전자식 주차 브레이크 ECU 개발

박기창(Kichang Park),전재우(Jaewoo Jeon),정하민(Hamin Jung),이병상(Byoungsang Lee) 한국자동차공학회 2008 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-

FDG-PET for Evaluating the Antitumor Effect of Intraarterial 3-Bromopyruvate Administration in a Rabbit VX2 Liver Tumor Model

Park, Hee Sun,Chung, Jin Wook,Jae, Hwan Jun,Kim, Young Il,Son, Kyu Ri,Lee, Min Jong,Park, Jae Hyung,Kang, Won Jun,Yoon, Jung Hwan,Chung, Hesson,Lee, Kichang unknown 2007 KOREAN JOURNAL OF RADIOLOGY Vol.8 No.3

<P><B>Objective</B></P><P>We wanted to investigate the feasibility of using FDG-PET for evaluating the antitumor effect of intraarterial administration of a hexokinase II inhibitor, 3-bromopyruvate (3-BrPA), in a rabbit VX2 liver tumor model.</P><P><B>Materials and Methods</B></P><P>VX2 carcinoma was grown in the livers of ten rabbits. Two weeks later, liver CT was performed to confirm appropriate tumor growth for the experiment. After tumor volume-matched grouping of the rabbits, transcatheter intraarterial administration of 3-BrPA was performed (1 mM and 5 mM in five animals each, respectively). FDG-PET scan was performed the day before, immediately after and a week after 3-BrPA administration. FDG uptake was semiquantified by measuring the standardized uptake value (SUV). A week after treatment, the experimental animals were sacrificed and the necrosis rates of the tumors were calculated based on the histopathology.</P><P><B>Results</B></P><P>The SUV of the VX2 tumors before treatment (3.87 ±1.51 [mean ±SD]) was significantly higher than that of nontumorous liver parenchyma (1.72 ±0.34) (<I>p</I> < 0.0001, Mann-Whitney <I>U</I> test). The SUV was significantly decreased immediately after 3-BrPA administration (2.05 ±1.21) (<I>p</I> = 0.002, Wilcoxon signed rank test). On the one-week follow up PET scan, the FDG uptake remained significantly lower (SUV 1.41 ±0.73) than that before treatment (<I>p</I> = 0.002), although three out of ten animals showed a slightly increasing tendency for the FDG uptake. The tumor necrosis rate ranged from 50.00% to 99.90% (85.48% ±15.87). There was no significant correlation between the SUV or the SUV decrease rate and the tumor necrosis rate in that range.</P><P><B>Conclusion</B></P><P>Even though FDG-PET cannot exactly reflect the tumor necrosis rate, FDG-PET is a useful modality for the early assessment of the antitumor effect of intraarterial administration of 3-BrPA in VX2 liver tumor.</P>

설비 결함 식별 최적화를 위한 오토인코더 기반 N 분할 주파수 영역 이상 탐지

박기창 ( Kichang Park ),이용관 ( Yongkwan Lee ) 한국정보처리학회 2024 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.13 No.3

제조 분야 설비 예지보전을 위해서 진동, 전류, 온도 등 물리 데이터를 기반으로 설비 이상을 탐지하는 인공지능 학습 모델이 활용되고 있다. 설비 결함, 고장 등 설비 이상 유형은 매우 다양하므로, 주로 오토인코더 기반 비지도 학습 모델을 이용한 이상 탐지 방법이 적용되고 있다. 설비 상태의 정상, 비정상 여부는 오토인코더의 재구성 오차를 이용해 효과적으로 분류할 수 있지만, 설비 이상의 구체적인 상태를 식별하는 데 한계가 있다. 설비 불균형, 정렬 불량, 고정 불량 등 설비 이상 상황 발생 시, 설비 진동 주파수는 특정 영역에서 정상 상태와 다른 패턴을 나타낸다. 본 논문에서는 전체 진동 주파수 범위를 N개 영역으로 나누어 이상 탐지를 수행하는 N 분할 이상 탐지 방법을 제시하였다. 압축기의 진동 데이터를 이용해 주파수와 강도를 달리한 9종의 이상 데이터를 대상으로 실험한 결과, N 분할을 적용하였을 때 더 높은 이상 탐지 성능을 나타냈다. 제안방법은 설비 이상 탐지 이후, 설비 이상 구체화에 활용될 수 있다. Artificial intelligence models are being used to detect facility anomalies using physics data such as vibration, current, and temperature for predictive maintenance in the manufacturing industry. Since the types of facility anomalies, such as facility defects and failures, anomaly detection methods using autoencoder-based unsupervised learning models have been mainly applied. Normal or abnormal facility conditions can be effectively classified using the reconstruction error of the autoencoder, but there is a limit to identifying facility anomalies specifically. When facility anomalies such as unbalance, misalignment, and looseness occur, the facility vibration frequency shows a pattern different from the normal state in a specific frequency range. This paper presents an N-segmentation anomaly detection method that performs anomaly detection by dividing the entire vibration frequency range into N regions. Experiments on nine kinds of anomaly data with different frequencies and amplitudes using vibration data from a compressor showed better performance when N-segmentation was applied. The proposed method helps materialize them after detecting facility anomalies.

텍스트마이닝을 이용한 건설공사 위험요소의 계절별 중요도 분석

박기창(Park, Kichang),김형관(Kim, Hyoungkwan) 대한토목학회 2021 대한토목학회논문집 Vol.41 No.3

건설사고는 근로자의 부주의, 안전장비 미착용, 안전규칙 미준수 등 다양한 요인이 복합적으로 작용해 발생할 수 있다. 건설사고를 유발하는 여러 요인 중 야외작업이 많은 건설업의 특성상 기상 조건은 건설사고 발생 요인 중 하나가 될 수 있다. 과거 발생한 건설사고 데이터는 사고예방을 위한 좋은 자료로 활용될 수 있지만, 건설업 재해사례 데이터는 자연어로 기술된 텍스트형태로 제공되기 때문에 건설업 재해사례 데이터에서 건설공사 위험요소(Hazard)를 추출하는 것은 많은 시간과 비용이 발생한다. 따라서, 본 연구에서는 텍스트마이닝을 이용해 국내에서 발생한 2,026건의 건설업 재해사례 텍스트데이터에서 건설공사 위험요소를 추출하고 빈도 분석(Frequency analysis)과 중심성 분석(Centrality analysis)을 통해 건설공사 위험요소의 계절별 중요도분석을 수행했다. 국토교통부에서 정의한 254개 건설공사 위험요소 중 51개 위험요소를 건설사고 텍스트데이터에서 추출했으며, 분석결과 봄, 가을은 거푸집, 여름은 비계, 겨울은 크레인이 계절별 가장 중요한 위험요소로 나타났다. 제안방법은 날씨, 계절, 기후 관련 건설사고 안전대책 마련에 활용될 수 있다. Construction accidents occur due to a number of reasons—worker carelessness, non-adoption of safety equipment, and failure to comply with safety rules are some examples. Because much construction work is done outdoors, weather conditions can also be a factor in accidents. Past construction accident data are useful for accident prevention, but since construction accident data are often in a text format consisting of natural language, extracting construction hazards from construction accident data can take a lot of time and that entails extra cost. Therefore, in this study, we extracted construction hazards from 2,026 domestic construction accident reports using text mining and performed a seasonal analysis of construction hazards through frequency analysis and centrality analysis. Of the 254 construction hazards defined by Korea’s Ministry of Land, Infrastructure, and Transport, we extracted 51 risk factors from the construction accident data. The results showed that a significant hazard was “Formwork” in spring and autumn, “Scaffold” in summer, and “Crane” in winter. The proposed method would enable construction safety managers to prepare better safety measures against outdoor construction accidents according to weather, season, and climate.

XML을 이용한 모바일 어플리케이션 UI 코드생성

박기창(Kichang Park),김종한(Chonghan Kim),정승문(Seungmoon Jeong) 한국멀티미디어학회 2008 한국멀티미디어학회 학술발표논문집 Vol.2008 No.1

XML은 구조적인 데이터 표현과 어플리케이션 독립적인 데이터 표현에 효과적으로 이용될 수 있다. 이러한 XML 문서의 특징으로 웹, 비즈니스, 금융, 과학 분야 등 다양한 분야에 활용되고 있으며 그 응용분야가 점차 확대되고 있다. 본 논문은 XML을 이용하여 모바일 어플리케이션의 UI명세를 위한 데이터 표현을 제안하고, UI 와 연관된 소스코드를 자동 생성하는 방안을 제시한다.

자산관리웰(AAS)을 이용한 제조 분야 가상 물리시스템(CPS) 개발

박우현 ( Woohyun Park ),김재현 ( Jaehyun Kim ),박기창 ( Kichang Park ),이용관 ( Yongkwan Lee ),이정준 ( Jeong Joon Lee ) 한국정보처리학회 2023 한국정보처리학회 학술대회논문집 Vol.30 No.1

장기분지 CO₂ 지중저장 실증을 위한 통합 관측공 모니터링 시스템 구축 및 관측정 완결

박권규(Kwon Gyu Park),Barry Freifeld,Mark Woitt,윤종렬(Jong-Reol Yoon),정해식(Hae Sik Jeong),전형진(Hyung Jin Jeon),이창현(Changhyun Lee),채기탁(Gitak Chae),김구영(Kuyoung Kim),박인화(Inhwa Park),양기창(Kichang Yang),윤병준(Byoung 대한지질학회 2017 대한지질학회 학술대회 Vol.2017 No.10

Feasibility of Percutaneous Pancreatic Stent Placement in Postoperative Pancreaticojejunostomy Stenosis

Park Juil,Han Kichang,Kwon Joon Ho,Kim Man-Deuk,Won Jong Yun,Moon Sungmo,Kim Gyoung Min 대한영상의학회 2023 Korean Journal of Radiology Vol.24 No.12

Objective: To evaluate the role of percutaneous pancreatic stent placement in postoperative pancreaticojejunostomy stenosis (PJS). Materials and Methods: This retrospective single-center study included seven procedures in five patients (four males and one female; median age, 63 years) who underwent percutaneous pancreatic stent placement for postoperative PJS between January 2005 and December 2021. The patients were referred to interventional radiology because of unfavorable anatomy or bowel abnormalities. The pancreatic duct was accessed under ultrasound and/or computed tomography guidance. A stent was placed after balloon dilatation of the PJS. Moreover, plastic stents were placed for the first two procedures, whereas bare-metal stents were used for the remaining five procedures. Technical success was defined as the successful placement of stents for the PJS, meanwhile, clinical success was defined as the normalization of pancreatic enzymes without recurrence of pancreatitis. Results: Pancreatic duct access and stent placement were successfully performed in all patients (technical success rate: 100%). All the procedures initially yielded clinical success. However, recurrence of pancreatitis was observed after two procedures that used plastic stents because of stent migration at 0.3 and 3 months after the procedure. In contrast, no instances of recurrent pancreatitis were noted after metal stent placement for a follow-up duration of 1–36 months. No serious procedure-related adverse events were observed. Conclusion: Percutaneous pancreatic stent placement may be a viable option for patients with postoperative PJS in whom an endoscopic approach is not feasible. Metal stents may be considered over plastic stents for the management of PJS, considering the possible lower stent migration and infeasibility of frequent endoscopic stent exchange due to the altered anatomy.

Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting

Park, Gilsoon,Kwak, Kichang,Seo, Sang Won,Lee, Jong-Min Frontiers Media S.A. 2018 Frontiers in neuroscience Vol.12 No.-

<P>In this paper, we introduce a novel automatic method for Corpus Callosum (CC) in midsagittal plane segmentation. The robust segmentation of CC in midsagittal plane is key role for quantitative study of structural features of CC associated with various neurological disorder such as epilepsy, autism, Alzheimer's disease, and so on. Our approach is based on Bayesian inference using sparse representation and multi-atlas voting which both methods are used in various medical imaging, and show outstanding performance. Prior information in the proposed Bayesian inference is obtained from probability map generated from multi-atlas voting. The probability map contains the information of shape and location of CC of target image. Likelihood in the proposed Bayesian inference is obtained from gamma distribution function, generated from reconstruction errors (or sparse representation error), which are calculated in sparse representation of target patch using foreground dictionary and background dictionary each. Unlike the usual sparse representation method, we added gradient magnitude and gradient direction information to the patches of dictionaries and target, which had better segmentation performance than when not added. We compared three main segmentation results as follow: (1) the joint label fusion (JLF) method which is state-of-art method in multi-atlas voting based segmentation for evaluation of our method; (2) prior information estimated from multi-atlas voting only; (3) likelihood estimated from comparison of the reconstruction errors from sparse representation error only; (4) the proposed Bayesian inference. The methods were evaluated using two data sets of T1-weighted images, which one data set consists of 100 normal young subjects and the other data set consist of 25 normal old subjects and 22 old subjects with heavy drinker. In both data sets, the proposed Bayesian inference method has significantly the best segmentation performance than using each method separately.</P>

하이브리드 굴삭기의 상위제어기 개발을 위한 MILS 환경 구축

진기창(Kichang Jin),박태호(Taeho Park),이지호(Jiho Lee),정유석(Yuseuk Jung),권영민(Youngmin Kwon),이형철(Hyoungcheol Lee) 한국자동차공학회 2009 한국자동차공학회 학술대회 및 전시회 Vol.2009 No.11

The hybrid excavator is designed and constructed by replacing the hydraulic components of the conventional hydraulic excavator with the electric components. The target hybrid excavator of this research is the compound hybrid excavator replacing only the swing part with the electric motor. This paper presents dynamic modeling of the compound hybrid excavator including an engine, a generator, ultra capacitors, hydraulic components and the swing part. The developed model is programmed with the AMESim and validated by the experimental data.