Kyeong-Seop Kim

Kyeong-Seop Kim

Auto-generated profile, based on publicly available information

Kyeong-Seop Kim

Konkuk University

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2019 in Journal of Healthcare Engineering
Verified
Journal Article
Open access
PDF file
JKJeong-Hwan Kim
Jeong-Hwan Kim
SSSeung-Yeon Seo
Seung-Yeon Seo
CSChul-Gyu Song
Chul-Gyu Song
KKKyeong-Seop Kim
Kyeong-Seop Kim
The aim of this study is to design GoogLeNet deep neural network architecture by expanding the kernel size of the inception layer and combining the convolution layers to classify the electrocardiogram (ECG) beats into a normal sinus rhythm, premature ventricular contraction, atrial premature contraction, and right/left bundle branch block arrhythmia. Based on testing MIT-BIH arrhythmia benchmark databases, the scope of training/test ECG data was configured by covering at least three and seven R-peak features, and the proposed extended-GoogLeNet architecture can classify five distinct heartbeats; normal sinus rhythm (NSR), premature ventricular contraction (PVC), atrial premature contraction (APC), right bundle branch block (RBBB), and left bundle brunch block(LBBB), with an accuracy of 95.94%, an error rate of 4.06%, a maximum sensitivity of 96.9%, and a maximum positive predictive value of 95.7% for judging a normal or an abnormal beat with considering three ECG segments; an accuracy of 98.31%, a sensitivity of 88.75%, a specificity of 99.4%, and a positive predictive value of 94.4% for classifying APC from NSR, PVC, APC beats, whereas the error rate for misclassifying APC beat was relative low at 6.32%, compared with previous research efforts.

1 November 2009 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
KKKyeong-Seop Kim
Kyeong-Seop Kim
TYTae-Ho Yoon
Tae-Ho Yoon
JLJeong-Whan Lee
Jeong-Whan Lee
DKDong-Jun Kim
Dong-Jun Kim

1 August 2006
Verified
Conference Paper
Closed access
JLJeong-Whan Lee
Jeong-Whan Lee
KLKang-Hwi Lee
Kang-Hwi Lee
KKKyeong-Seop Kim
Kyeong-Seop Kim
DKDong-Jun Kim
Dong-Jun Kim
KKkyungho kim
kyungho kim
The design of an intelligent toothbrush, capable of monitoring brushing motion, orientation through the grip axis, during toothbrushing is described. Inappropriate tooth-brushing styles, even in adults, sometimes cause dental problems, cavities, gingivitis, etc. This smart system provides user to monitor his or her brushing pattern using accelerometer and magnetic sensors for evaluation of toothbrushing style. Directional information of toothbrush with respect to the earth's magnetic field and activity data were measured by a miniaturized low-power micro-controller, MSP430 and transmitted to personal computer by 2.4 GHz radio transmitter, nRF2401. A personal computer provides an on-line display of activity and orientation measurements during toothbrushing. The signal trace is then analyzed to extract clinically relevant information. This preliminary study showed that the proposed monitoring system was conceived to aid dental care personnel in patient education and instruction in oral hygiene regarding brushing style

1 February 2015 in Bio-Medical Materials and Engineering
Verified
Journal Article
Open access
PDF file
SSSeung-Won Shin
Seung-Won Shin
KKKyeong-Seop Kim
Kyeong-Seop Kim
CSChul-Gyu Song
Chul-Gyu Song
JLJeong-Whan Lee
Jeong-Whan Lee
JKJeong-Hwan Kim
Jeong-Hwan Kim
GJGyeo-Wun Jeung
Gyeo-Wun Jeung
The very first step to process electrocardiogram (ECG) signal is to eliminate baseline wandering interference that is usually caused by electrode-skin impedance mismatch, motion artifacts due to a patient’s body moment or respiratory breathing. A new method is thus suggested to remove baseline wandering in ECG by improving the detrending method that was originally proposed for eliminating slow non-stationary trends from heart rate variability (HRV). In our proposed method, a global trend is estimated in terms of baseline wandering by merging the local trend based on an ECG segment that represents a part of the ECG signal. The experimental results show that the improved detrending method can efficiently resolve baseline wandering without distorting any morphological characteristic embedded in the ECG signal in no time delay manner.

1 January 2005
Verified
Conference Paper
Closed access
KKKyeong-Seop Kim
Kyeong-Seop Kim
TYTae-Ho Yoon
Tae-Ho Yoon
JLJeong-Whan Lee
Jeong-Whan Lee
DKDong-Jun Kim
Dong-Jun Kim
HKHeung-Seo Koo
Heung-Seo Koo
This study investigates the possibility of using the normalized time-domain features of electrocardiogram (ECG) for improving the capability of human identification. For this purpose, we measured lead-1 rest ECG (normal heart rate) and physically active one (fast heart rate) from the pre-selected group. The characteristic points on the ECG waveform, P, QRS, T are extracted in terms of its time location and the ECG data is reconstructed in beat-by-beat basis by Fourier synthesis. R-T interval, Q-T interval, and QRS interval on the reconstructed ECG sequence in rest and in physical active mode are computed. The beat-by-beat based discriminatory analysis is performed on the rest and physical active ECG data by applying Malalanobis' distance between these intervals

17 September 2018 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
JKJeong-Hwan Kim
Jeong-Hwan Kim
KLKang-Hwi Lee
Kang-Hwi Lee
JLJeong-Whan Lee
Jeong-Whan Lee
KKKyeong-Seop Kim
Kyeong-Seop Kim