Percorrer por autor "Rodrigues, Joao"
A mostrar 1 - 10 de 29
Resultados por página
Opções de ordenação
- Affective computing databases: in-depth analysis of systematic reviews and surveysPublication . Migueis Vaz Martins, Pedro Jorge; Rodrigues, Joao; Cardoso, PedroThe field of affective computing (AffC) is a hot research topic, where keeping track of the latest state-of-the-art can be cumbersome. Probably, due to this, a huge increase in publications of systematic reviews or surveys (SRoS) is appearing in different journals, covering various aspects such as databases, methods, and overall perspectives. Nevertheless, this increase does not mean more and better information, or at least a clarification of information. The present study analyses 10 SRoS, all published within the last 4 years, focusing only on covering AffC databases, with emphasis on collections where emotion or sentiment can be extracted from the body. It was observed that, depending on the SRoS, different information was presented, sometimes with missing or discrepant data, due to lack of information or by the way it was interpreted. As a result, from those 10 SRoS, a total of 111 different databases were analyzed, which were segmented into three groups (tiers, i.e., citation-based categorization) by their relative importance of appearance in the SRoS. In addition, it is proposed a taxonomy with a minimum set of characterizing information that researchers should address when publishing or reviewing databases.
- Affective computing emotional body gesture recognition: evolution and the cream of the cropPublication . Migueis Vaz Martins, Pedro Jorge; Rodrigues, Joao; Cardoso, PedroThe field of affective computing (AffC) has experienced significant growth, making it challenging to stay up to date with the latest advancements. This surge in interest has likely contributed to a significant rise in the number of systematic reviews or surveys (SRoS) being published across various journals, covering topics like databases, methods, and general perspectives. This paper provides three key contributions: 1) A comprehensive analysis of the evolution of emotion recognition methods from 2002 to 2024, with particular emphasis on emotional body gesture recognition, documenting a clear transition from traditional machine learning to sophisticated deep learning architectures; 2) Identification and detailed analysis of the most impactful papers (the ‘‘cream of the crop’’) that have shaped body-based AffC methods, revealing that modern approaches increasingly use attention mechanisms, graph-based representations for skeletal data, and advanced spatial-temporal modeling techniques; and 3) A systematic categorization and analysis of emotion recognition methods across architectural types (machine learning, deep learning, and hybrid) and modalities (emotional body gesture recognition, facial emotion recognition, multimodal emotion recognition, and speech emotion recognition), demonstrating the field’s progression from unimodal to more robust multimodal approaches. Through an analysis of 10 selected SRoS papers published between 2021-2024, referencing 292 papers collectively, this study reveals critical challenges including limited availability of large-scale body-based emotional databases, computational demands of modern architectures, and cross-database generalization issues.
- Application of vision transformers in the early detection of excavation in the BRSET basePublication . Ferreira, Joel Santos; Fernandes, Miguel M.; Leite, Danilo D. L.; Gonzalez, Dibet; Gonzalez, Jose Carlos J. C. Raposo da Camara; Cunha, António A. C.; Rodrigues, JoaoEnlarged excavation of the optic papilla, caused by the loss of fibres that originate in the retina and transmit electrical stimuli to the visual cortex, is a critical indicator in the early detection of glaucoma, a disease that can lead to irreversible blindness. As the optic papilla shows morphological variations in the population, its identification can be a challenge. Methods based on deep learning have shown promise in helping doctors analyse these images more accurately. Recently, models such as Vision Transformers (ViT) have shown significant results in various medical applications, including glaucoma detection. However, the scarcity of quality data remains a major obstacle to training these models. This study evaluated the performance of the Swin Transformer, DeiT and Linformer models in detecting optic papilla excavation, using the new Brazilian Multilabel Ophthalmological Dataset (BRSET). The results showed that the DeiT model obtained the best accuracy, with 0.94, followed by the Swin Transformer, with 0.88, and the Linformer, with 0.85. The findings of this study suggest that ViT models can not only significantly improve the detection of glaucomatous papillary excavation, but also strengthen Human-Machine Collaboration, promoting more effective interaction between doctors and automated systems in medical diagnosis.
- Co-designing an inclusive bus stop for a tourist transportation hubPublication . Pires Rosa, Manuela; Golestaneh, Seyed Homayoun; Mello, Germana Santiago de; Rodrigues, Joao; Sousa, Nelson; Gameiro, Celeste; Sousa, Carlos; Cavaleiro, Rui; Lamarão, HugoThis study explores the integration of sustainable mobility and universal design principles in creating accessible public transportation infrastructure. The research focuses on the co-design of a bus stop at Faro International Airport, engaging diverse stakeholders, including older tourists and adults with disabilities, through surveys, group reflections, walk-throughs, and workshops. The methodology incorporated multiple methods, such as, inquiries, observations and interviews, and digital prototyping to gather comprehensive insights into the specific needs of the participants. By addressing societal vulnerabilities and promoting social sustainability, the co-design process fostered innovation, resulting in a bus stop design that is functional, inclusive, and adaptable. The study underscores the role of sustainable mobility in enhancing equitable urban transportation systems and demonstrates how inclusive design principles contribute to achieving the broader goals of environmental, social, and economic sustainability. The design incorporates accessibility features, such as tactile paving, raised platforms, intuitive seating, and smart technology, tailored to the diverse needs of users. Special emphasis was placed on minimising barriers for individuals with mobility, visual, or hearing impairments while addressing the practical requirements of older adults. The inclusive bus stop serves as a model for future initiatives, highlighting the importance of active community engagement in designing transportation infrastructure that supports diverse societal needs.
- Continual learning for object classification: integrating AutoML for binary classification tasks within a modular dynamic architecturePublication . Turner, Daniel; Cardoso, Pedro; Rodrigues, JoaoFor humans it is quite easy to identify a new object after learning to identify existing ones, but not for a machine. Deep neural networks (DNN) are the foundation of the current state-of-the-art methods for training machines to recognize sets of objects. The issue is that any modification to the DNN weights that were trained to classify an initial set of objects has the potential to seriously impair the network’s ability to make those initial classifications; this behaviour is referred to as catastrophic forgetting (CF). This paper presents a continual learning (CL) architecture that can deal with CF. The architecture is composed of two primary parts: (i) The feature extraction component, which is based on the ResNet50 backbone and (ii) the modular dynamic classification (MDC) component. The latter is made up of multiple sub-networks that gradually assemble themselves into a tree-like structure that reorganizes itself as it learns over time, so that each sub-network can operate independently. The MDC relies heavily on binary classification, and here the application of automated machine learning (AutoML) was introduced, where each binary classifier is tailored on-the-fly, and is/can be different from object to object. The strategy involves a calculated selection from a predefined list of model types and parameters, optimizing them for their respective tasks. Results demonstrate that we advanced the adaptability and performance of the network, emphasizing the transformative potential of AutoML in modular CL approaches. Tests on the CORe50 dataset showed accuracy results of 81.1%, which are above the state of the art for CL architectures.
- CTCovid19: automatic Covid-19 model for computed tomography scans using deep learningPublication . Antunes, Carlos; Rodrigues, Joao; Cunha, AntónioCOVID-19 is an extremely contagious respiratory sickness instigated by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Common symptoms encompass fever, cough, fatigue, and breathing difficulties, often leading to hospitalization and fatalities in severe cases. CTCovid19 is a novel model tailored for COVID-19 detection, specifically honing in on a distinct deep learning structure, ResNet-50 trained with ImageNet serves as the foundational framework for our model. To enhance its capability to capture pertinent features related to COVID-19 patterns in Computed Tomography scans, the network underwent fine-tuning through layer adjustments and the addition of new ones. The model achieved accuracy rates that went from 97.0 % to 99.8 % across three widely recognized and documented datasets dedicated to COVID-19 detection.
- Cultural heritage visits supported on visitors' preferences and mobile devicesPublication . Cardoso, Pedro; Rodrigues, Joao; Pereira, Joao; Nogin, Sergey; Lessa, Joana; Ramos, Celia; Bajireanu, Roman; Gomes, Miguel; Bica, PauloMonuments, museums and cities are great places to feel and experience neat and interesting things. But cultural heritage is experienced differently by different visitors. The more erudite may know beforehand what they intend to explore, while the least literate usually know and are capable of expressing some of their preferences but do not exactly realize what to see and explore. This paper proposes the use of a mobile application to set an itinerary where you can move at your own pace and, at the same time, have all the complementary information you need about each of the points of interest. The application is designed in face of an adaptive user interface where the routing and augmented reality are connected to acknowledge the needs of different user categories, such as elders, kids, experts or general users
- Development of a multiresidue method for the determination of 24 pharmaceuticals in clams by QuEChERS and liquid chromatography-triple quadrupole tandem mass spectrometryPublication . Rodrigues, Joao; Albino, Stephanie; Silva, Sofia; Cravo, Alexandra; Cardoso, Vitor Vale; Benoliel, Maria Joao; Almeida, Cristina M. M.Data on different therapeutic classes of pharmaceutical compounds (PhCs) in clams or other bivalves living in natural conditions are scarce. The aim of this work was the optimization and validation of a method for the determination of PhCs in clams for further evaluation of any potential human exposure risk due to their consumption. A quick, easy, cheap, effective, rugged, and safe (QuEChERS) approach is proposed for sample clean-up and concentration of 24 PhCs in clams, with subsequent analysis by liquid chromatography-tandem mass spectrometry. This method showed a good linear range for all PhCs with determination coefficients (r(2)) between 0.9949 and 0.9993 and coefficients of variation (CVm) lower than 5.5%. This method allowed the quantification of target compounds at trace concentration levels (ngg(-1)), being the most abundant PhC in clam caffeine. This PhC was detected in more than 70% of samples with concentrations ranging from 0.10 to 12ngg(-1) wet weight.
- Digital cultural heritagePublication . Portalés, Cristina; Rodrigues, Joao; Rodrigues Gonçalves, Alexandra; Alba, Ester; Sebastián, JorgeMost contemporary thinkers agree that we are going through a time of historical change, building a different concept and model of social interrelation. Our ways of life and work have changed, as have the ways in which we communicate and relate to each other. Likewise, an increasing consensus indicates the need to reconfigure traditional social and cultural structures. The Internet, the virtual social networks, and the Information and Communication Technologies (ICTs) have coalesced into a new collective consciousness—a world intercommunicated from the local to the global [1]. The fusion of tradition, culture, history, and legacy with technology, innovation, and interaction provides an attractive system that serves both as an artistic expression and as a fundamental tool for diffusion in cultural institutions [2]. For instance, the usage of interactive technologies such as virtual reality (VR) or augmented reality (AR), combined with multidimensional or multimodal representations [3], provides a significant novelty. User interaction offers a broader perspective, making people more aware of their actions, helping them become the true center of the application. It also enables interactive artistic expression through alternative realities, as well as narration supported by the use of virtual avatars.
- Editorial for the special issue applied and innovative computational intelligence systems (3rd Edition)Publication . Cardoso, Pedro; Rodrigues, Joao; Portalés, CristinaWe are pleased to present the third edition of the Special Issue “Applied and Innovative Computational Intelligence Systems” in Applied Sciences, a journal with an Impact Factor of 2.7 and a CiteScore of 4.5 (2022). This Special Issue offers a unique opportunity for computational intelligence (CI) researchers and practitioners to share their latest theoretical and experimental outcomes with the international community. Supported by a wide range of approaches—including machine learning, deep learning, fuzzy systems, and evolutionary computation—CI aims to develop intelligent systems characterized by adaptability, fault tolerance, and high performance, enabling or facilitating intelligent behavior in complex and dynamic environments. The ultimate goal is to create technology that allows machines to think, behave, or act in ways that are increasingly human-like. In this context, the Special Issue explores both the foundational and applied aspects of CI, welcoming contributions in artificial intelligence, machine learning, deep learning, computer vision, data analysis and science, fault detection, affective computing, natural language processing, privacy and ethics, and robotics. By embracing this broad scope, we aim to capture the diversity and dynamism of contemporary research on CI and its complementary fields.
- «
- 1 (current)
- 2
- 3
- »