• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.375-382
• /
• 2004

This paper presents control designs using neural networks (NN) for a XY positioning table. The proposed neuro-controller is composed of an outer PD tracking loop for stabilization of the fast flexible-mode dynamics and an NN inner loop used to compensate for the system nonlinearities. A tuning algorithm is given for the NN weights, so that the NN compensation scheme becomes adaptive, guaranteeing small tracking errors and bounded weight estimates. Formal nonlinear stability proofs are given to show that the tracking error is small. The proposed neuro-controller is implemented and tested on an IBM PC-based XY positioning table, and is applicable to many precision XY tables. The algorithm, simulation, and experimental results are described. The experimental results are shown to be superior to those of conventional control.

• Proceedings of the KIEE Conference
• /
• 2009.04b
• /
• pp.32-34
• /
• 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 model reference adaptive fuzzy control(MFC) 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 adaption mechanism(FAM), MFC and estimation of speed using ANN. The proposed control algorithm is applied to induction motor drive system using FAM, MFC and ANN controller. Also, this paper is proposed the analysis results to verify the effectiveness of this controller.

• The Journal of Information Technology
• /
• v.4 no.2
• /
• pp.117-127
• /
• 2001

A self-structured neural network algorithm that finds optimal fuzzy membership functions and nile base to fuzzy model is proposed and a fuzzy-neural network controller is designed to get more accurate position and velocity control of wheeled mobile robot. This procedure that is composed of three steps has its own unique process at each step. The elements of output term set are increased at first step and then the rule base Is varied according to increase of the elements. The adjusted controller is in competition with controller which doesn't include any increased elements. The adjusted controller will be removed if the control-law lost. Otherwise, the controller is replaced with the adjusted system. After finished regulation of output term set and rule base, searching for input membership functions is processed with constraints and fine tuning of output membership functions is done.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.5
• /
• pp.639-650
• /
• 1999

Generally, a performance management consists of the iterative process of performance monitoring, performance analysis, and performance tuning. In this paper, we describe the design and implementation of performance monitor and performance tuner which can be used on the top of SPAX, also known as TICOM IV. SPAX has a hierarchical structure. All nodes, each of which has a local memory, are connected to the interconnection network and constructed to form clusters. Therefore, it is necessary to develop a new performance monitor reflecting the underlying hierarchical structure of SPAX, to implement performance monitoring more effectively. Implemented performance monitor can monitor the state of nodes, clusters, and total system of SPAX at realtime. And, implemented performance tuner can change the value of variables related to the performance of SPAX. System manager can perform an effective performance management by using the proposed performance management tools.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.6
• /
• pp.1092-1098
• /
• 2002

This paper discusses the composition of the theory of reinforcement teaming, which is applied in real-time teaming, and evolutionary strategy, which proves its the superiority in the finding of the optimal solution at the off-line teaming method. The individuals are reduced in order to team the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It is possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because of the teaming process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against the outside disturbances.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• Journal of Power Electronics
• /
• v.16 no.5
• /
• pp.1939-1949
• /
• 2016

This paper presents an alternative frequency adaptive grid synchronization technique named HDN-FLL, which can accurately extract the fundamental positive- and negative-sequence components and interested harmonics in adverse three-phase grid voltage. The HDN-FLL is based on the harmonic decoupling network (HDN) consisting of multiple first order complex vector filters (FOCVF) with a frequency-locked loop (FLL), which makes the system frequency adaptive. The stability of the proposed FLL is strictly verified to be global asymptotically stable. In addition, the linearization and parameters tuning of the FLL is also discussed. The structure of the HDN has been widely used as a prefilter in grid synchronization techniques. However, the stability of the general HDN is seldom discussed. In this paper, the transfer function expression of the general HDN is deduced and its stability is verified by the root locus method. To show the advantages of the HDN-FLL, a simulation comparison with other gird synchronization methods is carried out. Experimental results verify the excellent performance of the proposed synchronization method.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2045-2049
• /
• 2018

An antenna arrays for a satellite navigation systems require more antenna elements to mitigate multiple jamming signals. In order to maintain the small array size while increasing the number of antenna elements, miniaturization technique is essential for antenna design. In this work, an electrically small circular microstrip patch antenna with a 3 dB hybrid coupler is designed as an element antenna, where the 3 dB hybrid coupler can yield the circularly polarized radiation characteristic. The miniaturized element antenna typically has too large capacitance in GPS L1 and GLONASS G1 bands, making it difficult to match with a single stand-alone non-Foster matching circuit (NFMC) in a stable state. Therefore, we propose a new matching technique, referred to as the hybrid matching method, which consists of a NFMC and a passive circuit. This passive tuning circuit manages reactance of antenna elements at an appropriate capacitance without a pole in the operating frequency range. The antenna array is fabricated, and the measured results show a reflection coefficient of less than -10 dB and an isolation of greater than 50 dB. In addition, peak gain of the proposed antenna is increased by 22.3 dB compared to the antenna without the hybrid matching network.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-64
• /
• 1995

Robot manipulator is a highly nonlinear-time varying system. Therefore, a lot of control theory has been applied to the system. Robot manipulator has two types of control; one is path planning, another is path tracking. In this paper, we select the path tracking, and for this purpose, propose the intelligent control¬ler which is combined with fuzzy logic and neural network. The fuzzy logic provides an inference morphorlogy that enables approximate human reasoning to apply to knowledge-based systems, and also provides a mathematical strength to capture the uncertainties associated with human cognitive processes like thinking and reasoning. Based on this fuzzy logic, the fuzzy logic controller(FLC) provides a means of converhng a linguistic control strategy based on expert knowledge into automahc control strategy. But the construction of rule-base for a nonlinear hme-varying system such as robot, becomes much more com¬plicated because of model uncertainty and parameter variations. To cope with these problems, a auto-tuning method of the fuzzy rule-base is required. In this paper, the GA-based Fuzzy-Neural control system combining Fuzzy-Neural control theory with the genetic algorithm(GA), that is known to be very effective in the optimization problem, will be proposed. The effectiveness of the proposed control system will be demonstrated by computer simulations using a two degree of freedom robot manipulator.