Evolutionary correlated gravitational search algorithm (ECGS) with genetic optimized Hopfield neural network (GHNN) – A hybrid expert system for diagnosis of diabetes

Jayashree, J; Kumar, S. Ananda

doi:10.1016/j.measurement.2018.12.083

Cited by 15 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the prediction accuracy of issue, Jayashree and Kumar (2019) presented evolutionary correlated gravitational search algorithm (ECGS) to determine the appropriate features for diabetes disease. Further, genetic optimized Hopfield neural network (GHNN) method is used to process the selected features.…”

Section: Related Workmentioning

confidence: 99%

Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques

Srivastava

Kumar

Singh³

2021

Expert Systems

View full text Add to dashboard Cite

In the field of medical science, accurate prediction is a difficult and challenging task. But, the presence of missing values and outliers can make the prediction task more complicated. Many researchers address the issue of missing value in medical data, either detect the missing value and delete the respective data instances from the dataset or adopt some default methods such as mean, median, neighbour etc., for filling the missing value. However, both methods are lacking to produce optimal results. Furthermore, outliers are also presented in data and degraded the performance of classifier. Few researchers also focus on the outlier detection in medical dataset, but it is not fully explored till date. This work considers the two well‐known problems of data that is, (i) missing value imputation, and (ii) outlier. The missing value imputation issue is addressed through K‐Mean++ based data imputation technique. This technique also validates the data through clustering and also compute the values for missing data. The outlier can be detected through an ABC based outlier detection technique. Further, the final outcome is determined using LS‐SVM classifiers. Hence, this work presents a hybrid disease diagnosis framework for diabetes prediction, called hybrid diabetes prediction framework. The reason behind to choose the diabetes dataset for implementation as it contains 763 missing values and several outliers. The simulation results showed that proposed hybrid framework effectively determines the missing values and outliers in diabetes dataset. Further, the performance of proposed hybrid diabetes prediction framework is evaluated using accuracy, sensitivity, specificity, kappa and AUC parameters and compared with 34 state of art techniques. Results confirmed that proposed hybrid framework obtains 96.57%, 93.37%, 98.12%, 98.17%, and 95.43% accuracy, sensitivity, specificity, kappa and AUC rate respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques

Srivastava

Kumar

Singh³

2021

Expert Systems

View full text Add to dashboard Cite

show abstract

“…When looking for the best traits to use to identify T2D patients with CVD risk factors, the mutation operation broadens the search field. (7) where F is a scaling factor with values between zero and one; (8) where x and y are solution vectors selected at random; The parent feature vector of T2D patients with CVD risk factors is crossed with the mutant vector to create a trial vector ( 9): (9), where is the crossing constant, is a real value between 0 and 1, and j is the index of the relevant array element. When using DE to establish patient characteristics for T2D, the fitness value from equation (15).…”

Section: Measuring Attribuable Costs With Kernel Density Estimates (Kde)mentioning

confidence: 99%

“…Let the value of membership in the unlabeled cluster sample be denoted by and the values of membership in the CVD risk factor class and the unmodified CVD risk factor class by and, respectively. It is possible to derive these numbers by using the formulas: [8] Once the target CVD risk factors categorization findings are determined, they are updated in the same manner using the K-nearest neighbour approach. Each clustered feature sample from a T2D patient without labels has its K closest neighbours calculated.…”

Section: Content-based Classification Through Partially Supervised Le...mentioning

confidence: 99%

Prediction Model for Cardiovascular Disease Risk in Type2 Diabetic Patients Using a Hybrid Artificial Bee Colony Model and Semi-Supervised Learning

2021

Webology

View full text Add to dashboard Cite

A significant risk factor for death in people with diabetes is cardiovascular disease (CVD). More than 22% of persons with type 2 diabetes mellitus also have cardiovascular disease, and it is thought that the two conditions are causally related. However, not all of the research put enough emphasis on semi-supervised learning techniques that use feature selection strategies to improve the prediction accuracy of classification techniques. This study was out to better predict outcomes by identifying key CVD variables affecting type 2 diabetes management. Patient data is preprocessed and dimensionality reduced using Kullback-Leibler divergence (KLD)-principal component analysis (PCA) in the proposed methods; attribute values are measured using kernel density estimation (KDE), which measures attribute values using a probability mass function with a Gaussian kernel function; and feature selection is carried out utilising an artificial bee colony with differential evolution (ABC-DE). Semi-supervised Modified Self-Organizing Feature Map Neural Network (MSOFMNN) classification technique is used to the data after it has been clustered using the Improved Fuzzy C Means (IFCM) clustering algorithm in a hybrid prediction model to verify the selected class label of the input data. With improved prediction accuracy and reduced error rate, the proposed technique investigates the behavioural aspects that lead to CVD risk factors in people with type 2 diabetes (T2D).

show abstract

“…GA is a computational processing algorithm inspired by Darwin's model, namely a survival for the fittest model (Feng et al, 2019). Furthermore, Jayashree and Kumar (2019) had underlined mutation and crossover as the key traits of GA in order to extract information and prioritize feature selection. Consequently, it is one of the prevalent metaheuristics used by many neural networkers, substantiating its compatibility for a comparison with the Imperialist Competitive Algorithm (ICA) mechanism.…”

Section: Introductionmentioning

confidence: 99%

Untitled

JST

View full text Add to dashboard Cite

Pertanika Journal of Science & Technology (JST) is the official journal of Universiti Putra Malaysia published by UPM Press. It is an open-access online scientific journal which is free of charge. It publishes the scientific outputs. It neither accepts nor commissions third party content.Recognized internationally as the leading peer-reviewed interdisciplinary journal devoted to the publication of original papers, it serves as a forum for practical approaches to improving quality in issues pertaining to science and engineering and its related fields.JST is a quarterly (January, April, July and October) periodical that considers for publication original articles as per its scope. The journal publishes in English and it is open to authors around the world regardless of the nationality.

show abstract

Evolutionary correlated gravitational search algorithm (ECGS) with genetic optimized Hopfield neural network (GHNN) – A hybrid expert system for diagnosis of diabetes

Cited by 15 publications

References 19 publications

Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques

Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques

Prediction Model for Cardiovascular Disease Risk in Type2 Diabetic Patients Using a Hybrid Artificial Bee Colony Model and Semi-Supervised Learning

Untitled

Contact Info

Product

Resources

About