No abstract

The development of a hybrid solution (hardware and software) integrating a computer and the Kinect sensor is presents in this paper. The solution proposed, here called GoNet, is a promising prototype to be used in dynamic and automatic evaluation of biomechanical rehabilitation processes. Experimental tests concerning the assessment of the range of motion of patients, particularly for elbow flexion, elbow extension, shoulder abduction, shoulder flexion, radial deviation and ulnar deviation, are presented and discussed. Eight healthy subjects were assessed using GoNet and a goniometer. The intraclass correlation coefficient (ICC) was used to analyze the reproducibility, and the Pearson correlation test was used in the analysis of transversal validity. The significance level was defined as equal to 5%. As to the intra-and inter-examiner reproducibility, high ICC values were found for the range of motion of shoulder flexion/extension, shoulder abduction/adduction, radial deviation and ulnar deviation. When evaluated by two experts the correlation between the goniometry and GoNet, significant results were observed for the amplitude of shoulder flexion/extension (r = 0.74; p = 0.03) and elbow flexion/extension (r = 0.67, p = 0.04). Based on the results obtained, GoNet proved to have high reproducibility, except for intraexaminer assessment of elbow flexion/extension. Regarding the transverse validity, relevant measurement results were found in terms of flexion/extension of the elbow and shoulder.

Prostheses play an important role in the rehabilitation of people who have suffered some type of amputation. However, due to its high‐cost and high complexity in performing movements of everyday tasks, users of these prostheses may encounter many difficulties. Therefore, this work proposes the development of a future artificial intelligence technology based on a low‐cost functional prosthesis prototype (manufactured in a 3D printer). In the present work, we describe an intelligent system that uses an artificial neural network to recognize patterns in muscle biopotential signals in order to control a prosthesis prototype in real time. Such a system is divided into three parts: the first that performs a human–machine integration through a graphical user interface; the second that performs the signal acquisition; the third that performs the training and generalization steps of the artificial neural network. The developed interface runs on a web application that has a database hosted in the cloud and in it the system user can: Acquisition of electromyography signals; Training phase of the artificial neural network; Sends the matrix of weights of the trained network to the microcontroller; Activates in the microcontroller, the state of action of the commands from the identified gestures. To compose the results of the present work, a search was initially carried out for the ideal parameters of the artificial neural network through signals obtained from 20 volunteers. In this step, it was possible to identify the topology that best classifies the signals of each gesture, as well as the investigation of the number of neurons in the hidden layer that causes a low generalization power due to overfitting. At the end of the project, it was possible to validate the use of the system with 15 new volunteers, and it was observed that in most cases, the performance of the commands in the prosthesis prototype were performed correctly. In addition, a project cost analysis was carried out, and it was possible to verify that the prototype developed is viable and has an affordable cost in relation to the Brazilian cost of living standards. In this way, the objective of the present work is in the development of a low cost artificial intelligence technology. Such a system is equipped with an algorithm based on neural networks that can deal with different muscle biopotential signals, in order to command a robotic prosthesis.

Modo de acesso: World Wide WebInclui bibliografia 1. Engenharia 2. Educação.I. Título CDD-620O conteúdo dos artigos e seus dados em sua forma, correção e confiabilidade são de responsabilidade exclusiva dos seus respectivos autores.

BACKGROUND Type 1 diabetes (T1DM) is a chronic disease with epidemic proportions and raising incidence. Persistent autoimmunity against beta cells may be present many years before the clinical onset of the disease and is considered the first stage of T1DM. Attempts have been made to modify the natural history of T1DM through intervention studies in stages 1 and 2 of the disease. However, difficulties related to underdiagnosis, high costs and low recruitment rates are important limiting factors in carrying out these studies. Using computer technology may be an efficient way to achieve this goal. However, in the best of our knowledge, the PRE1BRAZIL is the first App developed and validated to support a fully automated multicenter prevention trial in T1DM patients. Dipeptidyl peptidase-4 inhibitors are safe and well-tolerated drugs, potentially capable of slowing the progression of T1DM. OBJECTIVE To develop and validate the PRE1BRAZIL, a web application (``App``) designed to perform an automated randomized clinical trial (RCT) with dipeptidyl peptidase-4 inhibitors (DPP-4i) in patients with stage 2 type 1 diabetes (T1DM). METHODS The RCT protocols guided the design of non-functional App requirements. A user-centered development approach was used. The App functional project was divided into two components: the web questionnaire, where patients' data will be entered; and the Web Control Panel (WBC) that will display and export the data to a spreadsheet. FrontEnd, BackEnd, and Database are the three WBC components. After web App design and development, a validation study was performed with 20 evaluators. RESULTS The validation test results showed a high usability and efficiency of the App, with high agreement rating between expert judges and target users. This app is able to support all RCT phases, from enrollment and randomization to report adverse events, and 85% of respondents agreeing that this app would be useful to facilitate your participation as a researcher. CONCLUSIONS This is the first web App developed and validated to support a fully automated T1DM prevention trial, which presented an excellent usability and efficiency profile. This technologies is expected to optimize patient allocation, data analysis, and reduce trial costs.