• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1992년도 추계학술대회
• /
• pp.26-28
• /
• 1992

Texture analysis, one of the mage processing techniques, using statistical characteristics is applied to the ultrasound images, which are then classified into each types through neural network. This is a method to be used to diagnose ultrasound images automatically and objectively. First tone kinds of texture analysis techniques proposed already are used to classify ultrasound images and compared in terms of classification rate, and then a new technique if proposed which is invariant to multiplicative gain changes and image resolution.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.3013-3015
• /
• 2000

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of conventional techniques such as the pole placement and the optimal control based on the local linearizations have narrow stabilizable regions, At the same time, the fine tunings of their gain parameters are also troublesome, Thus, in this paper, an Evolving Neural Network ControlleY(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algorithm (RVEGA) was presented for stabilization of an IP system with nonlinearity, This proposed ENNC was described by a simple genetic chromosome. Through the simulation and experimental results, we showed that the finally acquired optimal ENNC was very useful in the stabilization control of IP system.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권6호
• /
• pp.433-439
• /
• 2004

The Helicopter Simulator System is non-linear and complex. Futhermore, because of absence of its accurate mathematical model, it is difficult to control accurately its attitudes such as elevation angle and azimuth one. Therefore, we proposed a Hybrid GA-PID WAVENET(Genetic Algorithm Proportional Integral Derivative Wavelet Neural Network)control technique to control efficiently these angles. The proposed Hybrid GA-PID WAVENET is made through the following process. First, the WAVENET fundamental functions are defined. And their dilation and translation values are adjusted by GA to construct the optimal WAVENET controller. Secondly, the proportional, integral, and derivative gain coefficients of PR controller are tuned optimally. Finally, WAVENET controller which has a good transient characteristic and GA-PE controller which has a good steady state characteristic is adequately combined in hybrid type. Through the computer simulations, it is proved that the Hybrid GA-PE WAVENET control technique has a more excellent dynamic response than PID control technique and GA-PID one.

• 한국항행학회논문지
• /
• 제18권2호
• /
• pp.107-113
• /
• 2014

본 논문에서는 무인항공기용 소형 터보제트엔진에 대해 압축기 서지현상 및 화염소실을 방지하면서 과도응답 특성을 개선하는 제어기를 설계하였다. 인공신경망과 PID 제어 알고리즘을 적용하는 터보제트엔진 제어기를 설계하고 인공신경망 역전파 알고리즘을 사용하였다. 터보제트 엔진의 가 감속 시 서지현상과 flame-out 현상을 방지하기 위해 연료 유량 제어 입력을 인공신경망 PID 제어기로 생성한다. 생성된 연료 유량 제어 입력은 신속하고 안전하게 원하는 속도로 수렴할 수 있도록 제어기를 설계한다. MATLAB을 이용한 시뮬레이션을 통해 이득 값에 따른 응답특성 비교 분석 및 신속하고 안전하게 원하는 속도로 수렴하는 제어성능을 확인하였다.

• 한국정보통신학회논문지
• /
• 제15권9호
• /
• pp.1871-1880
• /
• 2011

본 논문에서는 최근 편리하고 간편한 이동수단으로 각광받고 있는 Segway 형태의 이륜 역진자로봇에 대해 기존의 방법보다 더 안정적인 밸런싱과 빠른 속도제어가 가능하도록 제어기를 설계하였다. 먼저 널리 사용되는 PID 제어 구조를 이륜 역진자로봇에 적용하고, 몇 단계로 지정된 탑승자의 각 몸무게에 대해 적절한 PID 제어기 이득을 시행착오적으로 선택하여 밸런싱과 속도제어가 잘 이루어지도록 하였다. 앞에서 지정된 몸무게 이외의 임의의 몸 무게에 대한 PID 제어기 이득값을 구하기 위해 보간 개념으로 신경회로망을 사용하였으며 앞에서 시행착오적으로 구한 제어 이득값을 학습데이터로 사용하였다. 이와 같이 신경회로망을 이용하여 설계된 제어기의 성능을 확인하기 위해서 시뮬레이션 연구를 수행하였으며, 기존의 PID 제어기보다 빨리 밸런싱과 속도제어가 됨을 확인할 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1983-1989
• /
• 2005

Industrial robots are powerful, extremely accurate multi-jointed systems, but they are heavy and highly rigid because of their mechanical structure and motorization. Therefore, sharing the robot working space with its environment is problematic. A novel pneumatic artificial muscle actuator (PAM actuator) has been regarded during the recent decades as an interesting alternative to hydraulic and electric actuators. Its main advantages are high strength and high power/weight ratio, low cost, compactness, ease of maintenance, cleanliness, readily available and cheap power source, inherent safety and mobility assistance to humans performing tasks. The PAM is undoubtedly the most promising artificial muscle for the actuation of new types of industrial robots such as Rubber Actuator and PAM manipulators. However, some limitations still exist, such as the air compressibility and the lack of damping ability of the actuator bring the dynamic delay of the pressure response and cause the oscillatory motion. In addition, the nonlinearities in the PAM manipulator still limit the controllability. Therefore, it is not easy to realize motion with high accuracy and high speed and with respect to various external inertia loads in order to realize a human-friendly therapy robot To overcome these problems a novel controller, which harmonizes a phase plane switching control method with conventional PID controller and the adaptabilities of neural network, is newly proposed. In order to realize satisfactory control performance a variable damper - Magneto-Rheological Brake (MRB) is equipped to the joint of the manipulator. Superb mixture of conventional PID controller and a phase plane switching control using neural network brings us a novel controller. This proposed controller is appropriate for a kind of plants with nonlinearity uncertainties and disturbances. The experiments were carried out in practical PAM manipulator and the effectiveness of the proposed control algorithm was demonstrated through experiments, which had proved that the stability of the manipulator can be improved greatly in a high gain control by using MRB with phase plane switching control using neural network and without regard for the changes of external inertia loads.

• 해양환경안전학회지
• /
• 제29권6호
• /
• pp.659-665
• /
• 2023

선박 발전기의 여자기는 출력 단자 전압을 일정하게 유지하기 위하여 여자전류 제어를 통해 자속을 조정한다. 여자기 내부에 있는 전압제어기는 통상적으로 비례 적분 제어방식이 사용되는데 게인과 시정수에 의해 결정되는 응답 특성은 적절치 못한 설정값에 의해 원하지 않는 출력을 내며 이로 인해 선내 전력의 품질과 안정성을 떨어뜨릴 수 있다. 본 논문에서는 IEEE에서 제공하는 AC4A 타입의 여자기 모델을 통해 얻을 수 있는 안정적인 입출력 데이터를 활용하여 신경망 회로를 학습시킨 후 기존의 비례 적분 제어방식의 전압제어기를 학습된 신경망 회로 제어기로 대체하여 시뮬레이션을 수행하였다. 그 결과 기존 대비 최대 9.63%까지 오버슈팅이 개선되었으며, 안정적인 응답 특성에 대한 우수성을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• 한국지능시스템학회논문지
• /
• 제15권1호
• /
• pp.24-29
• /
• 2005

일반적으로 다변수 계통에 대한 퍼지 제어에서 퍼지 규칙을 얻기가 어려워 입출력 사이의 페어링을 이용한 독립적인 단일 입력 단일 출력의 병렬 구조를 이용한다. 그러나, 결합되지 않은 입출력 변수간의 상호작용으로 제어 성능에 나쁜 영향을 준다. 특히, 강한 결합 특성을 가진 계통의 경우 제어 성능을 아주 저하시킨다. 본 논문에서는 이러한 상호작용에 의한 영향을 보상해주기 위해 상대 이득 행렬을 이용한 신경 회로망을 도입하였다 제안한 뉴로 퍼지 제어기는 역전파 알고리즘으로 학습되며 강호작용에 대한 결합강도를 자동으로 조정하여준다. 제안한 뉴로 퍼지 제어기의 성능을 200MW급 보일러 계통에 대한 컴퓨터 모의실험을 통해 입증하였다.

• 로봇학회논문지
• /
• 제12권4호
• /
• pp.425-431
• /
• 2017

As drones gain more popularity these days, drone detection becomes more important part of the drone systems for safety, privacy, crime prevention and etc. However, existing drone detection systems are expensive and heavy so that they are only suitable for industrial or military purpose. This paper proposes a novel approach for training Convolutional Neural Networks to detect drones from images that can be used in embedded systems. Unlike previous works that consider the class probability of the image areas where the class object exists, the proposed approach takes account of all areas in the image for robust classification and object detection. Moreover, a novel loss function is proposed for the CNN to learn more effectively from limited amount of training data. The experimental results with various drone images show that the proposed approach performs efficiently in real drone detection scenarios.