Sungbin Im

Prof. Dr. Sungbin Im

Soongsil University, School of Electronic Engineering
orcid

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

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

Representative Publications

View All Publications
22 February 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JCJungyu Choi
Jungyu Choi
SISungbin Im
Sungbin Im
Conventional schemes to detect leakage in water pipes require leakage exploration experts. However, to save time and cost, demand for sensor-based leakage detection and automated classification systems is increasing. Therefore, in this study, we propose a convolutional neural network (CNN) model to detect and classify water leakage using vibration data collected by leakage detection sensors installed in water pipes. Experiment results show that the proposed CNN model achieves an F1-score of 94.82% and Matthew’s correlation coefficient of 94.47%, whereas the corresponding values for a support vector machine model are 80.99% and 79.86%, respectively. This study demonstrates the superior performance of the CNN-based leakage detection scheme with vibration sensors. This can help one to save detection time and cost incurred by skilled engineers. In addition, it is possible to develop an intelligent leak detection system based on the proposed one.

30 December 2020 in Electronics
Verified
Journal Article
Open access
PDF file
BKBobae Kim
Bobae Kim
SISungbin Im
Sungbin Im
GYGeonwook Yoo
Geonwook Yoo
As the technology node shrinks and shifts towards complex architectures, accurate control of automated semiconductor manufacturing processes, particularly plasma etching, is crucial in yield, cost, and semiconductor performance. However, current endpoint detection (EPD) methods relying on the experience of skilled engineers result in process variations and even errors. This paper proposes an enhanced optimal EPD in the plasma etching process based on a convolutional neural network (CNN). The proposed approach performs feature extraction on the spectral data obtained by optical emission spectroscopy (OES) and successfully predicts optimal EPD time. For the purpose of comparison, the support vector machine (SVM) classifier and the Adaboost Ensemble classifier are also investigated; the CNN-based model demonstrates better performance than the two models.

1 March 1997 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
SISungbin Im
Sungbin Im
EPE.J. Powers
E.J. Powers
The objective of this paper is to present an adaptive algorithm to identify third-order frequency-domain Volterra filter coefficients, which correspond to the discrete Fourier transform (DFT) of the time-domain Volterra filter coefficients. The approach rests upon the block least mean square (LMS) algorithm based on the overlap-save method.

28 February 2022 in IEEE Access
Verified
Journal Article
Open access
JCJungyu Choi
Jungyu Choi
BKBobae Kim
Bobae Kim
SISungbin Im
Sungbin Im
GYGeonwook Yoo
Geonwook Yoo
The advancement of semiconductor technology nodes requires precise control of their manufacturing process, including plasma etching, which is highly important in terms of the yield, cost, and device performance. Endpoint detection (EPD) is an imperative technique for controlling this process. Here, we propose a novel EPD scheme based on multivariate kernel density estimation (MKDE). The proposed approach is developed by extending the conventional unsupervised learning MKDE method to supervised learning. The performance of the proposed scheme is validated on randomly selected optical emission spectroscopy data collected from an industrial semiconductor manufacturing process. Because the proposed approach uses target values (labeling) of data, it demonstrates enhanced EPD performance compared to the conventional MKDE method, even without threshold presetting.

14 August 2017 in Sensors
Verified
Journal Article
Open access
PDF file
SKSunho Kim
Sunho Kim
SISungbin Im
Sungbin Im
TPTaehyung Park
Taehyung Park
Accelerometers are applied to various applications to collect information about movements of other sensors deployed at diverse fields ranging from underwater area to human body. In this study, we try to characterize the nonlinear relationship between motion artifact and acceleration data. The cross bicoherence test and the Volterra filter are used as the approaches to detection and modeling. We use the cross bicoherence test to directly detect in the frequency domain and we indirectly identify the nonlinear relationship by improving the performance of eliminating motion artifact in heartbeat rate estimation using a nonlinear filter, the second-order Volterra filter. In the experiments, significant bicoherence values are observed through the cross bicoherence test between the photoplethysmogram (PPG) signal contaminated with motion artifact and the acceleration sensor data. It is observed that for each dataset, the heartbeat rate estimation based on the Volterra filter is superior to that of the linear filter in terms of average absolute error. Furthermore, the leave one out cross-validation (LOOCV) is employed to develop an optimal structure of the Volterra filter for the total datasets. Due to lack of data, the developed Volterra filter does not demonstrate significant difference from the optimal linear filter in terms of t-test. Through this study, it can be concluded that motion artifact may have a quadaratical relationship with acceleration data in terms of bicoherence and more experimental data are required for developing a robust and efficient model for the relationship.

1 May 1996 in Journal of the Franklin Institute
Verified
Journal Article
Closed access
SISungbin Im
Sungbin Im
EPEdward J. Powers
Edward J. Powers