Application of Artificial Neural Networks for Different Engineering Problems

Abstract

This paper presents some applications of data and signal processing using artificial neural nets (ANNs) which have been investigated at the University of Tübingen. The applications covering a wide range of different interesting domains: color restoration, gas sensing systems, internet information search and delivery, online quality control and nerve signal processing. In order to achieve the requirements of each application supervised learning as well as unsupervised learning artificial neural nets have been used. The paper presents each application in detail and describes the problems which have been solved using artificial neural nets.

Determination of the Effect of Different Nitrogen Doses on the Yield, Yield Components and Chlorophyll Contents of Bread Wheat (Triticum aestivum L.) Cultivars using Artificial Neural Network

“…In Feed-Forward, the output of the network is calculated. In back propagation, weights are changed (Bogdan et al, 1999). When back propagation learning is used, the weights of the hidden layer are arranged using errors in the output layer.…”

Fundamentals of soft models in textiles

“…Adequate representation and preprocessing (cleaning, dimension reduction, scaling, etc.) of input data can have a dramatic infl uence on the success of neural network models [88]. information visualization and visual data analysis can help to deal with the fl ood of information.…”

Neural Network Analysis of Ex-vivo Expansion of Hematopoietic Stem Cells

“…The network input and output data were obtained from literature 1,2,[4][5][6][7][8][9][10][11][12][14][15][16][17][18][19][20][21][22][23][24][25]27,[29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][46][47][48][49] for evaluation and prediction. Altogether 341 data were collected and summarized in Table 1.…”

“…Over the last few years, neural networks has been successfully applied in biology, microbiology, medicine, image manipulation and voice discrimination etc. 4,5,10,14,24,31,38,41,42,46 Therefore the neural network model may be a reasonable tool to setup the relationship between the expansion fold of HSCs and the influencing factors.…”