Implementation of adaptive neuro fuzzy inference system for malaria diagnosis. (A case study at Kwesimintsim Polyclinic)

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Health issues have become one of the problems bedeviling most developing and under-developed countries in our world today. Ghana is of no exception from this menace especially in Africa. One of the prevalent diseases battling with Ghanaians and Africa as a whole is the malaria disease. In 1994, the WHO reported that malaria and measles were the most common causes of premature death. in children under five(5) years. Diagnosis of malaria in many cases has not been accurate by most doctors or physicians due to external human factors such as fatigue and hastiness among others, thereby leading to patients being subjected to treatment again which also come with cost. Hence the need for this research work entitled, “Implementation Of Adaptive Neuro Fuzzy Inference System For Malaria Diagnosis. (A Case Study At Kwesimintsim Polyclinic) This paper employs the use of Adaptive Neuro Fuzzy Inference System (ANFIS) to provide a better option for malaria diagnosis than the traditional diagnosis method which is characterized by erotic guess work and observation of patients by doctors. ANFIS, which is derived from the term Adaptive Network Fuzzy Inference System, was first proposed by Jyh-Shing and Jang and later changed to Adaptive Neural Fuzzy Inference System. This system is designed to allow IF-THEN rules and membership functions (fuzzy logic) to be constructed based on the historical data and also includes the adaptive nature for automatic tuning of the membership functions. Related works done by various authours in the area of study were reviewed. One hundred(100) datasets of patients from the clinic were used in this research work. Sixty(60) of the datasets were used as training datasets for training the ANFIS and forty(40) datasets were used checking datasets. The results tested after training showed that ANFIS has the ability to diagnose malaria efficiently than the traditional method with very minimal error.
A thesis submitted to the Department of Computer Science, Kwame Nkrumah University of Science and Technology in partial fulfillment of the requirements for the award of degree of Master of Science (Information Technology), 2015