文章基本信息

标题：ADAPTIVE NOISE CANCELLERS FOR CARDIAC SIGNAL ENHANCEMENT FOR IOT BASED HEALTH CARE SYSTEMS
本地全文：下载
作者：MD NIZAMUDDIN SALMAN ; P TRINATHA RAO ; MD ZIA UR RAHMAN 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：10
出版社：Journal of Theoretical and Applied
摘要：Cardiac Signals (CS) are affected with various artifacts during the acquisition and transmission. So these artifacts must be removed before presenting it to a doctor. In the proposed paper Normalized Median Least Mean Square (NMLMS) algorithm is being introduced for elimination of Power Line Interference (PLI), Baseline Wander (BW), Muscle artifacts (MA) and Electrode Motion (EM) from CS. The NMLMS has many advantages over the other conventional algorithms, i.e., it tends to reject single occurrence of large spikes of noise which otherwise introduces impulsive errors. Computational complexity can be reduced by the combination of sign algorithms with the NMLMS algorithm, which results in three new different algorithms. Based on the above algorithms, various Adaptive Noise Cancellers (ANC�s) have been developed to eliminate BW, MA and EM from the CS. The above mentioned algorithms have applied to real CS obtained from the MIT-BIH database. The simulation results confirm that the NSRMLMS algorithm is better than the conventional LMS algorithms in terms of Signal to Noise Ration Improvement (SNRI), Excessive Mean Square Error (EMSE) and Misadjustment (MSD). From the simulation results it is clear that NSRMLMS achieves the highest SNRI than the conventional LMS algorithms. The values are as follows: 11.2748dB, 9.4715dB, 10.6917dB and 10.7076 dB. These are the average values in terms of SNRI for PLI, BW, MA and EM respectively. Due to the reduced computational complexity these algorithms are usefull for Internt of Things (IOT) based remote health care monitoring systems.
关键词：Adaptive Algorithms; Adaptive Noise Cancellers; Artifacts; Cardiac Signal; health care systems.