Secure blockchain enabled Cyber- Physical health systems using ensemble convolution neural network classification. (July 2022)

• Record Type: Journal Article
• Authors: Ramanan, M.; Singh, Laxman; Kumar, A. Suresh; Suresh, A.; Sampathkumar, A.; Jain, Vishal; Bacanin, Nebojsa
• Is Part Of: Computers & electrical engineering. Volume 101(2022)
• Publication Date: 2022-07
• Subjects: Cyber–physical system -- Cybersecurity -- Blockchain -- Breast cancer -- Malignant; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108058
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Breast cancer is most widely recognized malignancy of women. The risk of death has been consistently associated with breast cancer. The cyber-physical (CPS) system is the processing and the data transfer of physical processes. This study presents a safe intrusive, block chain-based data transfer using CPS Classification Model in the health industry to overcome the problem. This article accords a reasonable thought of arrangement to examine the mammogram image to discover the detection and classification of various stages of cancer. Abstract: Breast cancer is the most widely recognized malignancy affecting women. The risk of death has been consistently associated with breast cancer. In addition, the cyber-physical system (CPS)is the processing and data transfer of physical processes. This study presents a safe, intrusive, blockchain-based data transfer using the CPS classification model in the health industry to overcome the problem. Considering the challenges in breast tumor classification, this paper accords a reasonablearrangement to examine the mammogram image to discover the detection and classification of various stages of cancer. The breast cancer detection images obtained from the mammogram were processed and experimentally evaluated for parameters such as a sensitivity of 90%, a specificity of 98%, andaclassification accuracy of 98%.The results of the ensemble convolution neural network (E-CNN) classifier, such as VGG-16 and Inception-v3, which separates ordinary and unusual cases from the applied advanced mammographic image, will be projected by comparing the two existing methods. Graphical abstract: Image, graphical abstract