A Study on the Effectiveness of Classifiers in Diagnosing Diabetes Using Machine and Deep Learning Models

Abstract

Machine learning and data mining have a crucial role in assisting in the early detection of diabetes, potentially resulting in improved health outcomes and more effective management for individuals at risk. This process is frequently termed diabetes prediction or diabetes risk assessment. This paper considers diabetes another-related dataset for applying data mining techniques to find suitable variables for future predictions. Machine learning algorithms can be harnessed in Industrial Internet of Things (IIoT) applications to unlock the advantages of cost reduction, enhanced efficiency, and improved performance. In the modern era, we've all witnessed the benefits of machine learning techniques, from streaming movie services suggesting titles based on viewing habits to identifying fraudulent activity through customer spending patterns. These algorithms excel at handling vast and intricate datasets, uncovering intriguing patterns and trends, including anomalies. This paper considers diabetes another-related dataset data data like age, gender, family diabetes, highbp, physically active, bmi, smoking, alcohol, sleep, sound sleep, regular medicine, junkfood, stress, bplevel, pregancies, pdiabetes, uriationfreq, diabetic. The machine learning approaches which is used to analysis and predict the dataset using Logistic, Multilayer Perceptron, SMO, Decision Stump, Hoeffding Tree, J48, and LMT. Numerical illustrations are provided to prove the proposed results with test statistics or accuracy parameters.