Eduardo Lázaro Martins Naves

Use of an artificial neural network to predict the incidence of malaria in the city of Cantá, state of Roraima

INTRODUCTION Malaria is endemic in the Brazilian Amazon region, with different risks for each region. The City of Cantá, State of Roraima, presented one of the largest annual parasite indices in Brazil for the entire study period, with a value always greater than 50. The present study aimed to use an artificial neural network to predict the incidence of malaria in this city in order to assist health coordinators in planning and managing resources. METHODS Data were collected on the website of the Ministry of Health, SIVEP--Malaria between 2003 and 2009. An artificial neural network was structured with three neurons in the input layer, two intermediate layers and an output layer with one neuron. A sigmoid activation function was used. In training, the backpropagation method was used, with a learning rate of 0.05 and momentum of 0.01. The stopping criterion was to reach 20,000 cycles or a target of 0.001. The data from 2003 to 2008 were used for training and validation. The results were compared with those from a logistic regression model. RESULTS The results for all periods provided showed that the artificial neural network had a smaller mean square error and absolute error compared with the regression model for the year 2009. CONCLUSIONS The artificial neural network proved to be adequate for a malaria forecasting system in the city studied, determining smaller predictive values with absolute errors compared to the logistic regression model and the actual values.INTRODUCTION: Malaria is endemic in the Brazilian Amazon region, with different risks for each region. The City of Canta, State of Roraima, presented one of the largest annual parasite indices in Brazil for the entire study period, with a value always greater than 50. The present study aimed to use an artificial neural network to predict the incidence of malaria in this city in order to assist health coordinators in planning and managing resources. METHODS: Data were collected on the website of the Ministry of Health, SIVEP - Malaria between 2003 and 2009. An artificial neural network was structured with three neurons in the input layer, two intermediate layers and an output layer with one neuron. A sigmoid activation function was used. In training, the backpropagation method was used, with a learning rate of 0.05 and momentum of 0.01. The stopping criterion was to reach 20,000 cycles or a target of 0.001. The data from 2003 to 2008 were used for training and validation. The results were compared with those from a logistic regression model. RESULTS: The results for all periods provided showed that the artificial neural network had a smaller mean square error and absolute error compared with the regression model for the year 2009. CONCLUSIONS: The artificial neural network proved to be adequate for a malaria forecasting system in the city studied, determining smaller predictive values with absolute errors compared to the logistic regression model and the actual values.

Electric-Powered Wheelchair Control Using Eye Tracking Techniques

This paper presents a system to control an electric-powered wheelchair using the movement of the eye, through an infrared eye tracker sensor. Eye tracking techniques consists in recording the eye movements from a stimulus, and then determining where the individual is gazing at through interpolation of points. Thus, people who have some kind of severe motor disability would be able to control a wheelchair with the help of this technique, acquiring some autonomy in locomotion. According to the results obtained, this technique was a promising alternative to be considered.

REALIDADE VIRTUAL E TECNOLOGIA ASSISTIVA: AMBIENTE SEGURO PARA TREINAMENTO DE CADEIRANTES CONTROLADO POR SINAIS ELETROMIOGRÁFICOS

This work aims to control a virtual wheelchair through surface electromyography signals (sEMG) developed by Silva (2013) [1], being a modular version on a platform that is more flexible and up to date. In addition, this module is part of an integrated system for multimodal control of a wheelchair. The objective is to make the module a training tool for users who will use the sEMG to control a real electricpowered wheelchair (EPW) autonomously and safely. The method used is based on Virtual Reality (VR) to develop an Assistive Technology (AT) and, therefore, it was used a virtual environment created in Unity to develop the interface and system control. The acquisition of the input signal was made using an EMG sensor coupled to a microcontroller with embedded signal processing and filtering.

A QoE assessment method based on EDA, heart rate and EEG of a virtual reality assistive technology system

The1 key aim of various assistive technology (AT) systems is to augment an individuals functioning whilst supporting an enhanced quality of life (QoL). In recent times, we have seen the emergence of Virtual Reality (VR) based assistive technology systems made possible by the availability of commercially available Head Mounted Displays (HMDs). The use of VR for AT aims to support levels of interaction and immersion not previously possibly with more traditional AT solutions. Crucial to the success of these technologies is understanding, from the user perspective, the influencing factors that affect the user Quality of Experience (QoE). In addition to the typical QoE metrics, other factors to consider are human behavior like mental and emotional state, posture and gestures. In terms of trying to objectively quantify such factors, there are wide ranges of wearable sensors that are able to monitor physiological signals and provide reliable data. In this demo, we will capture and present the users EEG, heart Rate, EDA and head motion during the use of AT VR application. The prototype is composed of the sensor and presentation systems: for acquisition of biological signals constituted by wearable sensors and the virtual wheelchair simulator that interfaces to a typical LCD display.

Reconstruction of gait biomechanical parameters using cyclograms and artificial neural networks

Introduction: Historically, assessing the quality of human gait has been a difficult process. Advanced studies can be conducted using modern 3D systems. However, due to their high cost, usage of these 3D systems is still restricted to research environments. 2D systems offer simpler and more affordable solutions. Methods: In this study, the gait of 40 volunteers walking on a treadmill was recorded in the sagittal plane, using a 2D motion capture system. The extracted joint angles data were used to create cyclograms. Sections of the cyclograms were used as inputs to artificial neural networks (ANNs), since they can represent the kinematic behavior of the lower body. This allowed for prediction of future states of the moving body. Results: The results indicate that ANNs can predict the future states of the gait with high accuracy. Both single point and section predictions were successfully performed. Pearson’s correlation coefficient and matched-pairs t-test ensured that the results were statistically significant. Conclusion: The combined use of ANNs and simple, accessible hardware is of great value in clinical practice. The use of cyclograms facilitates the analysis, as several gait characteristics can be easily recognized by their geometric shape. The predictive model presented in this paper facilitates generation of data that can be used in robotic locomotion therapy as a control signal or feedback element, aiding in the rehabilitation process of patients with motor dysfunction. The system proposes an interesting tool that can be explored to increase rehabilitation possibilities, providing better quality of life to patients.

Measurement of post-stroke spasticity based on tonic stretch reflex threshold: implications of stretch velocity for clinical practice

Abstract Purpose: The most commonly used method for the clinical evaluation of spasticity is the modified Ashworth scale (MAS), which is subjective. In this regard, the spasticity assessment through the tonic stretch reflex threshold, which is an objective method, has emerged as an alternative. It is based on the value of the dynamic stretch reflex threshold, which is measured at different stretch velocities. However, by this definition, it is not possible to define the speed at which passive stretches should be performed during evaluation. Objective: This study aimed to evaluate whether the speed-variation sequence used to acquire the dynamic stretch reflex threshold influences the tonic stretch reflex threshold (TSRT) and, consequently, the estimation of spasticity by this method. Methods: Three forms of stretching-variation speed were adopted, i.e., increasing, decreasing, and randomised. The study was performed using 10 post-stroke patients. Results and Conclusions: The results showed that the stretch protocols were not all the same and that the method of increasing was most suitable for performing manual passive stretches to evaluate TSRT in these patients. Another analysis was the correlation between MAS and tonic stretch reflex threshold; a weak correlation was observed between the increasing and decreasing methods, and moderate correlation was observed between the random methods. Implications for Rehabilitation We demonstrated that the protocol of execution of passive stretches influences in the measurement of the tonic stretch reflex threshold (TSRT). We recommend the method of increasing velocity for performing manual passive stretches. We also build software with a reliable biological data acquisition system, which makes acquisition and processing of data in real time. In this way, the TSRT is a promising quantitative measure to assess post-stroke spasticity, calculated automatically. We also we provided the use of portable instruments to facilitate the assessment of spasticity in clinical practice.

PROPOSTA DE UM DISPOSITIVO PARA COMUNICAÇÃO AUMENTADA ALTERNATIVA

To ensure a good social life, it is necessary for people to be able to transmit information so that it can be correctly understood. Communication can be verbal, in the form of speech or writing, or nonverbal, through body language. When diagnosing the communication disability of a person, it’s possible to help increase and/or improve the communication through the creation of augmented and alternative communication devices (AAC). The goal of this work is to propose a method for the creation of an AAC device with a centered-user design, in which the main characteristics are portability and low cost, using the available technologies. A questionnaire was applied and the results showed that the devices used by the interviewed patients do not fully attend their needs, showing an importance of the development of a new AAC device. This way, it’s expected that the proposed methodology of this study should be used to create a new AAC device that can comply with the real needs of the users.

CONTROLE DE CADEIRA DE RODAS MOTORIZADA POR MEIO DE COMANDOS MUSCULARES FACIAIS VIA TABLET

This paper introduces the development of an application to control a wheelchair through electromyographic signals from the masseter muscle. Electromyography is the analysis of muscle activity, and has numerous applications, including studies in Assistive Technology (AT). A technological advance in this area has allowed greater independence, higher quality of life and social inclusion for people with disabilities. Thus, it is possible to implement electromyography devices to facilitate the control of motorized wheelchairs, for people with more severe disabilities. The system consists of an electromyography sensor Myoware, an Arduino for analysis of the signal acquired by the sensor, a tablet, to display an interface to show the activities for the user and an adapted wheelchair.

Is it possible to identify the gender and age group of adults from gait analysis with hip-knee cyclograms?

INTRODUCTION: Cyclograms are gait analysis tools that characterize the geometric aspect of the pattern of locomotion. Cyclograms are angle-angle diagrams that are very useful for representing cyclic patterns such as walking. This study is based on the hypothesis that parameters extracted from hip-knee cyclograms of individuals walking on a treadmill with 0° and 5° slopes can be used to determine the age group and sex of the volunteers. METHODS: In total, 40 physically active healthy adult volunteers, 20 young people (10 of each gender) and 20 elderly (10 of each gender), were divided into 4 groups, and the average value of area (A), perimeter (P) and the ratio P/√A of cyclogram were calculated, as well as the speed and cadence. RESULTS: The young male (YM) speeds were higher than the elderly male (EM) speeds (p=0.00), and the young female (YF) speeds were higher than the elderly female (EF) speeds (p=0.00). No difference in speed was found between YM and YF (p=0.59) or between EM and EF (p=0.95). The parameters extracted directly from the cyclogram allowed us to distinguish the studied groups according to age group (p 0.51). CONCLUSION: The hypothesis was partially confirmed because parameters extracted from the hip-knee cyclograms could differentiate volunteers by age group but not gender.