The objective of this work was to evaluate a group of classificcation algorhytms that allow us to solve the problem of recognition for hand-written digits. We used WEKA tools and algorhytms implemented with it. We worked with MNIST data base which includes 60000 îmages in numbers (de 28x28 pixels) for training and 10000 for validation with exits labeled from O to 9. In order to reduce the high dimensionality of data bases we applied techniques for analysis of principal components (PCA) and extract the most important characteristics with which we made tests.

This study shows the results of investigations to determine harmonics in electrical current through the use of Artificial Neural Networks (ANN) using the methods of Feedforward-Backpropagation through a generator of electrical signals in C# (C Sharp). We studied the causes of current harmonics, what a re its implications in everyday work and filters to attenuate these harmonics. For generation of harmonics, we implemented a transmitter of electrical signals by software, also developed in C# (C Sharp) so as to obtain raw and real data as possible, in order to perform tests for simulating errors in the signal power that occur in real time and then process this data.It was determined that the best method for the detection of harmonics using Artificial Neural Networks is Feedforward — Backpropagation with supervised training in order to handle the input and output to get a better result.Th...