2018
Authors
Saraiva, AA; Fonseca Ferreira, NM; Valente, A;
Publication
Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 1: BIODEVICES, Funchal, Madeira, Portugal, January 19-21, 2018.
Abstract
The article refers to a new model of genetic algorithm. The method used has finality of optimize the filtering of artifacts in DICOM images in two-steps.The first step is constituted by filterings with BM4D, 3d median filter and ellipsoid filter. The second step is formed by the application of operators of simple mutations in the previously recovered image, for that was used: intensity change, gaussian filter and mean filter. As a result, a better performance filter was obtained and which provides an improvement in diagnosis, in diseases assessment and in decisions making by the professional. Copyright
2018
Authors
Saraiva, AA; Nogueira, AT; Ferreira, NMF; Valente, A;
Publication
2018 IEEE 6TH INTERNATIONAL CONFERENCE ON SERIOUS GAMES AND APPLICATIONS FOR HEALTH (SEGAH '18)
Abstract
This work presents a technique that uses the immersion of patients in an interactive 3D virtual environment in the orthoptic treatment of strabismus. The most important part of this work is the act of forcing the eyes to cooperate, increasing the level of adaptation of the nervous system to the binocular vision, allowing the diverted eye to be rehabilitated. Returning to the patient better visual comfort and quality of life. The virtual environment, because it is attractive, has the function of entertainment, possessing as its property the ability to propose challenges directed towards specific objectives. In addition to offering real-time biological feedback to the healthcare professional who is making use of this product. Another point is that this interface has ideal approaches to be used in orthoptic treatment. And all of it was developed with free software and made by a low-cost virtual reality glasses, Google Cardboard, which uses a smartphone as a display for its display.
2018
Authors
Saraiva, AA; Barros, MP; Nogueira, AT; Fonseca Ferreira, NMF; Valente, A;
Publication
INFORMATION
Abstract
This study presents a technique that uses an interactive virtual environment for the rehabilitation treatment of patients with mechanical strabismus and/or amblyopia who have lost eye movement. The relevant part of this treatment is the act of forcing the two eyes to cooperate with each other by increasing the level of adaptation of the brain and allowing the weak eye to see again. Accordingly, the game enables both eyes to work together, providing the patient with better visual comfort and life quality. In addition, the virtual environment is attractive and has the ability to overcome specific challenges with real-time feedback, coinciding with ideal approaches for use in ocular rehabilitation. The entire game was developed with free software and the 3D environment, which is made from low-cost virtual reality glasses, as well as Google Cardboard which uses a smartphone for the display of the game. The method presented was tested in 41 male and female patients, aged 8 to 39 years, and resulted in the success of 40 patients. The method proved to be feasible and accessible as a tool for the treatment of amblyopia and strabismus. The project was registered in the Brazil platform and approved by the ethics committee of the State University of Piaui-UESPI, with the CAAE identification code: 37802114.8.0000.5209.
2018
Authors
Saraiva, AA; Nascimento, RC; Sousa, JVM; Soares, S; Vital, JPM; Ferreira, NMF; Valente, A; Barroso, J;
Publication
PROCEEDINGS OF THE 2018 2ND INTERNATIONAL CONFERENCE ON TECHNOLOGY AND INNOVATION IN SPORTS, HEALTH AND WELLBEING (TISHW)
Abstract
This article is devoted to the problem of training cyclists from a system approach. Technologies were used to monitor and evaluate in an integrated way the physical form, load parameters and level of functional capabilities of the athlete's body. For correlation between the physiological indices and performance, data from cardiac activity (ECG), muscle activity (EMG and temperature), respiratory processes (oximetry), as well as data from the environment where this athlete is inserted (ambient temperature, pressure, humidity).
2018
Authors
Vital, JPM; Fonseca Ferreira, NMF; Soares, SFSP; Valente, A; Pereira Barroso, JMP;
Publication
PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON SOFTWARE DEVELOPMENT AND TECHNOLOGIES FOR ENHANCING ACCESSIBILITY AND FIGHTING INFO-EXCLUSION (DSAI 2018)
Abstract
Kinematic analysis of human movement is very important in several areas, such as in sports (e.g., for athletic performance analysis), health (e.g., rehabilitation of people with motor disabilities) and others. The study of the kinematics of the human body involves several methods that resort to the analysis of several parameters that come from the movement. Important parameters to take into account are the acceleration, velocity and position (linear or angular) of the various articulations of the human body, which can be measured by sensors or through the analysis of repeated images obtained by camera. In this paper will be presented a suit that acquire the different position of human joints that will be useful in rehabilitation, FatoXtract. It is through the analysis of human movement that we can analyze whether the movement in rehabilitation is adequate or not.
2018
Authors
Campaniço, AT; Valente, A; Serôdio, R; Escalera, S;
Publication
Motricidade
Abstract
The study explores the technical optimization of an athlete through the use of intelligent system performance metrics that produce information obtained from inertial sensors associated to the coach's technical qualifications in real time, using Mixed Methods and Machine Learning. The purpose of this study is to illustrate, from the confusion matrices, the different performance metrics that provide information of high pertinence for the sports training in context. 2000 technical fencing actions with two levels of complexity were performed, captured through a single sensor applied in the armed hand and, simultaneously, the gesture’s qualification through a dichotomous way by the coach. The signals were divided into segments through Dynamic Time Warping, with the resulting extracted characteristics and qualitative assessments being fed to a Neural Network to learn the patterns inherent to a good or poor execution. The performance analysis of the resulting models returned a prediction accuracy of 76.6% and 72.7% for each exercise, but other metrics indicate the existence of high bias in the data. The study demonstrates the potential of intelligent algorithms to uncover trends not captured by other statistical methods. © Edições Desafio Singular.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.