http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Jaekwang Nam,Gun Hee Jang,Seung Mun Jeon,Kyun Choi IEEE 2014 IEEE transactions on magnetics Vol.50 No.11
<P>We develop a crawling microrobot with high stability and high steering capability to navigate through a sharply bent tubular environment. The proposed microrobot can stably crawl forward and backward using the asymmetric friction force between a flexible leg and a wall. Our design can effectively change the moving direction even in sharply bent tubular environments using both the magnetic torque and the propulsive force generated by the crawling motion. The steering angle of the microrobot is simulated using a mathematical model of cantilever beam. We then perform various experiments to verify the validity of the proposed microrobot.</P>
Nam, Jaekwang,Lee, Wonseo,Jang, Bongjun,Jang, Gunhee Institute of Electrical and Electronics Engineers 2017 IEEE transactions on industrial electronics Vol.64 No.6
<P>We propose a novel magnetic navigation system (MNS) with the resonant effect of an RLC circuit to generate large magnetic field in high frequency. The variable capacitors of the proposed MNS make it possible not only to change the resonant frequency of the RLC circuit, but also tomaximize the output current without phase delay at variable resonant frequencies. The proposed MNS can compensate for the amplitude decrease and phase delay due to the inductance effect of a conventional MNS, while generating a uniform magnetic field with a wide range of rotating frequencies to effectively operate a helical robot in human blood vessels. For verification of the constructed MNS, we measured currents and magnetic fields at several resonant frequencies, and the experimental values corresponded well with the calculated values. We finally demonstrated that the proposed MNS substantially improves both moving and unclogging capabilities of a helical robot as compared to the conventional MNS.</P>
Magnetic Helical Robot for Targeted Drug-Delivery in Tubular Environments
Nam, Jaekwang,Lee, Wonseo,Kim, Jongyul,Jang, Gunhee IEEE 2017 IEEE/ASME transactions on mechatronics Vol.22 No.6
<P>We propose a novel magnetic helical robot (HR) that can helically navigate, release a drug to a target area, and generate a mechanical drilling motion to unclog tubular structures of the human body. The proposed HR is composed of two rotating cylindrical magnets (RMs), four fixed cylindrical magnets (FMs), and a helical body. The RMs can be rotated in different directions under two orthogonal external rotating magnetic fields (ERMF). Utilizing these ERMFs, we can generate various motions. The ERMF along the axis of the RMs can generate the drug-release motion, while the ERMF orthogonal to the axis of the RMs can generate navigating and drilling motions. On the other hand, the magnetic torque and the attractive magnetic force between RMs and FMs tightly seal the nozzles in the drug chamber. We analyze these magnetic torque and force of the magnets for the navigating, drug-release, and drilling motion. Especially, the drug-release motion utilizes an eccentric rotational motion of the RMs due to the attractive and repulsive magnetic force between RMs and FMs. This motion squeezes and discharges the drug through a nozzle. We designed the mechanical structure of the proposed HR considering the magnetic properties to achieve the proposed functions. Finally, we prototyped the HR and conducted several experiments to verify the navigating, drug-delivery and drilling capabilities of the HR. We also confirmed that drug-enhanced drilling could unclog the clogged area more effectively than the simple drilling motion.</P>
Nam, Jaekwang,Lee, Wonseo,Jung, Eunsoo,Jang, Gunhee Institute of Electrical and Electronics Engineers 2018 IEEE transactions on industrial electronics Vol.65 No.7
<P>We propose a novel closed-circuit magnetic navigation system (CMNS), which utilizes eight electromagnets connected by back yokes to maximize a magnetic field. We first show the effectiveness of a closed magnetic circuit (CMC) and conduct a parametric analysis to design a single CMC, which is utilized to construct the whole CMNS. A magnetic field mapping method is also developed utilizing the finite-element method and polynomial regression to evaluate and control the magnetic field over almost the whole workspace in real time. We investigated how the magnetic field changed based on the shape of core tips by comparing the isotropic magnetic field control authority, which is the ability to generate an equal magnetic field over the workspace regardless of the position and direction of the magnetic field. We experimentally verified the mathematical assumption that the magnetic field generated from the proposed CMNS can be linearly proportional to the applied current and that the magnetic field of the proposed CMNS can be expressed as a superposition of the magnetic fields generated by each electromagnet. Finally, we verified the effectiveness of the developed CMNS by performing experiments related to steering a commercial magnetic catheter.</P>
박남준(Park, Nam-Jun),김재광(Kim, Jaekwang) 한국방송·미디어공학회 2022 한국방송공학회 학술발표대회 논문집 Vol.2022 No.11
최근 자연어 처리 분야에서 기계학습 독해 관련 연구가 활발하게 이루어지고 있다. 그러나 그 중에서 한국어 기계독해 학습을 통해 문제풀이에 적용한 사례를 찾아보기 힘들었다. 기존 연구에서도 수능 영어와 수능 수학 문제를 인공지능(AI) 모델을 활용하여 문제풀이에 적용했던 사례는 있었지만, 수능 국어에 이를 적용하였던 사례는 존재하지 않았다. 또한, 수능 영어와 수능 수학 문제를 AI 문제풀이를 통해 도출한 결괏값이 각각 12점, 16점으로 객관식이라는 수능의 특수성을 고려했을 때 기대에 못 미치는 결과를 나타냈다. 이에 본 논문은 한국어 기계독해 데이터셋을 트랜스포머(Transformer) 기반 모델에 학습하여 수능 국어 문제 풀이에 적용하였다. 이를 위해 객관식으로 이루어진 수능 문항의 각각의 선택지들을 질문 형태로 변형하여 모델이 답을 도출해낼 수 있도록 데이터셋을 변형하였다. 또한 BERT(Bidirectional Encoder Representations from Transformer)가 가진 입력값 개수의 한계를 극복하기 위해 더 큰 입력값을 처리할 수 있는 트랜스포머 기반 모델 중에서 한국어 기계독해 학습에 적합한 KoBigBird를 사전학습모델로 설정하여 성능을 높였다.