TY - GEN
T1 - Generalized learning vector quantization particle swarm optimization (GLVQ-PSO) FPGA implementation for real-time electrocardiogram
AU - Wardhana, Yulistiyan
AU - Jatmiko, Wisnu
AU - Rachmadi, M. Febrian
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/3/6
Y1 - 2017/3/6
N2 - Cardiovascular system is the most important part of human body which has role as distribution system of Oxygen and body's wastes. To do the job, there are more than 60.000 miles of blood vessels participated which can caused a problem if one of them are being clogged. Unfortunately, the conditions of clogged blood vessels or diseases caused by cardiovascular malfunction could not be detected in a plain view. In this matter, we proposed a design of wearable device which can detect the conditions. The device is equipped with a newly neural network algorithm, GLVQ-PSO, which can give recommendation of the heart status based on learned data. After the research is conducted, the algorithm produce better accuracy than LVQ, GLVQ and FNGLVQ in the high level language implementation. Yet, GLVQ-PSO still has relatively worse performance in its FPGA implementation.
AB - Cardiovascular system is the most important part of human body which has role as distribution system of Oxygen and body's wastes. To do the job, there are more than 60.000 miles of blood vessels participated which can caused a problem if one of them are being clogged. Unfortunately, the conditions of clogged blood vessels or diseases caused by cardiovascular malfunction could not be detected in a plain view. In this matter, we proposed a design of wearable device which can detect the conditions. The device is equipped with a newly neural network algorithm, GLVQ-PSO, which can give recommendation of the heart status based on learned data. After the research is conducted, the algorithm produce better accuracy than LVQ, GLVQ and FNGLVQ in the high level language implementation. Yet, GLVQ-PSO still has relatively worse performance in its FPGA implementation.
UR - http://www.scopus.com/inward/record.url?scp=85016982457&partnerID=8YFLogxK
U2 - 10.1109/IWBIS.2016.7872897
DO - 10.1109/IWBIS.2016.7872897
M3 - Conference contribution
AN - SCOPUS:85016982457
T3 - 2016 International Workshop on Big Data and Information Security, IWBIS 2016
SP - 103
EP - 108
BT - 2016 International Workshop on Big Data and Information Security, IWBIS 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 International Workshop on Big Data and Information Security, IWBIS 2016
Y2 - 18 October 2016 through 19 October 2016
ER -
