• 전기학회논문지
• /
• 제67권4호
• /
• pp.586-594
• /
• 2018

In this paper, we propose a livestock theft detection system through moving object classification and tracking method. To do this, first, we extract moving objects using GMM(Gaussian Mixture Model) and RGB background modeling method. Second, it utilizes a morphology technique to remove shadows and noise, and recognizes moving objects through labeling. Third, the recognized moving objects are classified into human and livestock using skeletal features and color similarity judgment. Fourth, for the classified moving objects, CAM (Continuously Adaptive Meanshift) Shift and Kalman Filter are used to perform tracking and overlapping judgment, and risk is judged to generate a notification. Finally, several experiments demonstrate the feasibility and applicability of the proposed method.

• 한국군사과학기술학회지
• /
• 제10권4호
• /
• pp.138-144
• /
• 2007

This paper introduces the design techniques of an IR module using the 2-D array un-cooled type infrared detector which is applied to the individual combat weapon. Considering the size and weight of the hand carried weapon system, we used a very small-sized detector and applied an adaptive temperature control algorithm so that the operation consumed with low power can be possible. We applied the AR(Auto Regressive) filter to improve the signal-to-noise ratio in a thermal image processing step. We also applied the plateau equalization and boundary enhancement techniques to improve the visibility for human visual system.

• Structural Engineering and Mechanics
• /
• 제17권3_4호
• /
• pp.303-329
• /
• 2004

Magnetostrictive materials are routinely employed as actuator and sensor elements in a wide variety of noise and vibration control problems. In infrastructural applications, other technologies such as hydraulic actuation, piezoelectric materials and more recently, magnetorheological fluids, are being favored for actuation and sensing purposes. These technologies have reached a degree of technical maturity and in some cases, cost effectiveness, which justify their broad use in infrastructural applications. Advanced civil structures present new challenges in the areas of condition monitoring and repair, reliability, and high-authority actuation which motivate the need to explore new methods and materials recently developed in the areas of materials science and transducer design. This paper provides an overview of a class of materials that because of the large force, displacement, and energy conversion effciency that it can provide is being considered in a growing number of quasistatic and dynamic applications. Since magnetostriction involves a bidirectional energy exchange between magnetic and elastic states, magnetostrictive materials provide mechanisms both for actuation and sensing. This paper provides an overview of materials, methods and applications with the goal to inspire novel solutions based on magnetostrictive materials for the design and control of advanced infrastructural systems.

• 대한전기학회논문지
• /
• 제39권4호
• /
• pp.364-370
• /
• 1990

In this paper, we propose a self-tuning PID controller for unknown systems with time-varying delay. Using pole placement equations, we derive the controller that can be extended to the multi-step time delay case. The time-varying delays are estimated by a prediction error delay method using multiple predictors. Since the order of the estimation vector is not increased, the persistant exciting condition of control input is alleviated. Since the least square method gives biased parameter estimates for colored noise cases, the recursive instrumental variable method is used to estimate system parameters. The computational burden of the proposed method is less than the conventional adaptive methods. Computer simulations are performed to illustrate the efficiency of the proposed method.

• 제어로봇시스템학회논문지
• /
• 제4권4호
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.558-561
• /
• 2002

A CCD camera with a laser strip was applied to realize the automation of welding Process in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noise such spatter and arc light. The adaptive Hough transformation was used to extract the laser stripe and to obtain specific weld points In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• 대한전자공학회논문지
• /
• 제7권2호
• /
• pp.26-32
• /
• 1970

제어 계통의 동특성에 대한 상관계산이 가능하게 시험신호 발생장치를 연구하였다. 의사 랜덤 2진 신호 중 M계열 신호데 대한 것을 중점으로 다뤘고, 구성된 신호발생기는 시험신호로서 만족할 수 있는 특성을 보였다.

• Earthquakes and Structures
• /
• 제22권4호
• /
• pp.421-430
• /
• 2022

This paper addresses the stochastic control problem of robots within the framework of parameter uncertainty and uncertain noise covariance. First of all, an open circle deterministic trajectory optimization issue is explained without knowing the unequivocal type of the dynamical framework. Then, a Linear Quadratic Gaussian (LQG) controller is intended for the ostensible trajectory-dependent linearized framework, to such an extent that robust hereditary NN robotic controller made out of the Kalman filter and the fuzzy controller is blended to ensure the asymptotic stability of the non-continuous controlled frameworks. Applicability and performance of the proposed algorithm shown through simulation results in the complex systems which are demonstrate the feasible to improve the performance by the proposed approach.

• Structural Engineering and Mechanics
• /
• 제81권1호
• /
• pp.51-57
• /
• 2022

The problem of optimal stochastic GA control of the system with uncertain parameters and unsure noise covariates is studied. First, without knowing the explicit form of the dynamic system, the open-loop determinism problem with path optimization is solved. Next, Gaussian linear quadratic controllers (LQG) are designed for linear systems that depend on the nominal path. A robust genetic neural network (NN) fuzzy controller is synthesized, which consists of a Kalman filter and an optimal controller to assure the asymptotic stability of the discrete control system. A simulation is performed to prove the suitability and performance of the recommended algorithm. The results indicated that the recommended method is a feasible method to improve the performance of active tuned mass damper (ATMD) shear buildings under random earthquake disturbances.

• 전자공학회논문지 IE
• /
• 제43권2호
• /
• pp.80-86
• /
• 2006

제4세대 무선 통신은 송신기와 수신기양단에 다중 안테나와 순시 채널의 상태 정보를 이용함으로써 LDPC와 OFDM 무선 전송에 있어서 MQAM(M-ary Quadrature Amplitude Modulation)을 사용하는 적응 공간 부반송파 부호화 변조 방식에 기반으로 하고 있다. 적응 부호화 변조는 시변 협대역 무선 채널에 대해서 대역 효율이 좋은 전송방식으로 인식되어 가고 있다. 전력이 제한된 AWGN 채널에 대해서, LDPC 부호들은 오류 제어 부호의 한 부류이며 이는 어떤 조건하에서는 터보부호보다 오류 정정 능력이 더 좋은 것으로 알려져 왔다. 본 논문에서는 MIMO 시스템에 적용된 LDPC 부호를 갖는 OFDM 방식과 적응 변조방식에 대해서 서술한다. 채널의 순시 정보를 알고 있다고 가정함으로써 각 부반송파에 대해서 비트와 전력 할당을 얻기 위한 최적화 알고리즘이 사용되였다. 시뮬레이션 결과는 제안한 시스템이 가능성을 가짐을 보여준다.