Title | ||
---|---|---|
Performance of small-world feedforward neural networks for the diagnosis of diabetes. |
Abstract | ||
---|---|---|
Small-world feedforward neural networks for the diagnosis of diabetes are considered.The NewmanWatts small-world model outperforms the WattsStrogatz model.The NewmanWatts small-world model yields the highest output correlation.The NewmanWatts small-world model yields the best output error parameters. We investigate the performance of two different small-world feedforward neural networks for the diagnosis of diabetes. We use the Pima Indians Diabetic Dataset as input. We have previously shown than the WattsStrogatz small-world feedforward neural network delivers a better classification performance than conventional feedforward neural networks. Here, we compare this performance further with the one delivered by the NewmanWatts small-world feedforward neural network, and we show that the latter is better still. Moreover, we show that NewmanWatts small-world feedforward neural networks yield the highest output correlation as well as the best output error parameters.
|
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.amc.2017.05.010 | Applied Mathematics and Computation |
Keywords | Field | DocType |
Diabetes, Feedforward neural network, NewmanWatts model, Rewiring, Small-world network, WattsStrogatz model | Feedforward neural network,Small-world network,Probabilistic neural network,Time delay neural network,Artificial intelligence,Mathematics,Machine learning | Journal |
Volume | ISSN | Citations |
311 | 0096-3003 | 6 |
PageRank | References | Authors |
0.44 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Okan Erkaymaz | 1 | 8 | 3.96 |
Mahmut Ozer | 2 | 71 | 9.68 |
Perc Matjaž | 3 | 570 | 58.27 |