ArticlePDF Available

An efficient clinical support system for heart disease prediction using TANFIS classifier

Authors:
s. Jayachitra at PSNACET
s. Jayachitra
Prasanth Aruchamy at Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology
Prasanth Aruchamy
  • Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology
S.L.A. Haleem at South Eastern University of Sri Lanka
S.L.A. Haleem
Amin Salih Mohammed
Amin Salih Mohammed
Amin Salih Mohammed
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Show all 5 authorsHide
Download full-text PDF
Read full-text
Download citation

Abstract

In today's world, the advancement of telediagnostic equipment plays an essential role to monitor heart disease. The earlier diagnosis of heart disease proliferates the compatibility of treatment of patients and predominantly provides an expeditious diagnostic recommendation from clinical experts. However, the feature extraction is a major challenge for heart disease prediction where the high dimensional data increases the learning time for existing machine learning classifiers. In this article, a novel efficient Internet of Things-based tuned adaptive neuro-fuzzy inference system (TANFIS) classifier has been proposed for accurate prediction of heart disease. Here, the tuning parameters of the proposed TANFIS are optimized through Laplace Gaussian mutation-based moth flame optimization and grasshopper optimization algorithm. The simulation scenario can be carried out using11 different datasets from the UCI repository. The proposed method obtains an accuracy of 99.76% for heart disease prediction and it has been improved upto 5.4% as compared with existing algorithms.
Content uploaded by S.L.A. Haleem
Author content
All content in this area was uploaded by S.L.A. Haleem on Mar 05, 2022
Content may be subject to copyright.
S.Jayachitra, A.Prasanth, Sulaima Lebbe Abdul Haleem, Amin Salih Mohammed, Shaik
Khamuruddeen. (2021), “An efficient clinical support system for heart disease prediction
using TANFIS classifier”, Computational Intelligence an International Journal, Willey Journal,
IF =2.333 (2020), Q3 Journal https://doi.org/10.1111/coin.12487
ABSTRACT
In today’s world, the advancement of tele diagnostic equipment plays an essential role to monitor
heart disease. The earlier diagnosis of heart disease proliferates the compatibility of treatment of
patients and predominantly provides an expeditious diagnostic recommendation from clinical
experts. However, the feature extraction is a major challenge for heart disease prediction where the
high dimensional data increases the learning time for existing machine learning classifiers. In this
article, a novel efficient Internet of Things-based tuned adaptive neuro-fuzzy inference system
(TANFIS) classifier has been proposed for accurate prediction of heart disease. Here, the tuning
parameters of the proposed TANFIS are optimized through Laplace Gaussian mutation-based moth
flame optimization and grasshopper optimization algorithm. The simulation scenario can be carried
out using11 different datasets from the UCI repository. The proposed method obtains an accuracy
of 99.76% for heart disease prediction and it has been improved up to 5.4% as compared with
existing algorithms.
KEYWORDS
classification, grasshopper optimization algorithm, heart disease prediction, internet of things, moth
flame optimization
You Can Access the full articles at this link
https://onlinelibrary.wiley.com/share/author/ZBDWKN5VMJNDTGPAUJN3?target=10.1111/coin.12487
... The prevalence of heart disease is still alarmingly high and affects millions of people worldwide. The World Health Organization claims that CVD are the leading cause of death in the world, with almost 18 million people dying from them every year (Sekar et al., 2022). In this scenario, age, gender, genetic factors, and lifestyle factors have been significant contributors to the increasing number of patients, with the risk in men being generally at a younger age when compared to women, whose risk is substantially increased after menopause (El-Shafiey et al., 2022;Eltrass et al., 2021). ...
Federated learning-based multimodal approach for early detection and personalized care in cardiac disease
Article
Full-text available
  • Apr 2025
Introduction Heart disease remains a leading cause of mortality globally, and early detection is critical for effective treatment and management. However, current diagnostic techniques often suffer from poor accuracy due to misintegration of heterogeneous health data, limiting their clinical usefulness. Methods To address this limitation, we propose a privacy-preserving framework based on multimodal data analysis and federated learning. Our approach integrates cardiac images, ECG signals, patient records, and nutrition data using an attention-based feature fusion model. To preserve patient data privacy and ensure scalability, we employ federated learning with locally trained Deep Neural Networks optimized using Stochastic Gradient Descent (SGD-DNN). The fused feature vectors are input into the SGD-DNN for cardiac disease classification. Results The proposed framework demonstrates high accuracy in cardiac disease detection across multiple datasets: 97.76% on Database 1, 98.43% on Database 2, and 99.12% on Database 3. These results indicate the robustness and generalizability of the model. Discussion Our framework enables early diagnosis and personalized lifestyle recommendations while maintaining strict data confidentiality. The combination of federated learning and multimodal feature fusion offers a scalable, privacy-centric solution for heart disease management, with strong potential for real-world clinical implementation.
View
... It is essential to pay close attention to the increasing demands for improved technologies that can handle problems with processing large data sets without affecting security and privacy 18,19 . Healthcare organizations employ tools for extensive data analysis that guarantee the availability 20 , confidentiality 21 , and integrity of protected health information 22 . The World Health Organization's estimates show that cardiac disease is the world's most significant cause of demise, which accounts for 17.9 million fatalities every year 23 . ...
Optimized machine learning mechanism for big data healthcare system to predict disease risk factor
Article
Full-text available
  • Apr 2025
Heart disease is becoming more and more common in modern society because of factors like stress, inadequate diets, etc. Early identification of heart disease risk factors is essential as it allows for treatment plans that may reduce the risk of severe consequences and enhance patient outcomes. Predictive methods have been used to estimate the risk factor, but they often have drawbacks such as improper feature selection, overfitting, etc. To overcome this, a novel Deep Red Fox belief prediction system (DRFBPS) has been introduced and implemented in Python software. Initially, the data was collected and preprocessed to enhance its quality, and the relevant features were selected using red fox optimization. The selected features analyze the risk factors, and DRFBPS makes the prediction. The effectiveness of the DRFBPS model is validated using Accuracy, F score, Precision, AUC, Recall, and error rate. The findings demonstrate the use of DRFBPS as a practical tool in healthcare analytics by showing the rate at which it produces accurate and reliable predictions. Additionally, its application in healthcare systems, including clinical decisions and remote patient monitoring, proves its real-world applicability in enhancing early diagnosis and preventive care measures. The results prove DRFBPS to be a potential tool in healthcare analytics, providing a strong framework for predictive modeling in heart disease risk prediction.
View
... In the future, the early cardiac diagnostics pattern will be focused on heart attack preventive medicine. The support of AI techniques for non-invasive medical imaging and different machine learning models has been studied in recent years [18,19]. It is important to find out an increased risk of a heart attack early and treat it with preventive drugs before the need to use more complicate forms of therapy [20]. ...
A novel recommender framework with chatbot to stratify heart attack risk
Article
Full-text available
  • Dec 2024
Cardiovascular diseases are a major cause of mortality and morbidity. Fast detection of life-threatening emergency events and an earlier start of the therapy would save many lives and reduce successive disabilities. Understanding the specific risk factors associated with heart attack and the degree of association is crucial in the clinical diagnosis. Considering the potential benefits of intelligent models in healthcare, many researchers have developed a variety of machine learning (ML)-based models to identify patients at risk of a heart attack. However, the common problem of previous works that used ML concepts was the lack of transparency in black-box models, which makes it difficult to understand how the model made the prediction. In this study, an automated smart recommender system (Explainable Artificial Intelligence) for heart attack prediction and risk stratification was developed. For the purpose, the CatBoost classifier was applied as the initial step. Then, the SHAP (SHapley Additive exPlanation) explainable algorithm was employed to determine reasons behind high or low risk classification. The recommender system can provide insights into the reasoning behind the predictions, including group-based and patient-specific explanations. In the final step, we integrated a Large Language Model (LLM) called BioMistral for chatting functionally to talk to users based on the model output as a digital doctor for consultation. Our smart recommender system achieved high accuracy in predicting a patient risk level with an average AUC of 0.88 and can explain the results transparently. Moreover, a Django-based online application that uses patient data to update medical information about an individual’s heart attack risk was created. The LLM chatbot component would answer user questions about heart attacks and serve as a virtual companion on the route to heart health, our system also can locate nearby hospitals by applying Google Maps API and alert the users. The recommender system could improve patient management and lower heart attack risk while timely therapy aids in avoiding subsequent disabilities.
View
View
View
Smart Medical Devices and Wearable Health Technologies
Chapter
  • Feb 2025
Smart medical devices are widely used to treat various disease, tracking patient's health status, and providing earlier treatments. The future healthcare depends upon the interrelations of humans to intelligent devices through communication networks for monitoring medical status of the patient. The Smart medical devices gather the data from the humans and makes smart decisions to the user from the measured data. In this chapter, the significant research works carried out in wearable Internet of Things and classifies the wearable medical devices with various categories as health, sports, athletics, and daily activity, tracking the information, and providing safety. The adoption of healthcare technologies such as Artificial Intelligence, Internet of Things plays a crucial role in healthcare system that brings the transformation from hospital to the patient and examining the physiological data remotely and providing recommendation. This chapter explores the function of wearable devices, and healthcare technologies, and challenges of wearable devices in healthcare.
View
View
Deep Convolutional Generative Adversarial Network for Improved Cardiac Image Classification in Heart Disease Diagnosis
Article
  • Dec 2024
Heart disease is a fatal disease that causes significant mortality rates worldwide. The accurate and early detection of heart diseases is the most challenging task to save valuable lives. To avoid these issues, the Deep Convolutional Generative Adversarial Network (DCGAN) model is proposed that generates synthetic cardiac images. Here, two types of heart disease datasets such as the Sunnybrook Cardiac Dataset (SCD) and the Automated Cardiac Diagnosis Challenge (ACDC) dataset are selected to choose real cardiac images for implementation. The quality and consistency of the cardiac images are enhanced by preprocessed real cardiac images. In the DCGAN model, the generator is used for converting real cardiac images into synthetic images and the discriminator is responsible for differentiating real and synthetic cardiac images by binary classification decisions. To enhance the model’s robustness and generalization ability, diverse augmentation techniques are implemented. The VGG16 model is applied in this paper for the image classification task and fine-tuned its parameters to optimize model convergence. For experimental validation, some of the significance metrics such as accuracy, precision, diagnostic time, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), false positive rate (FPR), false negative rate (FNR), and mean squared error (MSE) are utilized. The extensive experimental evaluations are carried out based on this metrics and attained a performance rate of the proposed method as 98.83%, 1.17%, 3.2%, 41.78, 4.52, 0.932, and 1.6 s from accuracy, FPR, FNR, PSNR, MSE, SSIM, and diagnostic time, respectively. The experimental evaluation results demonstrate that the proposed heart disease diagnosis model attains superior performances than state-of-the-art methods.
View
Spatiotemporal data fusion and deep learning for remote sensing-based sustainable urban planning
Article
  • Nov 2024
Urban settlements exhibit a high degree of dynamism and complexity, since they are subject to fast changes in spatial organization, temporal patterns, and socioeconomic dynamics. The achievement of sustainable development in cities requires the implementation of planning strategies that are informed by empirical knowledge and guided by a comprehensive comprehension of the complex urban changes taking place. This study aims to use spatiotemporal data fusion and deep learning methods to integrate various urban data streams and effectively predict intricate urban development patterns. The goal is to utilize these models to provide valuable insights for sustainable planning strategies. Convolutional fusion architectures are used to integrate high-resolution satellite images with population census information, transportation networks, land use maps, and housing statistics. The use of a long short-term memory neural network facilitates the comprehensive capture of complex spatial and temporal relationships. The methodology is used to three rapidly expanding cities to model detailed future urbanization scenarios and assess the sustainability implications of different growth strategies in the next several decades. The findings demonstrate that the fusion framework has a high level of reliability in accurately forecasting emerging development hotspots, urban density patterns, and infrastructure challenges, with an accuracy rate of 80%. The findings from simulations indicate that if peripheral growth is not regulated, it would place significant pressure on water supplies and exacerbate the phenomenon of urban heat islands. However, implementing certain policies that promote densification may help alleviate these problems and facilitate the adoption of sustainable development pathways. This paper presents a scalable methodology that use data-driven techniques to anticipate and guide the complex dynamics of rapidly evolving urban areas towards sustainable development.
View
One new family of smooth semi-supervised support vector classifier based on Fourier series approximation technique
Article
Full-text available
  • Nov 2024
  • PATTERN ANAL APPL
This article presents a new family of smooth semi-supervised support vector machines based on Fourier series approximation technique (FS-S⁴VMs) for classification. The semi-supervised support vector machine (S³VM) is the powerful tool for coping with quantities of unlabeled data in the real world. However, the symmetric hinge loss function of S³VM is not smooth. It will decrease the classification accuracy and endure heavy burden calculation. To deal with this problem, the Fourier series approximation smooth technique for replacing the non-smooth item have been investigated. One novel family of FS-S⁴VMs classifier is derived. Thus, one fast SAGA algorithm for solving non-convex FS-S⁴VMs can be utilized to decrease the computing scale. The nonlinear case and convergence analysis are presents as well. To attest how the new FS-S⁴VMs can be implemented into practice, experiments on synthetic and real data sets are accessed. In the final, theoretical explanation and simulation comparisons illustrate the FS-S⁴VMs enhance the robustness of S³VM, and increase the classification accuracy at about 1%–3% than other smooth techniques.
View
Internet of things in health management systems: A review
Article
Full-text available
In today's health care context, the application of the Internet of Things (IoT) offers suitability for doctors and patients as we can use them in many medical fields. So, we have emphasized the particular use of the IoT in medicine and health care, such as clinical devices management, medication management, clinical data management, distant medicine, mobile medical care, and individual health management. We have done an organized review to enhance health management systems via many up‐to‐date IoT‐oriented health care applications. The article approbates with the methodological necessities of systematic literature reviews. We have identified several issues caused by the quick acceptance of IoT‐oriented systems' health management. IoT necessitates new safety infrastructure, according to the novel practical principles. Outcomes illustrate that health experts can assist in supplying necessities, information, or standards to improve IoT devices or systems. Also, they are able to present novel fields or applications for which IoT is fit. This survey aids the hospitals and relevant institutions to recognize IoT needs. Also, the article will serve as an initial location for future IoT security management and design. Policymakers and opinion formers need to understand the IoT and its implications.
View
Multi-Feature Analysis for Automated Brain Stroke Classification Using Weighted Gaussian Naïve Bayes Classifier
Article
Full-text available
In today’s world, brain stroke is considered as a life-threatening disease provoked by undesirable blockage among the arteries feeding the human brain. The timely diagnosis of this brain stroke detection in Magnetic Resonance Imaging (MRI) images increases the patient’s survival rate. However, automated detection plays a significant challenge owing to the complexity of the shape, dimension of size and the location of stroke lesions. In this paper, a novel optimized fuzzy level segmentation algorithm is proposed to detect the ischemic stroke lesions. After segmentation, the multi-textural features are extracted to form a feature set. These features are given as input to the proposed weighted Gaussian Naïve Bayes classifier to discriminate normal and abnormal stroke lesion classes. The experimental result manifests that the proposed methodology achieves a higher accuracy as compared with the existing state-of-the-art techniques. The proposed classifier discriminates normal and abnormal classes efficiently and attains 99.32% of accuracy, 96.87% of sensitivity and 98.82% of F1 measure.
View
A Healthcare Monitoring System for the Diagnosis of Heart Disease in the IoMT Cloud Environment Using MSSO-ANFIS
Article
Full-text available
  • Jul 2020
The IoT has applications in many areas such as manufacturing, healthcare, and agriculture, to name a few. Recently, wearable devices have become popular with wide applications in the health monitoring system which has stimulated the growth of the Internet of Medical Things (IoMT). The IoMT has an important role to play in reducing the mortality rate by the early detection of disease. The prediction of heart disease is a key issue in the analysis of clinical dataset. The aim of the proposed investigation is to identify the key characteristics of heart disease prediction using machine learning techniques. Many studies have focused on heart disease diagnosis, but the accuracy of the findings is low. Therefore, to improve prediction accuracy, an IoMT framework for the diagnosis of heart disease using modified salp swarm optimization (MSSO) and an adaptive neuro-fuzzy inference system (ANFIS) is proposed. The proposed MSSO-ANFIS improves the search capability using the Levy flight algorithm. The regular learning process in ANFIS is dependent on gradient-based learning and has a tendency to become trapped in local minima. The learning parameters are optimized utilizing MSSO to provide better results for ANFIS. The following information is taken from medical records to predict the risk of heart disease: blood pressure (BP), age, sex, chest pain, cholesterol, blood sugar, etc. The heart condition is identified by classifying the received sensor data using MSSO-ANFIS. A simulation and analysis is conducted to show that MSSA-ANFIS works well in relation to disease prediction. The results of the simulation demonstrate that the MSSO-ANFIS prediction model achieves better accuracy than the other approaches. The proposed MSSO-ANFIS prediction model obtains an accuracy of 99.45 with a precision of 96.54, which is higher than the other approaches.
View
A Novel Smart Healthcare Design, Simulation, and Implementation Using Healthcare 4.0 Processes
Article
Full-text available
  • Jun 2020
Blockchain technology is found to have its applicability in almost every domain because of its advantages such as crypto-security, transparency, immutability, decentralized data network. In present times, a smart healthcare system with a blockchain data network and healthcare 4.0 processes provides transparency, easy and faster accessibility, security, efficiency, etc. Healthcare 4.0 trends include industry 4.0 processes such as the internet of things (IoT), industrial IoT (IIoT), cognitive computing, artificial intelligence, cloud computing, fog computing, edge computing, etc. The goal of this work is to design a smart healthcare system and it is found to be possible through integration and interoperability of Blockchain 3.0 and Healthcare 4.0 in consideration with healthcare ground-realities. Here, healthcare 4.0 processes used for data accessibility are targeted to be validated through statistical simulation-optimization methods and algorithms. The blockchain is implemented in the Ethereum network, and with associated programming languages, tools, and techniques such as solidity, web3.js, Athena, etc. Further, this work prepares a comparative and comprehensive survey of state-of-the-art blockchain-based smart healthcare systems. The comprehensive survey includes methodology, applications, requirements, outcomes, future directions, etc. A list of groups, organizations, and enterprises are prepared that are working in electronic health records (EHR), electronic medical records (EMR) or electronic personal records (EPR) mainly, and a comparative analysis is drawn concerning adopting the blockchain technology in their processes. This work has explored optimization algorithms applicable to Healthcare 4.0 trends and improves the performance of blockchain-based decentralized applications for the smart healthcare system. Further, smart contracts and their designs are prepared for the proposed system to expedite the trust-building and payment systems. This work has considered simulation and implementation to validate the proposed approach. Simulation results show that the Gas value required (indicating block size and expenditure) lies within current Etherum network Gas limits. The proposed system is active because block utilization lies above 80%. Automated smart contract execution is below 20 seconds. A good number (average 3 per simulation time) is generated in the network that indicates a health competition. Although there is error observed in simulation and implementation that lies between 0.55% and 4.24%, these errors are not affecting overall system performance because simulated and actual (taken in state-of-the-art) data variations are negligible.
View
A Tuned Classification Approach for Efficient Heterogeneous Fault Diagnosis in IoT-enabled WSN Applications
Article
  • Jun 2021
  • MEASUREMENT
The advancement of the Internet of Things (IoT) technologies will play a significant role in the growth of smart cities and industrial applications. Wireless Sensor Network (WSN) is one of the emerging technology utilized for sensing and data transferring processes in IoT-based applications. However, heterogeneous faults like hardware, software, and time-based faults are the major determinants that affect the network stability of IoT based WSN (IWSN) model. In this paper, a novel Energy-Efficient Heterogeneous Fault Management scheme has been proposed to manage these heterogeneous faults in IWSN. Efficient heterogeneous fault detection in the proposed scheme can be achieved by using three novel diagnosis algorithms. The new Tuned Support Vector Machine classifier facilitates to classify the heterogeneous faults where the tuning parameters of the proposed classifier will be optimized through Hierarchy based Grasshopper Optimization Algorithm. Finally, the performance results evident that the diagnosis accuracy of the proposed scheme acquires 99% and the false alarm rate sustains below 1.5% during a higher fault probability rate. The diagnosis accuracy rate is enhanced up to 17% as compared with existing techniques.
View
The Role of the Internet of Things in Healthcare: Future Trends and Challenges
Article
  • Dec 2020
  • COMPUT METH PROG BIO
Background and Objective With the recent advances in the Internet of Things (IoT), the field has become more and more developed in healthcare. The Internet of things will help physicians and hospital staff perform their duties comfortably and intelligently. With the latest advanced technologies, most of the challenges of using IoT have been resolved, and this technology can be a great revolution and has many benefits in the future of digital. Healthcare is one of the most useful areas for IoT use. The most important application of IoT is to monitor and make quick decisions in critical situations. Thanks to this technology-based treatment approach, there is an unprecedented opportunity to better the quality and productivity of treatments and better the patient's well-being and better government funding. Methods In this paper, we provide a comprehensive overview of the primary uses of IoT in healthcare. We used the Systematic Literature Review (SLR) method to analyze and comparison articles published in this field between 2015 and March 2020. Results A comprehensive taxonomy is presented based on the contents of the articles under study. In this article, a brief overview of selected articles based on research questions is given and highlights the most critical challenges and case studies for the future use of IoT in healthcare. Conclusions According to a detailed study of the 89 articles and a glimpse into about 208 articles, challenges and future trends in healthcare have been identified.
View
An integrated methodology to control the risk of cardiovascular disease in patients with hypertension and type 1 diabetes
Article
  • Oct 2020
Today, air pollution, smoking, use of fatty acids and ready‐made foods, and so on, have exacerbated heart disease. Therefore, controlling the risk of such diseases can prevent or reduce their incidence. The present study aimed at developing an integrated methodology including Markov decision processes (MDP) and genetic algorithm (GA) to control the risk of cardiovascular disease in patients with hypertension and type 1 diabetes. First, the efficiency of GA is evaluated against Grey Wolf optimization (GWO) algorithm, and then, the superiority of GA is revealed. Next, the MDP is employed to estimate the risk of cardiovascular disease. For this purpose, model inputs are first determined using a validated micro‐simulation model for screening cardiovascular disease developed at Tehran University of Medical Sciences, Iran by GA. The model input factors are then defined accordingly and using these inputs, three risk estimation models are identified. The results of these models support WHO guidelines that provide medicine with a high discount to patients with high expected LYs. To develop the MDP methodology, policies should be adopted that work well despite the difference between the risk model and the actual risk. Finally, a sensitivity analysis is conducted to study the behavior of the total medication cost against the changes of parameters.
View
A hybrid recurrent neural network‐logistic chaos‐based whale optimization framework for heart disease prediction with electronic health records
Article
  • Oct 2020
Heart disease, known interchangeably as “Cardio Vascular Disease,” blocks the blood vessels in the heart and causes heart attack, chest pain, and stroke. Heart disease is one of the leading causes of morbidity and mortality worldwide and it is one of the major causes of morbidity and mortality globally and a trending topic in clinical data analysis. Assessing risk factors related to heart disease is considered as an important step in diagnosing the disease at an early stage. Clinical data present in the form of electronic health records (EHR) can be extracted with the aid of machine learning (ML) algorithms to provide valuable decisions and predictions. ML approaches also play a vital role in early diagnosis and therapeutic monitoring of heart disease. Several research works have been carried out recently to predict heart disease. To this end, we propose a novel hybrid recurrent neural network (RNN)‐logistic chaos‐based whale optimization (LCBWO) structured hybrid framework for predicting heart disease within 5 years using EHR data. Meanwhile, in the hybrid model established multilayer bidirectional LSTM is used for feature selection, LCBWO algorithm for structural improvement and fast convergence, and LSTM for disease prediction. This research used 10 cross‐validations to obtain generalized accuracy and error values. The findings and observations provided here are focused on the knowledge obtained from the EHR report. The results show that the proposed novel hybrid RNN‐LCBWO framework achieves a higher accuracy of 98%, a specificity of 99%, precision of 96%, Mathews correlation coefficient of 91%, F‐measure of 0.9892, an area under the curve value of 98%, and a prediction time of 9.23 seconds. The accurate predictions obtained from the comparative analysis shows the significant performance of our proposed framework.
View
Energy Efficient Clustering with Disease Diagnosis Model for IoT based Sustainable Healthcare Systems
Article
  • Sep 2020
Sustainable energy efficient networking models are needed to satisfy the increasing demands of the information and communication technologies (ICT) applications like healthcare, smart cities, education, and so on. The futuristic sustainable computing solutions in e-healthcare applications are based on the Internet of Things (IoT) and cloud computing platform, has offered numerous features and real time services. Several studies revealed that the amount of energy spent on transmitting data from IoT devices to a cloud server is considerably high and resulted in rapid energy depletion. In this view, this paper presents an Energy Efficient Particle Swarm Optimization (PSO) based Clustering (EEPSOC) technique for the effective selection of cluster heads (CHs) among diverse IoT devices. The IoT devices used for sensing healthcare data are grouped into a form of clusters and a CH will be elected by the use of EEPSOC. The elected CH will forward the data to the cloud server. Then, the CH is responsible for transmitting data of the IoT devices to the cloud server through fog devices. Next to that, an artificial neural network (ANN) based classification model is applied to diagnose the healthcare data in the cloud server to identify the severity of the diseases. For experimentation, a systematic student perspective healthcare data is produced utilizing UCI dataset and medicinal gadgets to foresee the diverse student levels of disease severity. A detailed comparative analysis is carried out and the simulation outcome ensured the goodness of the EEPSOC-ANN model over the compared methods under various aspects.
View
Data preprocessing for heart disease classification: A systematic literature review
Article
  • Jul 2020
  • COMPUT METH PROG BIO
Context Early detection of heart disease is an important challenge since 17.3 million people yearly lose their lives due to heart diseases. Besides, any error in diagnosis of cardiac disease can be dangerous and risks an individual's life. Accurate diagnosis is therefore critical in cardiology. Data Mining (DM) classification techniques have been used to diagnosis heart diseases but still limited by some challenges of data quality such as inconsistencies, noise, missing data, outliers, high dimensionality and imbalanced data. Data preprocessing (DP) techniques were therefore used to prepare data with the goal of improving the performance of heart disease DM based prediction systems. Objective The purpose of this study is to review and summarize the current evidence on the use of preprocessing techniques in heart disease classification as regards: (1) the DP tasks and techniques most frequently used, (2) the impact of DP tasks and techniques on the performance of classification in cardiology, (3) the overall performance of classifiers when using DP techniques, and (4) comparisons of different combinations classifier-preprocessing in terms of accuracy rate. Method A systematic literature review is carried out, by identifying and analyzing empirical studies on the application of data preprocessing in heart disease classification published in the period between January 2000 and June 2019. A total of 49 studies were therefore selected and analyzed according to the aforementioned criteria. Results The review results show that data reduction is the most used preprocessing task in cardiology, followed by data cleaning. In general, preprocessing either maintained or improved the performance of heart disease classifiers. Some combinations such as (ANN + PCA), (ANN + CHI) and (SVM + PCA) are promising terms of accuracy. However the deployment of these models in real-world diagnosis decision support systems is subject to several risks and limitations due to the lack of interpretation.
View