Please use this identifier to cite or link to this item:
http://repository.aaup.edu/jspui/handle/123456789/2621
Title: | Using Enhanced Artificial Neural Networks Model for Classification and Prediction of Diabetes رسالة ماجستير |
Authors: | Qteat, Haneen Omar Ismail$AAUP$Palestinian |
Keywords: | machine learning,dataset attributesmpidd data set |
Issue Date: | 2019 |
Publisher: | AAUP |
Abstract: | Diabetes mellitus is one of the deadliest and chronic diseases that affect the persons who have an increase in their blood glucose levels. Type 1 Diabetes Mellitus “T1DM” is considered as one of the most dangerous types of diabetes as it is the reason why diabetes is called the silent killer. Due to the common symptoms of type 1 and 2 diabetes, diabetes specialists face doubts about their diagnosis of the type of diabetes in the patient where the uncertainty about the diagnosis of the disease may lead to delays in controlling the potential complications, especially if they have T1DM. In this thesis, we have collected a local Palestinian dataset "DataPal" With the assistance of the Palestinian Diabetes Institute. A local Palestinian dataset was applied using machine learning algorithms to predict diabetes. The DataPal consists of 9 predictors used to diagnose diabetes types. The dataset consists of 314 instances of diabetic females. Where the women are more likely to die due to diabetes, so we gave them priority in this thesis. Thus, our samples were for females with both types 1 and 2 diabetes, aged between 5 and 89 years. The local dataset "DataPal" and the global dataset "PIDD" were preprocessed using the K-nn algorithm to fill their missing values because in medical diagnosis there is no room for error. The SVM algorithm also applied to the datasets to select the most optimal features to predict diabetes. Both the two-fold and four-fold cross-validation methods were applied to the datasets to evaluate the applied models fairly. A hybrid model "PSO-FFNN" uses the PSO evolutionary algorithm to train an FFNN and find the optimal weight values of the trained network. The PSO-FFNN model was applied to the VI preprocessed datasets. Then the performance of the model was evaluated using different metrics such as the overall accuracy, recall, specificity, G-mean, and AUC and others. The obtained results show that the proposed PSO-FFNN model outperformed all models applied in this thesis in the classification of diabetes and its types |
Description: | Master`s degree in Computer Science |
URI: | http://repository.aaup.edu/jspui/handle/123456789/2621 |
Appears in Collections: | Master Theses and Ph.D. Dissertations |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
حنين اقطيط.pdf | 1.35 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
Admin Tools