Journals Published by Vilnius Tech
Not a member yet
12596 research outputs found
Sort by
Autonomous modular construction strategy using robotized crane based on deep learning and reinforcement learning
Get PDFModular construction offers significant advantages including faster construction time, higher quality control and less environmental impact. To further enhance its advantages, advanced robotic construction technologies are being developed. This research develops an automated modular construction framework that incorporates the robotic kinematics, deep learning and deep reinforcement learning using a robotized crane. The proposed modular construction strategy utilizes YOLOv5-S for modular container identification and localization. An improved proximal policy optimization (PPO-I) is developed and implemented in this strategy for collision-free three-dimensional (3D) lifting path planning and modular container transportation. States and rewards of the PPO-I and robot kinematics design of a real mobile crane are developed. The feasibility of the proposed modular construction strategy is verified through four case studies in 3D virtual environments. More than 97% success rate is observed meaning that the proposed strategy can be implemented in the robotized crane to localize the modular container and transport it to the target position with collision avoidance. The results indicate the potential of the proposed robotic-assisted modular construction strategy in the field of automated construction
Optimising scheduled maintenance on operational buildings: a microservice-based BIM framework
Get PDFOperation and Maintenance (O&M) aims to preserve the quality of the building throughout its life, keeping maintenance costs within acceptable limits. Maintenance involves different tasks, from replacing air conditioning filters to restoring structural elements. Each task has an optimal frequency, which can be flexible within a specific time range, a cost, and a duration. These maintenance activities may disrupt building operations by repeatedly interrupting ongoing activities. This research seeks to reduce these disruptions by grouping tasks within reasonably close time frames to schedule preventive maintenance plans while respecting their frequency. We propose an optimisation model, solvable using a general-purpose solver, which identifies the best time range for grouping O&M tasks. By penalising deviations from the optimal period, the model ensures that tasks are performed at the most cost-effective time. Integrated within a microservice-based architecture, the optimisation engine seamlessly links an input database and a BIM model, orchestrated using Dynamo for Revit. A case study illustrates the effectiveness of this system, consolidating multiple tasks into optimised work clusters and significantly reducing operational disruptions. The originality of this work lies in its innovative combination of optimisation techniques and BIM tools, providing a practical and scalable solution for efficient O&M management
Heavy rainfall resilience: adoption of climate smart agriculture among marginal farmers in a sub-basin of India
Get PDFHeavy rainfall is a significant challenge for marginal farmers in the aspect of sustainable agriculture. This research analyzed data from eight grid points over 42 years to determine rainfall criteria: 50.91 mm to 79.65 mm for heavy rain, 76.95 mm to 101.21 mm for extreme rain, and 101.21 mm for rare 24-hour occurrences. The vulnerability mapping found 58 agriculturally susceptible communities. Research shows cashew nuts, coriander, sugarcane, sweet potatoes, and turmeric are the five main crops in the 58 most susceptible villages to heavy rainfall. These villages contain a greater number of marginal farmers. The DELPHI method revealed that coriander is the most susceptible crop. In this study, climate-smart agricultural practices such as Integrated Pest Management methods, shifting crop seasons, and Meghdoot application projections are used to minimize the damages caused by heavy rainfall. This includes protecting crops before heavy rainfall and monitoring them after heavy rainfall. For emission reduction as one of the pillars of Climate Smart Agriculture, biochar from biomass breakdown without oxygen is suggested. A poll found that 44% of respondents would use social entrepreneurship for biochar kilns. As, a result 33 farmers from 7 villages used the suggested Integrated Pest Management Technique and Meghdoot to harvest their second season with minimum losses
Integration of ethnoecopreneuship, collaborative, and creative economy as an effort for sustainability of mangrove ecotourism
Get PDFIn the face of global tourism industry challenges, innovation in tourism services is essential for achieving sustainable development goals. This research aims to address the multifaceted challenges of sustainable mangrove ecotourism in Indonesia through an integrative approach combining ethnoecopreneuship, collaborative, and creative economy. Utilizing participatory rural appraisal (PRA) and focus group discussion (FGD), data analysis combines strengths, weaknesses, opportunities, threats (SWOT) analyses and analytic hierarchy process (AHP) method. The results emphasize the importance of community involvement, ecological considerations, effective promotion, and adoption of digital technology in the sustainability of mangrove ecotourism. The research calls for collaboration among stakeholders, policy emphasis on local government responsibilities, and active involvement of local communities and non-governmental organizations in mangrove conservation and management. This research underscores the potential for sustainable development, aligning with the sustainable development goals (SDGs) and enhancing economic and social outcomes in Indonesia’s mangrove ecotourism sector
Detection of pneumonia from chest X-rays using convolutional neural networks
Get PDFPneumonia detection from chest X-rays is crucial for early diagnosis, and deep learning models –specifically convolutional neural networks (CNNs) – have shown promise in automating this process. In this study, a CNN using the DenseNet-121 architecture was developed and trained, referred to as LDCS2, to classify chest X-ray images as pneumonia or normal, using a combined dataset from three publicly available sources. The CNN approach was chosen over Vision Transformers (ViT) due to lower computational requirements and better performance with limited data. A traditional training, validation, and testing split was used instead of k-fold cross-validation to reduce execution time. LDCS2 demonstrated excellent discrimination between pneumonia and normal images alongside high computational efficiency. These findings highlight the potential of DenseNet-based CNNs for automated pneumonia diagnosis, particularly in resource-constrained settings.
Article in English.
Pneumonijos nustatymas iš krūtinės ląstos rentgenogramų, naudojant konvoliucinius neuroninius tinklus
Santrauka
Pneumonijos nustatymas iš krūtinės ląstos rentgenogramų yra itin svarbus ankstyvajai diagnostikai, o giliojo mokymosi modeliai – ypač konvoliuciniai neuroniniai tinklai (CNN) – rodo didelį potencialą automatizuojant šį procesą. Šiame tyrime sukurtas ir apmokytas CNN, paremtas DenseNet-121 architektūra ir pavadintas LDCS2, skirtas klasifikuoti krūtinės ląstos rentgeno vaizdams, iš kurių matyti pneumonija arba sveiki plaučiai, naudojant sujungtą duomenų rinkinį iš trijų viešai prieinamų šaltinių. CNN metodas pasirinktas vietoje Vision Transformers (ViT) dėl mažesnių skaičiavimo išteklių reikalavimų ir geresnių rezultatų, kai duomenų kiekis ribotas. Siekiant sutrumpinti vykdymo laiką, vietoje k kartų kryžminės validacijos taikytas tradicinis mokymo, validacijos ir testavimo skaidymas. LDCS2 pademonstravo puikią atskyrimo gebą tarp pneumonijos ir sveikų plaučių vaizdų bei aukštą skaičiavimo efektyvumą. Šie rezultatai pabrėžia DenseNet pagrindu veikiančių CNN potencialą automatizuotai plaučių uždegimo diagnostikai, ypač išteklių stokojančiose aplinkose.
Reikšminiai žodžiai: LDCS2, konvoliuciniai neuroniniai tinklai (CNN), krūtinės ląstos rentgeno vaizdų klasifikavimas, pneumonijos aptikimas, DenseNet-121, medicininis vaizdavimas, gilusis mokymasis sveikatos priežiūros srityje, duomenų augmentacija, perkėliminis mokymasis
A rapid review on ontology- and data-driven business process modelling
Get PDFIn modern organizations, the ability to efficiently manage and adapt business processes is essential. Business process modelling (BPM) is widely used to visualize, analyse, and improve operational processes. As the complexity of business environments increases, the integration of ontological modelling and data-driven approaches becomes increasingly relevant. Ontologies offer a semantic foundation for organizing and structuring process-related information, while data-driven methods support evidence-based decision-making and enable the adaptation of processes to dynamic conditions. Although both approaches show promise, the academic literature still lacks a coherent view of how they are jointly applied within BPM. This research conducts a rapid review of recent scientific publications to investigate how ontological and data-based methods are being used, what challenges are most often identified, and which research directions are emerging. The analysis reveals that the integration of these methods could address issues such as semantic consistency, process automation, and real-time decision-making. The results highlight existing research gaps and provide a clearer understanding of how BPM methodologies can be advanced by combining these two perspectives. This research contributes to the theoretical development of BPM by mapping current practices and offering insights for future researches.
First published online 23 January 202
Improving AHP consistency through cognitive collaboration with large language models
Get PDFThe Analytic Hierarchy Process (AHP) is a human-centered method designed to structure complex problems and extract the authentic, consistent opinions of decision-makers. However, its practical application is often limited by inconsistency in human judgments, often caused by the respondent’s insufficient understanding of the task rather than simple mathematical error. The main goal of the article is to explore the possibilities of integration of innovative Artificial Intelligence (AI) tools for improving the AHP method. In order to improve respondent understanding and facilitate more intuitive and transparent consistency adjustments, this study also analyzes how to reduce the occurrence of inconsistency in pairwise comparison matrices and improve the Consistency Ratio (CR) by using advanced capabilities of large language models. The initial stage of study included a literature review, identifying typical problems in this area, reviewing the tools and methods used for obtaining better results, and presenting areas for improvement. At the second stage, the possibilities for improving consistency by increasing the influence of humans as decision makers, moving from the use of powerful mathematical optimization mechanisms to the application of human-centered explanatory AI techniques were analyzed. Based on the study results, the description of approaches for improvement of consistency in AHP was presented.
First published online 27 January 202
Global sensitivity analysis and optimal control of Typhoid fever transmission dynamics
Get PDFThis paper presents a mathematical model aimed at studying the global behaviour and optimal control strategies for Typhoid fever. The primary objective of this study is to identify the most effective control strategy that minimizes the spread of the disease. To achieve this, we calculate the effective and basic reproduction numbers and utilize them to investigate the existence and stability of the equilibria. Furthermore, we investigate the global impact of each model parameter on the variables using Latin Hypercube Sampling and Partial Rank Correlation Coefficient. The necessary conditions of the optimal control problem are analyzed using Pontryagin’s maximum principle, and the numerical values of the model parameters are estimated using the maximum likelihood estimator. The results indicate that the optimal use of vaccination for susceptible individuals, as well as the screening and treatment of asymptomatic infected individuals, have a significant impact on reducing the spread of the disease in endemic regions
The inverse problem of determining profiles of electrophysical parameters in eddy-current structuroscopy using apriori information on multifrequency probing
Get PDFBased on the proposed methodology, the essence of which is to identify the profiles of electrophysical parameters of planar objects of eddy-current testing by means of surrogate optimization in the active PCA-space of reduced dimensionality, the effectiveness of the approach is proved by modeling the process of measurement control using apriori accumulated information about an object, in particular, multifrequency probing. The particularity of these studies is the consideration of previously collected information not only on profile variations, but also on the effect of various object probing frequencies on the signal of the surface probe. The functions of the storage device and information carrier were performed by a neural network metamodel, characterized by a high computational efficiency. Numerical experiments have determined the accuracy indicators of the proposed improved method for determining the distributions of magnetic permeability and electrical conductivity along the subsurface layer of a metal object with changes in a microstructure. The analysis of the modeling results indicates a significant reduction in the level of computational resources required to solve the problem and an increase in the accuracy of profile identification
Micropolar fluid-thin elastic structure interaction: variational analysis
Get PDFWe consider the non-stationary flow of a micropolar fluid in a thin channel with an impervious wall and an elastic stiff wall, motivated by applications to blood flows through arteries. We assume that the elastic wall is composed of several layers with different elastic characteristics and that the domains occupied by the two media are infinite in one direction and the problem is periodic in the same direction. We provide a complete variational analysis of the two dimensional interaction between the micropolar fluid and the stratified elastic layer. For a suitable data regularity, we prove the existence, the uniqueness and the regularity of the solution to the variational problem associated to the physical system. Increasing the data regularity, we prove that the fluid pressure is unique, we obtain additional regularity for all the unknown functions and we show that the solution to the variational problem is solution for the physical system, as well