Percorrer por autor "Rodrigues, João"
A mostrar 1 - 10 de 18
Resultados por página
Opções de ordenação
- A deep neural network video framework for monitoring elderly personsPublication . Farrajota, Miguel; Rodrigues, João; du Buf, J. M. H.The rapidly increasing population of elderly persons is a phenomenon which affects almost the entire world. Although there are many telecare systems that can be used to monitor senior persons, none integrates one key requirement: detection of abnormal behavior related to chronic or new ailments. This paper presents a framework based on deep neural networks for detecting and tracking people in known environments, using one or more cameras. Video frames are fed into a convolutional network, and faces and upper/full bodies are detected in a single forward pass through the network. Persons are recognized and tracked by using a Siamese network which compares faces and/or bodies in previous frames with those in the current frame. This allows the system to monitor the persons in the environment. By taking advantage of parallel processing of ConvNets with GPUs, the system runs in real time on a NVIDIA Titan board, performing all above tasks simultaneously. This framework provides the basic infrastructure for future pose inference and gait tracking, in order to detect abnormal behavior and, if necessary, to trigger timely assistance by caregivers.
- Artificial intelligence applications and innovations: day-to-day life impactPublication . Rodrigues, João; Cardoso, Pedro; Chinnici, MartaThe idea of an intelligent machine has fascinated humans for centuries. But what is intelligence? Some define it as the capacity for learning, reasoning, understanding or, from a different perspective, the aptitude to grasp truths, relationships, facts, or meanings. All these perspectives require the capacity to acquire data from the surrounding world and, possibly, act over that environment. In short, the building of more or less autonomous agents, served with sensors and actuators, capable of learning and producing educated answers has been long foreseen. New trends in intelligente systems comprise, among other aspects, pervasive robotization, ubiquitous online data access, empowered edge computing, smart spaces, and digital ethics. These trends build the research on “Artificial Intelligence Applications and Innovation”, impacting our day-to-day life, our cities, and even our free time. Nevertheless, artificial intelligence (AI) is still closely associated with some popular misconceptions that cause the public to either have unrealistic fears about it or to have unrealistic expectations about how it will change our workplace and life in general. It is important to show that such fears are unfounded and that new trends, innovations, technologies, and smart systems will be able to improve the way we live, benefiting society without replacing humans in their core activities.
- Autonomous temporal pseudo-labeling for fish detectionPublication . Veiga, Ricardo; Exposito Ochoa, Iñigo; Belackova, Adela; Bentes, Luis; Parente Silva, João; Semiao, J.; Rodrigues, JoãoThe first major step in training an object detection model to different classes from the available datasets is the gathering of meaningful and properly annotated data. This recurring task will determine the length of any project, and, more importantly, the quality of the resulting models. This obstacle is amplified when the data available for the new classes are scarce or incompatible, as in the case of fish detection in the open sea. This issue was tackled using a mixed and reversed approach: a network is initiated with a noisy dataset of the same species as our classes (fish), although in different scenarios and conditions (fish from Australian marine fauna), and we gathered the target footage (fish from Portuguese marine fauna; Atlantic Ocean) for the application without annotations. Using the temporal information of the detected objects and augmented techniques during later training, it was possible to generate highly accurate labels from our targeted footage. Furthermore, the data selection method retained the samples of each unique situation, filtering repetitive data, which would bias the training process. The obtained results validate the proposed method of automating the labeling processing, resorting directly to the final application as the source of training data. The presented method achieved a mean average precision of 93.11% on our own data, and 73.61% on unseen data, an increase of 24.65% and 25.53% over the baseline of the noisy dataset, respectively.
- BINK: Biological binary keypoint descriptorPublication . Saleiro Filho, Mario; Terzic, Kasim; Rodrigues, João; du Buf, J. M. H.Learning robust keypoint descriptors has become an active research area in the past decade. Matching local features is not only important for computational applications, but may also play an important role in early biological vision for disparity and motion processing. Although there were already some floatingpoint descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compute and to match. Most of these descriptors are based on purely computational methods. The few descriptors that take some inspiration from biological systems are still lagging behind in terms of performance. In this paper, we propose a new biologically inspired binary keypoint descriptor: SINK. Built on responses of cortical V1 cells, it significantly outperforms the other biologically inspired descriptors. The new descriptor can be easily integrated with a V1-based keypoint detector that we previously developed for real-time applications. (C) 2017 Elsevier B.V. All rights reserved.
- A decision-support system to Analyse Customer Satisfaction Applied to a Tourism Transport ServicePublication . Ramos, Celia; Cardoso, Pedro; Fernandes, Hortênsio C. L.; Rodrigues, JoãoDue to the perishable nature of tourist products, which impacts supply and demand, the possibility of analysing the relationship between customers’ satisfaction and service quality can contribute to increased revenues. Machine learning techniques allow the analysis of how these services can be improved or developed and how to reach new markets, and look for the emergence of ideas to innovate and improve interaction with the customer. This paper presents a decision-support system for analysing consumer satisfaction, based on consumer feedback from the customer’s experience when transported by a transfer company, in the present case working in the Algarve region, Portugal. The results show how tourists perceive the service and which factors influence their level of satisfaction and sentiment. One of the results revealed that the first impression associated with good news is what creates the most value in the experience, i.e., “first impressions matter”..
- Dialectical Polyptych: an interactive movie installationPublication . Mendes Da Silva, Bruno; António, Rui; Rodrigues, João; Tavares, MirianMost of the known video games developed by important software companies usually establish an approach to the cinematic language in an attempt to create a perfect combination of narrative, visual technique and interaction. Unlike most video games, interactive film narratives normally involve an interruption in time whenever the spectator has to make choices. “Dialectical Polyptych” is an interactive movie included in a project called “Characters looking for a spectactor”, which aims to give the spectator on-the-fly control over film editing, thus exploiting the role of the spectator as an active subject in the presented narrative. This paper presents an installation based on a mobile device, which allows seamless real-time interactivity with the movie. Different finger touches in the screen allow the spectator to alternate between two parallel narratives, both producing a complementary narrative, and change the angle or shot within each narrative.
- Epidemiological and clinical aspects of Cutaneous and Mucosal Leishmaniases in Portugal: retrospective analysis of cases diagnosed in public hospitals and reported in the literature between 2010 and 2020Publication . Rocha, Rafael; Conceição, Cláudia; Gonçalves, Luzia; Carvalho, Ana Cláudia; Maia, André; Martins, André; Carujo, António; Maio, António; Forra, Catarina; Melita, Catarina; Couto, Daniela; Fernandes, Diana; Pereira, Dulce; Leal, Ema; Sarmento, Helena; Sousa, Inês; Gonçalves, Jean-Pierre; Marinho, Joana; Vasconcelos, Joana; Cunha, João; Rodrigues, João; Silva, José Miguel; Caley, Lídia; Malheiro, Luís; Santos, Luís; Garcia, Margarida; Cunha, Maria; Lima, Maria; Andrade, Maria Margarida; Marques, Marta; Alpalhão, Miguel; Silva, Mónica; Ferraz, Rita; Soares, Rui; Fernandes, Salomão; Llobet, Samuel; Cruz, Sofia; Guimarães, Teresa; Branco, Tiago; Nunes, Tomás Robalo; Almeida, Vasco; Maia, CarlaLeishmania infantum, a zoonotic vector-born parasite, is endemic in the Mediterranean region, presenting mostly as visceral (VL), but also as cutaneous (CL) and mucosal leishmaniasis (ML). This study aimed to describe the epidemiological and clinical aspects of the CL and ML cases diagnosed in mainland Portugal between 2010 and 2020. Collaboration was requested from every hospital of the Portuguese National Health System. Cases were screened through a search of diagnostic discharge codes or positive laboratory results for Leishmania infection. Simultaneously, a comprehensive literature search was performed. Descriptive statistics and hypothesis testing were performed using IBM (R) SPSS (R) Statistics. A total of 43 CL and 7 ML cases were identified, with a predominance of autochthonous cases (86%). In CL, immunosuppressed individuals constituted a significant proportion of patients (48%), and in this group, disseminated CL (22%) and simultaneous VL (54%) were common. In autochthonous cases, lesions, mostly papules/nodules (62%), were frequently observed on the head (48%). The approach to treatment was very heterogeneous. ML cases were all autochthonous, were diagnosed primarily in older immunosuppressed individuals, and were generally treated with liposomal amphotericin B. The findings suggest a need for enhanced surveillance and reporting, clinical awareness, and diagnostic capacity of these forms of leishmaniasis to mitigate underdiagnosis and improve patient outcomes. A holistic One Health approach is advocated to address the multifaceted challenges posed by leishmaniases in Portugal and beyond.
- Experimenting on film: technology meets artsPublication . António, Rui; Mendes Da Silva, Bruno; Rodrigues, João; Tavares, MirianInteractive films depend on the participation of viewers. This participation usually translates into making decisions that determine the sequence of the narrative. Many interactive films make use of an interaction design that reduces the viewer’s immersiveness by interrupting the narrative to allow choices and the use of graphics to alert about decision points. This article describes how “Dialectical Polyptych” focuses on the possibility of creating an interactive aesthetic experience of filmic visualization without the interference of visual elements, allowing immersive participation with a transparent interface.
- Framework for a Hospitality Big Data Warehouse: The Implementation of an Efficient Hospitality Business Intelligence SystemPublication . Ramos, Celia; Martins, Daniel; Serra, Francisco; Lam, Roberto; Cardoso, Pedro; Correia, Marisol; Rodrigues, Joãoorder to increase the hotel's competitiveness, to maximize its revenue, to meliorate its online reputation and improve customer relationship, the information about the hotel's business has to be managed by adequate information systems (IS). Those IS should be capable of returning knowledge from a necessarily large quantity of information, anticipating and influencing the consumer's behaviour. One way to manage the information is to develop a Big Data Warehouse (BDW), which includes information from internal sources (e.g., Data Warehouse) and external sources (e.g., competitive set and customers' opinions). This paper presents a framework for a Hospitality Big Data Warehouse (HBDW). The framework includes a (1) Web crawler that periodically accesses targeted websites to automatically extract information from them, and a (2) data model to organize and consolidate the collected data into a HBDW. Additionally, the usefulness of this HBDW to the development of the business analytical tools is discussed, keeping in mind the implementation of the business intelligence (BI) concepts.
- Guia para a proteção e transferência de conhecimento na Universidade do AlgarvePublication . Vairinhos, Sofia; Rodrigues, JoãoO presente Guia apresenta-se como um documento de trabalho apto a auxiliar os processos de transferência de conhecimento. Neste contexto, a presente iniciativa é premente e reflete o trabalho que a Universidade do Algarve (UAlg) tem vindo a assumir na dinamização de processos de proteção de direitos intangíveis e na promoção e apoio à proteção, transferência e valorização do conhecimento gerado. O “Guia para a Proteção e Transferência de Conhecimento da Universidade do Algarve”, representa um contributo para a valorização económica e social dos conhecimentos gerados a partir da Investigação e Desenvolvimento (I&D) na Universidade do Algarve.