Browsing by Author "Madeira, Rui Neves"
Now showing 1 - 10 of 13
Results Per Page
Sort Options
- Adaptation to TV delays based on the user behavior towards a cheating-free second screen entertainmentPublication . Madeira, Rui Neves; Centineiro, Paulo; Correia, NunoRecent advances in technology created new opportunities to enhance TV personalization, providing viewers with individualized ways to watch TV and to interact with its content. Second screen applications are promising vehicles to enhance the viewers’ experiences, but researchers need to take into account the effect that the TV delay has on viewers, in particular when watching broadcasted live events. In this paper, we propose a software-based solution to deal with TV delays. It is mainly directed for a gaming context in which the user has the means to control the synchronisation between the second screen application and the TV content. Taking this scenario into account, we implemented a cheating-detection mechanism to cope with the potential exploitation of the system by its users.
- AI-powered solution for plant disease detection in viticulturePublication . Madeira, Miguel; Porfírio, Rui; Santos, Pedro Albuquerque; Madeira, Rui NevesIn an era dominated by the intersection of advanced technology and traditional industries, the domain of agriculture is on the verge of a revolutionary transformation. This article introduces a solution for vineyard producers, harnessing satellite imagery, weather data, and deep learning (DL) to identify vineyard diseases robustly. This solution, designed for proactive plant health management, stands as a transformative tool towards digital viticulture. Such tools transition from luxuries to essentials as vineyards confront evolving challenges like climate change and new pathogens. Our research builds on the hypothesis that customising deep learning architectures for specific tasks is crucial in enhancing their effectiveness. We contribute by introducing a tailored convolutional neural network (CNN) architecture, developed specifically for the classification of plant diseases using vineyard imagery. The experimental results demonstrate that our custom CNN architecture exhibits performance on par with established state-of-the-art models like ResNet50 and MobileNetV2, underscoring the value of specialized solutions in addressing the unique challenges of viticulture. This paper introduces an overview of the solution’s architecture, presents the implementation of DL modules with their corresponding results, and describes use case scenarios.
- Building on Mobile towards Better Stuttering Awareness to Improve Speech TherapyPublication . Madeira, Rui Neves; Macedo, Patrícia; Pita, Pedro; Bonança, Íris; Germano, HelenaThis paper describes the project I Aware my Stuttering , which is a system with a focus on a mobile application for smartphones directed to people who stutter. This software will allow users to register their stuttering related situations, registering, for example, the contexts in which they occur, the interlocutors and their reactions to the situations, and the emotions felt. The application provides a reporting module that includes charts to help visualizing how stuttering situations evolve according to several features. It will help promote daily self-monitoring of speech as a means of controlling stuttering, being personalized according to the user profile. The system also offers a module for the speech therapist, which can monitor and receive reports related to users which are her/his patients. This collected data will improve the therapeutic process by enhancing discussion about registers performed immediately after a real context situation. Additionally, this paper presents a first user study conducted to assess and validate the project’s purpose and the central module for registration of stuttering related situations.
- Co-creation and multidisciplinary education as a learning framework for developing ICT-based solutions for informal caregivers: insights from a pilot experience in Higher EducationPublication . Soares, Célia; Madeira, Rui Neves; Colaço, Gabriela; Macedo, Patrícia
- Exploring explainable AI techniques for plant disease classification in digital agriculturePublication . Porfírio, Rui Pedro; Madeira, Rui Neves; Santos, Pedro AlbuquerqueIntegrating smart farming technologies in agriculture is crucial to address the pressing challenges of food security, economic stability, and environmental sustainability. Solutions based on artificial intelligence (AI) for plant disease detection play a critical role in optimizing crop health and yield. However, the complexity and opacity of these AI models can hinder their acceptance and practical application by end-users. To address this issue, our ongoing research explores applying explainable AI (XAI) techniques to enhance the explainability of vision-based plant disease classification models. Our experiments assess the transparency of vision-based models by applying XAI techniques, such as LIME, Grad-CAM, and occlusion-based attribution, to visualize the reasoning behind model predictions. Additionally, we analyze inherently transparent machine learning models, such as k-Nearest Neighbors, through custom visualization graphics and examine how explainability varies with model accuracy. These findings highlight the role of XAI techniques in enhancing the transparency of predictions for crucial vision tasks in agriculture such as plant disease classification. Building on these results, we explore the potential integration of X AI techniques into third-party applications or prototypes, emphasizing how tailored visual and textual explanations can enhance the transparency and interpretability of plant disease classification models.
- Just Physio kidding: NUI and Gamification based Therapeutic Intervention for Children with Special NeedsPublication . Madeira, Rui Neves; Antunes, André; Postolache, OctavianThis paper presents the “just Physio kidding” approach, which intends to improve the engaging qualities of therapy programmes towards children with special needs, mainly with cerebral palsy, spinal muscular atrophy, or developmental delay. Therefore, “just Physio kidding” intends to address both physiotherapy and cognitive stimulation therapy. The system is functioning as a complement to the work of therapists, with and without their live supervision. It is part of a project with the aim of developing software based on the concept of personalized serious games for rehabilitation. The paper presents the concept and the prototype behind “just Physio kidding”.
- Mobile Apps to improve ThErapyPublication . Madeira, Rui Neves; Macedo, Patrícia; Pereira, Carla; Germano, Helena; Ferreira, JoãoThere is an emerging consumer-driven demand for a more personalised health system and, there is no question, the rapid evolution of the mobile apps market became an important driver for personalisation in the health field. The MAiThE (Mobile Apps to improve ThErapy) project focuses on the deployment and study of personalised mHealth apps to provide patients and carers with self-management capabilities to help them feel empowered in their ability to find strategies in a more informed and collaborative way, and to optimise therapy outside the clinical context, with remote support from health practitioners. The insight gathered with the development and assessment of the apps tailored to the end-users’ needs will result in a conceptual model to guide in the development of future mHealth apps. The project will produce an impact study based on thorough apps evaluations conducted on the field with participants from different contexts.
- Mobile Apps to improve therapy: the health practitioner in your pocket knows youPublication . Madeira, Rui Neves; Macedo, Patrícia; Pereira, Carla; Germano, Helena; Ferreira, JoãoThere 1 is an emerging consumer-driven demand for a more personalised health system and, there is no question, the rapid evolution of the mobile apps market became an important driver for personalisation in the health field. The MAiThE (Mobile Apps to improve ThErapy) project focuses on the deployment and study of personalised mHealth apps to provide patients and carers with self-management capabilities to help them feel empowered in their ability to find strategies in a more informed and collaborative way, and to optimise therapy outside the clinical context, with remote support from health practitioners. The insight gathered with the development and assessment of the apps tailored to the end-users’ needs will result in a conceptual model to guide in the development of future mHealth apps. The project will produce an impact study based on thorough apps evaluations conducted on the field with participants from different contexts.
- ONParkinson – Innovative mHealth to support the triad: patient, carer and health professionalPublication . Madeira, Rui Neves; Pereira, Carla Mendes; Clipei, Sergiu; Macedo, PatríciaThe ONParkinson mHealth platform aims to empower an integrated assistance to support end-users of the triad “people with Parkinson’s Disease, their carers and health professionals”, promoting the self-management in Parkinson’s disease. Therefore, ONParkinson is expected to optimize the communication between the triad users, helping them find relevant knowledge to support their clinical issues, as well as allowing the monitoring of patients` daily routine and the recommendation for daily exercises. This mHealth solution was created and materialized after an initial study of the end-users’ needs. This paper presents the usability study of the first version of the ONParkinson prototype. According to the usability tests’ findings, ONParkinson was perceived by the triad users as easy to use, with functionalities well integrated, useful and attractive. Some recommendations were suggested to enhance its usability, users’ satisfaction and continuance intentions.
- Personalising the user experience of a mobile health application towards Patient EngagementPublication . Madeira, Rui Neves; Germano, Helena; Macedo, Patrícia; Correia, NunoStuttering is a multifactorial speech disorder that usually has several impacts on daily life, especially regarding loss of confidence in social situations and increased anxiety levels. BroiStu is a mobile health application that was developed to address the impacts of stuttering on people who stutter, allowing them to be more aware of their speech disorder in their everyday life. The personalisation of the user experience may be particularly important to maintain the patient engaged with the application towards a long-term use to take full advantage of the application’s features. This paper presents the implementation of personalisation aspects in BroiStu, introducing the model that is being followed, describing the features used, and presenting the results obtained with a preliminary experiment. The personalisation mechanisms are provided by a cloud-based platform that is designed to serve different applications. Interesting findings and further work are presented.