• Corpus ID: 32315454

A Hybrid Method of Feature Selection and Neural Network with Genetic Algorithm to Predict Diabetes

@inproceedings{Dadgar2017AHM,
  title={A Hybrid Method of Feature Selection and Neural Network with Genetic Algorithm to Predict Diabetes},
  author={Seyyed Mohammad Hossein Dadgar and Mostafa Kaardaan},
  year={2017}
}
iabetes is one of the most serious challenges of health care in developing and developed countries. In the medical field, examination of the patient data using different classifications is used to derive a predictive model. A high number of hypotheses is necessary in order to analyze the system using thermodynamic method, without these hypotheses, thermodynamic analysis of the actual application requires a large number of non-linear equations, whose solutions are either impossible, or that too… 

Figures and Tables from this paper

Diabetes Mellitus Prediction System Using Hybrid KPCA-GA-SVM Feature Selection Techniques

The proposed research on applying feature reduction before feature selection will reduce the irrelevant features that will improve the accuracy of the classification based on the selected relevant features.

SMOTE-SMO-based expert system for type II diabetes detection using PIMA dataset

  • Huma NazS. Ahuja
  • Computer Science
    International Journal of Diabetes in Developing Countries
  • 2021
The output of the study confirms that the proposed integrated approach of DM could be used as an expert system for diagnosing diabetes in patients at an early stage.

A Survey Study Support Vector Machines and K-MEAN Algorithms for Diabetes Dataset

A survey was conducted on data testing on SVM technology using a different kernel as well as data test results were surveyed with a complementary algorithm between SVM and K-mean to diagnose diabetes and compare their results with previous studies.

Deep learning approach for diabetes prediction using PIMA Indian dataset

  • Huma NazS. Ahuja
  • Medicine, Computer Science
    Journal of Diabetes & Metabolic Disorders
  • 2020
A methodology for diabetes prediction using a diverse machine learning algorithm using the PIMA dataset is presented to develop a novel automatic prognosis tool that can be helpful in early detection of the disease.

LSTM Tabanlı Derin Ağlar Kullanılarak Diyabet Hastalığı Tahmini

Anahtar Kelimeler Uzun kısa süreli bellek, Diyabet tahmini, Evrişimsel sinir ağ Öz: Diyabet, vücudun yeterli miktarda insülini üretmemesi veya iyi kullanamadığı durumda kan şekerinin normalin üstüne

IAES International Journal of Artificial Intelligence (IJ-AI)

  • 2022

An Optimization-Based Diabetes Prediction Model Using CNN and Bi-Directional LSTM in Real-Time Environment

A real-time monitoring hybrid deep learning-based model to detect and predict Type 2 diabetes mellitus using the publicly available PIMA Indian diabetes database and it is demonstrated that CNN-Bi-LSTM surpasses the other deep learning methods in terms of accuracy, sensitivity, and specificity.

References

SHOWING 1-10 OF 13 REFERENCES

Predict the onset of diabetes disease using Artificial Neural Network (ANN)

An Artificial Neural Network (ANN) based classification model is suggested as one of the powerful method in intelligent field for classifying diabetic patients into two classes and it can be a very good candidate for many real time domain applications as these are simple with good performances.

A hybrid intelligent system for medical data classification

Classification of Heart Disease Using Support Vector Machine

Results obtained show that support vector machine can be successfully used for diagnosing diabetes disease and the machine learning method focus on classifying diabetes disease from high dimensional medical dataset is successful.

A fuzzy classification system based on Ant Colony Optimization for diabetes disease diagnosis

Decision tree discovery for the diagnosis of type II diabetes

  • Asma A. Al Jarullah
  • Computer Science, Medicine
    2011 International Conference on Innovations in Information Technology
  • 2011
In this study, decision tree method was used to predict patients with developing diabetes using the Pima Indians Diabetes Data Set, which collects the information of patients with and without developing diabetes.

Using Bayes Network for Prediction of Type-2 diabetes

  • Yang GuoG. BaiYan Hu
  • Medicine, Computer Science
    2012 International Conference for Internet Technology and Secured Transactions
  • 2012
Results have been obtained which proves using the proposed Bayes network to predict Type-2 diabetes is effective, and the dataset used is the Pima Indians Diabetes Data Set, which collects the information of patients with and without developing Type-1 diabetes.

A survey on feature selection methods

Feature selection based on mutual information and redundancy-synergy coefficient

A hashing mechanism is proposed to calculate the mutual information on the feature subset based on mutual information and redundancy-synergy coefficient and the experiment results showed the good performance of the new feature selection method.