 |
PhD student of university of technology designing real-time diagnostics system's electrical diagrams of the human heart |
PhD student of university of technology designing real-time diagnostics system's electrical diagrams of the human heart
The researcher who gained his PhD appreciated with high degree his tagged: (design and implementation of real-time diagnosis of the image graphic electric heart of the system based on arrays of logic gates of programmable on site) to build a real-time diagnosis system's of the image graphic electric heart for the classification of eight cases of heart disease, high accuracy.
He suggested four workbooks for heart disease, three of which traditionally are the entry decision (TD) multilayer neural cognitive and network (MLP), machinery directed support (SVM) The other, which were proposed for the first time in the diagnosis of graphic electric heart is: the neural network non-existent weight to apparent generalizable digital virtual RAM.
The results of the simulations of the four works the adoption of the database (MIT-BIH) that the highest success rate for the classification of cardiac cases have been obtained using seed NVG-RAM, a 100%, followed by seeded TD and who achieved a pass rate of 97.06%, as well as enable the researcher to conduct the practical implementation of the work TD seeded NVG-RAM with higher rates of success on the physical device Spartan-3A DSP 3400A using logic gates programmable in situ (FPGA).
|
|
