Tuberculosis is a contiguous disease that is causing death both in developed and developing countries. The main aim of this research work was to a developed an intelligent system for diagnosing Tuberculosis using adaptive neuro-fuzzy methodology. Eleven symptoms of tuberculosis which are persistent cough for more than two weeks, cough with blood, weight loss, tiredness, chest pain, fever, difficulty in breathing, loss of appetite, lymph node enlargement, history of TB contact and night Sweat are assigned with weights which are categorize best on severity level as mild, moderate, severe and very severe, yes and no which serve as inputs to the adaptive neuro-fuzzy inference system (ANFIS). MATLAB 7.0 is used to implement this experiment, Trapezoidal Membership function was used, back propagation algorithm was used for training and testing, the error obtain is 0.41777 at epoch 2 which shows that the training performance is exactly 99.58223 and testing performance of the system are 99.58197 at epoch 2.   

No abstract

An electronic device is reliable if it is available for use most of the times throughout its life. The reliability can be affected by mishandling and use under abnormal operating conditions. High quality product cannot be achieved without proper verification and testing during the product development cycle. If the design is difficult to test, then it is very likely that most of the faults will not be detected before it is shipped to the customer. This paper describes how product quality can be improved by making the hardware design testable. Various designs for testability techniques were discussed. A three bit counter circuit was used to illustrate the benefits of design for testability by using scan chain methodology.