A Novel approach to predict diabetes mellitus using modified Extreme learning machine

Priyadarshini, Rojalina; Dash, Nilamadhab; Mishra, Rachita

doi:10.1109/ecs.2014.6892740

Cited by 31 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applied Naïve Bayes algorithm developing an artificial intelligent system, based on the comparison of certain parameters used to predict whether a person is having diabetic problem or not [2,3]. The artificial intelligent-based methods are very effective and popular one in recent years [24].…”

Section: Literature Surveymentioning

confidence: 99%

“…The recent blooming in the data mining approaches has provided a solid platform for various applications in the healthcare field. In healthcare, data mining is playing a vital role in different fields like intrusion detection, pattern recognition, cheaper medical treatments' availability for the patients, disease diagnosing and finding its procurement methods [2,3]. An artificial intelligence makes the system more sensitive and activates the system to think.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes

Jackins¹,

Vimal²,

Kaliappan³

et al. 2020

J Supercomput

195

View full text Add to dashboard Cite

Healthcare practices include collecting all kinds of patient data which would help the doctor correctly diagnose the health condition of the patient. These data could be simple symptoms observed by the subject, initial diagnosis by a physician or a detailed test result from a laboratory. Thus, these data are only utilized for analysis by a doctor who then ascertains the disease using his/her personal medical expertise. The artificial intelligence has been used with Naive Bayes classification and random forest classification algorithm to classify many disease datasets like diabetes, heart disease, and cancer to check whether the patient is affected by that disease or not. A performance analysis of the disease data for both algorithms is calculated and compared. The results of the simulations show the effectiveness of the classification techniques on a dataset, as well as the nature and complexity of the dataset used.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes

Jackins¹,

Vimal²,

Kaliappan³

et al. 2020

J Supercomput

195

View full text Add to dashboard Cite

show abstract

“…The idea of modified extreme learning machine was analyzed by Priyadarshini et al [14] for recognizing the patients of being diabetic or non-diabetic basing on some previously provided data which assist the medical people for detecting whether someone is affected by diabetes or not. The application of two popular machine learning methods: Back propagation neural network and modified Extreme learning machine were examined and distinguished and it helps as binary classifiers to mention the diabetes prediction problem.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Initially, the medical implication of every attribute is examined in correlation to the DM. The attribute "no of pregnancies "is defined to have low impact on the DM [14] and this numeric value is changed to a nominal value by assigning 0 for non-pregnant and 1 for pregnant. This resulted in the minimization of the data complexity.…”

Section: Figure 1: Block Diagram Of the Proposed Intelligent System Fmentioning

confidence: 99%

Improved K-Means with Adaptive Divergence Weight Bat Algorithm (IKM-ADWBA) and Feature Selection for Type 2 Diabetes Mellitus Prediction

2019

IJRTE

View full text Add to dashboard Cite

Increase in blood glucose (hyperglycaemia) leads to Diabetes Mellitus. There are two kinds of Diabetes mellitus: (Type 1 Diabetes Mellitus (T1DM) and (Diabetes Mellitus (T2DM), then former one is dependent on insulin and the latter one is independent of insulin. Various factors make it difficult to diagnose it. SO the author focuses at binging-in and analyzing the method for making a novel robust diagnosis system using data mining methods. Complete datasets is necessary for data mining techniques, but these techniques doesn’t give accurate results with missing values and all features. So, for prediction, Handling Missing value replacement and selection of important features are becomes a major issue. Hence, Adaptive Neuro Fuzzy Inference System (ANFIS) were proposed to acquire the missing value in dataset and to rectify the above mentioned issue. Then for an effective seed selection in Improved K-means algorithm, Enhanced Inertia Weight Binary Bat Algorithm (EIWBBA) is proposed, which results in high convergence speed. This research work proposed for feature selection with the help of Improved Distributed Kernel based Principal Component analysis (IDKPCA) with less time, after minimizing the entire feature space to the best features set. Then for classification of clustered samples, the author brought-in the Support Vector Machine (SVM). The experimental result confirms that the proposed algorithm gives the best classification accuracy rate when compared with other methods. From Pima Indians Diabetes, the data set has been considered and the experiment is done with the help of MATLAB for examining the Knowledge and the results were distinguished with other outcomes using appropriate toolkits.

show abstract

“…Classification is performed with the help of ten folds crossvalidation technique. Priyadarshini et al [17] applied the concept of modified Extreme Learning Machine (ELM) to determine the patients being affected by diabetic or not depending on the information provided, which facilitates the clinical people in identifying the diabetic and nondiabetic patients. It characterizes and correlates the application of two famous machine learning techniques: One is the Back Propagation Neural Network (BPNN) and the other is modified ELM which in turn acts as binary classifiers that help in the prediction of diabetics.…”

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

A Novel approach to predict diabetes mellitus using modified Extreme learning machine

Cited by 31 publications

References 2 publications

AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes

AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes

Improved K-Means with Adaptive Divergence Weight Bat Algorithm (IKM-ADWBA) and Feature Selection for Type 2 Diabetes Mellitus Prediction

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

Contact Info

Product

Resources

About