Performance Comparison of Machine Learning Models for Diabetes Prediction

2021 ◽  
Author(s):  
Pinar Cihan ◽  
Hakan Coskun
Keyword(s):  
Machine Learning ◽  
Performance Comparison ◽  
Learning Models ◽  
Diabetes Prediction ◽  
Machine Learning Models

scholarly journals Significance Of Multilayer Perceptron Model For Early Detection Of Diabetes Over Ml Methods

2021 ◽  
Vol 23 (08) ◽  
pp. 148-160
Author(s):  
Dr. V.Vasudha Rani ◽  
◽  
Dr. G. Vasavi ◽  
Dr. K.R.N Kiran Kumar ◽  
◽  
...  
Keyword(s):  
Machine Learning ◽  
Multilayer Perceptron ◽  
Predictive Analytics ◽  
Early Stage ◽  
Feature Selection Method ◽  
Health Condition ◽  
Performance Comparison ◽  
Learning Approaches ◽  
Learning Models ◽  
Machine Learning Models

Diabetes is one of the chronicdiseases in the world. Millions of people are suffering with several other health issues caused by diabetes, every year. Diabetes has got three stages such as type2, type1 and insulin. Curing of diabetes disease at later stages is practically difficult. Here in this paper, we proposed a DNN model and its performance comparison with some of the machine learning models to predict the disease at an earlystage based on the current health condition of the patient. An artificial neural network (ANN) is a predictive model designed to work the same way a human brain does and works better with larger datasets. Having the concept of hidden layers, neural networks work better at predictive analytics and can make predictions with more accuracy. Novelty of this work lies in integration of feature selection method used to optimize the Multilayer Perceptron (MLP) to reduce the number of required input attributes. The results achieved using this method and several conventional machines learning approaches such as Logistic Regression, Random Forest Classifier (RFC) are compared. The proposed DNN method is proved to show better accuracy than Machine learning models for early stage detection of diabetes. This paper work is applicable to clinical support as a tool for making predecisions by the doctors and physicians.

Diabetes Prediction using Feature Extraction and Machine Learning Models

2021 ◽  
Author(s):  
Sunil Ghane ◽  
Namrata Bhorade ◽  
Nikita Chitre ◽  
Bhargavi Poyekar ◽  
Rishita Mote ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Learning Models ◽  
Diabetes Prediction ◽  
Machine Learning Models

Using a Binary Classification Approach to Assess the Accuracy of Hand Posture and Force Estimation with Machine Learning Models

2021 ◽  
Vol 65 (1) ◽  
pp. 1248-1249
Author(s):  
Mengcheng Wang ◽  
Chuan Zhao ◽  
Alan Barr ◽  
Suihuai Yu ◽  
Jay Kapellusch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Binary Classification ◽  
Confusion Matrix ◽  
Strong Relationship ◽  
Performance Comparison ◽  
Learning Models ◽  
Force Estimation ◽  
Classification Approach ◽  
Future Performance ◽  
Machine Learning Models

Recent studies have successfully reported the accuracy of using artificial neural networks to predict grip force in controlled settings. However, only relying on accuracy to evaluate the machine learning models may lead to overoptimistic results, especially on imbalanced datasets. The Matthews correlation coefficient (MCC) showed an advantage in capturing all the data characteristics in the confusion matrix. Therefore, a binary classification approach and the MCC value were introduced to assess the performance of previously proposed machine learning models. Our results show that the overall correlations ranging between 0.48 and 0.59 indicate a strong relationship between predictions and actual scenarios. The binary classification approach and the MCC values could be used for future performance comparison with other machine learning models.

Sign in / Sign up

Export Citation Format

Share Document