Vilnius Tech DSpace Repository
Not a member yet
52562 research outputs found
Sort by
Cyber security management model for improving the security of critical energy infrastructure of states
No full textDisertacijoje nagrinėjama kibernetinio saugumo valdymo problema kritinės energetikos infrastruktūroje. Tyrimų objektas – valstybių kritinės energetikos infrastuktūros kibernetinio saugumo valdymas. Darbo tikslas – sukurti valstybių kritinės energetikos infrastruktūros kibernetinio saugumo valdymo modelį, integruojantį veiksnius, būtinus efektyviai užtikrinti saugumo valdymą ir stiprinti kibernetinį saugumą.
Disertaciją sudaro įvadas, trys skyriai, bendrosios išvados, naudotos literatūros ir autoriaus publikacijų sąrašai, penki priedai.
Analizuojant egzistuojančias kibernetinio saugumo sampratas, buvo pastebėta, kad kol kas nėra bendros kritinės infrastruktūros sąvokos. Įvairių valstybių požiūris į kritinę infrastruktūrą priklauso nuo jų poreikių, tačiau visos valstybės taiko tuos pačius pagrindinius principus ‒ apsaugoti kibernetinę aplinką nuo išpuolių ir užtikrinti konfidencialumą, vientisumą ir prieinamumą. Tyrimo duomenys parodė, kad pagrindinis kibernetinio saugumo pažeidimų veiksnys išlieka žmogus.
Įvertinus kritinės energetinės infrastruktūros kibernetinio saugumo valdymo ypatumus bei atsižvelgiant į jo esamą standartą, paaiškėjo, kad pagrindinė kibernetinio saugumo problema yra kibernetinių grėsmių nustatymas, prevencinių priemonių taikymas, strategijų, kaip reaguoti į kibernetinius išpuolius ir netikėtus scenarijus, trūkumas bei nepakankamas pažeidžiamumo įvertinimas. Esami kibernetinio saugumo valdymo modeliai neužtikrina tinkamos apsaugos.
Išanalizavus kritinės energetinės infrastruktūros silpnąsias vietas, įvertinus užsienio valstybėse taikomas gerąsias praktikas, nustatyta, kad kritinės infrastruktūros saugumo lygis yra nepakankamas. Todėl buvo sukurtas ir ekspertų įvertintas valstybių kritinės energetikos infrastruktūros kibernetinio saugumo valdymo modelis.
Naują valdymo modelį galima tobulinti ir toliau. Siekiant padidinti valstybių kritinės energetikos infrastruktūros kibernetinį saugumą, tikslinga sukurti specialų saugumo operacijų centrą (angl. Security Operation Centre (SOC)), integruojantį visus modelio komponentus ir galintį žymiai pagerinti kibernetinės saugos vadybą kritinėje energetinėje infrastruktūroje valstybės mastu.
Disertacijos tema paskelbtos aštuonios publikacijos recenzuojamuose mokslo leidiniuose. Dvi iš jų įtrauktos į Scopus duomenų bazę. Disertacijoje atliktų tyrimų rezultatai pristatyti keturiose mokslinėse konferencijose Lietuvoje ir užsienyje.The dissertation examines the problem of cyber security management in critical energy infrastructure. The research object is the cyber security management of critical energy infrastructure in states. The dissertation aims to develop a model for the cyber security management of states’ critical energy infrastructure, integrating factors necessary to ensure effective security management and enhance cyber security.
The dissertation consists of an introduction, three chapters, general conclusions, lists of references and the author’s publications, and five annexes.
The analysis of the existing cyber security concepts revealed the lack of a common concept of critical infrastructure. Although countries approach critical infrastructure depending on their needs, the fundamental principles remain the same: to protect the cyber environment from attacks and achieve confidentiality, integrity and availability. Research data has shown that humans are the main factor contributing to cyber security breaches.
Having evaluated the cyber security management in critical energy infrastructure and considering existing standards, it became apparent that the main cyber security problems are identifying cyber threats, applying preventive measures, the lack of strategies for responding to cyber-attacks and unexpected scenarios, and a weak vulnerability assessment. Existing cyber security management models do not ensure adequate protection.
Having analysed the weaknesses of critical energy infrastructure and evaluated best practices applied in foreign countries, it was determined that the security level of critical infrastructure is insufficient. Therefore, a model for the cyber security management of states’ critical energy infrastructure was developed and assessed by experts.
The new management model can be further improved to enhance the effectiveness of the cyber security model for states’ critical energy infrastructure. It is possible to create a dedicated Security Operation Centre (SOC), integrating all model components, aiming to significantly improve cyber security management on a national scale in critical energy infrastructure.
The research results of the dissertation have been published in eight peer-reviewed scientific publications, two of which are included in the Scopus database. The research results were presented at four scientific conferences in Lithuania and abroad.Taip / Ye
Digitization processes in education
No full textThe rapid advancement of digital technologies, driven by the Industry revolutions, has triggered significant changes in education on a global scale. The digitisation of educational processes is important because of its transformative impact on the learning experience, its increased accessibility, its alignment with market needs and its role in addressing contemporary challenges, and its potential to improve educational governance. The paper analyses the extent of scollars interest and research activities in the field of digitisation of educational processes and aims to identifie future research domains in this field. The analysis and synthesis of scientific literature was carried out taking Web of Science and Scopus databases as primary sources, VOSviewer software was engaged for data analysis.Taip / Yes
Exploring the Effectiveness of Vision Transformers in Diabetic Retinopathy Identification via Retinal Imaging
No full textVision transformers (ViTs) have begun to be adopted in medical imaging analysis. However, despite their success in other areas of computer vision, ViTs are still largely unexplored in this specific medical imaging task. In this preliminary study, we aim to assess the performance of the ViT in the detection of diabetic retinal retinopathy. In addition, we seek to identify potential avenues for future research and provide insight into the unique challenges and advantages associated with the use of VITs in the context of the identification of diabetes retinal diseases.Taip / Ye
Empowering Industrial Energy Management: Advancing Short-Term Load Forecasting with LSTM and CNN Deep Learning Models - Insights from a Moroccan Case Study
No full textSelf-consumption of electricity plays an important role in the energy transition and using green, sustainable energy sources for industrial self-sufficiency and electricity bills, meeting part of their own energy needs and even generating 20% of the annual surplus that could be sold to the grid. This study aims to forecast short-term load spanning between 2022 and 2023, employing deep learning models, specifically Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. Various performance metrics have been used to evaluate and compare the accuracy of these two models, including mean squared error, root mean squared error, mean absolute error, and mean absolute deviation. Results reveal LSTM's superior performance over CNN, with LSTM demonstrating adeptness in capturing underlying patterns while CNN tends to learn noise, leading to a divergence in performance metrics between training and validation data. The findings underscore the significance of LSTM for accurate load forecasting and suggest the inclusion of additional hyperparameter optimization to enhance the reliability of short-term load predictions, distinct from previous studies.Taip / Ye
The role of employment agencies in regulating the Georgian labor market and reducing youth unemployment
No full textThe labor market in Georgia, a crucial component of its evolving market economy, is currently undergoing formation, marked by numerous challenges. Effective institutional regulation and the development of labor market infrastructure are pivotal in addressing the persistent issue of unemployment. The underdeveloped labor market infrastructure has led to prolonged unemployment, particularly afflicting the youth. Key contributors to labor market regulation and unemployment reduction are recruitment agencies. This paper aims to scrutinize the role and significance of employment agencies in regulating the labor market in Georgia. The measures are designed to augment the influence of both state and private employment services.Taip / Yes
Biblioteka informuoja, 2024 Nr. 31 (675)
No full textNaujai į Web of Science ir Scopus įtrauktų Vilnius Gedimino technikos darbuotojų publikacijų sąrašai ir kitos bibliotekos aktualijos.31 (675)202
Modern Building Materials, Structures and Techniques MBMST 2023, 5-6 October, Vilnius, Lithuania
No full textThis book gathers the latest advances, innovations and applications in the field of sustainable construction materials and structures, as presented by leading international researchers and engineers at the 14th International scientific conference “Modern Building Materials, Structures and Techniques” (MBMST 2023), held in Vilnius, Lithuania, on 5–6 October 2023. It covers topics such as modern building materials and their production technologies; investigation and design of reinforced concrete, steel, glass, timber and composite structures; innovative calculation techniques for bridges; geotechnics; new building technologies and management; and building information modelling. The contributions, which were selected through a rigorous international peer-reviewed process, share exciting ideas that will spur novel research directions and foster new multidisciplinary collaborations
Military spending and economic growth: is there an interdependence? Case of developed countries
No full textThis study investigates the impact of military spending and arms exports on economic growth. Using data from developed countries spanning the period 1973–2022, we employ a regression model to analyse the relationship between gross domestic investment, military expenditure, arms exports, and GDP per capita growth. Our findings indicate that domestic investment has a significant positive influence on economic growth, while military spending and arms exports show negligible effects. The results emphasize the critical importance of domestic investment in fostering economic development, highlighting its superiority over military-related expenditures and exports in shaping economic outcomes.Taip / Yes
Contemporary marketing personalization through clustering approach
No full textMarketing personalization is attracting a growing interest from researchers and practitioners alike because customers demand tailored and resonating products, services, and communications. Marketing Personalization is utilizing knowledge about customers to build long-lasting relationships by matching their needs and preferences with relevant content and offers. Modern technology advancements enable customer data collection, analysis, and modelling in a way that allows for treating every customer as a segment of one, increasing their satisfaction and loyalty. This study aims to provide a comprehensive overview of Marketing Personalization definitions, clusters, and keywords. Based on the literature review and bibliometric analysis, an extensive analysis of the critical clusters that indicate promising areas for future research is offered.Taip / YesIRiga Technical UniversityID 4828ZM- 2024/2
Neraiškiaisiais skaičiavimais ir mašininiu mokymusi pagrįstas naftos išsiliejimų geolog-inėje aplinkoje prognozavimas su mažu duomenų rinkiniu
No full textOil spills on the ground cause significant damage to the geological environment, including groundwater, which becomes uninhabitable once contaminated. It is necessary to predict the scale of an oil spill and the consequences of contamination on the geological environment to minimise the damage of pollution. Specialists could use the prediction results to choose a strategy for its elimination. The literature provides many approaches for predicting an oil spill on the water. However, approaches are lacking for predicting oil spills in the geological environment.
A detailed analysis of the prediction of oil spills on the geological environment and the water shows that scientists most often use machine learning algorithms and fuzzy logic to solve these problems. However, it is unclear what machine learning algorithms and fuzzy inference should apply to oil spill prediction in the geological environment. Moreover, in the real-world cases of oil spills in the geological environment, scientists and practitioners often face the challenge of a small dataset, which makes prediction difficult.
The dissertation consists of an introduction, three main chapters, general conclusions, and a list of references. The first chapter provides a literature review and formulates the dissertation’s objectives. The second chapter proposes fuzzy inference and machine learning-based prediction with a small dataset of oil spills on a ground environment. It consists of two main parts: the first, where the fuzzy inference model for predicting oil spill contamination of the geological environment uses the fuzzification of two in-puts (the spilt oil product volume and the specific oil capacity), and defuzz-ification, applying a newly proposed procedure based on the area ratio of a fuzzy membership function, to predict whether an oil product will penetrate the ground layer; and the second, where the proposed approach of machine learning (Linear Regression, Decision Trees, SVR, Ensembles, and GPR) and fuzzy inference allow for the prediction of the consequences of oil spills into the groundwater using small datasets.
The third chapter describes a two-part experiment with the proposed fuzzy inference model, machine learning algorithms, and an ANFIS-based model. The results of the experiment with the fuzzy inference model show that the proposed model is correct and does not contradict reality. The two calculated performance measures (MAE and RMSE) show that the proposed fuzzy inference model can predict the geological consequences of an oil spill with sufficient accuracy.Naftos išsiliejimas ant žemės daro didelę žalą geologinei aplinkai, įskaitant požeminį vandenį, užteršia ją ir daro netinkamą gyventi. Todėl būtina numatyti naftos išsiliejimo mastą ir užterštumo pasekmes geologinei aplinkai, kad taršos žala būtų kuo mažesnė, o specialistai, remdamiesi prognozavimo rezultatais, galėtų pasirinkti jos likvidavimo strategiją. Literatūroje yra daug būdų ir metodų, kaip prognozuoti naftos išsiliejimą vandenyje. Tačiau naftos išsiliejimo geologinėje aplinkoje prognozavimo metodų trūksta.
Išsami naftos išsiliejimo geologinėje aplinkoje ir vandenyje analizė rodo, kad mokslininkai dažniausiai taikė mašininio mokymosi algoritmus ir neraiškiaisiais skaičiavimais grindžiamą prognozavimą, kad išspręstų šias problemas. Tačiau neaišku, kokie mašininio mokymosi algoritmai ir neraiškiaisiais skaičiavimais grindžiamas prognozavimas turėtų būti taikomi prognozuojant naftos išsiliejimą geologinėje aplinkoje. Be to, realiais naftos išsiliejimo geologinėje aplinkoje atvejais mokslininkai ir praktikai dažnai susiduria su nedidelio duomenų rinkinio iššūkiu, o tai apsunkina prognozes.
Disertaciją sudaro įvadas, trys pagrindiniai skyriai, bendrosios išvados ir literatūros sąrašas. Pirmame skyriuje atliekama literatūros apžvalga ir suformuluoti disertacijos tikslas ir uždaviniai. Antrame skyriuje siūlomas neaiškiaisiais skaičiavimais ir mašininiu mokymusi grindžiamos prognozės metodas su nedideliu duomenų rinkiniu apie naftos išsiliejimus ant žemės paviršiaus. Šį metodą sudaro dvi pagrindinės dalys. Pirma, neraiškiaisiais skaičiavimais grindžiamas išvadų modelis, skirtas prognozuoti geologinės aplinkos taršai išsiliejus naftai, jame naudojamas dviejų kintamųjų įvesties (t. y. išsiliejusio naftos produkto tūrio ir specifinės naftos talpos) fuzifikavimas ir išvesties defuzifikavimas, taikant pasiūlytą naują būdą, grindžiamą neaiškios narystės funkcijos ploto santykiu. Antra, siūlomas neraiškiaisiais skaičiavimais ir mašininiu mokymusi (tiesine regresija, sprendimų medžiais, SVR, ansambliais ir GPR) grindžiamos prognozės metodas leidžia nuspėti naftos išsiliejimo į požeminį vandenį pasekmes, naudojant nedidelius duomenų rinkinius.
Trečiame skyriuje aprašomas eksperimentas, kurį sudarė dvi dalys, eksperimentuojant su siūlomu neraiškiaisiais skaičiavimais grindžiamu prognozės modeliu, su mašininio mokymosi algoritmais ir ANFIS pagrindu sukurtu modeliu. Eksperimento su neraiškiaisiais skaičiavimais grindžiamu modeliu rezultatai rodo, kad pasiūlytas modelis yra tinkamas ir neprieštarauja tikrovei. Apskaičiuoti du statistiniai testai (MAE ir RMSE) rodo, kad siūlomas neraiškiaisiais skaičiavimais grindžiamas metodas gali gana tiksliai numatyti geologines naftos išsiliejimo pasekmes.Taip / Ye