E. C. IGODAN

The global threat of cancer to human health is significant. It is one of the main factors contributing to rising mortality and morbidity, particularly in developing African countries. The lack of medical professionals in Nigeria's development of medical health centers is one of a number of issues related to cancer. Additionally, the fatality rate from most cancers, including skin cancer, has increased due to a lack of awareness, making treatment more challenging. The research suggests using machine learning approaches for erythemato squamous disease diagnosis. The objective of the work is to develop and implement a hybrid ensemble approach using filter-embedded feature selection and ensemble of classifiers through bagging, boosting, and stacking. The classification algorithms adopted in this study includes decision trees, naive bayes, multilayer perceptrons, support vector machines, KNN, and logical regression. While some of the feature selection methods are chi-square, information gain, reliefF, gain ratio, and recursive feature selection - SVM. The performance of our models showed improved accuracy especially when using the ensemblemethods. This project proves that using ensemble methods to predict erythemato squamous disease can address some of our challenges and the project also shows future prospects.

Football appears to be the most popular sports the world over, making it a game of betting for money making among other thing. This business of betting, over the years has gown making it a difficult and complex task in predicting correctly the outcome of football matches. This is as a result of the numerous number of factors that are considered but cannot be quantitatively valued or modeled. The aim of the project is to develop a machine learning algorithms for the prediction of football matches. The classification algorithms adopted in this project includes: K-Nearest Neighbor (KNN), support vector machines (SVM), Gaussian naïve Bayes (GNB), decision tree (DT) and Logistic Regression (LR) techniques. The dataset used was gathered from football- data-co.uk. The models was built using python programming language environment. The comparative analysis carried out in this project support that machine learning algorithms perform well and shows room for future improvement.