An Improved Method for Disease Prediction Using Fuzzy Approach

Chetty, Naganna; Vaisla, Kunwar Singh; Patil, Nagamma

doi:10.1109/icacce.2015.67

Cited by 32 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used four clustering algorithms, namely K-Means, EM, PAM, Fuzzy C-Means [12]. The K-Means classification algorithm works by partitioning n observations in k-subclasses defined by centroids, where k is chosen before the algorithm begins.…”

Section: Clustering Techniquesmentioning

confidence: 99%

“…EM (expectation-maximization) is a statistical model that depends on the unobserved latent variables to estimate the maximum likelihood parameters. Partitioning around medoids (MAP) is similar to Kmeans that partitioning is based on the K-medoids method, which divides data into a number of disjoint clusters [12]. In fuzzy clustering, data elements can belong to multiple clusters.…”

Section: Clustering Techniquesmentioning

confidence: 99%

“…In [12] In [13] performed the chronic disease prediction by using data mining approach such as Naïve Bayes, Decision tree, Support Vector Machine (SVM) and Artificial Neural Networks (ANN) for the diagnosis of diabetes and heart disease. The result analysis shows that SVM gives highest accuracy of 95.556% in case of heart disease and Naïve bayes gives accuracy of 73.588% in case of diabetes.…”

Section: Related Workmentioning

confidence: 99%

“…The main focus of the paper is on classification as well as clustering techniques. In clustering process such as K-means, EM, Fuzzy c-means, etc, data is partitioned into sets of clusters or sub-classes [12].Machine learning techniques such as KNN, SVM, Naïve bayes etc, can be used to classify different objects on the basis of a training set of data whose outcome value is known.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Algorithm for Predictive Data Mining Approach in Medical Diagnosis

Jatav¹,

Sharma²

2018

IJCSIT

View full text Add to dashboard Cite

show abstract

Section: Clustering Techniquesmentioning

confidence: 99%

Section: Clustering Techniquesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Algorithm for Predictive Data Mining Approach in Medical Diagnosis

Jatav¹,

Sharma²

2018

IJCSIT

View full text Add to dashboard Cite

show abstract

“…The outputs prove that the formulated work is better than current techniques. Chetty et al [16] handled PIMA and Liver-disorder databases. Several researchers have formulated the utilization of K-Nearest Neighbour (KNN) algorithm for the prediction of diabetes disease.…”

Section: Literature Reviewmentioning

confidence: 99%

Correlation Feature Selection (CFS) and Probabilistic Neural Network (PNN) for Diabetes Disease Prediction

Kalaiselvi¹,

Sujarani²

2018

IJET

View full text Add to dashboard Cite

The healthcare sector is a broad area with the abundance of patient information, which creates enormously large records day b y day. Though the scientific industry is rich in information but it is poor in knowledge. Diabetics are considered as a primary health issue of the world. As per the WHO 2014 survey According to WHO 2014 report, over 422 million people are affected from the diabetics globa lly. In the minimization of massive investigations implied on the patients, the data mining uses many mechanisms and strategies to diagnose the diabetic problem. The main objective of this proposal is to introduce assemble Data Mining based Diabetes Disease Prediction System which provides a detailed analysis of diabetics using the database of diabetics patient. The formulated work comprises of two stages such as feature selection ad prediction methods which are made known to maximize the outputs of diabetes disease predi ction. Initially Correlation Feature Selection (CFS) is formulated to identify the salient features for the diabetic repository. The identified features are fed into the classifier named Probabilistic Neural Network (PNN) classifier. As the diabetic of the patient is classified using PNN meanwhile the accuracy can be finetuned when using the identified features. Depending on the category of data, the diabetic information is gathered from the learning repository. The outputs are correlated with the current algorithms namely Back Propagation Neural Network (BPNN), Multilayer Perceptron, Neural Network (MLPNN) were used to fetch the outputs.

show abstract

An Empirical Model for Thyroid Disease Diagnosis Using Data Mining Techniques

Sidiq

Aaqib

2019

Sustainable Communication Networks and Application

View full text Add to dashboard Cite

An Improved Method for Disease Prediction Using Fuzzy Approach

Cited by 32 publications

References 9 publications

An Algorithm for Predictive Data Mining Approach in Medical Diagnosis

An Algorithm for Predictive Data Mining Approach in Medical Diagnosis

Correlation Feature Selection (CFS) and Probabilistic Neural Network (PNN) for Diabetes Disease Prediction

An Empirical Model for Thyroid Disease Diagnosis Using Data Mining Techniques

Contact Info

Product

Resources

About