Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Bio-Algorithms and Med-Systems

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Influence of neural network structure and data-set size on its performance in the prediction of height of growth hormone-treated patients

Smyczyńska U., Smyczyńska J., Tadeusiewicz R.

Bio-Algorithms and Med-Systems

2016

Vol. 12, no. 2

53--59

It is well known that the structure of neural network and the amount of available training data influence the accuracy of developed models; however, the exact character of this relation depends on the chosen problem. Thus, it was decided to analyze what impact these parameters have on the solution of the problem on which we work – the prediction of final height of children treated with growth hormone. It was observed that multilayer perceptron with a wide range of numbers of hidden neurons (from 1 to 100) could solve the problem almost equally well. Thus, this task seems to be rather simple, not requiring complex models. Larger networks tended to produce less accurate results and did not generalize well while working with the data not used in training. Repeating the experiment with the training data set reduced to 50% of its original content, as expected, caused a decrease in accuracy.

Neural modelling of growth hormone therapy for the prediction of therapy results

Smyczyńska U., Smyczyńska J., Tadeusiewicz R.

Bio-Algorithms and Med-Systems

2015

Vol. 11, no. 1

33--45

In this paper, we presented the problem of predicting response to recombinant human growth hormone (GH) treatment in GH-deficient children. Such a prediction can be done by techniques of mathematical modelling and is important because the therapy consists of daily injections and is expensive; thus, it should be administered only to those patients who will, with high probability, benefit from it. Until now, the leading methodological approach to this problem was multiple regression analysis. Several authors demonstrated that it is possible to derive useful models by this method; however, it has some obvious limitations that can be avoided with the use of the proposed neural network approach.