Assessment of the risk factors for type II diabetes using an improved combination of particle swarm optimization and decision trees by evaluation with Fisher’s linear discriminant analysis

Abdullah, A. Sheik; Selvakumar, S.

doi:10.1007/s00500-018-3555-5

Cited by 18 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KELM-HAFPSO model proposed has been assessed for Accuracy, Sensitivity, Specificity, MCC, and KS by means of 5-fold crossvalidation on the basis of two related datasets. Comparative Analysis was conducted between the proposed KELM-HAFSO with the other five competitive methods namely ELM-GA [43], Decision Tree C4.5-PSO [27], k-NN [22], MLP [21], LR [17], SVM [38] and NB [16].…”

Section: Discussionmentioning

confidence: 99%

“…The least-square solution obtained in equation ( 26) is based on Karush-Kuhn-Tucker Theory [37] and it can be derived as shown in equation (27).…”

Section: Kelmmentioning

confidence: 99%

“…The main aim of this work is to predict diabetic retinopathy with an effective deep learning method. prognosis at an early stage.We have performed an advanced study A. Sheik Abdullah et al[27] using an enhanced combination of PSO and Decision Trees to examine the risk factors correlated with Type II diabetes. This study evaluated the risk factors associated with diabetes using a mathematical model named Fishers Linear Discriminant Analysis (They have considered the problem of predicting early readmission of patients suffering with diabetes to the hospitals due to its problems.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Risk Assessment of Type 2 Diabetes Mellitus Prediction using an Improved Combination of NELM-PSO

Reddy

Mahesh

2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

Risk iAssessment of iDiabetes Type-II is crucial in ipreventing it and ireducing the risk of various comorbidities. There are many iexisting machine ilearning models for predicting iType-II diabetics in ishort term future or in unspecified future. But obtaining a model having optimal performance and predicting idiabetes risk in long term future are the main problems. iThese problems are ihandled in this work by iproposing ia stacking based integrated KELM imodel to predict the irisk of diabetes Type-II for a person within five years after assessment. The Pima Indian Diabetic Dataset (PIDD) and a Diabetic Research Center dataset are used in this study. iA Min-Max normalization is iused to pre-process ithe noisy idatasets. The HAFPSO ialgorithm used in ithis work iexplores the best combination of Base ilearners by increasing the iClassification Accuracy (CA) iand decreasingi the kernel icomplexity of the ioptimal learners. iFinally, the model is iintegrated by utilizing the iKELM as a meta-classifier that icombines the ipredictions of the twenty Base Learners. The iproposed imethod is assessed iwith different imeasures such as accuracy, isensitivity, ispecificity, Mathews iCorrelation iCoefficient, and Kappa Statistics. iThe proposed KELM-HAFPSO iapproach has got ibetter values iof the considered metrics confirming its effectiveness in identifying type-II diabetes. iThe proposed method helps the clinicians to predict the ipatients who iare at a ihigh risk of Type-II diabetes iin the ifuture with the ihighest iaccuracy of 98.5%. The results iobtained show that ithe KELM-HAFPSO iapproach is a ipromising new itool for identifying type-II diabetes.

show abstract