• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.842-848
• /
• 2008

This paper deal with uncertainty problem by using Type-2 fuzzy logic set for nonlinear system modeling. We design Type-2 fuzzy logic system in which the antecedent and the consequent part of rules are given as Type-2 fuzzy set and also analyze the performance of the ensuing nonlinear model with uncertainty. Here, the apexes of the antecedent membership functions of rules are decided by C-means clustering algorithm and the apexes of the consequent membership functions of rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The proposed model is demonstrated with the aid of two representative numerical examples, such as mathematical synthetic data set and Mackey-Glass time series data set and also we discuss the approximation as well as generalization abilities for the model.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.05a
• /
• pp.302-307
• /
• 2001

This research is concerned with the development of a real-time adaptive PPF controller for the active vibration suppression of smart structure. In general, the tuning of the PPF controller is carried out off-line. In this research, the real-time learning algorithm is developed to find the optimal filter frequency of the PPF controller in real time and the efficacy of the algorithm is proved by implementing it in real time. To this end, the adaptive algorithm is developed by applying the gradient descent method to the predefined performance index, which is similar to the method used popularly in the optimization and neural network controller design. The experiment was carried out to verify the validity of the adaptive PPF controller developed in this research. The experimental results showed that adaptive PPF controller is effective for active vibration control of the structure which is excited by either impact or harmonic disturbance. The filter frequency of the PPF controller can be tuned in a very short period of time thus proving the efficiency of the adaptive PPF controller.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.612-621
• /
• 1996

In this paper, we propose the low sidelobe digital FIR doppler filter bank synthesis algorithm through the Gradient Descent method and it can be practially appliable to coherent pulse doppler radar signal processing. This algorithm shows the appropriate calculation of tap coefficients or zeros for FIR transversal fiter which has been employed in radar signal processor. The span of the filters in the filter bank be selected at the desired position the designer want to locate, and the lower sidelobe level that has equal ripple property is achieved than one for which the conventional weithtedwindow is used. Especially, when we implemented filter zeros as design parameters it is possible to make null filter gain at zero frequency intensionally that would be very efficient for the eliminatio of ground clutter. For the example of 10 tap filter synthesis, when filter coefficients or zeros are selected as design parameters the corresponding sidelobelevel is reducedto -70db or -100db respectively and it has good convergent characteristics to the desired sidelobe reference value. The accuracy ofapproach to the reference value and the speed of convergence that show the performance measure of this algorithm are tuned out with some superiority and the fact that the bandwidth of filter appears small with respect to one which is made by conventional weighted window method is convinced. Since the filter which is synthesized by this algorithm can remove the clutter without loss of target signal it strongly contributes performance improvement with which detection capability would be concerned.

• Journal of Power Electronics
• /
• v.14 no.5
• /
• pp.1008-1027
• /
• 2014

An electric scooter with a V-belt continuously variable transmission (CVT) driven by a permanent magnet synchronous motor (PMSM) has a lot of nonlinear and time-varying characteristics, and accurate dynamic models are difficult to establish for linear controller designs. A PMSM servo-drive electric scooter controlled by a novel hybrid modified recurrent Legendre neural network (NN) control system is proposed to solve difficulties of linear controllers under the occurrence of nonlinear load disturbances and parameters variations. Firstly, the system structure of a V-belt CVT driven electric scooter using a PMSM servo drive is established. Secondly, the novel hybrid modified recurrent Legendre NN control system, which consists of an inspector control, a modified recurrent Legendre NN control with an adaptation law, and a recouped control with an estimation law, is proposed to improve its performance. Moreover, the on-line parameter tuning method of the modified recurrent Legendre NN is derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, two optimal learning rates for the modified recurrent Legendre NN are derived to speed up the parameter convergence. Finally, comparative studies are carried out to show the effectiveness of the proposed control scheme through experimental results.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.965-973
• /
• 2011

Small unmanned ground vehicles(SUGVs) are typically operational on unstructured environments such as crashed building, mountain area, caves, and so on. On those terrains, driving control can suffer from the unexpected ground disturbances which occasionally lead turnover situation. In this paper, we have proposed an algorithm which sustains driving stability of a SUGV as preventing from turnover. The algorithm exploits potential field method in order to determine the stability of the robot. Then, the flipper and manipulator posture of the SUGV is optimized from local optimization algorithm known as gradient descent method. The proposed algorithm is verified using 3D dynamic simulation, and results showed that the proposed algorithm contributes to driving stability of SUGV.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.1964-1966
• /
• 2001

Active Noise control(ANC) is rapidly becoming the most effective way to reduce noises that can otherwise be very difficult and expensive to control. This research presents ANFIS (Adaptive Network Fuzzy Inference System) controller for adaptively noise cancelling in a duct. ANC system generates secondary control sound pressure with same amplitude and with opposite phase as noise to be eliminated. ANFIS controller is trained to optimize its parameters for adaptively cancelling noise. That is ANFIS train its parameters by gradient descent and LSE method so called hybrid method. This paper present ANFIS in active noise control which provides an improvement convergence speed and limitation of linearity condition. It can model nonlinear functions of arbitrary complexity and ANFIS can construct an input-ouput mapping based on both human knowledge in the form of Takagi and Sugeno's fuzzy if-then rules and stipulated input-output data pairs. This paper also shows that the proposed ANFIS active noise control system successfully cancelled noise.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Korean Journal of Remote Sensing
• /
• v.15 no.1
• /
• pp.39-50
• /
• 1999

It is complicate and time-consuming process to classify a multi-band satellite imagery according to the application. In addition, classification rate sensitively depends on the selection of training data set and features in a supervised classification process. This paper introduced a classification network adopting a fuzzy-based $\gamma$-model in order to select a training data set and to extract feature which highly contribute to an actual classification. The features used in the classification were gray-level histogram, textures, and NDVI(Normalized Difference Vegetation Index) of target imagery. Moreover, in order to minimize the errors in the classification network, the Gradient Descent method was used in the training process for the $\gamma$-parameters at each code used. The trained parameters made it possible to know the connectivity of each node and to delete the void features from all the possible input features.

• Korean Journal of Optics and Photonics
• /
• v.33 no.6
• /
• pp.245-251
• /
• 2022

We have developed a multi-channel fiber laser for tiled laser beam combining and a laser output array system for multi-beam alignment. The fiber laser is a master oscillator power amplifier configuration that has a common seed, a preamplifier, and a 7-channel amplifier. The output power of each channel is more than 10 W. The laser output array system is a packed cylindrical configuration for a high fill-factor, and it has capabilities for collimation and tilt control with built-in PZT. Multi-beam alignment to a target is successfully implemented using PZT controlled with a stochastic parallel gradient descent (SPGD) algorithm.