• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.3
• /
• pp.364-371
• /
• 2013

Because of the increases in international oil prices and the level of global warming, the automotive industry has much interest in developing green cars with high fuel efficiencies. In addition, researchers in Korea are actively responding to high oil prices and $CO_2$ emission regulations in many ways. One example is, the multi-mode hybrid system, which is being studied to improve its performance. Because a multi-mode hybrid system is able to overcome the weaknesses of a system that uses simple planetary gears, excellent fuel efficiency and driving performances are the key features of the system. This paper analyzes the driving performance of the power-train system of GM-2MT70, which consists of one engine, two electric motors, one simple planetary gear, one double planetary gear, two clutches, and two brakes. The driving performance of the system's steady state is analyzed using performance modeling. The dynamic performance is analyzed using Matlab Simulink.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.316-320
• /
• 1993

Electromagnetic suspension (E.M.S) type levitation system is studied in the control system design viewpoint. Dynamic characteristics in theoretical analysis as well as hardware implementation is considered. Open loop unstable, non-linear and timevarying characteristics are reviewed in the theoretcal section, while levitation control system for multi-vehicle train as well as magnet drive system is reviewed in the practical section. This paper suggests not only some well-known problem appearing in levitation control system design but also a subtle problem and solution candidates. But there exist many unmentioned problems wating for a smart problem solver.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2009.04a
• /
• pp.559-560
• /
• 2009

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.8B
• /
• pp.1085-1091
• /
• 2001

이 논문에서는 주기적인 특성을 가진 펄스 열들이 서로 다른 초기 위상을 가지고 수신기에 입력되었을 때 도래시간 차이를 이용하여 펄스 열을 분리하는 방법을 제시하고자 한다. 주기적인 펄스 열을 주파수 관점에서 고찰해 보면 하나의 펄스 열 주파수 값으로 특성 지울 수 있으며 이러한 성질은 다중의 펄스 열이 포함된 신호 환경 하에서도 동일하게 나타난다. 제안된 기법은 기존의 스펙트럼 영역에서 사용된 신호 도래 시간의 지수함수로의 매핑을 대신하여 신호 도래 시간 차이를 이용하였으며 실제 다중 환경에서 나타날 수 있는 신호 성분들의 펄스 열 주파수 추정을 위하여 기존의 방법과 비교함으로써 제시한 방법의 타당성을 검증하였다.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.474-476
• /
• 1998

In this paper, a multi variable neuro-fuzzy controller for a boiler-turbine system is designed. Two architectures are used. The first consists of boiler-turbine system identification and the second is designing a controller. A generalized backpropagation algorithm is developed and used to train the neuro-fuzzy controller. Designed controller is good tracking property and rejects the input and output disturbances. The results of the proposed design method is verified through simulation.

• Proceedings of the KIEE Conference
• /
• 1997.07e
• /
• pp.1859-1860
• /
• 1997

다전극 DFB(distributed feedback) 레이저서, 레이징모드간 비팅을 통하여 초고속으로 자려펄스열을 발생시킬 수 있음을 제안한다. 이러한 자려펄스생성을 수정된 시영역 동적 모델(large signal time-domain dynamic model)을 이용하여 조사하였다.

• Proceedings of the KSR Conference
• /
• 2003.05a
• /
• pp.263-271
• /
• 2003

In this paper, we presents the results of the leading 2 European projects in the real-time train conflict dection and resolution field. One is MARCO(Multi-level Advanced Railways Conflicts Resolution and Operation Control) and the other is COMBINE(enhanced COntrol center for a Moving Block sigNaling systeEm) project. From the results of the survey, we derive the basic principles in order to use in the similar project of Korea Nation Railway.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.274-286
• /
• 2022

Multi-object tracking has been studied for a long time under computer vision and plays a critical role in applications such as autonomous driving and driving assistance. Multi-object tracking techniques generally consist of a detector that detects objects and a tracker that tracks the detected objects. Various publicly available datasets allow us to train a detector model without much effort. However, there are relatively few publicly available datasets for training a tracker model, and configuring own tracker datasets takes a long time compared to configuring detector datasets. Hence, the detector is often developed separately with a tracker module. However, the separated tracker should be adjusted whenever the former detector model is changed. This study proposes a system that can train a model that performs detection and tracking simultaneously using only the detector training datasets. In particular, a Siam network with augmentation is used to compose the detector and tracker. Experiments are conducted on public datasets to verify that the proposed algorithm can formulate a real-time multi-object tracker comparable to the state-of-the-art tracker models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.3A
• /
• pp.172-178
• /
• 2012

This paper studies the application of a fuzzy-ARTMAP (FAM) neural network to multi-user detector (MUD) for direct sequence (DS)-code division multiple access (CDMA) system. This method shows new solution for solving the problems, such as complexity and long training, which is found when implementing the previously developed neural-basis MUDs. The proposed FAM based MUD is fast and easy to train and includes capabilities not found in other neural network approaches; a small number of parameters, no requirements for the choice of initial weights, automatic increase of hidden units, no risk of getting trapped in local minima, and the capabilities of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random in a linear channel with Gaussian noise. The performance of FAM based MUD is compared with other neural net based MUDs in terms of the bit error rate.