Comparative Analysis of Resampling Techniques and Machine Learning Classifiers in Multiclass Classification of Diabetes Mellitus

Afshan  Hashmi; Md Tabrez  Nafis; Sameena Naaz; Imran  Hussain

Comparative Analysis of Resampling Techniques and Machine Learning Classifiers in Multiclass Classification of Diabetes Mellitus

Afshan Hashmi, Md Tabrez Nafis, Sameena Naaz, Imran Hussain

School of Arts, Humanities, and Social Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This research study explores the effects of various
resampling techniques with different machine learning
classifiers on the accuracy of multi-class classification of
Diabetes using an imbalanced dataset. The diabetes dataset of
Mendeley is a multi-class dataset with information about
patients with no diabetes, pre-diabetes, and diabetes. The
dataset is imbalanced, where the majority class is diabetic. This
study is a comparative analysis of various oversampling
techniques, undersampling techniques, and hybrid techniques
with different machine learning algorithms to accurately
classify the person as diabetic, pre-diabetic, or non-diabetic.
Eight machine-learning algorithms and ten resampling
techniques were applied to the dataset to classify the patient
accurately. The result indicates that the combination of
XGBoost with K mean smote and smote N attains the highest
accuracy of 99.2%. It also suggests that oversampling
techniques perform better than undersampling techniques and
hybrid techniques.

Original language	English
Title of host publication	International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS 2023)
Publisher	IEEE Computer Society
Publication status	Published - 6 Dec 2023

Cite this

@inproceedings{0f11874a31d54799880bc528d7900f36,

title = "Comparative Analysis of Resampling Techniques and Machine Learning Classifiers in Multiclass Classification of Diabetes Mellitus",

abstract = "This research study explores the effects of variousresampling techniques with different machine learningclassifiers on the accuracy of multi-class classification ofDiabetes using an imbalanced dataset. The diabetes dataset ofMendeley is a multi-class dataset with information aboutpatients with no diabetes, pre-diabetes, and diabetes. Thedataset is imbalanced, where the majority class is diabetic. Thisstudy is a comparative analysis of various oversamplingtechniques, undersampling techniques, and hybrid techniqueswith different machine learning algorithms to accuratelyclassify the person as diabetic, pre-diabetic, or non-diabetic.Eight machine-learning algorithms and ten resamplingtechniques were applied to the dataset to classify the patientaccurately. The result indicates that the combination ofXGBoost with K mean smote and smote N attains the highestaccuracy of 99.2%. It also suggests that oversamplingtechniques perform better than undersampling techniques andhybrid techniques.",

author = "Afshan Hashmi and Nafis, {Md Tabrez} and Sameena Naaz and Imran Hussain",

year = "2023",

month = dec,

day = "6",

language = "English",

booktitle = "International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS 2023)",

publisher = "IEEE Computer Society",

}

Comparative Analysis of Resampling Techniques and Machine Learning Classifiers in Multiclass Classification of Diabetes Mellitus. / Hashmi, Afshan ; Nafis, Md Tabrez ; Naaz, Sameena et al.
International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS 2023). IEEE Computer Society, 2023.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Comparative Analysis of Resampling Techniques and Machine Learning Classifiers in Multiclass Classification of Diabetes Mellitus

AU - Hashmi, Afshan

AU - Nafis, Md Tabrez

AU - Naaz, Sameena

AU - Hussain, Imran

PY - 2023/12/6

Y1 - 2023/12/6

N2 - This research study explores the effects of variousresampling techniques with different machine learningclassifiers on the accuracy of multi-class classification ofDiabetes using an imbalanced dataset. The diabetes dataset ofMendeley is a multi-class dataset with information aboutpatients with no diabetes, pre-diabetes, and diabetes. Thedataset is imbalanced, where the majority class is diabetic. Thisstudy is a comparative analysis of various oversamplingtechniques, undersampling techniques, and hybrid techniqueswith different machine learning algorithms to accuratelyclassify the person as diabetic, pre-diabetic, or non-diabetic.Eight machine-learning algorithms and ten resamplingtechniques were applied to the dataset to classify the patientaccurately. The result indicates that the combination ofXGBoost with K mean smote and smote N attains the highestaccuracy of 99.2%. It also suggests that oversamplingtechniques perform better than undersampling techniques andhybrid techniques.

AB - This research study explores the effects of variousresampling techniques with different machine learningclassifiers on the accuracy of multi-class classification ofDiabetes using an imbalanced dataset. The diabetes dataset ofMendeley is a multi-class dataset with information aboutpatients with no diabetes, pre-diabetes, and diabetes. Thedataset is imbalanced, where the majority class is diabetic. Thisstudy is a comparative analysis of various oversamplingtechniques, undersampling techniques, and hybrid techniqueswith different machine learning algorithms to accuratelyclassify the person as diabetic, pre-diabetic, or non-diabetic.Eight machine-learning algorithms and ten resamplingtechniques were applied to the dataset to classify the patientaccurately. The result indicates that the combination ofXGBoost with K mean smote and smote N attains the highestaccuracy of 99.2%. It also suggests that oversamplingtechniques perform better than undersampling techniques andhybrid techniques.

M3 - Conference contribution

BT - International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS 2023)

PB - IEEE Computer Society

ER -