Diagnosis of Pulmonary Tuberculosis using fuzzy Inference System

Artificial intelligence is a set of real time computational methodologies to address complex real-world problems. In this paper, Neurofuzzy Inference System for analysis of pulmonary tuberculosis (TB)disease is discussed. For effective result, simulation is being done by using the realistic causes of pulmonary TB. The Neurofuzzy system is used for decision making based on a predefined rule based upon the symptoms of the patient are taken as inputs and the corresponding TB risk quotient is evaluated as the output. This crisp result obtained allows us to diagnose the low or high risk of the disease in the patient. Hybrid learning algorithm is applied for minimization of error in the output.