Browsing by Issue Date, starting with "2025-01-16"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- From design to evaluation: a human-centered approach to AI-powered remote cognitive training for stroke patientsPublication . Paulino, Teresa da Conceição Madureira; Cameirão, Mónica da SilvaStroke is a leading cause of long-term disability worldwide, often resulting in cognitive impairments that significantly impact patients' quality of life and independence. This doctoral thesis presents the design, development of the client-side modules, and evaluation of the NeuroAIreh@b platform, a remote cognitive training system specifically tailored for stroke survivors. The focus of this thesis is dual. First, a focus on a comprehensive human-centered design approach was used to design the modular platform that addresses the specific needs of stroke patients and healthcare professionals. Second, the automation of cognitive training through the development of the software module Reh@Sync allows the training to be performed remotely with reduced need for therapist intervention. The system integrates a set of cognitive training apps that incorporate activities of daily living, enhancing ecological validity and potential skill transfer to real-life situations. One of the key innovations of the Reh@Sync is the implementation of personalization and difficulty adaptation features, which use cognitive profiles and machine learning models to tailor interventions to the individual patient's needs and abilities. Moreover, the engineered system can universally integrate independent apps beyond the cognition dimension, making it a multipurpose system for multidimensional training. The design process involved multiple stakeholders and employed various techniques, including requirements engineering, ideation sessions, prototyping, and iterative usability evaluations. The development phase resulted in a modular system capable of integrating multiple cognitive training apps while maintaining customizability for individual users. The results of a feasibility study with 10 chronic stroke survivors who used the system for 4 weeks showed high levels of adherence, usability, and user satisfaction, indicating the potential for widespread adoption in home based rehabilitation settings. Regarding clinical outcomes after the intervention, we observed significant improvements for a subgroup that showed baseline cognition below the norm. Evaluation of the automation process revealed that the system efficiently personalized and adapted the training to each participant's profile. This research contributes to the fields of cognitive rehabilitation, informatics engineering, and human-computer interaction by providing a detailed account of the design, engineering, and development process of an automated remote cognitive training system for stroke survivors. The findings support the feasibility of self-administered digital cognitive training and highlight areas for future improvements, including expanding the difficulty range to accommodate higher-functioning individuals and incorporating a wider variety of content to enhance engagement.
- Generation of business rules code from natural languagePublication . Gonçalves, Nuno Miguel Sousa; Valente, Pedro Dionísio; Fermé, Eduardo LeopoldoThe coding of business rules (BR) is a critical task in information systems (IS) development, particularly within the typical model-view-controller (MVC) architecture. In this architecture, the controller (which includes business logic and BR) handles the flow of data between the view (user interface) and the model (database). Although implementing BR can be complex, time-consuming, and even daunting, current software development tools remain more focused on designing the user interface and the database. This emphasis is understandable, given the challenges of defining complex structures like classes or tables, as well as their relationships, attributes, and fields. However, an alternative approach lies in the domain of natural language processing (NLP). Natural language (NL) may offer a more suitable means of modeling BR, especially as citizen developers become increasingly involved in software development. With this perspective in mind, this thesis reviews the state of the art in generating BR code from NL. The study examined 604 articles through forward, backward, and lateral snowballing techniques, starting with four cornerstone papers and ultimately narrowing the field to 11 relevant articles. These selected articles propose solutions that leverage the semantics of business vocabulary and business rules (SBVR) or decision model and notation (DMN) as a "bridge" to produce code in object constraint language (OCL), entity-relationship (ER) diagrams, or extensible markup language (XML). Our findings suggest that while these solutions are valuable, they fall short of generating BR code in diverse programming languages such as C, Java, or Python. To address this gap, we aim to create a prototype that can effectively translate natural language into machine-readable code. This thesis is part of a larger project called "Hydra Code Generation Tool (HydraCGT)," which belongs to the Department of the University of Madeira – Office for the Development of Information Technology Applications (GDAI).
- Boas práticas de gestão num estabelecimento hoteleiro: estudo caso Grupo EnotelPublication . Açafrão, Sónia Patrícia Sousa; Teles, Susana; Almeida, António Manuel Martins deEste estudo procurou compreender as práticas de gestão utilizadas no Grupo Enotel em relação aos seus trabalhadores, bem como analisar a perceção desses sobre a cultura organizacional da empresa e identificar quais são os fatores que contribuem para a motivação e o compromisso dos trabalhadores. Adicionalmente, procurou-se estabelecer uma relação entre as práticas de gestão e os resultados organizacionais, identificando quais práticas contribuem para a obtenção de melhores resultados e que fomentam uma melhoria contínua da empresa. Assim, foi utilizado o método quantitativo, através da aplicação de questionários aos colaboradores. O tamanho da amostra foi limitado ao número de colaboradores vinculados à empresa, sendo que no período em que decorreu a distribuição de questionários, estavam vinculados 278 colaboradores, tendo sido possível recolher 241 questionários. A recolha de dados foi realizada de 1 a 15 março, tendo sido aplicado o questionário de forma presencial. Foram contemplados vários aspetos, como a formação e o desenvolvimento pessoal, a avaliação de desempenho, a remuneração e os benefícios e também os aspetos culturais, como os valores, o clima organizacional, a liderança, a comunicação e a participação ativa dos trabalhadores. A pesquisa mostrou que a empresa distingue-se por ter uma gestão eficiente, que valoriza os seus trabalhadores, promove uma cultura organizacional positiva e com iniciativas de sustentabilidade. Os dados indicaram que a empresa produz serviços de qualidade e na perspetiva do trabalhador tem um futuro promissor, gere bem seus funcionários e possui uma forte cultura organizacional. As práticas de gestão do Grupo estão assentes em quatro pilares fundamentais: valorização dos colaboradores, cultura organizacional, sustentabilidade e prestação de serviços de excelência. A combinação destes pilares contribui para o sucesso da empresa, consolidando a sua posição de referência no setor hoteleiro. Os resultados obtidos revelam ainda que é importante investir num ambiente de trabalho positivo e motivador e na formação dos trabalhadores adotando práticas sustentáveis de forma a minimizar o seu impacto ambiental. Assim, este estudo também procura contribuir para a literatura académica no tema da gestão hoteleira, oferecendo insights valiosos sobre as práticas de gestão eficazes e os fatores que influenciam a motivação e o compromisso dos colaboradores nas empresas do setor hoteleiro.