Repositório Comunidade: CALG
https://hdl.handle.net/1822/14394
CALG2024-03-28T10:09:31ZDesenvolvimento de uma aplicação móvel de monitorização de calorias para Linux Ubuntu Touch
https://hdl.handle.net/1822/90218
Título: Desenvolvimento de uma aplicação móvel de monitorização de calorias para Linux Ubuntu Touch
Autor: Fernandes, Ivo; Pereira, José Luís
Resumo: A necessidade de complementar a oferta de aplicações na loja da Ubuntu Touch representa uma oportunidade de desenvolvimento de aplicações inovadoras e com interesse para a comunidade de potenciais utilizadores. Este artigo, descreve o trabalho realizado no âmbito de uma dissertação de mestrado onde se desenvolveu uma aplicação open-source para monitorização das calorias consumidas diariamente por um utilizador. Como processo de desenvolvimento recorreu-se ao Scrum Solo. Os requisitos funcionais e não-funcionais da aplicação foram definidos por diversos product owners, tendo sido todos implementados. Após um período de testes preliminares concluiu-se que a aplicação desenvolvida apresenta funcionalidades relevantes e diferenciadoras de outras aplicações similares disponíveis na loja da Ubuntu Touch.; The need to complement the offer of applications in the Ubuntu Touch store represents an
opportunity to develop innovative applications of interest to the community of potential users.
This article describes the work carried out within the scope of a master's thesis where an open source application was developed to monitor the calories consumed daily by a user. As a
development process, Scrum Solo was used. The application's functional and non-functional
requirements were defined by several product owners, all of which were implemented. After a
period of preliminary tests, it was concluded that the developed application presents relevant
and differentiating features from other similar applications available in the Ubuntu Touch store.
<b>Tipo</b>: conferencePaper2024-03-28T09:29:26ZApplying SWARA approach and refined Kano model to classify and rank customer requirements, case study: automotive industry in Portugal
https://hdl.handle.net/1822/90217
Título: Applying SWARA approach and refined Kano model to classify and rank customer requirements, case study: automotive industry in Portugal
Autor: Hariri, Ahmad; Domingues, José Pedro Teixeira; Sampaio, Paulo
Resumo: Companies aim to increase the quality of products and competitiveness to gain and retain customers. This study proposes a new approach for identifying and prioritising customer requirements (CRs) to improve black uniformity as a luminance characteristic on the surface of a display by evaluating the CRs. The refined Kano and stepwise weight assessment ratio analysis (SWARA) was applied to rank the 112 CRs identified into main categories: 1) technical; 2) quality; 3) delivery; 4) sustainability; 5) cost to develop the product. To validate the approach, an example is performed on automotive display’ CRs. The findings showed that mechanical and delivery CRs are critical. Today, climate change is a significant challenge and a severe customer concern. Although sustainability of CRs is not classed as essential items in the production process, suppliers must be diligent in providing them. The results help to improve the automotive industry and other production systems.
<b>Tipo</b>: articleFeature selection optimization for heart rate variability
https://hdl.handle.net/1822/90216
Título: Feature selection optimization for heart rate variability
Autor: Antunes, Ana Rita Oliveira; Silva, Joaquim P.; Braga, A. C.; Gonçalves, Joaquim
Resumo: Feature selection optimization has gained attention since it helps extract good insights about a given subject. It is commonly used to reduce the dimensionality of the problem and to identify the best combination of features with aim of improving the prediction or classification model performance. Thereby, the present study intended to determine the best subset of features to classify the drowsiness state, into awake and drowsy, considering the heart rate variability. This approach is a gap in the literature since the studies available only classify the drowsy state without understanding which features have more impact on the transition from awake to drowsy. Single-objective optimization was performed using the genetic algorithm, with the purpose of maximizing accuracy, F1 score, and recall. Different machine learning algorithms were computed, and comparisons were made. Therefore, logistic regression and the extra tree algorithms had the best results for all the evaluation metrics. The best results were achieved with fewer heart rate variability features than initially introduced. With the proposed methodology it was possible to identify 13 features that occurred most to classify the drowsiness state. Where from the time, frequency, and nonlinear domains there were 6, 5, and 2 features, respectively. As future work, time series must be implemented to verify if it is possible to predict the drowsiness state and visualize trends and seasonality.
<b>Tipo</b>: conferencePaperDrowsiness detection using multivariate statistical process control
https://hdl.handle.net/1822/90215
Título: Drowsiness detection using multivariate statistical process control
Autor: Antunes, Ana Rita Oliveira; Braga, A. C.; Gonçalves, Joaquim
Resumo: Drowsiness at the wheel has been studied for different countries since it is important for road safety and its prevention. Since it is considered a public health problem, solutions must be found to avoid worse scenarios and to identify a low-cost system. Therefore, this work aims to detect the drowsy state, without labeling it manually, considering the heart rate variability. To make this possible, driving simulations were performed, using a wearable device. In terms of methodology, multivariate statistical process control, considering principal component analysis, was implemented, and compared with a similar study. Three principal components were computed taking into consideration time, frequency, and non-linear domain, every two minutes. Thereafter, Hotelling T2 and squared prediction error statistics were estimated. These statistics were estimated considering each principal component, individually. Thereby, the results achieved seemed to be promising to identify drowsiness peaks. However, the study developed has limitations, like the identification of points out-of-control occurred due to signal noise and it does not identify all the drowsiness peaks. Conversely, it was not used information from the participants’ awake states as a reference. Therewith, new simulations must be done, and new information must be added to avoid noise and to detect more drowsiness peaks.
<b>Tipo</b>: conferencePaperTrajectory tracking for the inspection of deformable objects considering manipulability of a 7-DoF serial manipulator
https://hdl.handle.net/1822/90212
Título: Trajectory tracking for the inspection of deformable objects considering manipulability of a 7-DoF serial manipulator
Autor: Borges, Carlos; Ribeiro, Jose; Louro, Luis; Vicente, Paulo; Faria, Carlos; Monteiro, Sergio; Bicho, Estela
Resumo: This work deals with the manipulation of deformable objects for defect inspection purposes. The required inspection movements, obtained from mimicking demonstrated trajectories, are realized with a 7-DoF serial arm and a fixed grasp support. These trajectories can be realized in different zones, as such, we use this freedom, with the various possibilities for the inverse kinematics problem and the elbow redundancy, to increase the distance to joint limits and singularities. Thus, we present a novel trajectory tracking method that leads to a high manipulability in each pose of the trajectory, facilitating the implementation of an online correction system. To achieve all this, we use a state-of-the-art approach as a base, but we extend it to consider the continuity of the arm angle in its domain boundary. Moreover, we propose a computer vision-based method to obtain the trajectories. This uses information from the demonstrator's hands to obtain position data and from the deformable object to get orientations. As main results, we could replicate the inspection movements and necessary deformations, achieving a high manipulability in each pose of the followed trajectories.
<b>Tipo</b>: conferencePaper2024-03-27T19:57:27Z