• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.2
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.7
• /
• pp.45-51
• /
• 2009

We have presented a routing mechanism that selects a route by considering channel statuses in order to fast transfer delay-sensitive data in WSNs (Wireless Sensor Networks). The existing methods for real-time data transfer select a path whose latency is the shortest or the number of hops is the smallest. An algorithm to select a real-time transfer path based on link error rates according to the characteristic of wireless medium was also suggested. However, the propagation delay and retransmission timeout affected by link error rates are shorter than channel assessment time and backoff time. Therefore, the mechanism proposed in this paper estimated the time spent in using a clear channel and sending out a packet, which is based on channel backoff rates. A source node comes to select a route with the shortest end-to-end delay as a fast transfer path for real-time traffic, and sends data along the path chosen. We found that this proposed mechanism improves the speed of event-to-sink data transfer by performing experiments under different link error and channel backoff rates.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.

• Journal of Navigation and Port Research
• /
• v.32 no.8
• /
• pp.589-596
• /
• 2008

In this paper, Artificial Neural Network(ANN) is applied to automatic berthing control for a ship. ANN is suitable for a maneuvering such as ship's berthing, because it can describe non-linearity of the system. Multi-layer perceptron which has more than one hidden layer between input layer and output layer is applied to ANN. Using a back-propagation algorithm with teaching data, we trained ANN to get a minimal error between output value and desired one. For the automatic berthing control of a containership, we introduced low speed maneuvering mathematical models. The berthing control with the structure of 8 input layer units in ANN is compared to 6 input layer units. From the simulation results, the berthing conditions are satisfied, even though the berthing paths are different.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.4
• /
• pp.196-205
• /
• 2018

This paper presents an algorithm for passive localization of a ship by applying the ray back-propagation technique to the ship radiation noise data. The previous method [S. H. Abadi, D. Rouseff and D. R. Dowling, J. Acoust. Soc. Am. 131, 2599-2610 (2012)] estimates the position of a sound source in the near-field environment with no array tilt by using the RBD (Ray-based Blind Deconvolution) and ray back-propagation techniques. However, when there exists an array tilt, the above method leads to a large position estimation error. In order to overcome the problem, this study proposes an algorithm that estimates the position of a sound source by correcting the array tilt using the RBD and ray back-propagation techniques. The proposed algorithm was verified by using the ship noise of SAVEX15 (Shallow-water Acoustic Variability EXperiment in 2015) experimental data.

• Journal of Information Technology Applications and Management
• /
• v.19 no.1
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• Journal of Astronomy and Space Sciences
• /
• v.21 no.3
• /
• pp.221-232
• /
• 2004

Gauss method for the initial orbit determination was tested using angle-only data obtained by orbit propagation using TLB and SGP4/SDP4 orbit propagation model.. As the analysis of this simulation, a feasible time span between observation time of satellite resulting the minimum error to the true orbit was found. Initial orbit determination is performed using observational data of GPS 26 and Koreasat 2 from 0.6m telescope of KAO(Korea Astronomy Observatory) and precise orbit determination is also performed using simulated data. The result of precise orbit determination shows that the accuracy of resulting orbit is related to the accuracy of the observations and the number of data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.10C
• /
• pp.921-926
• /
• 2006

The Presence of a line-of-sight(LoS) blockage can degrade the UWB positioning accuracy for two reasons. Firstly, it makes estimation of the time of arrival(ToA) of the direct path signal difficult by complicating the multipath structure of the propagation channel. Secondly, the higher dielectric constant of the LoS blocking material than that of free space introduces excess propagation delay which will bias the range estimation. In this paper, methods based on ray tracing to reduce the ranging error resulting from the second reason are Posed. We take two different approaches; a statistical approach and a map-aided method. In the statistical approach, we establish a conditional distribution of the excess propagation delay caused by LoS blockages using a ray tracing technique. The lo6wer bound of the ranging performance based on this model is estimated. Ine ray tracing method is also used for the map-aided ToA positioning approach. UWB propagation measurement data taken in an office environment is used to examine the performance of this method.

• Atmosphere
• /
• v.21 no.2
• /
• pp.163-172
• /
• 2011

Numerical forecasting depends on the initial condition error strongly because numerical model is a chaotic system. To calculate the sensitivity of some forecast aspects to the initial condition in the Korea Meteorological Administration (KMA) Unified Model (UM) which is originated from United Kingdom (UK) Meteorological Office (MO), an algorithm to calculate adjoint sensitivities is developed by modifying the adjoint perturbation forecast model in the KMA UM. Then the new algorithm is used to calculate adjoint sensitivity distributions for typhoon DIANMU (201004). Major initial adjoint sensitivities calculated for the 48 h forecast error are located horizontally in the rear right quadrant relative to the typhoon motion, which is related with the inflow regions of the environmental flow into the typhoon, similar to the sensitive structures in the previous studies. Because of the upward wave energy propagation, the major sensitivities at the initial time located in the low to mid- troposphere propagate upward to the upper troposphere where the maximum of the forecast error is located. The kinetic energy is dominant for both the initial adjoint sensitivity and forecast error of the typhoon DIANMU. The horizontal and vertical energy distributions of the adjoint sensitivity for the typhoon DIANMU are consistent with those for other typhoons using other models, indicating that the tools for calculating the adjoint sensitivity in the KMA UM is credible.