Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease
Diabetes signifies different types of metabolic diseases that cause high blood glucose, either because of insufficient insulin production or because the body cells fail to respond to insulin the body makes normally. Early detection of diabetes remains necessary in today's healthcare industry in...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914821001908 |
| _version_ | 1798035201224343552 |
|---|---|
| author | Seyed Reza Kamel Reyhaneh Yaghoubzadeh |
| author_facet | Seyed Reza Kamel Reyhaneh Yaghoubzadeh |
| author_sort | Seyed Reza Kamel |
| collection | DOAJ |
| description | Diabetes signifies different types of metabolic diseases that cause high blood glucose, either because of insufficient insulin production or because the body cells fail to respond to insulin the body makes normally. Early detection of diabetes remains necessary in today's healthcare industry in order to reduce the mortality rate caused by kidney failure and loss of vision that both often lead to death. Until now, the diagnosis of diabetes has been examined through different techniques, including machine learning and data mining methods. However, due to the complexity of calculations or the time-consuming processes, their given accuracy is not acceptable. The present research proposes a feature selection method based on a grasshopper optimization algorithm (GOA) to increase the accurate results of diabetes type II testing and employs different machine learning techniques to find an enhanced classifier. In doing so, a 10-fold cross-validation method is used to gain the reliability of the obtained responses. The feature selection technique is used in this study to identify the important features in the dataset. This approach is applied on the Prima Indian Dataset, using MATLAB software. The study result has shown promising accuracy of 97% achieved by the Support-Vector Machine (SVM) algorithm. A comparison is also made between the most recent AI algorithms and that of the present study to show the superiority of the grasshopper algorithm in selecting features and increasing the accuracy of diabetes testing. |
| first_indexed | 2024-04-11T20:54:56Z |
| format | Article |
| id | doaj.art-aa332b0f5d0d46588c5c67761ee87df0 |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-04-11T20:54:56Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-aa332b0f5d0d46588c5c67761ee87df02022-12-22T04:03:44ZengElsevierInformatics in Medicine Unlocked2352-91482021-01-0126100707Feature selection using grasshopper optimization algorithm in diagnosis of diabetes diseaseSeyed Reza Kamel0Reyhaneh Yaghoubzadeh1Department of Computer Engineering, Islamic Azad University, Mashhad Branch, Mashhad, IranCorresponding author.; Department of Computer Engineering, Islamic Azad University, Mashhad Branch, Mashhad, IranDiabetes signifies different types of metabolic diseases that cause high blood glucose, either because of insufficient insulin production or because the body cells fail to respond to insulin the body makes normally. Early detection of diabetes remains necessary in today's healthcare industry in order to reduce the mortality rate caused by kidney failure and loss of vision that both often lead to death. Until now, the diagnosis of diabetes has been examined through different techniques, including machine learning and data mining methods. However, due to the complexity of calculations or the time-consuming processes, their given accuracy is not acceptable. The present research proposes a feature selection method based on a grasshopper optimization algorithm (GOA) to increase the accurate results of diabetes type II testing and employs different machine learning techniques to find an enhanced classifier. In doing so, a 10-fold cross-validation method is used to gain the reliability of the obtained responses. The feature selection technique is used in this study to identify the important features in the dataset. This approach is applied on the Prima Indian Dataset, using MATLAB software. The study result has shown promising accuracy of 97% achieved by the Support-Vector Machine (SVM) algorithm. A comparison is also made between the most recent AI algorithms and that of the present study to show the superiority of the grasshopper algorithm in selecting features and increasing the accuracy of diabetes testing.http://www.sciencedirect.com/science/article/pii/S2352914821001908DiabetesData miningGrasshopper optimization algorithm (GOA)Support vector machine (SVM)Feature selection |
| spellingShingle | Seyed Reza Kamel Reyhaneh Yaghoubzadeh Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease Informatics in Medicine Unlocked Diabetes Data mining Grasshopper optimization algorithm (GOA) Support vector machine (SVM) Feature selection |
| title | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| title_full | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| title_fullStr | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| title_full_unstemmed | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| title_short | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| title_sort | feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease |
| topic | Diabetes Data mining Grasshopper optimization algorithm (GOA) Support vector machine (SVM) Feature selection |
| url | http://www.sciencedirect.com/science/article/pii/S2352914821001908 |
| work_keys_str_mv | AT seyedrezakamel featureselectionusinggrasshopperoptimizationalgorithmindiagnosisofdiabetesdisease AT reyhanehyaghoubzadeh featureselectionusinggrasshopperoptimizationalgorithmindiagnosisofdiabetesdisease |