Neural networks and logistic regression: Part I

Neural Network Modelling and Sensitivity Analysis of a Mechanical Poultry Catching System

In this paper the feature extraction of the EEG Signal is done by computing the Discrete Wavelet Transform. The wavelet transform coefficients compress the number of data points into few features. Various statistics were used to further reduce the dimensionality. The Classification of the EEG sleep stages is done by using neural network which provides more accurate sleep stage classification compared to other techniques.

Sleep stages classification using wavelettransform & neural network

This paper will present and evaluate a neural network-based approach to predicting solar radiation for a given site. This data is necessary to create valid decisions as to when to use other resources to generate energy in the micro-grid structure proposed for Smart Grid

Comparison of Methods Used for Forecasting Solar Radiation

Advantages of Using Factorisation Machines as a Statistical Modelling Technique

Currently an ever increasing number of articles on Neural Networks are appearing in especially the engineering and computer science journals. Neural Networks are applied to a wide variety of problems, but considerable successes have been obtained when applying Neural Networks to classification problems. Statisticians concern themselves with such problems and have, over the years, proposed various techniques for solving classification problems. In this article we will discuss the motivations for, the fundamentals and some applications of Neural Networks. The paper will introduce this exciting new area to statisticians and hopefully will serve to stimulate statistical research into the subject.

P.J. De Wet

Papers

An introduction to neural networks