IoHT with Wearable Devices–Based Feature Extraction and a Deep Neural Networks Classification Model for Heart Disease Diagnosis

2021 ◽  
pp. 177-190
Author(s):  
K. Shankar ◽  
Eswaran Perumal ◽  
Deepak Gupta
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Heart Disease ◽  
Deep Neural Networks ◽  
Disease Diagnosis ◽  
Wearable Devices ◽  
Classification Model ◽  
Heart Disease Diagnosis

An Efficient System for Heart Disease Prediction Using Hybrid OFBAT with Rule-Based Fuzzy Logic Model

2016 ◽  
Vol 26 (04) ◽  
pp. 1750061 ◽  
Author(s):  
G. Thippa Reddy ◽  
Neelu Khare
Keyword(s):  
Fuzzy Logic ◽  
Heart Disease ◽  
Fuzzy System ◽  
Disease Diagnosis ◽  
Fuzzy Logic System ◽  
Classification Model ◽  
Rule Based ◽  
Diagnosis System ◽  
Heart Disease Diagnosis ◽  
Logic System

The objective of the work is to predict heart disease using computing techniques like an oppositional firefly with BAT and rule-based fuzzy logic (RBFL). The system would help the doctors to automate heart disease diagnosis and to enhance the medical care. In this paper, a hybrid OFBAT-RBFL heart disease diagnosis system is designed. Here, at first, the relevant features are selected from the dataset using locality preserving projection (LPP) algorithm which helps the diagnosis system to develop a classification model using the fuzzy logic system. After that, the rules for the fuzzy system are created from the sample data. Among the entire rules, the important and relevant group of rules are selected using OFBAT algorithm. Here, the opposition based learning (OBL) is hybrid to the firefly with BAT algorithm to improve the performance of the FAT algorithm while optimizing the rules of the fuzzy logic system. Next, the fuzzy system is designed with the help of designed fuzzy rules and membership functions so that classification can be carried out within the fuzzy system designed. At last, the experimentation is performed by means of publicly available UCI datasets, i.e., Cleveland, Hungarian and Switzerland datasets. The experimentation result proves that the RBFL prediction algorithm outperformed the existing approach by attaining the accuracy of 78%.

scholarly journals Heart Disease Diagnosis by Neural Networks

2021 ◽  
pp. 202-208
Author(s):  
Khyati Varshney ◽  
Mrinal Paliwal
Keyword(s):  
Neural Networks ◽  
Heart Disease ◽  
Mortality Rate ◽  
Intelligent Systems ◽  
Heart Diseases ◽  
Disease Diagnosis ◽  
Daily Basis ◽  
The World ◽  
Multilayer Neural Networks ◽  
Heart Disease Diagnosis

In the present time the Mortality rate will be increased all around the world on their daily basis. So the cause for this might possibly be largely ascribe to the developing in the numbers of the patients with the cardiovascular patient’s diseases. To aggravate the cases, many physicians that have been known for the misdiagnosis of the patients announce heart related ailments. In this research paper, the intelligent systems have been designed in which they will help in the successful diagnosis of the forbearing to avoiding misdiagnosis. In the dataset of a UCI stat log of heart disease that will be using in this investigation. The dataset contains 14 attributes which are essential in the diagnosis of the heart diseases. A system is sculpted on the multilayer neural networks trained with convolutional & simulated convolutional neural networks. The identification of 89% was acquired from the testing of the networks.

scholarly journals Coronary heart disease diagnosis by artificial neural networks including genetic polymorphisms and clinical parameters

2012 ◽  
Vol 59 (2) ◽  
pp. 190-194 ◽  
Author(s):  
Oleg Yu. Atkov ◽  
Svetlana G. Gorokhova ◽  
Alexandr G. Sboev ◽  
Eduard V. Generozov ◽  
Elena V. Muraseyeva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Coronary Heart Disease ◽  
Artificial Neural Networks ◽  
Heart Disease ◽  
Genetic Polymorphisms ◽  
Disease Diagnosis ◽  
Clinical Parameters ◽  
Artificial Neural ◽  
Heart Disease Diagnosis

scholarly journals Classification and Feature Selection Approaches by Machine Learning Techniques: Heart Disease Prediction

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
N. Satish Chandra Reddy ◽  
Song Shue Nee ◽  
Lim Zhi Min ◽  
Chew Xin Ying
Keyword(s):  
Feature Selection ◽  
Heart Disease ◽  
Causes Of Death ◽  
Disease Diagnosis ◽  
Performance Model ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Heart Disease Diagnosis ◽  
The Cost

The heart disease has been one of the major causes of death worldwide. The heart disease diagnosis has been expensive nowadays, thus it is necessary to predict the risk of getting heart disease with selected features. The feature selection methods could be used as valuable techniques to reduce the cost of diagnosis by selecting the important attributes. The objectives of this study are to predict the classification model, and to know which selected features play a key role in the prediction of heart disease by using Cleveland and statlog project heart datasets. The accuracy of random forest algorithm both in classification and feature selection model has been observed to be 90–95% based on three different percentage splits. The 8 and 6 selected features seem to be the minimum feature requirements to build a better performance model. Whereby, further dropping of the 8 or 6 selected features may not lead to better performance for the prediction model.

Sign in / Sign up

Export Citation Format

Share Document