MKELM: Mixed Kernel Extreme Learning Machine using BMDA optimization for web services based heart disease prediction in smart healthcare. Issue 10 (27th July 2022)

• Record Type: Journal Article
• Authors: Sheeba, Adlin; Padmakala, S.; Subasini, C. A.; Karuppiah, S. P.
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 25:Issue 10(2022)
• Page Start: 1180
• Page End: 1194
• Publication Date: 2022-07-27
• Subjects: Machine learning -- healthcare -- M-health -- heart disease prediction -- BMDA -- Swarm intelligence algorithm -- MKELM -- web services; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2022.2034795
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: In recent years, cardiovascular disease becomes a prominent source of death. The web services connect other medical equipments and the computers via internet for exchanging and combining the data in novel ways. The accurate prediction of heart disease is important to prevent cardiac patients prior to heart attack. The main drawback of heart disease is delay in identifying the disease in the early stage. This objective is obtained by using the machine learning method with rich healthcare information on heart diseases. In this paper, the smart healthcare method is proposed for the prediction of heart disease using Biogeography optimization algorithm and Mexican hat wavelet to enhance Dragonfly algorithm optimization with mixed kernel based extreme learning machine (BMDA–MKELM) approach. Here, data is gathered from the two devices such as sensor nodes as well as the electronic medical records. The android based design is utilized to gather the patient data and the reliable cloud-based scheme for the data storage. For further evaluation for the prediction of heart disease, data are gathered from cloud computing services. At last, BMDA–MKELM based prediction scheme is capable to classify cardiovascular diseases. In addition to this, the proposed prediction scheme is compared with another method with respect to measures such as accuracy, precision, specificity, and sensitivity. The experimental results depict that the proposed approach achieves better results for the prediction of heart disease when compared with other methods.