• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.10a
• /
• pp.261-262
• /
• 2012

In this research, intelligent protection system for laser boat is introduced. The function of system is to measure the distance and velocity of object from our boat and generate control signals to avoid collision with moving targets. A novel approach to estimate object's position from our ship is tackled on this paper. To do this laser sensors are used to measure distance from ship to targets. The ship position and velocity is estimated by th Kalman filter algorithm. In the real phase, the filtering method will be applied to process signal gathered by laser sensors. Simulation to estimate ship's position and velocity under noise are executed and the results are introduced to show the effectiveness of the algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.885-888
• /
• 2018

This paper researches a way of detecting fish robots moving in an aquarium. The fish robot was designed and developed for interactions with humans in aquariums. It was studied merely to detect a moving object in an aquarium because we need to find the positions of moving fish robots. The intention is to recognize the location of robotic fish using an image processing technique and a video camera. This method is used to obtain the velocity for each pixel in an image, and assumes a constant velocity in each video frame to obtain positions of fish robots by comparing sequential video frames. By using this positional data, we compute the distance between fish robots using a mathematical expression, and determine which fish robot is leading and which one is lagging. Then, the lead robot will wait for the lagging robot until it reaches the lead robot. The process runs continuously. This system is exhibited in the Busan Science Museum, satisfying a performance test of this algorithm.

• Proceedings of the KIPE Conference
• /
• 2008.10a
• /
• pp.199-201
• /
• 2008

In this paper proposed the solar tracking system to use direct fuzzy control order to increase an output of the PV (Photovoltaic) array. The solar tracking system operated two DC motors driving by signal of photo sensor. The control of dual axes is not an easy task due to nonlinear dynamics and unavailability of the parameters. Recently, artificial intelligent control of the fuzzy control, neural-network and genetic algorithm etc. have been studied. The fuzzy control made a nonlinear dynamics to well perform and had a robust and highly efficient characteristic about a parameter variable as well as a nonlinear characteristic. Hence the fuzzy control was used to perform the tracking system after comparing with error values of setting-up, nonlinear altitude and azimuth. In this paper designed a DFC(Direct Fuzzy Control)controller for improving output of PV array and evaluated comparison with efficient of conventional PI controller. The data which were obtained by experiment were able to show a validity of the proposed controller.

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.129-140
• /
• 1998

An interface system was developed to offer the welding capability to a robot controller which had not any embedded function for arc welding before, and also an arc sensor algorithm was proposed for weld seam tracking of the welding robot. For the interface system between the robot controller and welding equipments, data communication software and interface connections were composed. The interface system was mae to correspond welding condition, correction data, operation sequence and current status with the robot controller by mutual had shaking and digital signal transfer. Graphic user interface program developed under the environment of windows made it easy to monitor data communication and operation status, and to control welding and sensing sequence. Arc sensing algorithm proposed in this study to compensate torch position error was based on a fuzzy logic with the variables of current difference and current differenced change at torch weaving extremities. The developed interface system could be successfully implemented in between welding equipments and the robot controller, and showed normal status and exact function in data and signal communication between the systems. The whole robot welding system was then examined to verify its welding and seam tracking capabilities in horizontal fillet, vertical fillet, and 3-dimensional fillet weldment. The experiments revealed sound weld bead shapes and also good seam tracing results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.163-169
• /
• 2021

In this paper, we implemented a deep learning-based automatic object tracking and handy motion control drone system and analyzed the performance of the proposed system. The drone system automatically detects and tracks targets by analyzing images obtained from the drone's camera using deep learning algorithms, consisting of the YOLO, the MobileNet, and the deepSORT. Such deep learning-based detection and tracking algorithms have both higher target detection accuracy and processing speed than the conventional color-based algorithm, the CAMShift. In addition, in order to facilitate the drone control by hand from the ground control station, we classified handy motions and generated flight control commands through motion recognition using the YOLO algorithm. It was confirmed that such a deep learning-based target tracking and drone handy motion control system stably track the target and can easily control the drone.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.05a
• /
• pp.159-160
• /
• 2019

It would be very important to localize people at risk as soon as possible in order to minimize the damage. Generally the infrastructure should be deployed additionally for indoor positioning system. In this paper, we proposed an indoor localization system for people at risk using the existing fire alarm networks. The system detects the signal of smart devices of people in danger immediately and let the main alarm controller ring all alarms in vessel and display the position. Thus, the proposed system can make the burden much less to deploy additional network and infrastructure.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.340-340
• /
• 2019

지구온난화로 유발되는 기후변동성이 증가함에 따라서 정확한 수문인자의 예측은 전 세계적으로 주요 관심사항이 되고 있다. 최근에는 고성능 컴퓨터 자원의 증가로 수문기상학 연구에서 동일한 학습량에 비하여 정확도의 향상이 뚜렷한 기계학습 구조를 활용하여 위성영상 기반의 대기예측, 태풍위치 추적 및 강수량 예측 등의 연구가 활발하게 진행되고 있다. 본 연구에는 기계학습 중 시계열 분석에 널리 활용되고 있는 순환신경망(Recurrent Neural Network, RNN) 기법의 대표적인 LSTM(Long Short-Term Memory) 네트워크를 이용하여 수문인자를 예측하였다. LSTM 네트워크는 가중치 및 메모리 요소에 대한 추가정보를 셀 상태에 저장하고 시계열의 길이 조정하여 모형의 탄력적 활용이 가능하다. LSTM 네트워크를 이용한 다양한 수문인자 예측결과 RMSE의 개선을 확인하였다. 따라서 본 연구를 통하여 개발된 기계학습을 통한 수문인자 예측기술은 권역별 수계별 홍수 및 가뭄대응 계획을 능동적으로 수립하는데 활용될 것으로 판단된다. 향후 연구에서는 LSTM의 입력영역을 Bayesian 추론기법을 활용하여 구성함으로 학습과정의 불확실성을 정량적으로 제어하고자 한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1023-1030
• /
• 2020

Wearable devices, such as a smart watch and a wrist band, store owner's private information in the devices so that security in a high level is required. Applications developed by third parties in Tizen request for an access to designated services through the desktop bus (D-Bus). The D-Bus verifies application's privileges to grant the request for an access. We developed a fuzzing tool, so-called DAN (the D-bus ANalyzer), to detect errors in implementations for privilege verifications and access controls within Tizen's system services. The DAN has found a number of vulnerable services which granted accesses to unauthorized applications. We built a proof-of-concept application based on those findings to demonstrate a bypass in the privilege examination.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.549-552
• /
• 2022

본 논문에서는 가상현실에서 헤드 마운티드 디스플레이(Head mounted display, HMD) 사용자와 Non-HMD 사용자에게 사용자의 걷기, 뛰기, 절름발이 움직임을 몰입감 있게 표현하기 위한 새로운 가상현실(VR, Virtual Reality) 인터페이스를 제안한다. 가상현실에서는 몰입감을 높이기 위해 시각적 감각을 활용한 HMD와 사용자의 자세나 움직임을 추적하는 장비를 활용하지만, 일반적인 사용자들에게 HMD 보급은 많이 이루어져 있지 않으며, 비용적인 측면과 멀미로 인해 가상현실 콘텐츠에 몰입하기 어렵다. 본 논문에서는 효율적으로 몰입도를 높이고 비용적인 부담을 줄여주기 위해 아두이노를 활용한 새로운 보행 인터페이스 장치를 제안한다. 보행 인터페이스 장치는 사용자의 다리 가속도 정보를 기반으로 사용자의 상태 변화에 맞게 패턴을 설정하여 사용자의 걷기, 뛰기, 절름발이 움직임을 통해 사용자 캐릭터의 움직임을 제어하고 표현할 수 있는 새로운 결과를 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.1038-1040
• /
• 2022

지속적인 지구 평균 기온 상승으로 인해 우리나라를 포함한 전 세계적으로 탄소중립을 위한 혁신이 이루어지고 있다. 본 연구는 해양수산부 '해양수산분야 2050 탄소중립 로드맵'의 기준에 따라 에너지 자립률을 극대화하고 효율을 최적화시킨 제로에너지 탄소중립 건축물을 제시한다. 태양광 발전 시스템에서, 패널의 태양 일주추적 기능을 통해 에너지 발전률을 극대화하고, 패널 하향정렬 및 딥러닝 모델을 통해 유지 보수를 용이하게 하여 성능 저하를 예방한다. 폐열을 이용한 열 회수/바이패스 환기 시스템을 통해 에너지 효율을 최적화하고, 온/습도에 가중치를 부여하여 모호했던 환기 시스템 결정 기준을 에너지 효율화에 맞게 최적화해 제시한다. 탄소중립 BEMS 기능이 내재된 앱 개발로 위의 건축물 시스템을 제어·관리한다. 본 연구를 통해 제로 에너지 건축물으로서 항만 건물의 가능성을 제고하고, 탄소중립 항만의 구현을 기대한다.