Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

2023

An Evolutionary Study of the Impact of Artificial Intelligence Technology on Foreign Language Education

Authors
Liang, T; Duarte, N; Yue, GX;

Publication
International Journal of Emerging Technologies in Learning (iJET)

Abstract
This study investigates the evolutionary impact of applying artificial intelligence (AI) technology to foreign language education. By employing complex systems thinking, the relationship between foreign language education and AI technology is explored, and dynamic models are employed to analyze the evolutionary patterns of AI technology in foreign language education. Through model analysis and numerical simulations, the interactive effects between foreign language education and AI technology in different modes are revealed. The findings demonstrate that, under different coupling modes, foreign language education and AI technology can achieve self-organizing evolution. When the interaction coefficient between foreign language education and AI technology is appropriately set, AI technology exhibits emergent properties for foreign language education. Lastly, suggestions are presented to promote the sound development of foreign language education and AI technology.

2023

AUTOMATIC DETECTION OF ABANDONED VINEYARDS USING AERIAL IMAGERY

Authors
Teixeira, I; Sousa, JJ; Cunha, A;

Publication
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM

Abstract
The European Union (EU) established through the Common Agricultural Policy (CAP) an aid system and subsidies for farmers that cultivate vineyards. Eligible areas should be controlled and registered in Geographic Information Systems. The agencies paying this support must check that the parcels have an agricultural activity through an on-the-spot check or the analysis of aerial or satellite images. Abandonment situations lead to the cancellation of aid payments. In the Douro Demarcated Region of Portugal, inspections are conducted according to EU-defined methods. However, due to the vast size of the region, which spans approximately 250,000 hectares with vineyard cultures occupying 43,843 hectares, the analysis time and specialized human resources required for these inspections are significant. In this study, we curated a new dataset for training convolutional neural networks (CNNs) and fine-tuned pre-trained VGG models to classify vineyards as abandoned or non-abandoned. The baseline model achieved an accuracy of 95.1% on the test dataset, while the top-performing model achieved an impressive overall accuracy and F1-score of 99% for both classes.

2023

Cutting-Edge Advances in Image Information Processing

Authors
Couto, P; Filipe, V;

Publication
APPLIED SCIENCES-BASEL

Abstract
[No abstract available]

2023

Model-Free VRFT-Based Tuning Method for PID Controllers

Authors
Vrancic, D; Oliveira, PM; Bisták, P; Huba, M;

Publication
MATHEMATICS

Abstract
The main objective of this work was to develop a tuning method for PID controllers suitable for use in an industrial environment. Therefore, a computationally simple tuning method is presented based on a simple experiment on the process without requiring any input from the user. Essentially, the method matches the closed-loop response to the response obtained in the steady-state change experiment. The proposed method requires no prior knowledge of the process and, in its basic form, only the measurement of the change in the steady state of the process in the manually or automatically performed experiment is needed, which is not limited to step-like process input signals. The user does not need to provide any prior information about the process or any information about the closed-loop behavior. Although the control loop dynamics is not defined by the user, it is still known in advance because it is implicitly defined by the process open-loop response. Therefore, no exaggerated control signal swings are expected when the reference signal changes, which is an advantage in many industrial plants. The presented method was designed to be computationally undemanding and can be easily implemented on less powerful hardware, such as lower-end PLC controllers. The work has shown that the proposed model-free method is relatively insensitive to process output noise. Another advantage of the proposed tuning method is that it automatically handles the tuning of highly delayed processes, since the method discards the initial process response. The simplicity and efficiency of the tuning method is demonstrated on several process models and on a laboratory thermal system. The method was also compared to a tuning method based on a similar closed-loop criterion. In addition, all necessary Matlab/Octave files for the calculation of the controller parameters are provided online.

2023

Trends on Communication, Educational Assessment, Sustainable Development, Educational Innovation, Mechatronics and Learning Analytics at TEEM 2022

Authors
Balbín, AM; Caetano, NS; Conde Á, M; Costa, P; Felgueiras, C; Fidalgo Blanco Á; Fonseca, D; Gamazo, A; García Holgado, A; García Peñalvo, FJ; Gonçalves, J; Hernández García Á; Lima, J; Nistor, N; O’Hara, J; Olmos Migueláñez, S; Piñeiro Naval, V; Ramírez Montoya, MS; Sánchez Holgado, P; Sein Echaluce, ML;

Publication
Lecture Notes in Educational Technology

Abstract
The 10th edition of the Technological Ecosystems for Enhancing Multiculturality (TEEM 2022) brings together researchers and postgraduate students interested in combining different aspects of the technology applied to knowledge society development, with particular attention to educational and learning issues. This volume includes contributions related to communication, educational assessment, sustainable development, educational innovation, mechatronics, and learning analytics. Besides, the doctoral consortium papers close the proceedings book from a transversal perspective. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

2023

Wind energy sustainability in Europe-A review of knowledge gaps, opportunities and circular strategies

Authors
Ramos, A; Magalhaes, F; Neves, D; Gonçalves, N; Baptista, A; Mata, T; Correia, N;

Publication
GREEN FINANCE

Abstract
Wind energy has become a very interesting option regarding the replacement of fossil-based energy sources by renewable options. Despite its eco-friendly character, some challenges remain across the whole lifecycle of wind turbines. These are mainly related to the use of more sustainable materials and processes in the construction phase, to lifetime extension for the structures currently installed and to waste management at the end-of-life phase, the disassembly or decommissioning phase. Following worldwide concerns about sustainability, the circular economy and decarbonization, several projects have been addressing the themes identified, proposing alternatives that are more suitable and contribute to the body of knowledge in the sector towards enhanced environmental and technical performance. This work presents the state of the art of the European wind energy sector, reflecting on the main drivers, barriers and challenges for circularity, while identifying knowledge gaps and strategic opportunities to develop new potential approaches. A compilation of key projects and main wind energy sites in Europe is shown, as well as a collection of lifecycle extension strategies and reported environmental impacts. Approaches to sustainability are highlighted, such as recyclability, ecodesign and eco-efficiency of the turbine blades. Furthermore, the associated potential environmental, economic and societal impacts are put forward to support the implementation of more circular solutions, which can also contribute to reducing EU energy dependency and more integration of in what relates to potential circular solutions and strategies towards a higher level of sustainability.

  • 779
  • 4536