• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.1
• /
• pp.26-32
• /
• 2012

In this study, we proposed an intelligent algorithm for the performance improvement of ASK system for giga-bit modem in millimeter band. The proposed intelligent algorithm is a fuzzy logic system. The inputs to the fuzzy logic system are the remainder and integral of remainder that occurred counter of receiver, and the output is bandwidth of LPF. In order to verify the effectiveness of the proposed method, simulation is performed to the proposed system and the fixed bandwidth system, and is confirmed to the BER performance.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.482-484
• /
• 2001

In orthopedics, hip arthroplasty is the operation that replaces damaged hip joint to artificial joint. In hip arthroplasty, quite better result can be achieved if robot is applied to machine cavity in bone, especially when cementless stem is used. So several kinds of robots were introduced for hip arthroplasty, but they used MRI, CT Scan, vision analysis and real time tracking of bone position for registration of robot. To overcome shortage of conventional robot surgery, gauge based registration method was proposed and small robot was designed. In this method, small robot is mounted on femur, and its position is determined by gauge registration method. Operation procedure was performed on model femur and result was analyzed. This robotic hip surgery system is expected to more adaptable in operation room.

• Journal of Chest Surgery
• /
• v.37 no.4
• /
• pp.369-372
• /
• 2004

Acute myocardial infarction due to coronary occlusion by emboli originating from the prosthetic valve thrombosis is very rare but fatal disease which needs immediate diagnosis and urgent treatment. We report a case of acute myocardial infarction after left anterior descending embolic occlusion in whom had previous mitral valve replacement. Redo valve replacement following the interventional catheterization and anti platelet therapy lead to successful results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.1
• /
• pp.115-122
• /
• 2017

Deep learning is artificial intelligence technology that can teach people like themselves who need machine learning. Deep learning has become of the most promising in the development of artificial intelligence to understand the world and detection technology, and Google, Baidu and Facebook is the most developed in advance. In this paper, we discuss the kind of deep learning frameworks, compare and analyze the efficiency of the image and speech recognition field of it.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.536-540
• /
• 1996

경험과 학습을 바탕으로 새로운 상황에 대처하는 인간의 신경계에서의 신경세포들의 상호작용을 규명하는 일은 많은 과학자들을 매료시켜 왔다. 이와 함께, 생물학적인 신경계를 닮은 인공적인 신경망을 구축하여 감지하고, 인식하고, 구별하고, 판단하는 일에 이용하고자 하는 노력도 끊임없이 진행되어 왔다. 인공 신경망의 구성은 전적으로 많은 경우의 수에 대한 테스트에 의존하게 되는 데, 이 경우 시간도 대단히 많이 소요 될 뿐더러 체계적으로 가장 좋아 보이는 신경망 모델에 도달하였는 지도 확실치 않다. 따라서 , 본 논문에서는 실험계획법을 다층 퍼셉트론 신경망의구조설계에 적용하여 적은 실험횟수로 적합한 신경망 모델을 구성할 수 있음을 검증하고, 실제사례에 적용하여 그 유용성을 제시하고자 한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.2
• /
• pp.309-315
• /
• 2012

We develpoed auto winch control which will be applied when we want to fix ship or marine structure in the ocean. In this paper, an effort has been made to design and develop a control unit for Winch control purpose. Developed result shows usefulness when it is applied to Han-river floating island.

• Journal of Digital Contents Society
• /
• v.7 no.1
• /
• pp.35-40
• /
• 2006

Game AI(Artificial Intelligence) technologies implement the movement of autonomous characters and control the movement of Non-Player Characters(NPC). In this paper, we present several types of game AI control systems such as Movement Scripts, FSM(Finite State Machines), Hierarchical State Machines, fuzzy State Machines, and Pathfinding techniques and their limitations.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.626-633
• /
• 1995

It is vary hard to identify the fuzzy rules and tune the membership functions of the fuzzy inference in fuzzy systems modeling, We propose a fuzzy neural network model which can automatically identify the fuzzy rules and tune the membership functions of fuzzy inference simultaneously using artificial neural networks, and modify backpropagation algorithm for improving the convergence. The proposed method is verified by the simulation for a robot manipulator.

• Korean Journal of Remote Sensing
• /
• v.12 no.2
• /
• pp.97-110
• /
• 1996

In this paper, we describe the structure, function, and the operation method of the high resolution CCD camera system on the KITSAT-3, which will be launched in 1998. We have developed the camera system with the University of Stellenbosch in the Republic of South Africa. Currently we are doing the environmental test for the engineering model of the camera system. The main purposes of the system are the technology acquisition and operation test. The around resolution of the system is 15 m at the 800 Km earth orbit.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.719-722
• /
• 2021

최근 인공지능의 새로운 기술들이 하루가 다르게 발전하고 있다. 이에 본 연구에서는 인공지능 교육과 글쓰기 교육을 연계하여 초등학생들의 어휘력 향상을 위한 수업을 설계하고자 한다. 그 방법으로는 본 수업에 앞서 어휘 10문제를 테스트하여 실험에 참가하기 전의 어휘력을 점검한다. 그 후 머신러닝 포키즈를 이용하여 여러 감정에 해당되는 단어들을 다양하게 훈련하도록 하였고, 그 후 관련된 어휘 10문제를 다시 테스트 하였다. 실험 결과 실험에 참가하기 전에는 100점 만점에 58.8점으로 나왔으나 훈련 후의 결과는 평균 68점으로 모든 학생의 성적이 좋아지는 결과를 얻을 수 있었다. 어휘력 문항수가 적은 점과 10명의 실험참가자로 일반화할 수 없는 한계가 있다. 향후 초등교재 한권을 선정하여 어휘를 모두 분석한 후 가장 많이 등장하는 어휘를 골라내어 테스트하여 좀 더 통계적으로 의미 있는 분석을 하고자 한다.