DocumentCode
2555095
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
fYear
1990
fDate
3-6 Jun 1990
Firstpage
282
Lastpage
289
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;
fLanguage
English
Publisher
ieee
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
Type
conf
DOI
10.1109/CBMSYS.1990.109410
Filename
109410
Link To Document