Authors: Ulzii-Orshikh Dorj; Young-Keun Lee; Sang-Seok Yun; Jae-Young Choi; Malrey Lee
Addresses: Center for Advanced Image and Information Technology, School of Electronics and Information Engineering, ChonBuk National University, 664-14, 1Ga, DeokJin-Dong, Jeonju, Chon buk, 561-756, South Korea ' Department of Orthopaedic Surgery, Research Institute of Clinical Medicine of Chonbuk National University – Biomedical Research Institute of Chonbuk National University Hospital 20, Geonji-ro, Jeonju, 54907, South Korea ' Shilla University, Division of Mechanical Convergence Engineering, 140 Baegyang-daero(Blvd), 700 beon-gil (Rd.), Sasang-gu, Busan 46958, South Korea ' Department of Computer Engineering, Sungkyunkwan University, South Korea ' Center for Advanced Image and Information Technology, School of Electronics and Information Engineering, Chonbuk National University, 664-14, 1Ga, Deokjin-Dong, 54896, South Korea
Abstract: Although cardiovascular diseases are the number one cause of death globally, they are often diagnosed in hospitals during the late stages of life. This paper aims to make a cardiovascular disease diagnose system in the mobile environment using the Artificial Neural Network. Survey data has been collected from public institutions based on characteristics including, gender type, age, height, weight, body mass index, high blood glucose, heart rates, end-systolic and end-diastolic pressure, history of cardiac infarction and angina pectoris. The collected data is manipulated through training functions. The training functions are compared using Bayesian Regulation backpropagation and Levenberg-Marquardt backpropagation. Subsequently, the computed results are analysed which show significant performance. Finally, the results are analysed by using performance functions: mean squared error and sum squared error. Consequently, this study validates the accuracy of cardiovascular disease diagnosis by comparing with error rates, trained results, and the actual data.
Keywords: mobile clinical decision supporting system; cardiovascular diagnosis; artificial neural network; sensor.
International Journal of Sensor Networks, 2018 Vol.26 No.2, pp.125 - 135
Available online: 28 Dec 2017Full-text access for editors Access for subscribers Purchase this article Comment on this article