Development of a Force‐Reflecting Robotic Platform for Cardiac Catheter Navigation

Park, Jun Woo,Choi, Jaesoon,Pak, Hui‐,Nam,Song, Seung Joon,Lee, Jung Chan,Park, Yongdoo,Shin, Seung Min,Sun, Kyung Blackwell Publishing Inc 2010 Artificial Organs Vol.34 No.11

<P><B>Abstract</B></P><P>Electrophysiological catheters are used for both diagnostics and clinical intervention. To facilitate more accurate and precise catheter navigation, robotic cardiac catheter navigation systems have been developed and commercialized. The authors have developed a novel force‐reflecting robotic catheter navigation system. The system is a network‐based master–slave configuration having a 3‐degree of freedom robotic manipulator for operation with a conventional cardiac ablation catheter. The master manipulator implements a haptic user interface device with force feedback using a force or torque signal either measured with a sensor or estimated from the motor current signal in the slave manipulator. The slave manipulator is a robotic motion control platform on which the cardiac ablation catheter is mounted. The catheter motions—forward and backward movements, rolling, and catheter tip bending—are controlled by electromechanical actuators located in the slave manipulator. The control software runs on a real‐time operating system‐based workstation and implements the master/slave motion synchronization control of the robot system. The master/slave motion synchronization response was assessed with step, sinusoidal, and arbitrarily varying motion commands, and showed satisfactory performance with insignificant steady‐state motion error. The current system successfully implemented the motion control function and will undergo safety and performance evaluation by means of animal experiments. Further studies on the force feedback control algorithm and on an active motion catheter with an embedded actuation mechanism are underway.</P>

Assessment of Liquefaction Potential Based on Modified Disturbed State Concept

Park, Keunbo,Choi, Jaesoon,Park, Innjoon 대한토목학회 2012 KSCE JOURNAL OF CIVIL ENGINEERING Vol.16 No.1

In this paper, the application of the disturbed state concept model for the assessment of liquefaction potential is examined through experimental and analytical investigation. In order to achieve a more realistic description of the dynamic responses of saturated sands, the disturbed state concept model was modified based on the dynamic effective stress path and excess pore pressure development. Static and cyclic undrained triaxial tests were performed for sands with different relative densities and confining stresses. Based on test results, a classification of liquefaction phases was proposed, in terms of the dynamic effective stress path and the excess pore pressure development. This was adopted into the modified disturbed state concept model. The liquefaction assessment method is also proposed, using the disturbed state concept model based on the deviatoric plastic strain trajectory. Factors of safety, calculated from the equivalent cyclic stress concept, were compared with the proposed method using the original and modified disturbed state concept models. This was proposed by using examples with different soil and earthquake conditions.

Seed: Metaphor of Minjung

JaeSoon Park 한국민중신학회 2004 Madang: Journal of Contextual Theology Vol.2 No.-

Development of capacitive pressure sensor for identifying guinea pigs large intestinal motility

Jaesoon PARK,Eungbo KIM,Wonseok CHOI,Yeunho JOUNG 한국진공학회 2016 한국진공학회 학술발표회초록집 Vol.2016 No.8

Haptic Virtual Fixture for Robotic Cardiac Catheter Navigation

Park, Jun Woo,Choi, Jaesoon,Park, Yongdoo,Sun, Kyung Blackwell Publishing Inc 2011 Artificial Organs Vol.35 No.11

<P><B>Abstract</B></P><P>In manual or robot‐assisted catheter intervention, excessive manipulation force may cause tissue perforation. Using images acquired by an imaging device routinely used for catheter interventions such as X‐ray fluoroscopy, the structure and size of blood vessels and the relative position of the catheter tip inside the vessel can be obtained. To prevent collision of the catheter tip and the vessel wall, vision‐assisted control methods using forbidden‐region virtual fixture (FRVF) technique can be utilized and an experimental implementation has been performed in this study. A master–slave configured robotic platform for cardiac catheter was used for this study. The robotic master handle can provide haptic rendering to the user. A vessel phantom model mimicking human vasculature for the inner radii was fabricated for simulated intervention experiments. A digital optical camera was used for image acquisition. After the vessel phantom and the catheter tip were segmented, distance between the vessel centerline and the catheter tip was calculated and the forbidden region that the catheter tip should keep away from was set for the safe catheter manipulation. Virtual force generation algorithm was implemented for feeding the signal indicating the catheter tip penetrating into the forbidden region back to the user in the robotic master handle. To validate the suggested method, in vitro experiments were conducted. Through a chain of image filtering procedures including edge detection, the catheter tip and the vessel wall were able to be well segmented. The virtual force generator worked appropriately. The developed FRVF technique could provide helpful auxiliary information to clinicians for safer manipulation of catheters in cardiac catheterization procedures.</P>

Seed: Metaphor of Minjung

JaeSoon Park 성공회대학교 신학연구소 2004 Madang: Journal of Contextual Theology Vol.2 No.-

다석 유영모의 평화 사상 : 국가주의적 폭력의 해체와 민주 평화 사상의 확립

박재순 ( Park Jaesoon ) 서울대학교 통일평화연구원 2018 통일과 평화 Vol.10 No.1

유영모는 국가주의적 전쟁과 폭력의 시대를 살면서 안창호·이승훈의 민주적 국민교육독립운동을 계승하여 민주평화사상을 확립했다. 그는 국가의 절대화, 국가의 국민지배를 해체하고 국민을 국가의 우위에 놓고 국민의 주체를 실현하는 민주적 평화를 추구했다. 물질적 가치와 군사주의적 국가의 폭력과 지배에 맞서 생명의 본성과 원리를 실현하는 삶의 평화를 추구했다. 국민의 욕망과 감정을 조작하고 강화하는 국가주의를 벗어나서 맘의 자유와 평화에 이르렀다. 국가주의가 조작하고 조장하는 비이성적 사상·철학· 이념의 왜곡과 도착을 비판하고 사상과 철학의 회통과 해방에 이르렀다. 땅의 정복과 지 배를 추구한 국가주의를 극복하고 주체와 전체가 함께 실현되고 완성되며 일치되는 하늘의 자유와 평화를 실현하려 하였다. 유영모는 통일보다 귀일을 앞세움으로써 인위적 강제적 통일이 아니라 서로 주체가 해방되고 실현되는 자연스럽고 평화로운 통일을 지향하였다. Yu Youngmo lived in the period of war & violence by nationalism, and engaged in the independence movement against Japanese imperialism by the people education of Ahn Changho and Lee Seunghoon. He established democratic peace thought. He sought democratic peace by denouncing the domination of absolute state over people and laying people over state and realizing the juche[主體, free subject] of people. He also sought peace of life that actualizes the nature and principle of life against the violence and domination of militaristic nation and materialism value. He arrived at the freedom and peace of mind through breaking out of nationalism agitating and reinforcing desire and emotion of people for the state. He also arrived at the unity and liberation of philosophy and thought from the distortion and perversion of thoughts and idea by the nationalism. He sought realization of freedom and peace of heaven that overcomes the nationalism pursuing domination and conquest over the earth and brings the juche and the whole of people to perfection. Yu Youngmo does not aim at the artificial forced unification but the natural, peaceful unification by emphasizing returning to unity over unification.

중요 특징 추출과 합성곱 신경망을 이용한 암 진단 모델 연구

박재순(JaeSoon Park),양소이(Soi Yang),이종혁(JongHyunk Lee),배지훈(Ji-Hoon Bae) 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.6

본 논문에서는 의료 진단 데이터셋을 이용한 딥러닝 기반의 유방암 분류 기법을 제안하고자 한다. 암은 진단 시기에 따라 생존율에 영향을 미치는데 기존 기술을 이용한 암 진단은 방대한 진단 데이터와 많은 불필요한 특징으로 인해 정확한 조기진단 비율은 저조하다. 따라서, 본 연구에서는 전체 특징 데이터로부터 중요 특징들을 추출하고, 상기 추출된 특징들을 이용한 합성곱 신경망 모델을 구현하여 암 진단에 대한 정확도 성능을 개선하고자 한다. 본 논문의 실험 결과에 따르면, 특징 데이터 전체를 사용하는 것보다 중요 특징들을 추출하고 이를 적용한 암 진단 모델이 보다 더 정확한 분류 정확도를 제공할 수 있음을 관찰할 수 있었다. 또한, 기존의 전통적인 기계학습 기법보다 암 분류 정확도 관점에서 제안 방법이 더 우수한 것을 관찰할 수 있었다. In this paper, we propose a deep-learning-based technique for the diagnosis of breast cancer using medical data. Cancer affects the survival rate depending on the time of diagnosis, but the accurate early diagnosis rate is low due to the vast amount of diagnostic data and many redundant features of cancer diagnosis using traditional approaches. Therefore, in this study, essential features are extracted from all feature data, and a convolutional neural network model is implemented using the extracted features to improve accuracy performance for cancer diagnosis. Experimental results confirm that the cancer diagnosis model using the extracted important features can provide more accurate classification accuracy than entire feature data. In addition, it can be observed that the proposed method is superior to the existing machine-learning-based methods in terms of the accuracy of cancer classification.

플랜트 배관계 미세누출 지능형 감지를 위한 딥러닝 모델 구현

박재순(JaeSoon Park),여도엽(Doyeob Yeo),최유락(Yurak Choi),이종혁(JongHyunk Lee),배지훈(Ji-Hoon Bae) 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.11

본 논문에서는 플랜트 배관계의 저전력 센싱 모듈에서 수집한 미세누출에 대한 데이터를 이용하여 딥러닝 기반의 경량화된 누출진단 학습모델을 제안하고자 한다. 초기 건설 시에 설치되었던 플랜트 배관들의 노후화가 진행됨에 따라 배관계의 조기 누출탐지 요구가 증대되고 있지만, 플랜트에서 발생되는 기계잡음과 소음으로 인해 미세누출의 진위 여부를 판별하는 데에 어려움이 있다. 따라서 본 연구에서는 학습 데이터가 작고 기계잡음이 존재하는 상황에서 실제 누출 신호에 대한 이상감지를 수행하기 위해 전이학습 기반의 미세누출 판별 딥러닝 모델을 제안한다. 본 연구의 결과에 따르면 제안모델의 정확도 성능이 기존 신경망 기반의 모델들 보다 더 우수한 미세누출 판별 정확도를 제공할 수 있음을 실험적으로 관찰할 수 있었다. 또한 모델 경량화 작업을 수행한 후 라즈베리파이와 같은 저사양 하드웨어에 탑재하여 정상적인 기능 동작과 빠른 추론 성능도 검증하였다. In this paper, we propose a lightweight leak diagnosis learning model based on deep-learning using low-level leakage data collected from the low-power sensing module of the plant piping system. As the aging of the plant pipes installed during the initial construction progresses, the demand for early leak detection in the piping system is increasing. However, it is difficult to determine the authenticity of low-level leaks due to the mechanical noise and noise generated in the plant. Therefore, in this study, we propose a transer learning-based low-level leak detection deep-learning model to perform anomaly detection on actual leak signals in the presence of a small training dataset and machinery noise. According to the results of this study, it was experimentally observed that the accuracy performance of the proposed model could provide better low-level leak detection accuracy than the existing neural network-based models. In addition, after performing the lightweight model work, it was mounted on low-spec hardware such as Raspberry Pi to verify normal functional operation and fast inference performance.

활성탄소섬유를 이용한 정화장치의 유동해석

황재순(Jaesoon Hwang),박경서(K. S. Park),박정수(J. S. Park) 한국생산제조학회 2023 한국생산제조시스템학회 학술발표대회 논문집 Vol.2023 No.12