studies were included from an initial set of 712 records. The results show that DES is widely adopted, with 63% of studies using pure DES and 37% employing hybrid simulation–optimization approaches; 67% of studies included case-based validation. Seven major categories of challenges were identified: weather and metocean conditions, vessel and fleet management, installation processes, port and logistics operations, operations and maintenance, information and coordination, and cost/time optimization. Reported benefits of DES-based DSS include improvements in cost efficiency, time performance, system availability, and resource utilization. The findings confirm that DES constitutes a robust and effective foundation for decision support in offshore wind logistics, particularly under uncertainty and resource constraints, while hybrid approaches further enhance its capabilities. Nevertheless, significant gaps remain, including inconsistent modeling assumptions (especially regarding metocean workability), limited transparency in verification and validation processes, and insufficient coverage of emerging areas such as floating wind, decommissioning, and digital integration (e.g., IoT, AI, and digital twins). These findings underline the need for improved standardization, reporting practices, and benchmark datasets in future research.

4

Linked open data concept in public institutions - Lower Silesia (Poland) case study

Lamek Anna

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2025

|

z. 218

411--426

EN

Purpose: The aim of the article is to review the level of advancement of linked open data (LOD) concept in public institutions, based on the example of Lower Silesia (Poland) organizations. Moreover, this paper considers the level of advancement of Lower Silesia institutions on the famous Tim Berners Lee’s scale and compares the obtained results. Design/methodology/approach: case study of important public institutions of Lower Silesia region, and the assessment of LOD concept advancement, based on 5-star Tim Berners Lee’s scale an short expert interviews. Findings: We can observe considerable interest and willingness to create a network of linked open data, which is visible in the growth of the number of data sets and the ever-expanding structure of the LOD cloud. Implementation of LOD in public institutions can be really helpful in management and decision-making processes. Public entities in Lower Silesia (Poland) should continue to develop their network to reach the highest level of advancement of LOD concept, especially in the context of integration with other data sets. Research limitations/implications: The limitation of the research was the fact that not all public institutions are still familiar with the concept of linked open data, or do not use it to its full extent. Practical implications: In the context of public institutions, LOD can play a key role in improving transparency, efficiency, and data-driven decision-making. Users can freely access information that is crucial to them and use it for interesting social or commercial projects, as well as individual ones. Social implications: The practical implementation of LOD is also related to its social impact, everything depends on the type of data that is made available to users. Very often, they are related to administration, public transport, budget management of smaller and larger communities or health care, what can really contribute to improving the quality of life. Originality/value: For the first time, the level of advancement of the linked open data concept in Polish public institutions was evaluated, which may improve the results in institutions already using this idea but also encourage them to develop the network of linked data resources. Keywords:

5

Experimental Investigation of Manufacturing Variables Effect on Electrical Discharge Machining of Titanium Alloy

Enzi Abass, Abdulameer Ahmed Ghazi, Hassoon Omar Hashim, Hamieh Abdallah

Management Systems in Production Engineering

|

2025

|

nr 2 (33)

202--211

EN

Titanium alloys are considered one of the materials required in industries. They can be used in various fields due to their high strength and corrosion resistance, but titanium alloys are considered difficult to machine using traditional methods. EDM is used to machine a workpiece using electrical discharges to cut hard materials that are challenging to cut with traditional methods. Therefore, this paper focuses on the machine of a high-strength material-titanium alloy Ti-6Al-4V and studies the influence of cutting process variables on the metal removal rate, tool wear rate, and surface roughness of the samples. The samples matrix form is created depending on the design of experiments method. Pulse-on time, discharge current, and gap process variables with three levels create mathematical models to predict the responses without conducting practical experiments. The results proved that machining variables impacted the responses, which were proven through results data analysis and the interaction plots. Also, the maximum error between experimental and predicted values using the mathematical model was 0.022 (mg/min) for the MRR, 1.719 (mg/min) for the TWR, and 0.334 (μm) for the Ra.

6

TPM w przedsiębiorstwie 4.0 szanse i zagrożenia

Mączyński Wojciech

Kierunek Spożywczy

|

2025

|

Nr 1

42-44

PL

Wszędzie słyszymy dziś o sztucznej inteligencji, coraz bardziej na sile przybiera też hasło Przemysł 4.0. Warto zadać sobie pytanie, czym właściwie on jest i jak możemy w odniesieniu do niego dopasować TPM.

7

Using artificial intelligence for sustainable crop production - a comprehensive review with a focus on potato production

Piekutowska Magdalena

Journal of Water and Land Development

|

2025

|

no. 64

181--193

EN

The article discusses the critical role of artificial intelligence (AI) in modern agriculture, with a particular focus on potato production. AI technologies are becoming essential tools enhancing both efficiency and sustainability in farming practices. By utilizing big data analysis, precision monitoring, and automation, AI can significantly improve agricultural outcomes. For instance, AI algorithms can optimise the use of natural resources and chemical inputs, leading to improved yield forecasting and more effective management of diseases and pests that affect crops. Additionally, AI can play a key role in agriculture with is its capability to monitor soil conditions and assess soil fertility. This enables farmers to optimise fertilisation techniques, leading to improved crop health but also better water management through precise irrigation practices. These advancements are especially crucial in addressing the rising food demand posed by global population growth, while simultaneously managing limited environmental resources. Despite the numerous benefits offered by AI, its implementation in agriculture faces challenges. High technology costs and the need for extensive education and training for farmers can hinder widespread AI adoption. Therefore, future research should aim at developing affordable AI solutions and comprehensive training programmes to maximise the technology's potential in fostering enhanced sustainable food production globally.

8

Challenges in predicting smart grid stability linked with renewable energy resources through spark MLlib Learning

Zouhri Amal, Boumhidi Ismail, Boumhidi Ismail, Ez-Zahout Abderrahmane, Chakouk Said, El Mallahi Mostafa

Journal of Automation Mobile Robotics and Intelligent Systems

|

2025

|

Vol. 19, No. 4

70--81

EN

This article conducts a numerical analysis focused on the predictive stability of smart grids, particularly in connection with renewable energy resources. The study leverages SparkMLlib machine learning tools to develop a predictive model. The aim is to enhance the understanding and forecasting of smart grid stability, with a specific emphasis on the integration of renewable energy sources. The numerical analysis involves the utilization of advanced algorithms and techniques provided by SparkMLlib to assess the intricate relationships among various factors impacting smart grid stability. The findings of this study contribute to the ongoing efforts to optimize the reliability and efficiency of smart grids in the context of increasing reliance on renewable energy resources.

9

The Importance of Data in the Modeling Process of the Realized Net Coal Production Level

Linczowska Agata, Kowal Barbara, Kęsek Marek, Piwowarczyk Paweł

Inżynieria Mineralna

|

2025

|

Vol. 1, no. 1

147--153

EN

Data analysis and model building are important elements of enterprise management, especially in mining, where the risk of conducting business is high. The article presents the procedure of building an econometric model that presents the realized level of net coal extraction. The procedure of model construction was carried out using one of the data selection methods, namely the graph method. Although the process of selecting variables for the model is correct, it is not sufficient for the correctness of the model itself. The example given shows what problems may arise and answers the question of whether modeling alone is a sufficient process to describe the analyzed phenomenon.

PL

Analiza danych i budowanie modeli są ważnym elementem zarządzania przedsiębiorstwem, szczególnie wydobywczym, gdzie ryzyko prowadzenia działalności jest duże. W artykule przeprowadzono procedurę budowy modelu ekonometrycznego przedstawiającego zrealizowany poziom wydobycia węgla netto. Przeprowadzono procedurę konstrukcji modelu z wykorzystaniem jednej z metod selekcji danych, a mianowicie metody grafowej. Pomimo, że proces doboru zmiennych do modelu jest prawidłowy, to jednak niewystarczający dla poprawności samego modelu. Przytoczony przykład pokazuje jakie problemy mogą się pojawić oraz odpowiada na pytanie czy samo modelowanie jest wystarczającym procesem do opisu analizowanego zjawiska.

10

Optimization of machine learning methods for de-anonymization in social networks

Smailov Nunzhigit, Uralova Fatima, Kadyrova Rashida, Magazov Raiymbek, Sabibolda Akezhan

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2025

|

T. 15, nr 1

101--104

EN

In recent years, social networks have struggled to meet user protection and fraud prevention requirements under unpredictable risks. Anonymity features are widely used to help individuals maintain their privacy, but they can also be exploited for malicious purposes. In this study, we develop a machine learning-driven de-anonymization system for social networks, with a focus on feature selection, hyperparameter tuning, and dimensionality reduction. Using supervised learning techniques, the system achieves high accuracy in identifying user identities from anonymized datasets. In experiments conducted on real and synthetic data, the optimized models consistently outperform baseline methods on average. Even in cases where they do not, significant improvements in precision are observed. Ethical considerations surrounding de-anonymization are thoroughly discussed, including the responsibility of implementation to maintain a balance between privacy and security. By proposing a scalable and effective framework for analyzing anonymized data in social networks, this research contributes to improved fraud detection and strengthened Internet security.

PL

W ostatnich latach sieci społecznościowe zmagają się z problemem spełnienia wymagań dotyczących ochrony użytkowników i zapobiegania oszustwom w warunkach nieprzewidywalnych zagrożeń. Funkcje anonimowości są powszechnie stosowane, aby pomóc użytkownikom zachować prywatność, ale mogą być również wykorzystywane do celów złośliwych. W niniejszym badaniu opracowaliśmy system deanonimizacji oparty na uczeniu maszynowym, przeznaczony dla sieci społecznościowych, koncentrując się na selekcji cech, dostrajaniu hiperparametrów i redukcji wymiarowości. Dzięki technikom uczenia nadzorowanego system osiąga wysoką dokładność w identyfikowaniu tożsamości użytkowników z anonimizowanych zbiorów danych. W eksperymentach przeprowadzonych na rzeczywistych i syntetycznych danych zoptymalizowane modele konsekwentnie przewyższały metody bazowe średnio. Nawet w przypadkach, gdy tak się nie działo, zaobserwowano znaczące poprawy w zakresie precyzji. Kwestie etyczne związane z deanonimizacją zostały dokładnie omówione, w tym odpowiedzialność za wdrożenie w celu utrzymania równowagi między prywatnością a bezpieczeństwem. Proponując skalowalny i efektywny model analizy anonimizowanych danych w sieciach społecznościowych, badanie to przyczynia się do poprawy wykrywania oszustw i wzmocnienia bezpieczeństwa w Internecie.

11

Application of facial recognition technologiesfor enhancing control in information security systems

Smailov Nurzhigit, Kadyrova Rashida, Abdulina Kamila, Uralova Fatima, Kubanova Nurgul, Sabibolda Akezhan

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2025

|

T. 15, nr 3

55--58

EN

This article investigates contemporary advancements in information security technologies, with a focus on automated access control systemsand their integration with biometric solutions. Particular emphasis is placed on the potential of facial recognition technologies to strengthen security protocols and streamline access management for restricted areas. A Python-based implementation utilizing the OpenCV library is presented, demonstrating real-time recognition capabilities and dynamic visitor data handling. In contrast to earlier conceptual works, this study providesa detailed description of the applied recognition algorithm, training procedure, and evaluation methodology. The system was tested in 200 experimental trialswith 20 participants under varying conditions, including changes in lighting, distance, and partial occlusions such as masks and sunglasses. Performance metrics–accuracy, precision, recall, and F1-score–were calculated based on confusion-matrix analysis. The results confirm that the proposed prototype ensures reliable operation in diverse environments, offering a scalable and cost-effective solution for enhancing access control mechanisms. By combining technical rigor with practical implementation, the study underscores the feasibility of adopting facial recognition systems to improve both securityand operational efficiency.

PL

Artykuł analizuje współczesne osiągnięcia w dziedzinie technologii bezpieczeństwa informacji, ze szczególnym uwzględnieniem zautomatyzowanych systemów kontroli dostępu oraz ich integracji z rozwiązaniami biometrycznymi. Szczególny nacisk położono na potencjał technologii rozpoznawania twarzy w zakresie wzmacniania protokołów bezpieczeństwa i usprawniania zarządzania dostępem do obszarów chronionych. Przedstawiono implementację w języku Python z wykorzystaniem biblioteki OpenCV, demonstrującą możliwości rozpoznawania twarzy w czasie rzeczywistym oraz dynamicznego przetwarzania danych dotyczących odwiedzających. W przeciwieństwie do wcześniejszych prac koncepcyjnych, niniejsze badanie zawiera szczegółowy opis zastosowanego algorytmu rozpoznawania, procedury uczenia oraz metodologii oceny. System został przetestowanyw 200 próbach eksperymentalnych z udziałem 20 uczestników w różnych warunkach, obejmujących zmiany oświetlenia, odległości oraz częściowe zasłonięcia, takie jak maseczki i okulary przeciwsłoneczne. Miary wydajności –dokładność, precyzja, czułość (recall) i miara F1 –zostały obliczonena podstawie analizy macierzy pomyłek. Uzyskane wyniki potwierdzają, że zaproponowany prototyp zapewnia niezawodne działanie w zróżnicowanych środowiskach, oferując skalowalne i opłacalne rozwiązanie na rzecz poprawy mechanizmów kontroli dostępu. Łącząc rygor naukowyz praktyczną implementacją, badanie podkreśla realne możliwości wdrożenia systemów rozpoznawania twarzy w celu zwiększenia zarównobezpieczeństwa, jaki efektywności operacyjnej.

12

Characteristic sky-background features around galaxy mergers

Suelves Luis E, Pearson William J., Pollo Agnieszka

Computer Science

|

2025

|

T. 26 (SI)

111--126

EN

In the context of finding galaxy mergers in large-scale surveys, we applied machine-learning algorithms that made use of flux measurements instead of using images (as is the current standard). By training multiple NNs using the Sloan Digital Sky Survey class-balanced data set of mergers and non-mergers, we found that sky-background error parameters could provide a validation accuracy of 92.64±0.15% and a training accuracy of 92.36±0.21%. Moreover, analyzing the NN identifications led us to find that a simple decision diagram using the sky error for two flux filters was enough to gain a 91.59% accuracy. By understanding how the galaxies vary along the diagram and trying to parametrize the methodology in the deeper images of the Hyper Suprime-Cam, we are currently trying to define and generalize this sky error-based methodology.

13

Dumped Ammunition : Never Ending Story?

Sałaciński Tomasz, Szala Mateusz, Wiaderek Barbara, Rzadkowska Klaudia

Central European Journal of Energetic Materials

|

2025

|

Vol. 22, no. 4

540--551

EN

Since the 1990s, the issue of the accumulation of ammunition, deliberately dumped in the 20th century, has been raised on a global scale. The main reason is the economic interest in the areas where these ammunition are located. There are also other reasons, such as the fact that ammunition in the aquatic environment is a source of many elements and chemicals, including those that have a negative effect on aquatic fauna and flora. In addition, ammunition that is intentionally sunk still poses a risk of explosion. So far, the removal of dumped ammunition has not been started on the full scale. There are many reasons raised by many researchers around the world, among others, the unsolved concerns on technical executing of the removal processes and the fear that as a result of starting disposal, it may lead to even greater problems. Moreover, due to the constant changes of the seabed, full restoring of dumped sites may be regarded as mission impossible. The presented paper focuses on arguments that are not often raised, however, it seems that they should be taken into account by researchers dealing with explosives and dumped ammunition, i.e. the general pollution of water reservoirs, the lack of sufficient methods for managing and analyzing large databases, as well as, the danger of terrorist threats.

14

The recycling of construction waste asphalt mixes – study case

Jiang Mengya, Cai Xiaoqing

Archives of Civil Engineering

|

2025

|

Vol. 71, nr 1

51--63

EN

Construction waste (CW) has become one of the main factors exacerbating regional environmental damage, and how to recycle and utilize CW as a resource is also a key focus of future urban construction in China. Although CW has good application effects in highway construction, its service life is still a factor that affects its promotion. Currently, CW is mostly concrete waste, so it is integrated with asphalt mixtures to prepare new types of recycled asphalt, extending the service life of asphalt roads, reducing construction costs and environmental damage. The experimental results show that the optimal asphalt to aggregate ratio of Recycled Concrete Aggregate (RCA) asphalt mixtures is between 4% and 5%. The road performance of four asphalt mixtures with different RCA contents meets the standard, and two RCA mixtures have better performance than traditional asphalt. When subjected to 150 cycles of temperature humidity coupling, the fatigue life of five different asphalt mixtures decreased, and the fatigue damage was in a rapid growth stage. The fatigue life of traditional mixtures decreases more than 1.3 times faster than that of CW asphalt mixtures. There are two types of CW asphalt mixtures that can still maintain good fatigue performance under different temperature and humidity coupling effects, which can effectively extend the service life of traditional asphalt pavement. RCA asphalt mixture has better adhesion performance, effectively alleviating the fracture impact of aggregate rigidity.

15

Optimization of photovoltaic system safety through data analysis: development and implementation of an interactive dashboard for event monitoring and preventive strategy formulation

Bednarczyk Łukasz, Starzyczny Magda, Wróblewski Wojciech

Zeszyty Naukowe SGSP / Szkoła Główna Służby Pożarniczej

|

2024

|

Nr 91 (tom 1)

45--57

EN

The development of the photovoltaic (PV) sector in Poland, as a crucial component of the renewable energy transition strategy, faces a challenge related to limited user awareness of operational risks. Our study addresses this gap by presenting the development and implementation of an interactive dashboard for the National Fire Department’s Decision Support System (SWD PSP), aimed at optimizing the safety of PV installations through data analysis and the formulation of preventive strategies. Utilizing data from fire protection units, this tool enables the monitoring of incidents and identification of potential threats, while simultaneously increasing societal awareness. The dashboard, leveraging advanced data visualization techniques, provides easy navigation and dynamic presentation of statistics, facilitating quick responses to changing data and potential hazards. The results of our study highlight the significance of such tools in enhancing the safety of using PV installations, which can contribute to the further development of the renewable Energy sector, ensuring its safety and efficiency.

16

Effectiveness of problem-based learning (PBL) on maritime courses in a blended learning modality

Germo R. R., Tan V.S., Casañare A. F.

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

|

2024

|

Vol. 18 No. 3

649--655

EN

This study aimed to determine the effectiveness of problem-based learning (PBL) on identified courses in improving the performance of maritime students. This study utilized pretest-posttest non-equivalent group design. Respondents were 480 BSMT students gathered using a match group design. Instrument used was a 45-item researcher-made multiple-choice test that has undergone content validity and reliability testing. Statistical tools used were mean and standard deviation for descriptive data analysis, Mann-Whitney test and Wilcoxon-Signed ranks for inferential data analysis, and Cohen’s d effect size, to determine the effectiveness of PBL. Results showed that the experimental and control group pretest performance before the intervention is described as poor and fair, while excellent and very good thereafter. No significant difference in the pretest scores of experimental and control groups. No significant differences in the posttest scores of experimental and control groups in NGEC 9, NAV 5, and SEAM 6, while there were significant differences in the posttest scores of experimental and control groups in NAV 2, NAV 4, and NAV 7. Significant differences were noted in the pretest and posttest scores of the experimental and control groups in all identified courses. The mean gain score of the experimental group in all identified courses is higher than the control group. No significant difference in the mean gains of experimental and control groups, for NGEC 9, NAV 5, and for SEAM 6 but significantly different was noted in NAV 2, NAV 4, and NAV 7. Based on the effect size results, PBL is highly effective on NAV 2 and NAV 7 compared to the traditional method. These results confirm how effective the PBL approach is as a teaching style in all identified courses. PBL approach is highly recommended for all maritime courses.

17

Analysis of inhibiting factors in shipyards in classterizing shipyards on the Northen coastal of ACEH Indonesia using the fuzzy AHP method: a preliminary study

Rizwan T., Chaliluddin M. A., Nuvus H., Arif M., Muchlis Y., Akhyar A.

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

|

2024

|

Vol. 18 No. 2

409--414

EN

The fishing shipyard in Banda Aceh City is a privately owned shipyard and is managed in a family manner. The shipyard here is active in carrying out maintenance, repair and construction of new ships when there is demand from consumers. Shipyards in Banda Aceh City generally make ships made of wood. The problem that is currently being faced is that there are many abandoned ships due to lack of finance, natural resources, human resources and the environmental, this is an obstacle to the progress and development of shipyards. The purpose of this study is to determine the inhibiting factors that exist in shipyards in the city of Banda Aceh and find alternative solutions to these problems. The method used in this study is a survey method used to look at existing symptoms and collect data on factors related to research variables and then analyzed using the Fuzzy AHP method. The results of this study indicate that the financial inhibiting factor is the most influential factor in shipyards with a resulting value of 0.4635, the inhibiting factor of Natural Resources is worth 0.35675, the inhibiting factor of Human Resources is worth 0.2865 and the inhibiting factor from the environment is the inhibiting factor which is the lowest or less influential with a value of 0.14325. The alternative solutions to financial problems are capital loans and investments. An alternative for natural resources is the addition of a minimum stock to anticipate stock scarcity and delays in the delivery of materials and tools. The alternative for human resources is the existence of an office, organizational structure, and division of tasks as well as awareness of occupational health and safety. As for the alternatives for the environment, namely the need for buildings or installation of tarpaulins for areas where ships are built, good land management and studies of other natural impacts.

18

Identyfikacja rodzaju szkła z zastosowaniem teorii zbiorów przybliżonych w programie RSES

Januszewski Piotr

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

18--21

PL

Artykuł przedstawia podejście do identyfikacji rodzaju szkła oparte na teorii zbiorów przybliżonych w programie RSES. Przedstawiono teoretyczne podstawy tej metody, opisano proces analizy danych oraz zaprezentowano wyniki identyfikacji rodzaju szkła.

EN

The article presents an approach to glass type identification based on rough set theory in the RSES program. The theoretical basis of this method is presented, the data analysis process is described and the results of glass type identification are presented.

19

Analiza wybranych metod walidacji krzyżowej w programie RSES

Kołpacki Radosław

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

5--8

PL

W artykule przeprowadzono analizę zbioru danych za pomocą dwóch metod walidacji krzyżowej. Wykorzystano program RSES do identyfikacji kluczowych właściwości i relacji w zbiorze. Wyniki wykazują wpływ niektórych parametrów na potencjalną dokładność wyników.

EN

This article presents an analysis of a dataset using two cross-validation methods. The RSES program was employed to identify key properties and relationships within the dataset. The results indicate the impact of certain parameters on the potential accuracy of the outcomes.

20

Analiza wybranych metod walidacji krzyżowej w programie RSES

Bethke Beata

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

11--14

PL

W artykule przeprowadzono analizę zbioru danych za pomocą dwóch metod walidacji krzyżowej. Wykorzystano program RSES do identyfikacji kluczowych właściwości i relacji w zbiorze. Wyniki wykazują wpływ niektórych parametrów na potencjalną dokładność wyników.

EN

This article presents an analysis of a dataset using two cross-validation methods. The RSES program was employed to identify key properties and relationships within the dataset. The results indicate the impact of certain parameters on the potential accuracy of the outcomes.