Title :
Neural network performance metrics for biomedical applications
Author :
Eberhart, Russell C. ; Dobbins, Roy W.
Author_Institution :
Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
Abstract :
Neural network performance measurements are discussed. Included are percent correct, average sum-squared error, receiver operating characteristics (ROC) curve measurements, other measurements based on ROC curve parameters, and the chi-square goodness-of-fit metric. The specific measure chosen depends on the type of system and other more loosely defined parameters such as the level of technical sophistication of the system end user
Keywords :
medical computing; neural nets; ROC curve parameters; average sum-squared error; biomedical applications; chi-square goodness-of-fit metric; percent correct; receiver operating characteristics; Artificial intelligence; Biomedical measurements; Error correction; Gold; Laboratories; Neural networks; Particle measurements; Physics; System performance; Testing;
Conference_Titel :
Computer-Based Medical Systems, 1990., Proceedings of Third Annual IEEE Symposium on
Conference_Location :
Chapel Hill, NC
Print_ISBN :
0-8186-9040-2
DOI :
10.1109/CBMSYS.1990.109410
