• 한국음향학회지
• /
• 제39권5호
• /
• pp.483-489
• /
• 2020

본 논문에서는 저자원 환경의 음성인식에서 음향 모델의 성능을 높이기 위한 음향 모델 학습 방법을 제안한다. 저자원 환경이란, 음향 모델에서 100시간 미만의 학습 자료를 사용한 환경을 말한다. 저자원 환경의 음성인식에서는 음향 모델이 유사한 발음들을 잘 구분하지 못하는 문제가 발생한다. 예를 들면, 파열음 /d/와 /t/, 파열음 /g/와 /k/, 파찰음 /z/와 /ch/ 등의 발음은 저자원 환경에서 잘 구분하지 못한다. 자기 주의 메커니즘은 깊은 신경망 모델로부터 출력된 벡터에 대해 가중치를 부여하며, 이를 통해 저자원 환경에서 발생할 수 있는 유사한 발음 오류 문제를 해결한다. 음향 모델에서 좋은 성능을 보이는 Time Delay Neural Network(TDNN)과 Output gate Projected Gated Recurrent Unit(OPGRU)의 혼합 모델에 자기 주의 기반 학습 방법을 적용했을 때, 51.6 h 분량의 학습 자료를 사용한 한국어 음향 모델에 대하여 단어 오류율 기준 5.98 %의 성능을 보여 기존 기술 대비 0.74 %의 절대적 성능 개선을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2949-2952
• /
• 2000

A new neural networks and learning algorithm are proposed in order to measure nonlinear heights of complexed road environments in realtime without pre-information. This new neural networks is Error Self Recurrent Neural Networks(ESRN), The structure of it is similar to recurrent neural networks: a delayed output as the input and a delayed error between the output of plant and neural networks as a bias input. In addition, we compute the desired value of hidden layer by an optimal method instead of transfering desired values by back-propagation and each weights are updated by RLS(Recursive Least Square). Consequently. this neural networks are not sensitive to initial weights and a learning rate, and have a faster convergence rate than conventional neural networks. We can estimate nonlinear models in realtime by ESRN and learning algorithm and control nonlinear models. To show the performance of this one. we control 7 degree of freedom full car model with several control method. From this simulation. this estimation and controller were proved to be effective to the measurements of nonlinear road environment systems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.530-532
• /
• 1998

In this paper, We Designed the torque compensatory controller for robot manipulator using modified chaotic neural networks with self feedback loop. The proposed torque compensatory controller compensate torque of the PD controller. In order to estimate the proposed controller, we implemented to the Cartesian space control of three-axis PUMA robot and compared the simulation results with recurrent neural networks(RNNs) controller. Simulation results show that the learning error drastically decrease at on-line learning. The proposed CNNs controller shows much better control performance and shorter processing time compared to the recurrent neural network controller in the robot trajectory control.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술대회 논문집 전문대학교육위원
• /
• pp.106-109
• /
• 2003

The repeatability error creeps in every corner of mechanical design as mechanical design becomes diverse and complicated. Inkjet printing has inherent repeatability error problem due to its nature of seamless incremental image synthesis of partial images. Without the calibration for the repeatability error realization of high print quality or enhancement of other printing performance could be impaired. Printer designers have met this recurrent problem even before the inception of inkjet print device and contrived various solutions as their own intelectual proprietary. Also, it is a trend to perform necessary calibration without painstaking human intervention. To come up with another useful and proprietary solution has become an important ingredient in inkjet printer design. This paper presents such a solution developed at Digital Printing Division of Samsung Electronics Company.

• 제어로봇시스템학회논문지
• /
• 제14권10호
• /
• pp.1014-1021
• /
• 2008

This paper proposes an intelligent sliding mode control method for robotic systems with the unknown bound of model uncertainties. In our control structure, the unknown bound of model uncertainties is used as the gain of the sliding controller. Then, we employ the function approximation technique to estimate the unknown nonlinear function including the width of boundary layer and the uncertainty bound of robotic systems. The adaptation laws for all parameters of the self-recurrent wavelet neural network and those for the reconstruction error compensator are derived from the Lyapunov stability theorem, which are used for an on-line control of robotic systems with model uncertainties and external disturbances. Accordingly, the proposed method can not only overcome the chattering phenomenon in the control effort but also have the robustness regardless of model uncertainties and external disturbances. Finally, simulation results for the five-link biped robot are included to illustrate the effectiveness of the proposed method.

• 스마트미디어저널
• /
• 제13권7호
• /
• pp.9-17
• /
• 2024

에너지 사용량의 증가와 친환경 정책으로 인해 건물 에너지를 효율적으로 소비할 필요가 있으며, 이를 위해 딥러닝 기반 이상 전력 탐지가 수행되고 있다. 수집이 어려운 이상치 데이터의 특징으로 인해 Recurrent Neural Network(RNN) 기반 오토인코더를 활용한 복원 에러 기반으로 이상 탐지가 수행되고 있으나, 시계열 특징을 온전히 학습하는데 시간이 오래 걸리고 학습 데이터의 노이즈에 민감하다는 단점이 있다. 본 논문에서는 이러한 한계를 극복하기 위해 Temporal Convolutional Network(TCN)과 UnSupervised Anomaly Detection for multivariate time series(USAD)를 결합한 TCN-USAD를 제안한다. 제안된 모델은 TCN 기반 오토인코더와 두 개의 디코더와 적대적 학습을 사용하는 USAD 구조를 활용하여 빠르게 시계열 특징을 온전히 학습할 수 있고 강건한 이상 탐지가 가능하다. TCN-USAD의 성능을 입증하기 위해 2개의 건물 전력 사용량 데이터 세트를 사용하여 비교 실험을 수행한 결과, TCN 기반 오토인코더는 RNN 기반 오토 인코더 대비 빠르고 복원 성능이 우수하였으며, 이를 활용한 TCN-USAD는 다른 이상 탐지 모델 대비 약 20% 개선된 F1-Score를 달성하여 뛰어난 이상 탐지 성능을 보였다.

• 한국항해학회지
• /
• 제21권3호
• /
• pp.55-66
• /
• 1997

In this paper, applications of neural networks to vibration control of flexible single link robot manipulator are ocnsidered. The architecture of neural networks is a hidden layer, which is comprised of self-recurrent one. Tow neural networks are utilized in a control system ; one as an identifier is called neuro identifier and the othe ra s a controller is called neuro controller. The neural networks can be used to approximate any continuous function to any desired degree of accuracy and the weights are updated by dynamic error-backpropagation algorithm(DEA). To guarantee concegence and to get faster learning, an approach that uses adaptive learning rates is developed by introducing a Lyapunov function. When a flexible manipulator is ratated by a motor through the fixed end, transverse vibration may occur. The motor torque should be controlle dinsuch as way, that the motor is rotated by a specified angle. while simulataneously stabilizing vibration of the flexible manipulators so that it is arrested as soon as possible at the end of rotation. Accurate vibration control of lightweight manipulator during the large body motions, as well as the flexural vibrations. Therefore, dynamic models for a flexible single link manipulator is derived, and LQR controller and nerual networks controller are composed. The effectiveness of the proposed nerual networks control system is confirmed by experiments.

• 인터넷정보학회논문지
• /
• 제24권1호
• /
• pp.39-47
• /
• 2023

The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.