• Journal of environmental and Sanitary engineering
• /
• v.21 no.4 s.62
• /
• pp.61-76
• /
• 2006

A Line Density algorithm was developed to quantify the sea surface temperature distribution using NOAA Sea Surface Temperature(SST) data and Geographic Information Systems(GIS), In addition, a GIS based automation model was designed to extract the Line Density Indices were determined by applying K-means Cluster. SST data in terms of March to May obtained on the coastal area of the Uljin from 2001 to 2004 in spring were used to make two data sets of average sea water temperature map in terms of year as well as month. From the result it was formed that water temperature gradient in April was the strongest among the other months, In particular very strog formation of oceanic front as well as temperature gradients were observed in front of the coastal area around Wonduk and Jukbyeon countries. Because those coastal area is a confront zone of two cold and a warm. It is expected that the development of a Line Density Algorithm would contribute to quantify of the SST for the research of Sea Surface Front(SSF) related to marine life management and the sea environmental conservation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.324-329
• /
• 2005

Dynamic Encoding Algorithm for Searches (DEAS) which is known as a fast and reliable non-gradient optimization method, was proposed [1]. DEAS reaches local or global optimum with binary strings (or binary matrices for multi-dimensional problem) by iterating the two operations; bisectional search (BSS) and unidirectional search (UDS). BSS increases binary strings by one digit (i.e., 0 or 1), while UDS performs increment or decrement of binary strings in the BSS' result direction with no change of string length. Because the interval of UDS exponentially decreases with increment of bit string length (BSL), DEAS is difficult to escape from local optimum when DEAS falls into local optimum. Therefore, this paper proposes hopping UDS (HUDS) which performs UDS by hopping as many as BSL in the final point of UDS process. HUDS helps to escape from local optimum and enhances a probability searching global optimization. The excellent performance of HUDS will be validated through the well-known benchmark functions.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2254-2259
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network(WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges advantages of neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of mobile robot using the gradient descent(GD) method. In addition, an approach that uses adaptive learning rates for the training of WFNN controller is driven via a Lyapunov stability analysis to guarantee the fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control performance of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1641-1644
• /
• 2005

Magnetic actuation utilizes the mechanic torque that is the result of interaction of the current in a coil with an external magnetic field. A main obstacle is, however, that torques can only be produced perpendicular to the magnetic field. In addition, there is uncertainty in the Earth magnetic field models due to the complicated dynamic nature of the field. Also, the magnetic hardware and the spacecraft can interact, causing both to behave in undesirable ways. This actuation principle has been a topic of research since earliest satellites were launched. Earlier magnetic control has been applied for nutation damping for gravity gradient stabilized satellites, and for velocity decrease for satellites without appendages. The three axes of a micro-satellite can be stabilized by using an electromagnetic actuator which is rigidly mounted on the structure of the satellite. The actuator consists of three mutually-orthogonal air-cored coils on the skin of the satellite. The coils are excited so that the orbital frame magnetic field and body frame magnetic field coincides i.e. to make the Euler angles to zero. This can be done using a Neural Network controller trained by PD controller data and driven by the difference between the orbital and body frame magnetic fields.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.22-30
• /
• 1995

In this Paper we study the convergence behavior of the least mean fourth (LMF) algorithm where the error raised to the power of four is minimized for a multiple sinusoidal input and Gaussian measurement noise. Here we newly obtain the convergence equation for the sum of the mean of the squared weight errors, which indicates that the transient behavior can differ depending on the relative sizes of the Gaussian noise and the convergence constant. It should be noted that no similar results can be expected from the previous analysis by Walach and Widrow.

• Journal of ILASS-Korea
• /
• v.6 no.1
• /
• pp.35-43
• /
• 2001

Previous studies on image processing techniques for panicle size measurement usually have focused on a single panicle or weakly overlapped particles. In the present work, the image processing algorithm for particle size measurement has been improved to process heavily-overlapped spherical-particle images. The algorithm consists of two steps; detection of boundaries which separate the images of the overlapped panicles from the background and the panicle identification process. For the first step, Sobel operator (using gray-level gradient) and the thinning process was adopted, and compared with the gray-level thresholding method that has been widely adopted. In the second, Hough transform was used. Hough transform is the detection algorithm of parametric curves such as straight lines or circles which can be described by several parameters. To reduce the measurement error, the process of finding the true center was added. The improved algorithm was tested by processing an image frame which contains heavily overlapped spherical panicles. The results showed that both the performances of detecting the overlapped images and separating the panicle from them were improved.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.74-81
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA(Dropout Genetic Algorithm) which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.23 no.1
• /
• pp.58-68
• /
• 1999

The entry compression wave, which forms at the entrance of a high-speed railway tunnel, is closely related to the pressure transients in the train/tunnel systems as well as an impulsive noise appearing at the exit of the tunnel. In order to alleviate such undesirable phenomena, some control strategies have been applied to the compression wave propagating inside the tunnel. The objective of the current work is to investigate the effect of tunnel entrance hoods on the entry compression wave at the vicinity of the tunnel entrance. Three types of entrance hoods were tested by the numerical method using the characteristics of method for a wide range of train speeds. The results show that the maximum pressure gradient of compression wave can be considerably reduced by the tunnel entrance hood. Optimum hood shape necessary to reduce the pressure transients and impulsive noise was found to be of an abrupt type hood with its cross-sectional area 2.5 times the tunnel area. It is believed that the current results are highly useful in predicting the effects of entrance hoods and in choosing the shape of proper hood.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.23 no.2
• /
• pp.234-242
• /
• 1999

Flow phenomena such as the pressure transients Inside a high-speed railway tunnel and the Impulsive waves at the exit of the tunnel are closely associated with the characteristics of the entry compression wave, which is generated by a train entering the tunnel. Tunnel entrance hood may be an effective means for alleviating the Impulsive waves and pressure transients. The objective of the current work is to explore the effects of the train nose shape and the entrance hood on the characteristics of the entry compression wave. Numerical calculations using the method of characteristics were applied to one-dimensional, unsteady, compressible flow field with respect to high-speed railway/tunnel systems. Two types of the entrance hoods and various train nose shapes were employed to reveal their influences on the entry compression wave for a wide range of train speeds. The results showed that the entry compression wave length increases as the train nose becomes longer and the train speed becomes lower. The entry compression wave length in the tunnel with hood becomes longer than that of no hood. Maximum pressure gradient in the compression wavefront reduces by the entrance hood. The results of the current work provide useful data for the design of tunnel entrance hood.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1700-1721
• /
• 2017

The problem of blocking artifacts is very common in block-based image and video compression, especially at very low bit rates. In this paper, we propose a post-processing method for JPEG-coded image deblocking via sparse representation and adaptive residual threshold. This method includes three steps. First, we obtain the dictionary by online dictionary learning and the compressed images. The dictionary is then modified by the histogram of oriented gradient (HOG) feature descriptor and K-means cluster. Second, an adaptive residual threshold for orthogonal matching pursuit (OMP) is proposed and used for sparse coding by combining blind image blocking assessment. At last, to take advantage of human visual system (HVS), the edge regions of the obtained deblocked image can be further modified by the edge regions of the compressed image. The experimental results show that our proposed method can keep the image more texture and edge information while reducing the image blocking artifacts.