ESE - Artigos em Revistas Indexados à WoS/Scopus
URI permanente para esta coleção:
Navegar
Percorrer ESE - Artigos em Revistas Indexados à WoS/Scopus por Objetivos de Desenvolvimento Sustentável (ODS) "09:Indústria, Inovação e Infraestruturas"
A mostrar 1 - 6 de 6
Resultados por página
Opções de ordenação
- Associations Between Neurofeedback, Anthropometrics, Technical, Physical, and Tactical Performance in Young Women’s Football PlayersPublication . Carvalho, Sílvio; Bezerra, Pedro; Teixeira, José Eduardo; Forte, Pedro; Silva, Rui M.; Cancela-Carral, José MariaNeurofeedback training has emerged as a promising tool for enhancing performance by targeting specific brain activity patterns linked to motor skills, decision-making, and concentration. This study aimed to explore the associations between neurofeedback outcomes and football-specific performance metrics, including anthropometric, physical, technical, and tactical dimensions. A quasi-experimental design was used to examine the effects of a six-week neurofeedback training program on motor skills, tactical decision-making, and physical performance in young women's football players (n = 8, aged 14-18). Participants underwent 30-min sessions three times a week targeting sensorimotor rhythms (SMRs) in the 12-15 Hz range within virtual football scenarios. Pre- and post-intervention assessments included anthropometric measures, neurophysiological evaluations, Loughborough Soccer Shooting Test (LSST), and Yo-Yo Intermittent Recovery Test Level 1 (YYIR1). Tactical decision-making was evaluated with a FUT-SAT-based instrument, and biological maturity was estimated using the Mirwald equations. Statistical analyses using Pearson's correlations revealed significant associations between neurofeedback outcomes, motor efficiency indices (MEIs), decision-making (DM), and football performance metrics. Correlation coefficients ranged from 0.504 to 0.998, with p-values from 0.010 to <0.001, indicating significant associations across physical, technical, and tactical dimensions. This study highlights the beneficial impact of neurofeedback on football performance in young female athletes.
- Classification of dementia risk in the elderly through gait analysis with machine learning algorithmsPublication . Costa, Raí Braz; Almeida, Samuel Gonçalves; Encarnação, Samuel; Schneider, André; Barbosa, Tiago M.; Teixeira, José Eduardo; Forte, Pedro; Monteiro, António M.The irreversible and progressive decline of physiological functions is known as aging. Among these changes is brain aging, which leads to cognitive decline and the onset of dementia. This directly affects memory, learning, and motor skills, reducing gait efficiency. This study aimed to investigate the feasibility of identifying and classifying the risk of dementia based on the analysis of kinematic variables related to gait in older adults using machine learning algorithms. This cross-sectional observational study examined a sample of 59 individuals aged 60 +/- 8 years, divided into two groups: 26 institutionalized older adults (GI) and 33 non-institutionalized older adults (GNI), all residing in Bragan & ccedil;a, Portugal. Gait data were collected during a 10-m walk, recorded on video, and analyzed using Kinovea software. Cognitive status was assessed using the Mini-Mental State Examination (MMSE). Python (TM) was used for statistical analysis and to develop machine learning models to classify dementia risk based on gait variables. The results showed that the algorithmic models achieved an overall accuracy of 74.6%, with the AdaBoost algorithm performing best at 83.5%. Cross-validation revealed an overall accuracy of 72%, with the Support Vector Machine (SVM) classifier achieving the highest individual performance at 80%, correctly classifying 80% of cases across different data subsets. In conclusion, gait analysis combined with machine learning algorithms demonstrated a strong relationship between gait variables and dementia, proving to be a safe and efficient technique for dementia classification. This approach offers a low-cost and accessible early identification and intervention method, with potential applications in clinical and public health settings.
- Exploring the Impact of Ultrasound-Assisted Extraction on the Phytochemical Composition and Bioactivity of Tamus communis L. FruitsPublication . Gouvinhas, Irene; Saavedra, Maria José; Alves, Maria José; Garcia, JulianaThe health benefits of Tamus communis fruits have been associated with their high phenolic content, which comprises several flavonoids. However, the extraction methods might significantly impact these valuable compounds' bioactivity. Therefore, the current study assesses how different extraction techniques affect T. communis extracts' antioxidant, anti-aging, antimicrobial, cytotoxic, anti-inflammatory, and phenolic contents. Conventional method (TCE-CM) and ultrasound-assisted extraction (TCE-UM) were the methods employed. Results: The increased phenolic content of TCE-UM, particularly flavonoids and phenolic acids, was demonstrated to be a contributing factor to its higher biological activity. Key enzymes linked to dermatological conditions, such as elastase, collagenase, hyaluronidase, and tyrosinase, were significantly inhibited by both extracts at 1 mg/mL; TCE-UM showed the highest tyrosinase inhibition (65.61 +/- 5.21%) compared to TCE-CM (21.78 +/- 2.19%). TCE-UM also demonstrated exceptional antibacterial performance, showing notable antibiofilm and metabolic inactivation effects and potent activity against pathogens such as Staphylococcus aureus, Escherichia coli, and Candida albicans. Both extracts showed concentration-dependent anti-inflammatory properties; TCE-UM had a lower IC50 value (26.46 +/- 2.30%) in nitric oxide inhibition tests, suggesting stronger anti-inflammatory capabilities. These findings underscore the superior bioactivity of TCE-UM and suggest that ultrasonic extraction is a more efficient method for isolating bioactive phenolic compounds from T. communis fruits, presenting promising applications in anti-aging and antimicrobial formulations.
- Innovative Applications of Artificial Neural Networks in Tax ForecastingPublication . Rodolfo, Bruno Couto de Abreu; Gonçalves, Bruno F.The importance of forecasting tax revenues is vital for economic planning and financial sustainability in Mozambique. The study addresses this topic by exploring the potential of Artificial Neural Networks (ANNs) to improve such predictions. The central problem is the limitation of conventional methods in capturing the complexity of fiscal data. The objective is to develop an ANN model that incorporates historical data and economic factors, providing a mixed methodology that enriches the analysis with qualitative and quantitative data. The rationale for adopting ANNs lies in their superior modeling and prediction capabilities in large and complex data environments. The results achieved demonstrate that ANNs can predict tax revenues with greater accuracy, surpassing traditional models. The conclusion points to the ANN as a valuable tool for tax authorities, enhancing efficiency in collection and contributing to the country's fiscal stability.
- Modeling Performance in IRONMAN® 70.3 Age Group TriathletesPublication . Thuany, Mabliny; Valero, David; Villiger, Elias; Forte, Pedro; Weiss, Katja; Andrade, Marilia Santos; Nikolaidis, Pantelis Theo; Cuk, Ivan; Rosemann, Thomas; Knechtle, BeatIndividual factors related to performance in age group triathletes competing in different race distances have been explored in scientific literature. However, only a few studies have been conducted using machine learning (ML) predictive models to explore the importance of those individual factors. This study intended to build and analyze machine learning regression models that predict the performance of IRONMAN (R) 70.3 age group triathletes, considering sex, age, country of origin, and event location as predictive factors. A total of 823,464 finishers records (625,398 men and 198,066 women) of IRONMAN (R) 70.3 age group triathletes participating in 197 different events in 183 different locations between 2004 and 2020 were analyzed. The triathletes' sex, age, country of origin, event location and year, and race finish times were thus obtained and considered for the study. Four different ML regression models were built to predict the triathletes' race times from their age, sex, country of origin, and race location. The model with the best performance was then selected and further analyzed using model-agnostic interpretability tools to understand which factors would contribute most to the model predictions.ResultsThe Random Forest Regressor model obtained the best predictive score. This model's partial dependence plots indicated that men under 30 years, from Switzerland or Denmark, competing in IRONMAN (R) 70.3 Austria/St. Polten, IRONMAN (R) 70.3 Switzerland, IRONMAN (R) 70.3 Sunshine Coast, and IRONMAN (R) 70.3 Busselton presented the best performance.ConclusionsOur results prove that ML models can be used to examine the complex, non-linear interactions between the factors that influence performance and gain insights that can help IRONMAN (R) 70.3 age group triathletes better plan their races.
- Technology-Mediated Education: impact of AI on the main distance learning modalitiesPublication . Morgado, Elsa; Silva, Levi Leonido; Pereira, Antonino; Gouveia, Luís BorgesArtificial Intelligence (AI) and distance learning (EaD) have profoundly transformed education, redefining teaching methodologies and learning dynamics. When integrated into educational environments, these technologies facilitate equitable access to knowledge, enable personalized learning, and enhance pedagogical flexibility. E-learning, blended learning (b-learning), and mobile learning (m-learning) exemplify technology-mediated instructional modalities that empower learners and educators to engage in innovative knowledge construction, transcending geographical barriers. This study critically examines the impact of AI-driven digital platforms on distance learning and their implications for pedagogical efficacy. A quantitative research design was employed to evaluate the benefits and challenges associated with AI-integrated digital platforms in distance education. Data were collected through an online survey administered to education professionals from three Portuguese-speaking regions with significant engagement in digital learning: Portugal (Europe), Brazil (Latin America), and Angola (Africa). The survey assessed perceptions regarding the extent to which AI-enhanced platforms influence pedagogical practices and learning outcomes. Analysis of 230 validated responses revealed substantial insights into the role of AI-driven platforms in education. Findings indicate that these technologies foster accessibility, support individualized learning pathways, and enhance instructional adaptability. Additionally, the study identifies key areas for improvement in the integration of AI-driven platforms within pedagogical frameworks to optimize educational efficacy. The findings highlight the transformative potential of AI and digital platforms in distance education, emphasizing their capacity to enhance learning experiences and promote knowledge democratization. Nevertheless, the study underscores the necessity for ongoing optimization of these technologies to fully harness their pedagogical benefits and address existing limitations.