• Proceedings of the KIPE Conference
• /
• 2006.06a
• /
• pp.345-347
• /
• 2006

In this paper, a novel method for wind speed estimation in wind power generation systems is presented. The proposed algorithm is based on estimating the wind speed using Support-Vector-Machines for regression (SVR). The wind speed is estimated using the generator power-speed characteristics as a set of training vectors. SVR is trained off-line to predict a continuos-valued function between the system's inputs and wind speed value. The predicted off-line function as well as the instantaneous generator power and speed are then used to determine the unknown winds speed on-line. The simulation results show that SVR can define the corresponding wind speed rapidly and accurately to determine the optimum generator speed reference for maximum power point tracking.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.10a
• /
• pp.108-112
• /
• 2000

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.2
• /
• pp.167-172
• /
• 2004

Neural networks are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division (Corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the KIEE Conference
• /
• 1994.07a
• /
• pp.252-254
• /
• 1994

This paper describes the control method in order that output current of a voltage source inverter tracks reference sinusoidal current so that its harmonic current components are reduced. Operating character of this inverter is analyzed with normalized values of parameter. And the method that apply multilayed feedfoeward neural networks, which play excellent steady state operation in control system, to inverter control system and training method are presented. Then, the output current of inverter which is driven by the proposed method. is considered throughout computer simulation and safe operating range of inverter parameter is resented.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.124-129
• /
• 2020

Autonomous underwater vehicle makes attracts to many researchers. This paper proposes a convolutional neural network (CNN) based fish detection method. Since there are not enough data sets in the process of training, overfitting problem can be occurred in deep learning. To solve the problem, we apply the dropout algorithm to simplify the model. Experimental result showed that the implemented method is promising, and the effectiveness of identification by dropout approach is highly enhanced.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.19-20
• /
• 2016

비디오로부터 객체를 검출하기 위해서는 오프라인에서 미리 객체를 검출할 수 있는 분류기가 학습되어있어야 한다. 이러한 분류기는 훈련에 사용된 훈련 집합에 매우 의존적이어서, 다양한 환경의 비디오 영상에 모두 적용할 수 있는 분류기의 설계는 불가능하다. 또한 분류기의 학습을 위해서는 상당히 많은 수의 훈련 집합이 필요하므로, 이는 신뢰도 높은 분류기 학습을 위한 높은 비용을 초래한다. 본 논문에서는 이러한 문제를 해결 할 수 있는 온라인 학습 기반 사람 추적 방법을 제안한다. 실험 영상으로부터 적절하게 훈련 집합을 수집함으로써 해당 실험 영상에 최적화된 분류기의 학습이 가능하며, 다양한 환경의 영상에 적용적으로 설계될 수 있다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.88-96
• /
• 1996

Computer vision-based gesture recognition systems consist of image segmentation, object tracking and decision. However, it is difficult to segment an object from image for gesture in computer systems because of vaious illuminations and backgrounds. In this paper, we describe a method to learn features for segmentation, which improves the performance of computer vision-based hand-gesture recognition systems. Systems interact with a user to acquire exact training data and segment information according to a predefined plan. System provides some models to the user, takes pictures of the user's response and then analyzes the pictures with models and a prior knowledge. The system sends messages to the user and operates learning module to extract information with the analyzed result.

• Nuclear Engineering and Technology
• /
• v.48 no.1
• /
• pp.129-143
• /
• 2016

Sometimes, we need or try to figure out somebody's thoughts from his or her behaviors such as eye movement, facial expression, gestures, and motions. In safety-critical and complex systems such as nuclear power plants, the inference of operators' thoughts (understanding or diagnosis of a current situation) might provide a lot of opportunities for useful applications, such as development of an improved operator training program, a new type of operator support system, and human performance measures for human factor validation. In this experimental study, a novel method for inference of an operator's thoughts from his or her eye movement data is proposed and evaluated with a nuclear power plant simulator. In the experiments, about 80% of operators' thoughts can be inferred correctly using the proposed method.

• Journal of the Korea Safety Management & Science
• /
• v.20 no.1
• /
• pp.33-40
• /
• 2018

The rate of fire in buildings is gradually increasing in these days and the damage of property are severely increasing. This study suggests a methodology that provides information of the emergency exits based on indoor location services. The methodology uses determination technology and the latest update of indoor map generation via the built-in sensors of smartphone. This paper enhances the accuracy of indoor localization, and also it is to study how to provide exact indoor layout for rescuing the workers in emergency, such as fires and natural disasters.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.27-39
• /
• 2018

Since the global positioning system (GPS) has been included in mobile devices (e.g., for car navigation, in smartphones, and in smart watches), the impact of personal GPS log data on daily life has been unprecedented. For example, such log data have been used to solve public problems, such as mass transit traffic patterns, finding optimum travelers' routes, and determining prospective business zones. However, a real-time analysis technique for GPS log data has been unattainable due to theoretical limitations. We introduced a machine learning model in order to resolve the limitation. In this paper presents a new, three-stage real-time prediction model for a person's daily route activity. In the first stage, a machine learning-based clustering algorithm is adopted for place detection. The training data set was a personal GPS tracking history. In the second stage, prediction of a new person's transient mode is studied. In the third stage, to represent the person's activity on those daily routes, inference rules are applied.