Moon Hwan Kim

Moon Hwan Kim

Auto-generated profile, based on publicly available information

Moon Hwan Kim

Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
17 August 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
TKTaehan Koo
Taehan Koo
MKMoon Hwan Kim
Moon Hwan Kim
MJMihn-Sook Jue
Mihn-Sook Jue
Direct microscopic examination with potassium hydroxide is generally used as a screening method for diagnosing superficial fungal infections. Although this type of examination is faster than other diagnostic methods, it can still be time-consuming to evaluate a complete sample; additionally, it possesses the disadvantage of inconsistent reliability as the accuracy of the reading may differ depending on the performer’s skill. This study aims at detecting hyphae more quickly, conveniently, and consistently through deep learning using images obtained from microscopy used in real-world practice. An object detection convolutional neural network, YOLO v4, was trained on microscopy images with magnifications of 100×, 40×, and (100+40)×. The study was conducted at the Department of Dermatology at Veterans Health Service Medical Center, Seoul, Korea between January 1, 2019 and December 31, 2019, using 3,707 images (1,255 images for training, 1,645 images for testing). The average precision was used to evaluate the accuracy of object detection. Precision recall curve analysis was performed for the hyphal location determination, and receiver operating characteristic curve analysis was performed on the image classification. The F1 score, sensitivity, and specificity values were used as measures of the overall performance. The sensitivity and specificity were, respectively, 95.2% and 100% in the 100× data model, and 99% and 86.6% in the 40× data model; the sensitivity and specificity in the combined (100+40)× data model were 93.2% and 89%, respectively. The performance of our model had high sensitivity and specificity, indicating that hyphae can be detected with reliable accuracy. Thus, our deep learning-based autodetection model can detect hyphae in microscopic images obtained from real-world practice. We aim to develop an automatic hyphae detection system that can be utilized in real-world practice through continuous research.

24 December 2024 in Ocean Engineering
Verified
Journal Article
Closed access
DKDong-Hwi Kim
Dong-Hwi Kim
MKMoon Hwan Kim
Moon Hwan Kim
JKJun Kim
Jun Kim
HBHyung-Min Baek
Hyung-Min Baek
YCYoung-Myung Choi
Young-Myung Choi
SLSeung Hwan Lee
Seung Hwan Lee

31 October 2019 in Journal of Ocean Engineering and Technology
Verified
Journal Article
Open access
PDF file
TYTs Yoo
Ts Yoo
MKMoon-Hwan Kim
Moon-Hwan Kim
SYSeon-Il Yoon
Seon-Il Yoon
DKDae-Joong Kim
Dae-Joong Kim
서 론 관성측정장치(IMU, Inertial measurement unit), 도플러 속도센 서(DVL, Doppler velocity log)는 수중 환경에서 복합 항법을 구 현하기 위해 사용하는 대표적인 센서이다. IMU는 비력(Specific force)을 측정하는 가속도계와 회전운동을 측정하는 자이로를 이용하여 항체의 가속도 및 각속도를 측정한다. 이를 통해 주위 환경에 영향 받지 않고 자세, 속도, 위치정보를 독립적으로 계 산할 수 있다. 하지만 IMU는 적분과정을 통해 항법 결과를 계 산하기 때문에 짧은 시간에는 정확하나 시간이 지남에 따라 항 법오차가 누적되는 단점이 있다(Titterton and Weston, 1997). 이 러한 IMU의 단점을 극복하기 위해 DVL 등 외부센서를 이용하 여 항법 결과값을 보정하는 방법이 다양하게 연구되고 있다. DVL은 도플러 효과를 이용하여 수중운동체의 속도를 측정하 는 센서다. 수중운동체가 움직이면서 지면에 음파를 송신하였 을 때 해저면으로부터 반사되어 돌아오는 수신신호의 진동수 변화를 관측함으로써 물체의 속도를 측정할 수 있다. DVL은 4 개의 트랜스듀서가 JANUS 형상에 따라 배치되어 있으며 각각 의 트랜스듀서에서 측정된 속도를 변환좌표계를 이용하여 동체 의 3축에 대한 속도로 변환한다(Rudolph and Wilson, 2012). 일반적으로 DVL을 이용한 관성항법장치(INS, Inertial navigation system)의 속도보정 알고리즘은 DVL에서 계산된 동체좌표계의 속 도를 칼만필터의 측정치로 이용하는 약결합(Loosely coupled) 방식 으로 구성된다. 약결합방식은 강결합방식에


4 February 2025 in IEEE Access
Verified
Journal Article
Open access
TYTae Suk Yoo
Tae Suk Yoo
SKSan Hee Kang
San Hee Kang
JLJunghan Lee
Junghan Lee
DJDaeHyeong Ji
DaeHyeong Ji
MKMoon Hwan Kim
Moon Hwan Kim
In this research, we introduce advanced navigation filters designed for underwater gliders, which are crucial to collecting oceanic data like temperature and salinity. Due to their dependence on low-cost, low-precision MEMS-based IMUs and unique operational constraints, these gliders experience significant navigational inaccuracies. To address this, we proposed two filters, each optimized for minimal sensor use: the first integrates an accelerometer, magnetometer, and depth gauge, and the second adds a gyroscope. These filters estimate the glider’s velocity and position by transforming sensor data into the navigation coordinate system. We not only conducted rigorous evaluations of our proposed filters through comprehensive simulations and Monte Carlo numerical analyses, but also fabricated an actual glider to apply these filters in real sea trials. The results of these sea trials were consistent with our simulation predictions, confirming the effectiveness of our navigation filters in practical scenarios.