Applications of DSP James D. Broesch, in Digital Signal Processing, 2009 Artificial Neural Networks Neural networks is a somewhat ambiguous term for a large class of massively parallel computing models. The terminology in this area is quite confused in that scientific well-defined terms are sometime...
The damage investigation and inspection methods for infrastructures performed in small-scale (type III) facilities usually involve a visual examination by an inspector using surveying tools (e.g., cracking, crack microscope, etc.) in the field. These met
Figure 1. Flaw A scan signal example for database construction: (a) crack; (b) porosity. Table 2. Ultrasonic weldment flaw database. To check the performance of the neural networks for training, the database was separated. To balance the learning between each flaw, 40% of the crack ...
The DSP (Digital Signal Processing) slices perform complex calculations and speed up the performance of the FPGA. Almost half of them are used by the network which leaves space for extension. It can be seen that almost no Muxes (multiplexers) are needed as they are avoided due to the ...