Neural networks and blood cell identification

The objective of this project is to propose a method of identifying cells found in human blood and to classify them based upon their morphological features using neural networks. The project focuses on three major blood cell types, namely, erythrocytes, leukocytes and platelets. The data are collected using peripheral blood smears from clinical patients. The image acquisition requires 100x magnification on all the blood smears, the preprocessing involves the use of median and edge enhance filters; the feature extraction is done by performing the wavelet transform on the images. Finally classification of the blood cell types is done using ALOPEX and Back Propagation trained neural networks. The efficacy of both networks is then compared by comparing their outputs and number of iterations required to reach the final result.     

Penetrating ocular injuries: an epidemiologic and retrospective study

Penetrating injuries of the eye are an important cause of unilateral visual loss. We studied a series of 82 cases of penetrating injuries treated here from 1987 through 1993. The injuries were caused by sharp objects in 66% and blunt trauma in 6%. The prognosis after a penetrating injury is greatly influenced by the nature of the injury and the extent of the initial drainage. Among factors associated with an unfavorable visual outcome were diminished preoperative visual acuity and scleral wounds with dense vitreous hemorrhage.     

Wideband wattmeter based on RMS voltage measurements

A wideband wattmeter for measuring active power over a frequency range of dc to 500 kHz is described. The wattmeter is based on the three-voltmeter method in which three rms voltage measurements are used to calculate power. The wattmeter active power uncertainty is estimated to be within 0.03% from dc to 20 kHz and within 1.5% to 500 kHz