Part I: An artificial neural network model of tuberculosis patient data Part II: A DFT computational model of metal hydrides

ABSTRACT PART I---The data of tuberculosis patients and a control group were analyzed with the artificial neural network in order to find genetic factors which inhibit and promote the patient to developing drug resistant tuberculosis. The data came from populations in Kyrgyzstan containing genetic and physical records as well as the type of tuberculosis they had contracted. Three models based on the data were developed: first, a model which differentiates TB from control patients; second, a model which differentiates both TB and control patients; and finally, a model which distinguishes infiltrative from chronic type tuberculosis. Factors which influenced the prediction are given in the results.;ABSTRACT PART II---The metal hydride is a capable candidate for mobile storage for hydrogen-powered vehicles. An artificial neural network has proved useful for many applications, and capable of much more in discovery of new materials. Because of its ability to generalize from examples presented to it, an ANN is a powerful tool for discovering new metal hydride combinations. An ANN can deduce quantitative structure property relationships for metal hydrides. The model found correlations between fundamental electronic and energy values modeled ab initio. Some of the properties successfully predicted with good correlation are: entropy, enthalpy, temperature at 1 atmosphere of pressure, pressure at 25°C, and the percent weight of hydrogen stored. The marriage of ANN to computational modeling produces good predictions for many important properties of metal hydrides.