Vol.70, No.1, 2022, pp.1557-1572, doi:10.32604/cmc.2022.019323
OPEN ACCESS
ARTICLE
Distributed Healthcare Framework Using MMSM-SVM and P-SVM Classification
  • R. Sujitha*, B. Paramasivan
Department of Information Technology, National Engineering College (Autonomous), Kovilpatti, 628503, Tamilnadu, India
* Corresponding Author: R. Sujitha. Email:
Received 10 April 2021; Accepted 27 May 2021; Issue published 07 September 2021
Abstract
With the modernization of machine learning techniques in healthcare, different innovations including support vector machine (SVM) have predominantly played a major role in classifying lung cancer, predicting coronavirus disease 2019, and other diseases. In particular, our algorithm focuses on integrated datasets as compared with other existing works. In this study, parallel-based SVM (P-SVM) and multiclass-based multiple submodels (MMSM-SVM) were used to analyze the optimal classification of lung diseases. This analysis aimed to find the optimal classification of lung diseases with id and stages, such as key-value pairs in MapReduce combined with P-SVM and MMSVM for binary and multiclasses, respectively. For non-linear classification, kernel clustering-based SVM embedded with multiple submodels was developed. Both algorithms were developed using Apache spark environment, and data for the analysis were retrieved from microscope lab, UCI, Kaggle, and General Thoracic surgery database along with some electronic health records related to various lung diseases to increase the dataset size to 5 GB. Performance measures were conducted using a 5 GB dataset with five nodes. Dataset size was finally increased, and task analysis and CPU utilization were measured.
Keywords
Lung cancer; COVID-19; machine learning; deep learning; parallel based support vector machine; multiclass-based multiple submodel
Cite This Article
Sujitha, R., Paramasivan, B. (2022). Distributed Healthcare Framework Using MMSM-SVM and P-SVM Classification. CMC-Computers, Materials & Continua, 70(1), 1557–1572.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.