Rough Neural Network System and Its Application in Electrocardiogram Auto-recognition

In this paper, a rough neural network system is given and applied in Electrocardiogram auto-recognition. Based on medical requires, this paper has picked up the characteristic parameters of signals from Massachusettes Institute of Technology (database). According to Rough sets theory, the attributes are optimized and studied with BP neural network. In the end, the Electrocardiogram samples are classified with those characteristic parameters. The result shows that the right ratio goes to 90%. The experiment shows that the system has the advantages of fast computation and easy realization and the system is better than other methods in optimizing attributes and enhancing the right ratio of classification.