Vilnius Tech DSpace Repository
Not a member yet
52562 research outputs found
Sort by
Design of a Hybrid Model Based on Statistical and Machine Learning Techniques for Effective Forecasting of Smart Home Energy Consumption
No full textSmart home technology is widely used across all cities to provide high security, comfort, and energy efficiency. This leads to an increase in energy consumption due to the growth in technology, population, and economy. This creates a necessity for forecasting energy consumption to fulfill the unrelenting demands of electricity consumers. In this view, researchers have implemented many statistical methods (namely autoregressive integrated moving average (ARIMA) and seasonal ARIMA (SARIMA)), machine learning models (namely decision trees, random forest, and gradient boosting), and deep learning models (namely artificial neural networks (ANNs), and long short-term memory (LSTM)) for forecasting. However, the implementation of these individual methods often produces inaccurate forecasting results. As a solution, this paper proposes a hybrid model that combines the methods of ARIMA and Extreme Gradient Boosting (XGBoost). These are considered for hybridization due to their simplicity in implementation when compared to other complex models. Usually, ARIMA captures only trends and seasonality, while XGBoost handles only complex and non-linear patterns. Thus, the proposed hybrid model solves these issues in individual models, producing superior results. For validating the effectiveness of the proposed hybrid model, various performance metrics, namely RMSE, MAPE, and R-squared, are computed and compared with the values obtained with the ARIMA and XGBoost when considered individually. These computations gave RMSE of 40.3% (ARIMA), 36% (XGBoost), 33.2% (proposed), MAPE of 48.84% (ARIMA), 53% (XGBoost), 37.26% (proposed), and Rsquared of 0.3 (ARIMA), 0.2 (XGBoost), 0.4 (proposed), thus the superiority of the proposed hybrid model is verified. This research work is implemented using a "smart home dataset" from Kaggle.Taip / Ye
Influence of the viability of Bacillus genus bacteria on the crack closure in concrete
No full textDisertacijoje nagrinėjamas į skirtingus nešiklius įmobilizuotų Bacillus genties bakterijų poveikis betonui ir jų gyvybingumas šarminėje aplinkoje. Disertacijos tikslas – parinkti biologinio betono sudėtį, kuri užtikrintų bakterijų gyvybingumą, bei ištirti plyšių užsivėrimą jame laboratorinėmis sąlygomis. Užtikrinus bakterijų gyvybingumą biologinio betono mišinyje, tokios konstrukcijos galėtų būti eksploatuojamos ilgesnį laiką ir būtų sumažintos jų priežiūros išlaidos.
Darbe sprendžiami keli uždaviniai, susiję su bakterijų gyvybingumu betone: ištirti cemento sudėties bei aplinkos poveikio įtaką skirtingų rūšių bakterijų gyvybingumui, parinkti bakterijų nešiklį biologiniame betone ir ištirti biologinio betono plyšių užsivėrimo efektyvumą. Šie uždaviniai suformuluoti atsižvelgiant į tai, kad vienas iš didžiausių iššūkių, kuriant biologinį betoną, yra ilgalaikio į jį įterptų bakterijų gyvybingumo užtikrinimas.
Disertaciją sudaro įvadas, trys skyriai, naudotos literatūros šaltiniai, bendrosios išvados, autorės publikacijų disertacijos tema sąrašai, rekomendacijos ir santrauka anglų kalba.
Įvadiniame skyriuje pristatoma tiriamoji problema, darbo aktualumas, aprašomas tyrimų objektas, formuluojamas darbo tikslas ir uždaviniai, aprašoma tyrimų metodika, darbo mokslinis naujumas, darbo rezultatų praktinė reikšmė, ginamieji teiginiai. Įvado pabaigoje pristatomos disertacijos tema autorės paskelbtos publikacijos, pranešimai konferencijose ir disertacijos struktūra.
Pirmasis skyrius skirtas literatūros apžvalgai. Šiame skyriuje aprašomi bakterinio CaCO3 išsodinimo keliai, apžvelgiami nešikliai, kurie gali būti naudojami bakterijų apsaugai biologiniame betone, aptariamos bakterijų bei kitų mikroorganizmų panaudojimo biologiniame betone galimybės. Skyriaus pabaigoje formuluojamos išvados ir disertacijos uždaviniai.
Antrajame skyriuje pateiktos tyrimo metu naudotos medžiagos, apra-šomi metodai, naudoti cemento pastų savybių, bakterijų gyvybingumo smulkiagrūdžiame betone ir savaiminio plyšių užsivėrimo tyrimams.
Trečiajame skyriuje aprašyti bakterijų gyvybingumo tyrimai biologiniame betone, naudojant skirtingas bakterijų rūšis ir nešiklius. Pateikta bakterijų gyvybingumo priklausomybė nuo cemento tipų, cemento hidratacijos temperatūros, aplinkos sąlygų. Taip pat ištirtas bakterijų gebėjimas užtaisyti atsivėrusius plyšius biologiniame betone.
Disertacijos tema paskelbti 5 moksliniai straipsniai: 4 – mokslo žurna-luose, įtrauktuose į Web of Science duomenų bazę, turinčiuose citavimo in-deksą̨, 1 – recenzuojamame mokslo žurnale. Disertacijos tema skaityti 8 pranešimai Lietuvos ir tarptautinėse konferencijose.This dissertation investigates the effect of Bacillus genus bacteria immobilised in different carriers on concrete and their viability in alkaline environments. The dissertation aims to select the composition of biological concrete that ensures the viability of the bacteria and to investigate the closure of cracks in it under laboratory conditions. Ensuring bacterial viability in biological concrete could allow such structures to last longer and reduce maintenance costs.
The dissertation approaches several objectives, such as investigating the influence of cement composition and environmental factors on the viability of different types of bacteria in biological concrete, selecting the most suitable bacterial carrier, and investigating the crack closure ability of the concrete. These tasks are formulated considering that one of the significant challenges in developing biological concrete is ensuring the long-term viability of the incorporated bacteria.
The dissertation consists of an introduction, three chapters, General Conclusions, References, lists of publications on the topic of the dissertation, Recommendations, and Summary in English.
The introduction presents the problem under investigation, the relevance of the dissertation, and the research object. It formulates the purpose and tasks, research methodology, scientific novelty, the practical significance of results, and defended statements. The introduction ends by presenting the author’s publications on the subject of the dissertation, information on presentations at scientific conferences, and describes the structure of the dissertation.
The first chapter revises the used literature. This chapter describes the pathways of bacterial CaCO3 precipitation, reviews the carriers that can be used to protect bacteria in biological concrete, and discusses the possibilities of using bacteria and other microorganisms in biological concrete. At the end of the chapter, conclusions are drawn, and the dissertation’s tasks are formulated.
The second chapter presents the materials used in the study and describes the methods used to investigate the properties of cement pastes, the viability of bacteria in concrete and the self-closing of cracks.
The third chapter presents bacterial viability studies in biological concrete using different bacterial species and carriers. It reveals the dependence of bacterial viability on cement types, cement hydration temperature, and environmental conditions. The efficiency of crack closure in biological concrete is also investigated.
Four articles on the dissertation topic were published in scientific journals included in the list of Web of Science, and one was published in another peer-reviewed journal. Eight presentations on the topic of the dissertation were made at national and international conferences
Biblioteka informuoja, 2025 Nr. 7 (704)
No full textNaujai į Web of Science ir Scopus įtrauktų Vilnius Gedimino technikos darbuotojų publikacijų sąrašai ir kitos bibliotekos aktualijos.7 (704)202
Deep Learning-Enabled Inventory Detection for Facility Management System
No full textFacility management benefits from efficient inventory tracking to optimize resource allocation and control costs. In this study, a deep learning-based method is presented for detecting and quantifying office inventory from office images. The proposed system employs YOLOv9 for object detection; however, since YOLOv9 does not include predefined categories for office supplies, a custom dataset is developed. A total of 10,000 images of common office inventory items are collected through web crawling, and 2,000 images are manually annotated using Roboflow to support model training. The dataset consists of 14 office inventory classes, ensuring comprehensive coverage of essential items. Experimental results demonstrate that the model effectively detects and counts office inventory items, providing a reliable solution for automated inventory management. The proposed approach minimizes manual effort, improves tracking accuracy, and enhances the efficiency of facility management operations.Taip / Ye
Darni aplinka: 28-oji teminė Jaunųjų mokslininkų konferencija "Mokslas - Lietuvos ateitis"
No full textKonferencija suteikia galimybę jauniesiems mokslininkams apibendrinti pasiekimus ir išryškinti problemas aplinkosaugos, geodezijos, kelių ir miestų inžinerijos, pastatų inžinerinių sistemų srityse, susitikti su kolegomis, keistis žiniomis ir patirtimi bei praplėsti kontaktų sąrašą. Konferencijos tikslas yra skatinti bendradarbiavimą tarp jaunųjų Lietuvos mokslininkų ir socialinių partnerių. Konferencija prasideda plenariniu posėdžiu, kuriame pristatomi aktualūs Lietuvai pranešimai, vėliau jaunieji mokslininkai išsiskirsto į sekcijas: Aplinkos apsaugos inžinerija, Geodezija ir kadastras, Kelių ir miestų inžinerija, Pastatų energetika. Sekcijose jaunieji mokslininkai, įmonių atstovai pristato žodinius pranešimus aktualiomis temomis
Biblioteka informuoja, 2025 Nr. 21 (718)
No full textNaujai į Web of Science ir Scopus įtrauktų Vilnius Gedimino technikos darbuotojų publikacijų sąrašai ir kitos bibliotekos aktualijos.21 (718)202
Intelligent Traffic Monitoring And Accident Detection System Using YOLOv11 And Image Processing
No full textThis paper presented improved road safety and traffic management by addressing delays in authorities’ response times through an intelligent traffic monitoring and accident detection system. Traditional traffic monitoring techniques frequently fall short of providing fast and accurate data required for immediate action due to the rising frequency of traffic congestion and vehicle accidents. To overcome these difficulties, the system made use of YOLOv11 to identify and track vehicles in traffic as well as image processing techniques to make real-time detection of road accidents. PyQt5 was used to create the stand-alone desktop application, which has an intuitive user interface and guarantees flawless operation even when offline. The system improved traffic officials’ capacity to react swiftly to accidents by giving them real-time data on vehicle movement and road accidents. The evaluation of the proposed algorithm showed comparable performance to existing state-of-the-art proving its effectiveness and reliability in traffic monitoring and accident detection with less compute. The result of this study has wide implications for smart city applications, local governance, and community welfare.Taip / Ye
A bibliometric review on artificial intelligence and entrepreneurship
No full textArtificial intelligence and entrepreneurship considered as useful for industries, institutions and society. We
selected peer-reviewed 149 articles by using Web of Science period from 2016 to 2024. We analyzed the data by utilizing
VoSviewer software. Our bibliometric data demonstrated an interesting cluster such as Cluster 1: technology
driven creative entrepreneurial activities, Cluster 2: integrating big data technology into managerial practices, Cluster
3: adoption of AI models into entrepreneurial education, Cluster 4: AI driven digitization of dynamic capabilities, Cluster
5: Impact of AI and ML on international entrepreneurial landscape, Cluster 6: User acceptance driven by digital
entrepreneurship. This bibliometric review provides useful insights for entrepreneurs by adoption of AI technologies
due to its disruption towards industries globally and locally. Our bibliometric review advance understanding on entrepreneurship
literature by integration of AI technologies due to digital transformation for businesses and society as well.Westminster International University in TashkentTaip / YesBata University in Zlin, Faculty of Management and EconomicsEnterprise performance and innovation: the role of corporate social responsibility, digitalization, servant leadership, and uncertaintyIGA/FaME/2025/01
Interaktyvūs PFAS ir dirvožemio charakteristikų mechanizmai: apžvalga
No full textStudies related to the interaction of PFAS (per- and polyfluoroalkylated) substances in soil media are essential
for finding means of removal from the environment. This review focuses on the most important soil characteristics,
such as pH, temperature, organic matter and nutrient content, potentially toxic elements, soil particle size distribution,
total nitrogen content and cation exchange capacity, which determine the different interactions of PFAS in soil media,
analysing the sorption mechanism at a deeper level. In addition, the analysis of the interaction of PFAS with soil properties
is important for predicting the sorption of PFAS in soil. The requirement for an effective PFAS removal method
and methodology with threshold values is greatly influenced by the properties of the medium, environmental conditions
and PFAS characteristics. This review discusses the most important features of the interaction between PFAS and
soil properties and the mechanisms of PFAS sorption in soil.Tyrimai, susiję su PFAS (per- ir polifluoralkilintų)
medžiagų sąveika dirvožemio terpėje, yra būtini ieškant
šalinimo iš aplinkos priemonių. Šioje apžvalgoje daugiausia
dėmesio skiriama svarbiausioms dirvožemio savybėms, tokioms
kaip pH, temperatūra, organinės medžiagos ir maistinių
medžiagų kiekis, potencialiai toksiški elementai, dirvožemio
granuliometrinė sudėtis, bendrasis azoto kiekis ir katijonų
mainų geba, kurios lemia skirtingas PFAS sąveikas dirvožemio
terpėje, analizuojant sorbcijos mechanizmą gilesniu lygmeniu.
Be to, PFAS sąveikos su dirvožemio savybėmis analizė svarbi
PFAS sorbcijai dirvožemyje prognozuoti. Efektyvaus PFAS
šalinimo metodo ir metodologijos su ribinėmis vertėmis
reikalavimui didelę įtaką turi terpės savybės, aplinkos sąlygos
ir PFAS charakteristikos. Šios apžvalgos tikslas – aptarti svarbiausius
PFAS ir dirvožemio savybių sąveikos bruožus ir PFAS
sorbcijos dirvožemyje mechanizmus.Taip / Ye