An investigation was conducted to determine and quantify the distortions in applied potential tomography (APT) images reconstructed from data originating from bodies of non-uniform reference conductivity distributions. The results show that the distortions in the images are dependent on the reference conductivity distribution and on whether the images are formed by back projection along the assumed equipotentials of a uniform reference conductivity distribution or along the equipotentials of the true conductivity distribution. We believe that this last finding is significant since our previously held expectation, similar to that of Yorkey and Webster (1987), that back projection along the true equipotentials of the reference conductivity distribution should result in an accurate reconstruction, is shown to be incorrect.

No abstract

No abstract

Artificial Neural Networks (ANNs) are one of the most comprehensive tools for classification. In this study, the performance of Feed Forward Neural Network (FFNN) with back-propagation algorithm is used to find out the appropriate activation function in the hidden layer using MATLAB 2013a. Random data has been generated and fetched to FFNN for testing the classification performance of this network. From the values of MSE, response graph and regression coefficients, it is clear that Tan sigmoid activation function is the best choice for the image classification. The FFNN with this activation function is better for any classification purpose of different applications such as aerospace, automotive, materials, manufacturing, petroleum, robotics, communication etc because to perform the classification the network designer have to choose an activation function.