Loading...
33 results
Search Results
Now showing 1 - 10 of 33
- Nutrition Control System Based on Short-term Personal DemandsPublication . Cunha, Carlos; P. Duarte, Rui; Oliveira, RafaelPersonalized nutrition considers an individual’s unique genetic, metabolic, and lifestyle factors to create a customized dietary plan tailored to their needs. People seeking to optimize their health and wellness through diet and lifestyle changes can benefit from technological advances in machine learning and deep learning approaches to create personalized models of nutritional requirements that override traditional food plans. These models will provide users with an unprecedented decision tool for informing them of the impact of specific food intake and exercise on their goals. This article presents the architecture, implementation, and preliminary results of a deep learning-based control system for nutrition. It allows users to understand the impact of their food and exercise immediate choices on their goals while reducing user interaction demands. Preliminary results have shown that it is possible to predict BMI (Body Mass Index) accurately within a time window of three days.
- Automatic Camera Calibration Using a Single Image to extract Intrinsic and Extrinsic ParametersPublication . P. Duarte, Rui; Cunha, Carlos; Pereira Cardoso, José CarlosThis article presents a methodology for accurately locating vanishing points in undistorted images, enabling the determination of a camera's intrinsic and extrinsic parameters as well as facilitating measurements within the image. Additionally, the development of a vanishing point filtering algorithm is introduced. The algorithm's effectiveness is validated by extracting real-world coordinates using only three points and their corresponding distances. Finally, the obtained vanishing points are compared with extrinsic parameters derived from multiple objects and with intrinsic parameters obtained from various shapes and images sourced from different test sites. Results show that through a single image, the intrinsic parameters are extracted accurately. Moreover, Using 3 points to determine the extrinsic parameters is an excellent alternative to the checkerboard, making the method more practical since it does not imply the manual positioning of the checkerboard to perform the camera calibration.
- KLM-GOMS Detection of Interaction Patterns Through the Execution of Unplanned TasksPublication . Cunha, Daniel; P. Duarte, Rui; Cunha, Carlos A.The availability of software applications has contributed to the increase in user demand, which has increased the complexity of these applications. This contributed to the adoption of automation mechanisms for the software testing process, in order to reduce coding errors and shorten the time needed to deploy a new version of the application to the user. Currently, automating the application testing process is a well-established reality and supported by many tools. However, the usability evaluation of an application requires solutions that allow to determine, in advance, the type of improvements that may be necessary in the application without the need for intensive user testing. This work deals with the automatic analysis of the impact on the user of changes in the design of an application, through the implementation of the Keystroke Level Model (KLM). Based on the execution of unplanned user interactions in a web interface, a KLM string is obtained and evaluated, providing a model that converts KLM operators and the execution time of each operator into information for designers. Moreover, performance indicators are obtained and interaction patterns are automatically defined.
- Play, Algorithmic Thinking and Early Childhood Education: Challenges in the Portuguese ContextPublication . Figueiredo, Maria Pacheco; Gomes, Cristina Azevedo; Amante, Susana; Gomes, Helena Margarida dos Santos Vasconcelos; Alves, Valter; Duarte; Rego, BelmiroALGOLITTLE is an EU-funded project, with partners from Portugal, Italy, Turkey, and Slovenia, supporting the integration of algorithmic thinking skills into preschool education for preparing future code literates from an early age. The paper presents the project and frames it in Portuguese Early Childhood Education. First, in terms of curricular areas and pedagogical approach, through a content analysis of the Portuguese Curricular Guidelines for Preschool Education. Second, by analyzing initiatives and projects that are connected to algorithmic thinking in Early Childhood Education in Portugal. Third, by presenting challenges that emerged from a set of discussions with several participants, highlighting the complexity and timeliness of the project.
- Time Domain Analysis of Geometrically Nonlinear Vibrations of Composite Laminated Plates by the Hierarchical Finite Element MethodPublication . P. Duarte, Rui; Ribeiro, P.Composite laminated plates are employed in many areas of engineering such as aeronautics, space engineering and naval industry [1,2,3]. For example in aircrafts they are submitted to large acoustic, aerodynamic and inertia excitations and therefore experience vibrations with large amplitude, i.e., in the geometrically nonlinear regime. Vibrations with large amplitude cause large stresses and the diminution of life due to fatigue. Quasi periodic and chaotic behaviours are other possible consequences of non-linearity, completely ignored by the linear models which are normally used in engineering design. Non-symmetrical laminated plates have been rarely studied, particularly in non-linear dynamics. In this work, a hierarchical finite element, in which the model is improved by increasing the number of shape functions in each element, is formulated. The element is general, in the sense that it applies to symmetric or asymmetric plates. Compared with h-version elements, it has the major advantages of requiring a small number of degrees of freedom for accuracy and of being free from shear locking. Different shear deformation theories (SDT) have been developed to include the effect of transverse shear deformation [1,2,3]. The first order shear deformation laminated plate theory is followed here. Hence, Kirchhoff's hypothesis [4] is relaxed by removing the third part, that is the transverse normals do not remain perpendicular to the mid-surface after deformation. 1 2 3 4 5 6 7 8 9 In this paper, the shape functions used are the Legendre polynomials in the Rodrigue's form [5,6,7,8,9]. A different number of transverse, middle plane, rotation about y and rotation about x, displacement shape functions are employed, and the convergence of the linear natural frequencies studied. Two symmetric, rectangular, graphite/epoxy composite laminated plates with constant thickness , width and length , composed of orthotropic layers oriented at different angles are considered. The element derived is employed to study the non-linear dynamic behaviour of some these laminated plates, in the time domain. The direct integration of the system of equations of motion is carried out by Newmark's method. In order to uncover the characteristics of the motions computed, time plots, phase planes and Fourier spectra are defined. For different fibre orientations, it is confirmed that the linear natural frequencies of the thick plate model are smaller than the thin plate ones. Harmonic excitations are applied, and the responses of the plates are determined with a reasonable computational cost, due to the reduced number of degrees of freedom of the model. For amplitudes of vibration much lower than the thickness of the plate, the solutions found are always periodic and highly dominated by the harmonic with frequency equal to the excitation frequency (principal harmonic). Increasing the force applied, the response amplitude increased in a non-linear way, the motions found are still periodic, but the time and phase plots show that higher harmonics are important.
- Real-time simulation of cumulus clouds through SkewT/LogP diagramsPublication . P. Duarte, Rui; Gomes, Abel J.P.Modeling, simulation, and realistic rendering of natural phenomena have been important goals in computer graphics for decades. Clouds, as a natural phenomenon, represent a real challenge because their birth, life, and death are amorphous and dynamic in nature. As a consequence, cloud simulation is very time-consuming when using physically-based methods. This paper presents a real-time cloud simulation method based on SkewT/LogP diagrams to overcome this time performance problem. These diagrams allow us to simulate 3D clouds from sounding data made public worldwide by weather agencies. More specifically, a SkewT/LogP diagram describes the vertical motion of a cloud in the atmosphere, i.e., our cloud simulator system is based on physics but avoids solving differential equations of cloud motion to achieve real-time rates. We have also built a visual tool for 2D SkewT/LogP diagrams that allows us to inspect, control and simulate the thermodynamic process of ascending clouds in the atmosphere, as well as a 3D synthetic environment where clouds are advected by buoyant forces. This lightweight physicallybased technique enables the incorporation of our cloud simulator in systems tied to important industries, namely movies, virtual environments, and video games.
- Multi-Device Nutrition ControlPublication . Cunha, Carlos A. S.; P. Duarte, RuiPrecision nutrition is a popular eHealth topic among several groups, such as athletes, 1 people with dementia, rare diseases, diabetes, and overweight. Its implementation demands tight 2 nutrition control, starting with nutritionists who build up food plans for specific groups or individuals. 3 Each person then follows the food plan by preparing meals and logging all food and water intake. 4 However, the discipline demanded to follow food plans and log food intake turns out into high 5 dropout rates. This article presents the concepts, requirements, and architecture of a solution that 6 assists the nutritionist in building up and revising food plans and the user following them. It does 7 so by minimizing human-computer interaction by integrating the nutritionist and user systems 8 and introducing off-the-shelf IoT devices in the system, such as temperature sensors, smartwatches, 9 smartphones, and smart bottles. An interaction time analysis using the Keystroke Level Model 10 provides a baseline for comparison in future work addressing both the use of machine learning and 11 IoT devices to reduce the interaction effort of users.
- Progressive Sophistication of Communication and Interaction in Videogames for Children and Young People with Autism Spectrum DisorderPublication . Alves, Valter; P. Duarte, RuiChildren and young people with Autism Spectrum Disorder (ASD) often struggle with communication and social interaction skills (Hyman et al., 2020). Studies show benefits for people with ASD from playing videogames (Baldassarri et al., 2020; Malinverni et al., 2017). Still, current solutions targeting this audience tend to assume and expose educational goals (e.g., Zakari et al., 2014). We’ve been researching and developing guidance on how to design videogames with the potential to improve those skills while providing experiences that players can perceived as purely ludic. Previously, we distilled a set of six guidelines (Alves et al., 2021) that we were able to put into practice in specific games. However, the guideline that suggests to “focus level design on the progressive sophistication of communication and interaction” has been more challenging. To a certain extent this can be attributed to the scale of the projects in which we were able to experiment with that guideline, so far, which did not allow the team to reach its full implementation. We realised that while the other guidelines can be applied right from early stages and in small developments, this guideline, consistently with what it suggests, implies more complexity, at least to include alternate ways to perform some game actions. The acknowledgement of this disparity and the desire to provide tangible instantiations of that “sophistication”, led us to dedicate even more attention to this aspect and to systematize some major ideas so that we can share them while we are also working in their application. A key point of our proposal is that the introduction of more complex ways to communicate and interact is meant to allow players to engage in new strategies (more challenging but also more advantageous), if/when they are willing to try them, but previous alternatives should remain as usable. The specificities of the target users demand a cautious approach to changes and to the anxiety implied by risking and possibly failing. Players should be able to mix the alternatives and go back and forth in complexity, according to what they are prepared to invest in each specific circumstance. Another important aspect is that the unfolding of new alternatives, regarding communication and interaction, should be triggered by each player’s behaviour patterns and not directly by the game levels common to all players. This implies to rethink or complement conventional patterns for game level design. Currently, we are working on ways to enrich the tools for players to communicate and interact. The underlaying ideas are not innovative per se, in the sense that we can reference games (for the general public) that integrate them in some way or context. Our argument is that it is relevant to assemble and redesign them, considering the specific purpose of this research. For instance, in previous experiments we understood that it would be relevant that a player (playing character) could signal other players an interest in their collaboration or proximity. This would support that kind of proactivity (should it emerge) while influencing others to interact. We also consider very worth integrating mechanisms that allow expressing empathy towards other characters, or other emotional displays. Again, many games embed solutions that include predefined messages and/or graphics (e.g. emojis), but the specificities of our target audience require that the system is tailored in a way that is suitable and may contribute to developing this type of externalization of one’s feelings. Ultimately, it would be relevant to test a message system closer to an in-game chat, for more advanced levels of communication. Finally, we are also very interested in further integrating trading systems, common to many games, as a way to entice players to interact.
- Are you lost? Using Facial Recognition to Detect Customer Emotions in Retail StoresPublication . Borges, Valter; P. Duarte, Rui; Cunha, Carlos; Mota, David; ThinkmindThe understanding of consumer behavior is a dynamic field, especially relevant to the success of companies and for consumer satisfaction. It is especially important in the situation of intense competition, currently characteristic for the retail store industry, where companies fight for every individual customer. Moreover, companies do not want customers to enter their system and leave without buying products they intended to buy. This has an impact on user satisfaction and retail stores income. In this paper we present a method that targets customer satisfaction in the aforementioned context using a facial recognition system acting at the emotional level of the customer. Our method is based on cumulative negative emotions that are associated to a sadness level, which triggers events for retail store assistants to help customers. Results show that this method is adequate to measure these emotions and is a useful reference for retail store assistant intervention.
- Automatic User Testing and Emotion Detection in Interactive Urban DevicesPublication . P. Duarte, Rui; Cunha, Carlos; Pereira Cardoso, José CarlosAutomated testing and evaluation of interfaces is a well-established reality supported by many tools that shorten the time to deploy new software versions to the user. However, exploring users’ emotions while interacting with interfaces as a tool to further increase the quality of traditional usability evaluation methods is still far from being a reality. This work uses the automatic analysis of users’ emotions while interacting with touchable interactive urban devices to detect usability issues. To this end, a coupled approach is implemented: the data is acquired from the interaction, and user emotions are extracted and processed to determine the emotional status during the interaction. This data is integrated into a web application so that designers can further improve the quality of the interface in the presence of negative emotions. Results show that the experimental tests showed that different users manifest similar negative emotions in the same contexts, which is a clear sign of usability issues that are to be corrected by the design team.