• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.5
• /
• pp.17-24
• /
• 2017

Recently Deep-learning, Technologies using Large or Deep Artificial Neural Networks, have Shown Remarkable Performance, and the Increasing Size of the Network Contributes to its Performance Improvement. However, the Increase in the Size of the Neural Network Leads to an Increase in the Calculation Amount, which Causes Problems Such as Circuit Complexity, Price, Heat Generation, and Real-time Restriction. In This Paper, We Propose and Test a Method to Reduce the Number of Network Connections by Effectively Pruning the Redundancy in the Connection and Showing the Difference between the Performance and the Desired Range of the Original Neural Network. In Particular, we Proposed a Simple Method to Improve the Performance by Re-learning and to Guarantee the Desired Performance by Allocating the Error Rate per Layer in Order to Consider the Difference of each Layer. Experiments have been Performed on a Typical Neural Network Structure such as FCN (full connection network) and CNN (convolution neural network) Structure and Confirmed that the Performance Similar to that of the Original Neural Network can be Obtained by Only about 1/10 Connection.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.615-624
• /
• 2006

The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data layer, node, md weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.116-116
• /
• 2022

현재 인공지능은 공학적 문제 해결 외에도 다양한 분야에 적용되어 매우 친숙하게 활용되고 있다. 특히 하천 분야에서는 시설물 주위 국부세굴 또는 어류 서식처 분석과 같이 관련 변수들의 복잡성으로 적절한 결과를 쉽게 얻어내기 어려운 것들에 적용되고 있다. 그 외에도 인공지능 기법을 적용할 수 있는 분야로 하천에서의 수위를 이용하여 유량을 예측하는 것이 있다. 기존에는 수위-유량 관계 곡선을 만들어 수위를 이용하여 유량을 예측하였으나, 관계곡선 제작에 활용된 수위와 유량 범위에서 벗어나는 경우 과다한 유량으로 계산되는 경우가 있다. 본 연구에서는 인공지능 기법 중 하나인 인공신경망 기법을 사용하여 하천의 유량 예측을 수행하였다. 기존 국가수자원관리종합정보시스템에 기록된 자료를 활용하여 수위와 유량 자료를ANN에 학습시키고 학습에 활용하지 않은 시기의 자료를 이용하여 전반적인 유량 예측 성능과 루프형 수위-유량 관계 곡선을 생성할 수 있는지를 검토하였다. 또한 학습 범위를 벗어난 홍수량에 대한 측정 결과를 검토하고, 기존 수위-유량 관계곡선과 비교하여 그 성능을 검토하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.6
• /
• pp.677-682
• /
• 2014

In the present study, a decision tree and artificial neural network were used to determine critical design parameters for lithium ion batteries and compare their performances. First, a design method that used a decision tree-artificial neural network model was used to determine the major design factors among early pole plate design factors that showed nonlinearity. Then, the artificial neural network was used to implement a weighted value analysis of the importance of the design factors and their effect on the current density. The second method involved the use of an artificial neural network model to construct artificial networks without separate determinations of the major early design factors to analyze the connections and weighted values related to the current density.

• Journal of Navigation and Port Research
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2011

The accuracy of forecasting is remarkably important to reduce total cost or to increase customer services, so it has been studied by many researchers. In this paper, the artificial neural network (ANN), one of the most popular nonlinear forecasting methods, is compared with autoregressive integrated moving average(ARIMA) model through performing a prediction of container traffic. It uses a hybrid methodology that combines both the linear ARIAM and the nonlinear ANN model to improve forecasting performance. Also, it compares the methodology with other models in performance for prediction. In designing network structure, this work specially applies the genetic algorithm which is known as the effectively optimal algorithm in the huge and complex sample space. It includes the time delayed neural network (TDNN) as well as multi-layer perceptron (MLP) which is the most popular neural network model. Experimental results indicate that both ANN and Hybrid models outperform ARIMA model.

• Tunnel and Underground Space
• /
• v.13 no.6
• /
• pp.434-443
• /
• 2003

In this study, it was purposed to develop the new method for the prediction of pollutant concentration in road tunnels. The new method was the use of artificial neural network with the back-propagation algorithm which can model the non-linear system of tunnel environment. This network system was separated into two parts as the visibility and the CO concentration. For this study, data was collected from two highway road tunnels on Yeongdong Expressway. The tunnels have two lanes with one-way direction and adopt the longitudinal ventilation system. The actually measured data from the tunnels was used to develop the neural network system for the prediction of pollutant concentration. The output results from the newly developed neural network system were analysed and compared with the calculated values by PIARC method. Results showed that the prediction accuracy by the neural network system was approximately five times better than the one by PIARC method. In addition, the system predicted much more accurately at the situation where the drivers have to be stayed for a while in tunnels caused by the low velocity of vehicles.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.59-70
• /
• 2008

도심지 터널의 설계, 시공 그리고 유지관리에 있어서 지반 변위 억제와 변형거동 예측은 중요하다. 국내 외 연구자들은 다양한 수치해석적인 기법과 현장 계측 결과를 이용하여 터널 시공과 관련된 변형거동 예측을 시도하였다. 하지만, 설계물성치의 산정과 지반 모델링 그리고 수치해석기법과 관련된 사용상의 어려움에 의해 아직까지 만족스러운 결과를 얻지는 못하였다. 본 논문은 수치해석적인 기법과 인공신경망을 이용하여 도심지 NATM 터널의 설계 물성치 산정과 변형거동 예측에 관한 방법을 제안하였다. 인공신경망 모델 개발을 위한 학습과 테스트과정은 데이터베이스된 수치해석결과를 이용하였다. 개발된 인공신경망 모델은 입력변수인 지반변위와 결과변수인 설계 물성치 간의 상호관계를 적절히 인식할 수 있다. 수치해석은 지반의 연화거동을 모사할 수 있는 변형률 연화모델을 적용하였다. 사례분석에 있어서 굴착 초기단계의 계측 값을 개발된 인공신경망 모델에 입력하여 설계 물성치를 계산하였으며, 수정된 설계 물성치는 수치해석을 통하여 다음 굴착단계에서의 터널 주변의 지반 변형거동을 예측하였다. 본 논문에서 제안된 방법을 토대로 시공조건이 엄밀한 도심지 터널의 설계물성치의 정량적인 평가 및 변형거동 예측이 계측이 입수된 초기 굴착단계에서 가능할 것으로 기대된다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.6
• /
• pp.914-921
• /
• 2010

When industrial structures are constructed on soft ground, ground subsidence is occurred by problems of bearing capacity. To protect ground subsidence have to improve soft ground, and have to predict settlement estimation for reasonable construction. Artificial Neural Networks(ANN) is adopted for prediction of settlement of construction during the initial design. In the study, Artificial Neural Networks are applied to predict the settlement estimation of initial condition ground and ground improved by D.C.M method. Also, this study compares results of Artificial Neural Networks and results of continuum analysis using Mohr-Coulomb models. In result, settlements of initial condition ground decreased over 0.7 times. Also, by comparing ANN and continuum analysis, coefficient of determination was comparatively high value 0.79. Thought this study, it was confirmed that settlements of improvement ground is predicted using laboratory experiment data.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.22 no.2
• /
• pp.126-132
• /
• 2010

An approach to calculating expected damage of breakwater assisted by artificial neural network was developed. Wave height in front of a breakwater was predicted by a trained artificial neural network with inputs of wave height in deep ocean and tidal level. Prediction results by the neural network can be comparable to that by professional numerical model for wave transformation. Using the wave prediction neural network, it was very easy and fast to obtain a number of significant waves at breakwater and finally analysis time for expected damage can be shortened. In addition, the effect of considering tidal level in the calculation of expected damage was revealed by comparing the expected damages with and without tidal variation. Therefore, it was pointed out that tidal variation should be considered to improve prediction accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.89-97
• /
• 2008

In this paper, we present a method for the enhancement of marker detection correctness and marker recognition speed by using artificial neural network. Contours of objects are extracted from the input image. They are approximated to a list of line segments. Quadrangles are found with the geometrical features of the approximated line segments. They are normalized into exact squares by using the warping technique and scale transformation. Feature vectors are extracted from the square image by using principal component analysis. Artincial neural network is used to checks if the square image is a marker image or a non-marker image. After that, the type of marker is recognized by using an artificial neural network. Experimental results show that the proposed method enhances the correctness of the marker detection and recognition.