RETRACTED ARTICLE: An automatic detection and classification of diabetes mellitus using CNN

In the recent years, most of the populations in the world are prone to diabetes mellitus disease. Diabetes is considered as severe syndrome as it causes severe damage to major parts of the body. Loss of vision, failure of kidneys, and vision loss are few examples of damages caused by this disease. Recently, in the year 2023, Diabetes Association from America has released several standards to patients suffering from diabetes. The standard includes guidelines to diagnose, prevent, and treat people suffering from diabetes. Therefore, any innovative approach facilitating early diagnosis of this serious disease is much need of the hour. Several machine learning algorithms have recently attracted more attention in the medical field and have been successfully used in a variety of medical applications. Thus, to function autonomously without seeking any assistance or help from a person, a well-known branch of machine learning called deep learning completes several related tasks parallely. The objective of this work is to design an efficient framework for the classification of the intrinsic complex diabetes dataset. Since tasks are assumed to be related to one another, the proposed framework which is a regularized version of multilayer perceptron has a massive advantage that it can identify the complex intricate features involved in the classification with very limited preprocessing layers. Therefore, the proposed work achieves better accuracy and outperforms well to the best of our knowledge.