Adaptive Neuro-Fuzzy System to Determine the Blood Glucose Level of Diabetic
Auwal Nata’ala,
Hamman Dikko Muazu,
Ibrahim Goni,
Abdullahi Mohammed Jingi
Issue:
Volume 4, Issue 3, May 2019
Pages:
63-67
Received:
9 March 2019
Accepted:
22 April 2019
Published:
12 October 2019
Abstract: Diabetes is a chronic disease that occurs when the pancreas does not produce enough insulin. The main aim of this research work was to determine the blood glucose level of diabetic patient using adaptive Neuro-fuzzy. Data of 80 diabetic patients were collected from Federal Medical Centre Jalingo. It was used for training and testing the system, Gaussian Membership function was used, hybrid training algorithm was used for training and testing, the error obtain is 0.0008333 at epoch 4 which shows that the training performance is exactly 99.99% and testing performance of the system are 99.99% at epoch 4. This shows that adaptive Neuro-fuzzy system can be applied to medical diagnosis because of the error obtained.
Abstract: Diabetes is a chronic disease that occurs when the pancreas does not produce enough insulin. The main aim of this research work was to determine the blood glucose level of diabetic patient using adaptive Neuro-fuzzy. Data of 80 diabetic patients were collected from Federal Medical Centre Jalingo. It was used for training and testing the system, Gau...
Show More
A New Seventh Order Runge-kutta Family: Comparison with the Method of Butcher and Presentation of a Calculation Software
Hippolyte Séka,
Assui Richard Kouassi
Issue:
Volume 4, Issue 3, May 2019
Pages:
68-75
Received:
5 September 2019
Accepted:
24 September 2019
Published:
14 October 2019
Abstract: This paper is in the context of the numerical resolution of ordinary differential equations. Most equations are unsolved in the analytic aspect. The goal is to find among the existing methods, the best method of numerical resolution. Also to facilitate the implementation of methods by introducing a calculation software. To do this, we use the Runge-Kutta method which is one of the best methods of numerical resolutions. That is why a family of Runge-Kutta methods of order 7 is presented. This family depends on the parameter b8 and contains the well known method of Butcher [8] (b8 =77/1440). To obtain convincing results, we compare methods according to the values of b8 with those of Butcher. The stability region is also studied to essentially perceive the numerical behavior that manifests itself when the steps of discretization tend to 0. The study shows that the stability region of this method does not depend on the coefficient b8. To get the values of b8, Java programming is used. Finally, to facilitate the implementation of the resolution, very simple software for numerical resolution of the ordinary differential equations is given. This software is designed for all students, also for all those who have no basis in numerical analysis and java programming to be able to find a solution approached with error estimate to an ordinary differential equation.
Abstract: This paper is in the context of the numerical resolution of ordinary differential equations. Most equations are unsolved in the analytic aspect. The goal is to find among the existing methods, the best method of numerical resolution. Also to facilitate the implementation of methods by introducing a calculation software. To do this, we use the Runge...
Show More
