Journals Published by Vilnius Tech
Not a member yet
12596 research outputs found
Sort by
Twice clustering based hybrid model for short-term passenger flow forecasting
No full textShort-term metro passenger flow prediction plays a great role in traffic planning and management, and it is an important prerequisite for achieving intelligent transportation. So, a novel hybrid Support Vector Regression (SVR) model based on Twice Clustering (TC) is proposed for short-term metro passenger flow prediction. The training sets and test sets are generated by TC with respect to values of passenger flow in different time periods to improve the prediction accuracy. Furthermore, each obtained cluster is decomposed by using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm and the Ensemble Empirical Mode Decomposition (EEMD) algorithm, respectively. The volatility of each component obtained after decomposition is further reduced. Then, the SVR model optimized by the Grey Wolf Optimization (GWO) algorithm is used to predict the decomposed components. Moreover, forecast based on one-month data from Xi’an Metro Line 2 Library Station (China). By comparing the prediction results of the TC condition, the Once Clustering (OC) condition and the non-clustering condition, it shows that the TC approach can adequately model the volatility and effectively improve the prediction accuracy. At the same time, experimental results show that the novel hybrid TC–CEEMDAN–GWO–SVR model has superior performance than Genetic Algorithm (GA) optimized SVR (SVR–GA) model and hybrid Back Propagation Neural Network (BPNN) model
Energy efficiency and COVID-19: a systematic literature review and bibliometric analysis on economic effects
Get PDFThe Corona Virus Disease 2019 (COVID-19) epidemic has deferred global progress in energy efficiency to a decade-long low, posing a threat to the achievement of international climate goals, and also profoundly affected the development of economics. To gain insight into the research frontiers and hotspots in energy efficiency and COVID-19, a systematic literature review and bibliometric analysis on economic effects are performed with the help of the bibliometric tools VOSviewer and Bibliometrix. This paper selects all the publications retrieved based on the subject terms in the Web of Science core collection. Firstly, this article performs a performance analysis of related publications to present the development and distribution of energy efficiency and COVID-19 from research areas, relevant sources, and influential articles. Afterward, a visual analysis of the literature called science mapping analysis is implemented to display the structural and dynamic organization of knowledge in energy efficiency and COVID-19 research. In the end, detailed discussions of two research hotspots and some theoretical and practical implications are concluded in the systematic literature review and bibliometric analysis findings, which may contribute to further development for researchers in the field of energy efficiency and eventually propel the progress of society and economy in an all-round way.
First published online 06 October 202
Sustainable food supply chain screening and relationship analysis with unknown criteria weight information
Get PDFSustainable food supply chain management (SFSC) can control food loss and waste by reducing resource consumption and environmental pollution, thereby ensuring sustainable food consumption and production patterns. Scholars have investigated specific aspects or links in SFSC but rarely studied the sustainability evaluation and selection of a whole supply chain to provide management suggestions under uncertain decision-making environments. This paper presents a comprehensive multiple criteria decision-making method called the SMAA-ORESTE method for SFSC selection. To reduce experts’ efforts, the holistic acceptability index in the SMAA-2 method is used to screen inferior SFSCs from a large number of alternatives. Then, the ORESTE method is combined with the SMAA method to evaluate SFSCs under uncertain information. The ORESTE method can specifically analyze the relationship between alternatives, and the SMAA method can analyze alternatives with unknown criteria weights by Monte Carlo simulation. The proposed method ensures the robustness and credibility of obtained ranking results. An illustrative example validates the applicability and robustness of the proposed method in selecting SFSCs with unknown criteria weights
Tram-train system as a potential transport solution for the Olomouc Region
No full textThe article is focused on the frequently discussed topic of suburban and regional railway system modernization comparing different approaches to consider by local authorities. To make a precedent and to better contribute to practical problems, a middle-sized city of Olomouc (Czechia) is chosen to demonstrate the upgraded regional transport system design with respect to the regional specifics and utilizing of the current railway and tramway infrastructure. With a new, innovative approach to the potential tram-train implementation in the Olomouc Region, the technical and operational features of the current tram-train systems and vehicles are analysed. By implementing the most suitable ones, the regional tram-train system proposal in the conditions of Olomouc may serve as a guide for similar planned systems in the countries with limited legislative and technical experience regarding the tram-train systems (especially in Central Europe), their suitability for the region, their design, and introduction. For the qualitative assessment of the different relevant approaches, a comparative analysis is used. As a result of the analysis, a tram-train system is recommended for the further transport planning stages as it significantly improves both urban and suburban public transport in the Olomouc Region by increasing their average speed and accessibility. For better financial and technical implementation, the project is divided into several stages. Unlike the already presented solutions, it combines shorter travel times of the regional rail and the populated area coverage reached by regional buses and serves as both an attractive and financially sane extension of a regional public transport system
Computer-aided simulation of unmanned aerial vehicle composite structure dynamics
No full textThe dynamic response of an aerial vehicle structure is a key parameter that must be determined before further aeroelastic phenomena can be analysed in the aerospace sector. Natural frequencies, mode shapes, and damping can be measured or predicted through experimental, operational, or computational studies. To reduce the costs and complexity of experimental investigations, there is a demand for numerical models that accurately represent the structure′s dynamic behaviour. This article focuses on modelling composite structures, which are increasingly utilised in the aerospace industry and whose dynamic properties are heavily influenced by fibre directionality. ANSYS software and the ACP module were employed to develop a numerical model of a wet Epoxy Carbon UD (230 GPa) composite commonly used in Unmanned Aerial Vehicle (UAV) components. Ten layers of 0.1 mm thick carbon fibre were incorporated into the model to create a 1 mm thick composite plate, with fibres oriented at 0°, 30°, 45°, and 90° relative to the horizontal direction of the plate. The simulations demonstrated that careful consideration and modelling of the material significantly impact the values of natural frequencies and, more importantly, the mode shapes.
First published online 28 January 202
Machine learning methods as applied to modelling thermal conductivity of epoxy-based composites with different fillers for aircraft
Get PDFThe thermal conductivity coefficient of epoxy composites for aircraft, which are reinforced with glass fiber and filled with aerosil, γ-aminopropylaerosil, aluminum oxide, chromium oxide, respectively, was simulated. To this end, various machine learning methods were used, in particular, neural networks and boosted trees. The results obtained were found to be in good agreement with the experimental data. In particular, the correlation coefficient in the test sample was 0.99%. The prediction error of neural networks in the test samples was 0.5; 0.3; 0.2%, while that of boosted trees was 1.5; 0.9%
A comprehensive analysis of competency and training perspectives among air traffic controllers
Get PDFThe aim of the study was to examine air traffic controllers’ perspectives on competency, performance, and training. Analysing data from 182 participants, the results revealed a strong focus on competency with the controllers actively evaluating their skills. Notably, the experienced controllers (19+ years) displayed a heightened commitment to continuous learning, reflected in their higher participation in individual training and perception of its value for their career goals and adaptation to the evolving aviation industry. Competency-based training programs also received positive feedback across experience levels, highlighting their potential effectiveness. Moreover, training was universally perceived as key to performance throughout careers. These results highlighted the importance of fostering a culture of continuous learning within air traffic control (ATC) communities. Aviation authorities can support this by providing diverse training opportunities, including individual and competency-based programs. Future research should continue investigating the impact of technological advancements and AI/machine learning on ATC competencies, the effectiveness of competency-based training programs, and the role of individual training in competency development, ultimately ensuring the vital role of air traffic controllers in aviation safety
Improvement of fatigue management methodology related to flight crew
Get PDFThis research focuses on flight crew fatigue and the improvement of a fatigue management methodology that helps in reducing fatigue for flight crew members, aiming to improve their well-being and overall aviation safety of flights. A thorough literature review established a foundation for understating fatigue and the available methodologies for fatigue management for flight crew members. To make the picture clearer, an empirical study was conducted, and it included surveys and interviews with flight crew members. The gathered data underwent detailed statistical and thematic analysis to identify key factors influencing fatigue among flight crew members. Findings revealed multiple contributors to the flight crew member fatigue. Using these insights, a fatigue management methodology is proposed, integrating real-world experiences with evidence-based strategies. The proposed methodology and the recommendations that were formed are relevant for a company management which is facing flight crew fatigue management issues
Valuation of reverse mortgages in the Spanish market for foreign residents
Get PDFThe continuous growth in life expectancy, besides to the difficult economic and financial situation of the public pension system in Spain, makes reverse mortgages an attractive solution for providing additional income to retirees. However, despite being almost 20 years old, the Spanish market remains immature. Consequently, providers face significant risks, due to factors such as interest rates, housing prices, and longevity. Numerous tourists visit Spain, and many retire there, obtaining legal residence. Therefore, lenders could be interested in marketing reverse mortgages to foreign residents. Nevertheless, the longevity risk faced by these lenders may differ depending on the nationality of the borrower, and profits and losses could vary. Consequently, we propose a methodology for comparing the pricing of reverse mortgages in Spain by considering differences in longevity risk. Specifically, we calculate the amount offered by three types of reverse mortgages to customers of different nationalities, genders, and ages with contracts made in Spain. Our conclusions are pertinent to Spanish lenders since the results indicate that, in general, a Spanish lender would assume a slightly larger risk when lending reverse mortgages to borrowers of the selected nationalities, regardless of other considerations, such as legal issues, which are not addressed in this article.
First published online 31 October 202
Improving the strategies of the market players using an AI-powered price forecast for electricity market
Get PDFThis paper analyses the recent evolution of the electricity price of one of the East-European countries’ Balancing Markets (BM) – Romania, aiming to understand the prices trend and predict them in the current economic and geopolitical context. This is especially important as the electricity producers have to allocate their output between wholesale electricity market, ancillary services markets and BM targeting to maximize value and achieve a sustainable economic development. Therefore, in this paper, we propose an AI-powered electricity price forecast using several types of standout Machine Learning (ML) algorithms such as classifiers and regressors to predict the electricity price on BM. This approach, consisting of two steps, identifies the imbalance sign and significantly enhances the performance of the price forecast. The proposed method offers valuable insights into the market participants’ trading opportunities using two prediction solutions. The first prediction solution consists of averaging the results of five ensemble ML algorithms. The second one consists in weighting the results of the five forecasting ML algorithms using either a linear regression or a decision tree algorithm. Thus, we propose to combine supervised and unsupervised ML algorithms and find the fundamentals for creating optimal bidding strategies for electricity market players.
First published online 14 November 202