• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.77-86
• /
• 2004

In general, small-sized neural networks, even though they show good generalization performance, tend to fail to team the training data within a given error bound, whereas large-sized ones learn the training data easily but yield poor generalization. Therefore, a way of achieving good generalization is to find the smallest network that can learn the data, called the optimal-sized neural network. This paper proposes a new scheme for network pruning with ‘impact factor’ which is defined as a multiplication of the variance of a neuron output and the square of its outgoing weight. Simulation results of function approximation problems show that the proposed method is effective in regression.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.490-495
• /
• 1999

In this paper, a method of improving the learning time and convergence rate is proposed to exploit the advantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR Problem, n bit parity problem which is used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image application. As a result of the experiments, it does not always guarantee the convergence. However, the network showed improved the teaming time and has the high convergence rate. The proposed network can be extended to an arbitrary layer Though a single layer structure Is considered, the proposed method has a capability of high speed 3earning even on large images.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.4
• /
• pp.31-36
• /
• 2001

In this paper we propose a method of pattern classification of the hand movement using EMG signals through Self-organizing feature map. Self-organizing feature map is an artificial neural network which organizes its output neuron through learning and therefore it can classify input patterns. The raw EMG signals become direct input to the Self-organizing feature map. The simulation and experiment results showed the effectiveness of the classification of EMG signal using the Self-organizing feature map.

• Proceedings of the KIPE Conference
• /
• 2020.08a
• /
• pp.282-283
• /
• 2020

3상 컨버터에서 스위치의 개방고장이 발생한 경우 고장 전류에 직류 및 고조파 성분이 발생할 수 있으며, 보호회로에 의한 고장 감지가 어려우므로 주변 기기에 2차 고장이 발생할 수 있다. 단일 및 이중 스위치 개방고장의 경우 21가지 고장 모드가 존재한다. 본 논문에서는 이러한 고장 모드를 진단하기 위해 정지 좌표계 d-q축 전류의 직류 및 고조파 성분을 활용하는 two-step 구조의 ANN(Artificial Neural Network)을 제안한다. 고장 시에 발생된 직류 및 고조파 성분 전류는 ADALINE(Adaptive-Linear Neuron)을 통해 얻는다. 고장 진단의 첫 번째 단계에서는 직류 성분을 기반으로 ANN을 이용하여 고장모드를 6개 영역으로 분류한다. 두 번째 단계에서는 6개의 각 영역에서 직류 성분과 전류의 THD(Total Harmonics Distortion)를 기반으로 ANN을 이용하여 개방고장이 발생한 스위치를 진단한다. 제안된 Two-step 방법으로 고장을 진단하므로써 간단한 구조로 ANN의 설계가 가능하다. 3.7kW급 3상 PWM 컨버터로 실험을 통해 제안된 방법의 효용성을 검증하였다.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.429-436
• /
• 2002

In order to apply the artificial neural network to the practical application, it is needed to implement it with the hardware system. It is most promising to make it with the hybrid VLSI among various possible technologies. When we Implement a trained network into the hybrid neuro-chips, it is to be performed the process of the quantization on its neuron outputs and its weights. Unfortunately this process cause the network's outputs to be distorted from the original trained outputs. In this paper we analysed in detail the statistical characteristics of the distortion. The analysis implies that the network is to be trained using the normalized input patterns and finally into the solution with the small weights to reduce the distortion of the network's outputs. We performed the experiment on an application in the time series prediction area to investigate the effectiveness of the results of the analysis. The experiment showed that the network by our method has more smaller distortion compared with the regular network.

• Journal of Korea Water Resources Association
• /
• v.51 no.1
• /
• pp.71-80
• /
• 2018

For the stream management, time of concentration is one of the important factors. In particular, as the requirement about various application of the stream increased, accuracy assessment of concentration time in the stream as waterfront area is extremely important for securing evacuation at the flood. the past studies for the assessment of concentration time, however, were only performed on the single hydrological event in the complex basin of natural streams. The development of a assessment methods for the concentration time on the complex hydrological event in a single watershed of urban streams is insufficient. Therefore, we estimated the concentration time using the rainfall- runoff data for the past 10 years (2006~2015) for the Oncheon stream, the representative stream of the Busan, where frequent flood were taken place by heavy rains, in addition, reviewed the reliability using artificial neural network method based on Matlab. We classified a total of 254 rainfalls events based on over unrained 12 hours. Based on the classification, we estimated 6 parameters (total precipitation, total runoff, peak precipitation/ total precipitation, lag time, time of concentration) to utilize for the training and validation of artificial neural network model. Consequently, correlation of the parameter, which was utilized for the training and the input parameter for the predict and verification were 0.807 and 0.728, respectively. Based on the results, we predict that it can be utilized to estimate concentration time and analyze reliability of urban stream.

• KIEAE Journal
• /
• v.15 no.4
• /
• pp.105-110
• /
• 2015

Purpose: This study aimed at finding the optimal input variables of the artificial neural network-based predictive model for the optimal controls of the indoor temperature environment. By applying the optimal input variables to the predictive model, the required time for restoring the current indoor temperature during the setback period to the normal setpoint temperature can be more precisely calculated for the cooling season. The precise prediction results will support the advanced operation of the cooling system to condition the indoor temperature comfortably in a more energy-efficient manner. Method: Two major steps employing the numerical computer simulation method were conducted for developing an ANN model and finding the optimal input variables. In the first process, the initial ANN model was intuitively determined to have input neurons that seemed to have a relationship with the output neuron. The second process was conducted for finding the statistical relationship between the initial input variables and output variable. Result: Based on the statistical analysis, the optimal input variables were determined.

• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.821-832
• /
• 1998

This study investigates the prediction of daily water supply, which is a necessary for the efficient management of water distribution system. Fuzzy neuron, namely artificial intelligence, is a neural network into which fuzzy information is inputted and then processed. In this study, daily water supply was predicted through an adaptive learning method by which a membership function and fuzzy rules were adapted for daily water supply prediction. This study was investigated methods for predicting water supply based on data about the amount of water supplied to the city of Kwangju. For variables choice, four analyses of input data were conducted: correlation analysis, autocorrelation analysis, partial autocorrelation analysis, and cross-correlation analysis. Input variables were (a) the amount of water supplied (b) the mean temperature, and (c)the population of the area supplied with water. Variables were combined in an integrated model. Data of the amount of daily water supply only was modelled and its validity was verified in the case that the meteorological office of weather forecast is not always reliable. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 18.35% and the average error was lower than 2.36%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.593-602
• /
• 2014

One of the purposes of an artificial neural netowrk(ANNet) is to implement the largest number of functions as possible with the smallest number of nodes and layers. This paper presents a CoreNet which has a multi-leveled input value and a multi-leveled output value with a 2-layered ANNet, which is the basic structure of an ANNet. I have suggested an equation for calculating the capacity of the CoreNet, which has a p-leveled input and a q-leveled output, as $a_{p,q}={\frac{1}{2}}p(p-1)q^2-{\frac{1}{2}}(p-2)(3p-1)q+(p-1)(p-2)$. I've applied this CoreNet into the simulation model 1(5)-1(6), which has 5 levels of an input and 6 levels of an output with no hidden layers. The simulation result of this model gives, the maximum 219 convergences for the number of implementable functions using the cot(${\sqrt{x}}$) input leveling method. I have also shown that, the 27 functions are implementable by the calculation of weight values(w, ${\theta}$) with the multi-threshold lines in the weight space, which are diverged in the simulation results. Therefore the 246 functions are implementable in the 1(5)-1(6) model, and this coincides with the value from the above eqution $a_{5,6}(=246)$. I also show the implementable function numbering method in the weight space.