Title :
Estimation of MIS using neural nets
Author :
Mandal, M. ; Mandal, A.K. ; Nath, A.K.
Author_Institution :
Dept. of Electron. & Telecommun. Eng., Jadavpur Univ., Calcutta, India
Abstract :
An artificial neural network is useful for modeling enzyme release and estimation of myocardial infarction size (MIS). The backpropagation technique is used for adjusting the weights of the network with a measured enzyme activity in blood serum together with histologic value of infarction size (HIS). Once the weights of the interlayer connections are fixed, the network is used to estimate the MIS for unknown cases. With a proper choice of nonlinear function, the results are excellent
Keywords :
backpropagation; biology computing; blood; cardiology; neural nets; proteins; backpropagation; blood serum; enzyme release; histologic value of infarction size; myocardial infarction size; neural nets; nonlinear function; Artificial neural networks; Backpropagation; Biochemistry; Blood; Equations; Filters; Iron; Myocardium; Neural networks; Size measurement;
Conference_Titel :
TENCON '92. ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' 1992 IEEE Region 10 International Conference.
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-0849-2
DOI :
10.1109/TENCON.1992.272005
