GPS 기법을 이용한 철도 선형제원의 복원

정의환(Jeong Eui-Hwan),이남수(Lee Nam-Soo) 한국철도학회 2003 한국철도학회 학술발표대회논문집 Vol.- No.-

The first design elements of horizontal alignment are very important things for improvement or movement in Railway. When the design elements are lost or damaged, it is necessary to recalculation. In this paper, an investigation is made on the method of representation of horizontal alignment as a result of design element using GPS method. The results show that northing calculated about 2~10 meters and easting calculated about 0~7 meters between calculated and design data in center points.

딥러닝 기반의 핵의학 폐검사 분류 모델 적용

정의환(Eui-Hwan Jeong),오주영(Joo-Young Oh),이주영(Ju-Young Lee),박훈희(Hoon-Hee Park) 대한방사선과학회(구 대한방사선기술학회) 2022 방사선기술과학 Vol.45 No.1

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

지형여건을 고려한 철도 완화곡선 연장방법의 적용성에 관한 연구

정의환(Jeong, Eui Hwan) 한국측량학회 2004 한국측량학회지 Vol.22 No.4

Zirconium 기반 박막 금속유리의 나노압입 연구

정의환(Uihwan Jeong),한정무(Jungmoo Han),Karuppasamy Pandian Marimuthu,이영서(Lee Youngseo),이형일(Hyungyil Lee) 대한기계학회 2020 대한기계학회 춘추학술대회 Vol.2020 No.12

Despite the excellent mechanical properties, practical application of bulk metallic glasses (BMGs) is limited due to difficulties in fabricating bulk products from BMG. Alternatively, BMGs are deposited as thin film on substrates i.e. thin-film metallic glass (TFMG) for utilizing their mechanical performances. As tensile or compression testing at nanoscale is infeasible for mechanical characterization, we use nanoindentation tests to investigate the nanomechanical behavior of Zr-TFMG deposited on various substrates. The deformation behaviors of Zr-TFMG and mechanical properties are then analyzed through finite element (FE) simulations. The effects of peak and cyclic loads and loading rate on the nanomechanical properties are investigated. Observation of significant pile-up of TFMG on Si substrate demonstrates that the deformation behavior of Zr-TFMG is affected by substrate material. Finally, based on the experimental and numerical nanoindentation studies, the nanomechanical properties of Zr-TFMG were evaluated.

철도 선형 복원을 위한 GPS 데이터 단순화 방법의 적용

정의환(Jeong, Eui Hwan) 한국측량학회 2004 한국측량학회지 Vol.22 No.1

핵의학 감마카메라 정도관리의 딥러닝 적용

정의환(Euihwan Jeong),오주영(Joo-Young Oh),이주영(Joo-Young Lee),박훈희(Hoon-Hee Park) 대한방사선과학회(구 대한방사선기술학회) 2020 방사선기술과학 Vol.43 No.6

In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.

해안지역 철도콘크리트궤도 도상재료의 성능향상을 위한 실험적 연구

정형진(Heang-Zin Jeong),장덕순(Deok-Soon Chang),라정균(Jeong-kyun Rha),정의환(Eui-Hwan Jeong) 한국철도학회 2013 한국철도학회 학술발표대회논문집 Vol.2013 No.5

해안지역의 철도 콘크리트궤도 도상재료의 내구성을 평가하기 위해 플라이애시의 분말도 및 치환율의 변화를 통해 압축강도 및 내구성 평가요소 중 탄산화 깊이 및 염화물 침투 깊이에 대한 실험을 실시한 결과 압축강도 특성은 분말도가 증가할수록 증가하는 경향을 나타낸 반면 치환율이 증가할수록 압축강도는 낮아지는 경향을 보였으며, 내구성 평가항목인 탄산화 깊이와 염화물 침투 깊이는 분발도가 증가할수록 줄어드는 경향을 보이고 있어 내구성이 향상됨을 알 수 있었다. To evaluate of durability of ballast material for railway concrete bed tracks in coastal areas, a test on carbonation depth and chloride penetration depth among evaluation criteria for compression strength and durability was conducted through fineness and replacement ratio of fly ash. The test outcome illustrates the tendency of compression strength in which higher fineness results in greater compression strength while higher replacement ratio turns into lower compression strength and the depth of carbonation and chloride penetration which is an evaluation criterion for durability is identified as getting smaller as fineness gets higher so that proves the improvement of durability.

철도선로유지 효율화를 위한 궤도주변시설 성능개선 연구

정형진(Heyong-Jin Jeong),정의환(Eui-Hwan, Jeong),라정균(eong-Kyun.Rha),장덕순(Deok-Soon Chang) 한국철도학회 2012 한국철도학회 학술발표대회논문집 Vol.2012 No.10

철도의 고속화 및 레일장대화로 궤도관리가 중요한 시기이지만 폭염 및 이상기후 현상으로 철도운행 환경이 악화되고 있는 상황이다. 특히, 열차소음방지 목적으로 설치되는 철도방음벽으로 밀폐된 구간에서의 레일온도 상승은 궤도유지관리에 어려움을 초래하게 된다. 혹서기에 안전한 열차운행을 위해서는 레일온도를 일정수준으로 유지하여야 하는데 레일온도 상승에 대응하는 방법으로 운행속도규제와 살수를 통한 방법이 적용되고 있지만, 살수에 의한 방법은 점착계수 저하로 인해 열차운행의 효율성 저하를 야기 시키고 있는 실정이다. 이에 선로주변에 설치되는 시설물인 방음벽에 온도 자동감지장치를 설치하여 사전에 설정된 온도에 따라 작동하는 가동기 및 자동 슬라이딩 방음판을 구성 레일의 과다온도 발생시 설정된 온도에서 방음판의 자동 열림으로 통풍에 의한 선로내 온도를 하강시켜 레일 온도를 적정하게 유지함으로써 혹서기 열차안전운행을 확보함은 물론 궤도재료인 레일보수주기를 연장시킬 수 있는 방음벽의 성능을 개선하였다. Owing to high speed railroad and continuous welded rail, rail management is important, yet heat waves and abnormal climate phenomenon aggravate railway operation. A temperature rise in the section closed by railway noise barrier incurs the difficulty in track maintenance. For safe of operation of railways during a scorching summer, it is needed to maintain the temperature of rails at a certain level. Sprinkling water and the regulation of operating speed are used to respond to a temperature rise of rails, yet sprinkling water incurs the degradation of the efficiency in operating railways owing to the degradation of adhesion coefficient. Thus, automatic temperature sensing devices were installed on the sound barriers installed around the tracks so actuators and automatic sliding sound boards in operation according to the temperate set in advance could maintain the rail temperature, reducing the temperature of tracks by ventilation owing to automatic opening of sound boards at set temperature in the event of excessive temperate rise, ensuring the safety of railways operation during summers, and improving the performance of sound boards facilitating the extension of the maintenance cycle for rails, the materials of tracks.

축지학적 방법에 의한 지각변동 매개변수 결정에 관한 연구

조규전(Cho, Kyu Jon),정의환(Jeong, Eui Whan) 한국측량학회 2001 한국측량학회지 Vol.19 No.4

게이트심장혈액풀검사에서 딥러닝 기반 좌심실 영역 분할방법의 유용성 평가

오주영(Joo-Young Oh),정의환(Eui-Hwan Jeong),이주영(Joo-Young Lee),박훈희(Hoon-Hee Park) 대한방사선과학회(구 대한방사선기술학회) 2022 방사선기술과학 Vol.45 No.2

The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert s processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.