• Fisheries and Aquatic Sciences
• /
• 제7권3호
• /
• pp.163-170
• /
• 2004

A fishing simulator for towed fishing gear was investigated in order to mimic the fish behavior in capture process and investigate fishing selectivity. A fish behavior model using a psycho-hydraulic wheel activated by stimuli is established to introduce Lorenz chaos equations and a neural network system and to generate the components of realistic fish capture processes. The fish positions within the specified gear geometry are calculated from normalized intensities of the stimuli of the fishing gear components or neighboring fish and then these are related to the sensitivities and the abilities of the fish. This study is applied to four different towed gears i.e. a bottom trawl, a midwater trawl, a two-boat seine, and an anchovy boat seine and for 17 fish species as mainly caught. The Alpha cluster computer system and Fortran MPI (Message-Passing Interface) parallel programming were used for rapid calculation and mass data processing in this chaotic behavior model. The results of the simulation can be represented as animation of fish movements in relation to fishing gear using Open-GL and C graphic programming and catch data as well as selectivity analysis. The results of this simulator mimicked closely the field studies of the same gears and can therefore be used in further study of fishing gear design, predicting selectivity and indoor training systems.

• ETRI Journal
• /
• 제42권4호
• /
• pp.491-504
• /
• 2020

We present AB9, a neural processor for inference acceleration. AB9 consists of a systolic tensor core (STC) neural network accelerator designed to accelerate artificial intelligence applications by exploiting the data reuse and parallelism characteristics inherent in neural networks while providing fast access to large on-chip memory. Complementing the hardware is an intuitive and user-friendly development environment that includes a simulator and an implementation flow that provides a high degree of programmability with a short development time. Along with a 40-TFLOP STC that includes 32k arithmetic units and over 36 MB of on-chip SRAM, our baseline implementation of AB9 consists of a 1-GHz quad-core setup with other various industry-standard peripheral intellectual properties. The acceleration performance and power efficiency were evaluated using YOLOv2, and the results show that AB9 has superior performance and power efficiency to that of a general-purpose graphics processing unit implementation. AB9 has been taped out in the TSMC 28-nm process with a chip size of 17 × 23 ㎟. Delivery is expected later this year.

• Journal of Advanced Research in Ocean Engineering
• /
• 제3권3호
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(5)
• /
• pp.269-272
• /
• 2002

In this study, we designed the expert system for the diagnosis of stroke. The causes of stroke in central nervous systems are very diverse, so a doctor who treats the patients with stroke must have the expert knowledge for the quick and correct diagnosis and for the adequate medical management. But the primary physician who engaged in the primary care of the patient with stroke does not have the export knowledge for the stroke. So, we need to develop the expert system for assisting the diagnosis of stroke. Also the diagnosis system can be used as simulator for the medical students who study the neurology. In this study, we developed the diagnosis expert system that offer a pathological name provided by artificial neural networks. And we designed the inference engine and interfaces. The artificial neural network is a system that provide a possible diagnosis of stroke. We implemented the system using Windows2000 Server, IIS5.0 and ASP.

• 한국정밀공학회지
• /
• 제22권1호
• /
• pp.61-72
• /
• 2005

In this paper, we develop anti-sway control in proposed techniques for an ATC system. The developed algorithm is to build the optimal path of container motion and to calculate an anti-collision path for collision avoidance in its movement to the finial coordinate. Moreover, in order to show the effectiveness in this research, we compared NNP PID controller to be tuning parameters of controller using NN with 2 DOF PID controller. The experimental results for an ATC simulator show that the proposed control scheme guarantees performances, trolley position, sway angle, and settling time in NNP PID controller than other controller. As a result, the application of NNP PID controller is analyzed to have robustness about disturbance which is wind of fixed pattern in the yard. Accordingly, the proposed algorithm in this study can be readily used for industrial applications

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.265-270
• /
• 2005

This paper presents a new attitude stabilization and control of an unmanned helicopter based on neural network compensation. A systematic derivation on the dynamics of an unmanned small-scale helicopter is performed. Combined rotor-fuselage-tail dynamics is derived in body-fixed reference frame with its origin at the C.G. of the helicopter. And the resulting nonlinear equation of motion consists of 6-DOF air vehicle dynamics as well as the rotor flapping and engine torque equations. A simulation model was modified using the existing simulator for an unmanned helicopter dynamic model, which reflects the unmanned test helicopter(CNUHELI). The dynamic response of the refined model was compared with the flight test data. It can be shown that a good coincidence was accomplished between the real unmanned helicopter system and the mathematical model. This dynamic model was linearized for classical controller design using small perturbation method. A Neuro-PD control system was designed for both longitudinal and lateral flight modes, and the results were compared with the PD-only control response. Simulation results show that the proposed Neuro-PD control system demonstrates better performance.

• 전자공학회논문지 IE
• /
• 제48권4호
• /
• pp.1-6
• /
• 2011

본 논문에서는 LCD 제조공정 상에서 발생할 수 있는 결함을 검사하고 분류할 수 있는 적응적인 LCD 표면 결함 검사 시스템을 제안하였다. 즉, 반복되는 LCD 패턴의 주기를 확정한 후에 결함 패턴을 검출하고 검출된 결함 패턴의 특징을 계산하여 결함을 분류하였다. 그리고 결함을 검출하는 과정에서 발생하는 잡음은 모폴로지 연산자를 이용하여 제거하였다. 또한, 검출된 결함 패턴에서 기하학적인 특징과 통계적 특징을 계산한 후 신경회로망 알고리즘을 이용하여 여러 종류의 결함 패턴을 적응적으로 분류하였으며, 실험 결과 92.3%의 결함 검출율 및 94.5%의 결함 분류 및 인식율을 획득함으로써, LCD 결함 검사 시스템의 실질적인 구현 가능성을 제시하였다.

• 열처리공학회지
• /
• 제31권4호
• /
• pp.180-186
• /
• 2018

High temperature flow behaviors of Fe-Cr-Mo-V-W-C tool steel were investigated using isothermal compression tests on a Gleeble simulator. The compressive test temperature was varied from 850 to $1,150^{\circ}C$ with the strain rate ranges of 0.05 and $10s^{-1}$. The maximum height reduction was 45%. The dynamic softening related to the dynamic recrystallization was observed during hot deformation. The constitutive model based on Arrhenius-typed equation with the Zener-Hollomon parameter was proposed to simulate the hot deformation behavior of Fe-Cr-Mo-V-W-C steel. An artificial neural network (ANN) model was also developed to compare with the constitutive model. It was concluded that the ANN model showed more accurate prediction compared with the constitutive model for describing the hot compressive behavior of Fe-Cr-Mo-V-W-C steel.

• 한국해양공학회지
• /
• 제36권5호
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권9호
• /
• pp.379-390
• /
• 2019

본 논문에서는 시각-언어 이동 문제를 위한 새로운 심층 신경망 모델인 LVLN을 제안한다. LVLN 모델에서는 자연어 지시의 언어적 특징과 입력 영상 전체의 시각적 특징들 외에, 자연어 지시에서 언급하는 주요 장소와 랜드마크 물체들을 입력 영상에서 탐지해내고 이 정보들을 추가적으로 이용한다. 또한 이 모델은 자연어 지시 내 각 개체와 영상 내 각 관심 영역, 그리고 영상에서 탐지된 개별 물체 및 장소 간의 서로 연관성을 높일 수 있도록 맥락 정보 기반의 주의 집중 메커니즘을 이용한다. 그뿐만 아니라, LVLN 모델은 에이전트의 목표 도달 성공율을 향상시키기 위해, 목표를 향한 실질적인 접근을 점검할 수 있는 진척 점검기 모듈도 포함하고 있다. Matterport3D 시뮬레이터와 Room-to-Room (R2R) 벤치마크 데이터 집합을 이용한 다양한 실험들을 통해, 본 논문에서 제안하는 LVLN 모델의 높은 성능을 확인할 수 있었다.