Portable electrocardiograph through android application.

An electrocardiograph was designed and implemented, being capable of obtaining electrical signals from the heart, and sending this data via Bluetooth to a tablet, in which the signals are graphically shown. The user interface is developed as an Android application. Because of the technological progress and the increasing use of full portable systems, such as tablets and cell phones, it is important to understand the functioning and development of an application, which provides a basis for conducting studies using this technology as an interface. The project development includes concepts of electronics and its application to achieve a portable and functional final project, besides using a specific programmable integrated circuit for electrocardiogram, electroencephalogram and electromyogram, the ADS1294. Using a simulator of cardiac signals, 36 different waveforms were recorded, including normal sinus rhythm, arrhythmias and artifacts. Simulations include variations of heart rate from 30 to 190 beats per minute (BPM), with variations in peak amplitude of 1 mV to 2 mV. Tests were performed with a subject at rest and in motion, observing the signals obtained and the damage to their interpretation due to the introduction of muscle movement artifacts in motion situations.

Upper-limb movement classification based on sEMG signal validation with continuous channel selection.

This paper aims to provide an efficient, automatic and auto-adaptive approach to establish a continuous electromyography (EMG) signal monitoring, to constantly identify an optimal electrode assortment to use as input of a pattern recognition method through time. The average classification accuracy for the adaptive input selection method was 83,96±5,79% against 72,06±7,15% in a non-adaptive system. Both systems make use of a neural network to classify 9 distinguish upper-limb movements.