• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.285-288
• /
• 2005

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose a neuro-adaptive controller for robot manipulators using the radial basis function network(RBFN) that is a kind of a neural network. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between the actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that the parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed neuro-adaptive controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.395-400
• /
• 2000

In this paper, we propose a new neuro-fuzzy controller based on reinforcement learning. The proposed system is composed of neuro-fuzzy controller which decides the behaviors of an agent, and dynamic recurrent neural networks(DRNNs) which criticise the result of the behaviors. Neuro-fuzzy controller is learned by reinforcement learning. Also, DRNNs are evolved by genetic algorithms and make internal reinforcement signal based on external reinforcement signal from environments and internal states. This output(internal reinforcement signal) is used as a teaching signal of neuro-fuzzy controller and keeps the controller on learning. The proposed system will be applied to controller optimization and adaptation with unknown environment. In order to verifY the effectiveness of the proposed system, it is applied to collision avoidance of an autonomous mobile robot on computer simulation.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.51-57
• /
• 1995

In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.203-208
• /
• 1998

This paper presents an adaptive fuzzy controller using an neural network and adaptation algorithm. Reference-model following neuro-fuzzy controller(RMFNFC) is invesgated in order to overcome the difficulty of rule selecting and defects of the membership function in the general fuzzy logic controller(FLC). RMFNFC is developed to tune various parameter of the fuzzy controller which is used for the discrete nonlinear system control. RMFNFC is trained with the identification information and control closed loop error. A closed loop error is used for design criteria of a fuzzy controller which characterizes and quantize the control performance required in the overall control system. A control system is trained up the controller with the variation of the system obtained from the identifier and closed loop error. Numerical examples are presented to control of the discrete nonlinear system. Simulation results show the effectiveness of the proposed controller.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.2
• /
• pp.17-28
• /
• 2002

Recently, the study on non-linear equalization, self-recovering equalization using the neural Network structure or Fuzzy logic, is lively in progress. In this thesis, if the value of error difference is large, coefficient adaptation rate is bigger, and if being small, it is smaller. We proposed the new FSG(Fuzzy Stochastic Gradient)/CMA algorithm combining TS(Tagaki-Sugeno) fuzzy model having fast convergence rate and low mean square error(MSE) and CMA(Constant Modulus Algorithm) which is prone to ISI and insensitive to phase alteration. As a simulation result of the designed channel adaptive equalizer using the proposed FSG/CMA algorithm, it is shown that SNR is improved about 3.5dB comparing to the conventional algorithm. 

• Proceedings of the KIEE Conference
• /
• 2003.07b
• /
• pp.1111-1113
• /
• 2003

This paper proposes an effective self-turning algorithm based on Artificial Neural Network (ANN) for fuzzy speed control of the indirect vector controlled induction motor. Indirect vector control method divides and controls stator current by the flux and the torque producing current so that the dynamic characteristic of induction motor may be superior. However, if motor parameter changes, the flux current and the torque producing one's coupling happens and deteriorates the dynamic characteristic. The fuzzy speed controller of an induction motor has the robustness over the effect of this parameter variation than a conventional PI speed controller in some degree. This paper improves its adaptability by adding the self-tuning mechanism to the fuzzy controller. For tracking the speed command, its membership functions are adjusted using ANN adaptation mechanism. This adaptability could be embodied by moving the center positions of the membership functions. Proposed self-tuning method has wide adaptability than existent fuzzy controller or PI controller and is proved robust about parameter variation through Matlab/Simulink simulation.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.05a
• /
• pp.404-407
• /
• 2009

The field oriented control of induction motors is widely used in high performance applications. However, detuning caused by parameter disturbance still limits the performance of these drives. In order to accomplish variable speed operation conventional PI-like controllers are commonly used. These controllers provide limited good performance over a wide range of operation even under ideal field oriented conditions. This paper is proposed adaptive fuzzy controller(AFC) and artificial neural network(ANN) based on the vector controlled induction motor drive system. Also, this paper is proposed control of speed and current using fuzzy adaptation mechanism(FAM), AFC and estimation of speed using ANN. The proposed control algorithm is applied to induction motor drive system using FAM, AFC and ANN controller. Also, this paper is proposed the analysis results to verify the effectiveness of this controller.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.