No abstract

No abstract

In this paper, we propose the use of wavelet neural networks (WNN) to predict software reliability. In WNN, we employed two kinds of wavelets -Morlet wavelet and Gaussian wavelet as transfer functions resulting in two variants of WNN. The effectiveness of WNN is demonstrated on a data set taken from literature. Its performance is compared with that of multiple linear regression (MLR), multivariate adaptive regression splines (MARS), backpropagation trained neural network (BPNN), threshold accepting trained neural network (TANN), pi-sigma network (PSN), general regression neural network (GRNN), dynamic evolving neuro-fuzzy inference system (DENFIS) and TreeNet in terms of normalized root mean square error (NRMSE) obtained on test data. Based on the experiments performed, it is observed that the WNN outperformed all the other techniques.

No abstract

With technological advancements in medical electronics, and computerization of all standard medical institutions, the amount of image data being produced in these fields has been increasing constantly. Each hospital or institute provides services to thousands of patients per day, and most of the diagnosis tools are images for example x-rays, ultrasound scanners, magnetic resonance imaging etc. Since most hospitals keep records of each patient's case history, it is possible to detect any diseases in a person in its early stages itself, by studying the cases of the previous patients who exhibited similar symptoms, and direct the doctors for further tests. A possible environment for testing the aforementioned procedure is to use images of the fundus of the eye, which are used to detect and monitor the presence or progress of diseases pertaining to the eye. Extraction of features from these images that generally indicate the presence of afflictions, namely exudates, is addressed in this paper. A novel algorithm for the detection of the Optical Disk and the presence of any exudates has been described in this paper. The algorithm has been tried in MATLAB version 2011b. An accuracy of 92% was achieved.