Ciências e Tecnologia | Artigos em revistas internacionais / Papers in international journals
URI permanente para esta coleção:
Navegar
Entradas recentes
- A framework for adaptive recommendation in online environmentsPublication . Azambuja, Rogério Xavier de; Morais, A. Jorge; Filipe, Vítor Manuel JesusRecent advancements in deep learning and large language models (LLMs) have led to the development of innovative technologies that enhance recommender systems. Different heuristics, architectures, and techniques for filtering information have been proposed to obtain successful computational models for the recommendation problem; however, several issues must be addressed in online environments. This research focuses on a specific type of recommendation, which combines sequential recommendation with session-based recommendation. The goal is to solve the complex next-item recommendation problem in Web applications, using the wine domain as a case study. This paper describes a framework developed to provide adaptive recommendations by rethinking the initial data modeling to better understand users’ dynamic taste profiles. Three main contributions are presented: (a) a novel dataset of wines called X-Wines; (b) an updated recommendation model named X-Model4Rec – eXtensible Model for Recommendation, which utilizes attention and transformer mechanisms central to LLMs; and (c) a collaborative Web platform designed to support adaptive wine recommendations for users in an online environment. The results indicate that the proposed framework can enhance recommendations in online environments and encourage further scientific exploration of this topic.
- Guiding evacuees to Improve fire building evacuation efficiency: hazard and congestion models to support decision making by a context-aware recommender systemPublication . Coelho, António; Neto, Joaquim; Morais, A. Jorge; Gonçalves, Ramiro Ramos MoreiraFires in large buildings can have tragic consequences, including the loss of human lives. Despite the advancements in building construction and fire safety technologies, the unpredictable nature of fires, particularly in large buildings, remains an enormous challenge. Acknowledging the paramount importance of prioritising human safety, the academic community has been focusing consistently on enhancing the efficiency of building evacuation. While previous studies have integrated evacuation simulation models, aiding in aspects such as the design of evacuation routes and emergency signalling, modelling human behaviour during a fire emergency remains challenging due to cognitive complexities. Moreover, behavioural differences from country to country add another layer of complexity, hindering the creation of a universal behaviour model. Instead of centring on modelling the occupant behaviour, this paper proposes an innovative approach aimed at enhancing the occupants’ behaviour predictability by providing real-time information to the occupants regarding the most suitable evacuation routes. The proposed models use a building’s environmental conditions to generate contextual information, aiding in developing solutions to make the occupants’ behaviour more predictable by providing them with real-time information on the most appropriate and efficient evacuation routes at each moment, guiding the occupants to safety during a fire emergency. The models were incorporated into a context-aware recommender system for testing purposes. The simulation results indicate that such a system, coupled with hazard and congestion models, positively influences the occupants’ behaviour, fostering faster adaptation to the environmental conditions and ultimately enhancing the efficiency of building evacuations.
- X-Model4Rec: an extensible recommender model based on the user’s dynamic taste profilePublication . Azambuja, Rogério Xavier de; Morais, A. Jorge; Filipe, Vítor Manuel JesusSeveral approaches have been proposed to obtain successful models to solve complex next-item recommendation problem in non-prohibitive computational time, such as by using heuristics, designing architectures, and applying information filtering techniques. In the current technological scenario of artificial intelligence, sequential recommender systems have been gaining attention and they are a highly demanding research area, especially using deep learning in their development. Our research focuses on an efficient and practical model for managing sequential session-based recommendations of specific products for users using the wine and movie domains as case studies. Through an innovative recommender model called X-Model4Rec – eXtensible Model for Recommendation, we explore the user's dynamic taste profile using architectures with transformer and multi-head attention mechanisms to solve the next-item recommendation problem. The performance of the proposed model is compared to that of classical and baseline recommender models on two real-world datasets of wines and movies, and the results are better for most of the evaluation metrics.
- X-Wines: dados sobre vinhos para ampla utilizaçãoPublication . Filipe, Vítor Manuel Jesus; Azambuja, Rogério Xavier de; Morais, A. JorgeNo atual cenário de crescimento tecnológico, à semelhança da maioria dos produtos agrícolas, o vinho apresenta um volume de dados disponibilizado muito reduzido ou com poucos elementos, o que limita a exploração científica, como é o caso nos sistemas de recomendação. Este artigo apresenta e avalia uma nova base de dados denominada X-Wines no seu primeiro ano de publicação. Ela é constituída por 100.646 rótulos de vinhos produzidos em 62 países e 21 milhões de classificações reais dos consumidores encontrados na Web aberta em 2022. X-Wines é disponibilizada para ser livremente utilizada em sistemas de recomendação, aprendizado de máquina e uso geral, como uma contribuição à ciência de dados.
- Integrating prey monitoring and stable isotope analysis to assess the diet of Octopus vulgaris in Portuguese coastal waterPublication . Seixas, Sónia; Baeta, Alexandra; Marques, João CarlosThis study explores the feeding ecology of Octopus vulgaris in the Cascais region through a combined approach of long-term prey monitoring and stable isotope analysis. Over several months, we worked with local fishermen to observe and record prey items found in octopus pots and those carried by octopuses at the time of capture. These field observations enabled the identification of key prey species, which were subsequently analysed isotopically to estimate their contribution to the octopus diet. The results show that Atrina fragilis is the main prey, making up about 70 %, followed by Polybius henslowii (18 %), with Cymbium olla and Cepola macrophthalma contributing smaller amounts. Our findings highlight the limitations of traditional stomach content analysis, which often underestimates soft-bodied or highly digested prey, and emphasise the importance of isotopic methods to provide a more comprehensive and long-term view of trophic interactions. This integrated approach enhances our understanding of O. vulgaris feeding strategies and has significant implications for ecological research and the sustainable management of fisheries in the region.
- The interplay of bottle storage and wood ageing technology: volatile and sensory profiles of wine spirits aged with chestnut woodPublication . Caldeira, Ilda; Anjos, Ofélia; Vitória, Cláudia; Oliveira Alves, Sheila; Fernandes, Tiago; Canas, Sara; Catarino, SofiaWine spirits are typically aged in wooden barrels. Recently, alternative ageing technologies, such as those using wood fragments in wine spirits stored in stainless steel tanks, have been investigated. However, a significant lack of information regarding the potential evolution of these beverages after bottling still remains. This study assessed the 12-month evolution of aroma in bottled wine spirits aged with chestnut wood using different technologies, including fragment application with several micro-oxygenation strategies and barrels (traditional). Chemical analysis using GC-FID and GC–MS methods, along with sensory analysis, was conducted on all sampled aged wine spirits. Significant changes in volatile compounds were detected over time, including volatile phenols, acids, and esters. Multivariate data analysis distinguished traditional and alternative aged samples, with slight sample discrimination based on bottle storage. Regarding the sensory results, a significant effect of the time in bottle in several sensory attributes was found, while the ageing technologies mainly affected the gustatory attributes. The tasters were also asked to rate the overall quality of the samples, which seems to be favoured by the time in the bottle. This initial assessment of the impact of 1 year of glass bottle storage on the volatile and sensory composition of aged wine spirits highlights that this stage must be considered as an additional technological factor in their production process. However, the differences induced by the wood ageing technologies applied remained evident after 1 year of glass bottle storage.
- Biopolymers in seed coating for sustainable agriculturePublication . Sprey, Layanne Muniz; Fernandes, Tiago; Kirillov, Alexander M.; Sousa, Ana CatarinaThe multibillion-dollar worldwide market for coated seeds is currently seeking new sustainable solutions that promote the use of natural (biobased) polymers for developing seed coating materials produced using clean methodologies. Seed coating is an effective method widely applied in modern agriculture. By uniformly depositing a variety of active ingredients on the seed surface, it is possible to obtain coated seeds with enhanced resistance, germination, and facilitated sowing. Moreover, seed coating is an attractive option for improving crop yield, resistance to biotic and abiotic factors, and restoring degraded soil systems. Petroleum derived polymers are commercially used in seed coating, which can negatively affect plants, soil, and pollinating animals. Biopolymer seed coatings offer various advantages for reducing environmental contamination, enhancing seed protection, and enabling the addition of beneficial microbial species that promote plant growth. Such seed coatings also improve seed germination, nutrient delivery, and sowing efficiency, while reducing reliance on chemical inputs and contributing to environmentally responsible agriculture. This review highlights the growing importance of biopolymers in seed coating and summarizes their multifaceted use in sustainable agricultural systems.
- Optimization of extraction of bioactive compounds from piper corcovadensis C.DC leaves using a generalized linear modelPublication . Fontoura, Bruno Henrique; Ramos, Luciano de Souza; Dallacorte, Lucas Vinícius; Rodrigues, Michelle Fernanda Faita; Marchese, José Abramo; Fernandes, Tiago; Cunha, Mário Antônio Alves da; Lima, Vanderlei Aparecido de; Carpes, Solange TeresinhaThis concerns P. corcovadensis, an endemic plant of Brazil commonly used by the population due to its therapeutic properties. Optimizing chemical extraction conditions is critical for increasing the availability of bioactive compounds from plants. These compounds have antioxidant potential derived from a plant’s specialized metabolism and can exhibit a variety of biological actions. Therefore, statistical tools such as the Random Forest and Lazy KStar machine learning algorithms were used to determine the optimal condition for the extraction of phenolic compounds from P. corcovadensis leaves, with model evaluated by coefficient of determination (R2), mean square root of calibration error (RMSEC), and residual predictive deviation (RPD). The optimal extraction condition was obtained using a mixture of 80/20% (ethanol/water) at 70 °C for 120 min. For those extracts, there were 11.64 ± 0.04 mg GAE g-1 and antioxidant activity of 21.27 ± 0.53 mmol Trolox g-1, 33.15 ± 11.66 mmol Trolox g-1, and 13.47 ± 1.37 mmol Fe2+ by DPPH, ABTS and FRAP tests. With this study, we have shown that mathematical modelling can also be helpful in experimental sciences and can be used to develop predictive models. It was possible to develop predictive models for total phenolic compounds determination using the Random Forest and Lazy KStar machine learning algorithms. The Random Forest algorithm performed very well for DPPH modelling, giving us the confidence to use it to prediction antioxidant activity.
- Storage time in bottle: influence on physicochemical and phytochemical characteristics of wine spirits aged using traditional and alternative technologiesPublication . Alves, Sheila C. Oliveira; Fernandes, Tiago; Lourenço, Sílvia; Soares, Joana Granja; Silva, Andreia B.; Bronze, Maria Rosário; Catarino, Sofia; Canas, SaraFew studies have investigated the influence on physicochemical and phytochemical compositions during storage in the bottle of wine spirits (WSs) aged using alternative ageing technology (AAT) compared to traditional ageing technology (TAT). The aim of this study was to evaluate the effect of the bottle storage over one and four years on the evolution of chromatic characteristics (CIELab method) and physicochemical characteristics (alcoholic strength, acidity, and total dry extract), total phenolic index (TPI), low molecular weight compound contents (HPLC-DAD technique), in vitro antioxidant activities (DPPH, FRAP, and ABTS assays), and phenolic characterisation (HPLC-DAD-ESI-MS/MS technique) of WSs aged with chestnut wood using TAT (barrels, B) and AAT (micro-oxygenation levels (MOX): O15, O30, and O60; and control (N)). The results showed that after four years of storage in the bottle, the O60 modality resulted in smaller changes in physicochemical characteristics, higher preservation of phenolic content, and greater evolution of chromatic characteristics, ensuring its overall quality compared to other modalities. Antioxidant activity decreased similarly in both technologies, such as phenolic acid content, in particular, gallic acid content. According to the findings of this study, alternative ageing technology might be the best alternative for wine spirit quality and ageing process sustainability.
- A spatial statistics methodology for inspector allocation against fare evasionPublication . Freiria, Susana; Sousa, NunoThis article discusses public transport fare evasion from the point of view of the relations between inspection actions and detected evasion, with the aim of improving the efficacy of the former. By applying spatial statistics methods to a large dataset from Lisbon, Portugal, namely, entropy-based local bivariate relationships (LBR) and geographically weighted regression (GWR), it is shown that the two variables are associated in a widespread manner throughout the city, mostly in a linear way. Mapping out marginal gains from inspection actions then shows where they detect the most evaders, allowing transport companies to relocate their inspector teams in a more effective manner. Results for Lisbon show that gains in effectiveness of circa 50% can be obtained, mostly by moving some inspector teams from the centre of the city to the periphery during daytime. The methodology requires only inspection/detection databases, which transport companies usually have, making it a valuable, practical tool to combat fare evasion.