• Korean Chemical Engineering Research
• /
• v.62 no.1
• /
• pp.118-124
• /
• 2024

A neural network is utilized for preprocessing of de-noizing in electrocardiogram signals, retinal images, seismic waves, etc. However, the de-noizing process could provoke increase of computational time and distortion of the original signals. In this study, we investigated a neural network architecture to analyze measurement data without additional de-noizing process. From the dynamical behaviors of DNA in aqueous solution, our neural network model aimed to predict the mole fraction of each DNA in the solution. By adding white noise to the dynamics data of DNA artificially, we investigated the effect of the noise to neural network's predictions. As a result, our model was able to predict the DNA mole fraction with an error of O(0.01) when signal-to-noise ratio was O(1). This work can be applied as a efficient artificial intelligence methodology for analyzing DNA related to genetic disease or cancer cells which would be sensitive to background measuring noise.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.10 no.2
• /
• pp.153-165
• /
• 2006

A damage in a structure changes its dynamic characteristics such as natural frequencies, damping ratios, and the mode shapes. In this paper the effort has been spent in obtaining the characteristics of the reduction ratio in natural frequencies and the damage detection is performed using the reduction ratios. Most of the emphasis has been on using the artificial neural network to determine the location and the extent of the damage as well as the existence of the damage. The data for learning and verifying neural network were obtained from the analytical analysis. The data have no errors. Considering the real measurements the data including errors which are difference this study between other studies also were used for neural network. The position and extent of the damage can be detected using the neural network trained by reduction ratios of natural frequencies.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3571-3584
• /
• 2024

Reactor core transient calculation is very important for the reactor safety analysis, in which the kernel is neutron kinetics calculation by simulating the variation of neutron density or thermal power over time. Compared with the point kinetics method, the time-space neutron kinetics calculation can provide accurate variation of neutron density in both space and time domain. But it consumes a lot of resources. It is necessary to develop a surrogate model that can quickly obtain the temporal and spatial variation information of neutron density or power with acceptable calculation accuracy. This paper uses the time-varying characteristics of power to construct a time function, parameterizes the time-varying characteristics which contains the information about the spatial change of power. Thereby, the amount of targets to predict in the space domain is compressed. A surrogate method using the machine learning is proposed in this paper. In the construction of a neural network, the input is processed by a convolutional layer, followed by a fully connected layer or a deconvolution layer. For the problem of time sequence disturbance, a structure combining convolutional neural network and recurrent neural network is used. It is verified in the tests of a series of 1D, 2D and 3D reactor models. The predicted values obtained using the constructed neural network models in these tests are in good agreement with the reference values, showing the powerful potential of the surrogate models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.449-453
• /
• 2001

In this paper, we propose an algorithm to design the adaptive structure of wavelet neural network with F-projection and geometric growing criterion. Geometric growing criterion consists of estimated error criterion considering local error and angle criterion which attempts to assign a wavelet function that is nearly orthogonal to all other existing wavelet functions. These criteria provide a methodology that a network designer can construct wavelet neural network according to one's intention. We apply the proposed constructing algorithm of the adaptive structure of wavelet neural network to approximation problems of 1-D and 2-D function, and evaluate the effectiveness of the proposed algorithm.

• Journal of Intelligence and Information Systems
• /
• v.15 no.3
• /
• pp.151-165
• /
• 2009

Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of its outstanding accuracy of control and forecasting area. We design a new classification model based on ANFIS and evaluate it in terms of classification accuracy. We identified ANFIS-based classification model has higher classification accuracy compared to existing classification model, C5.0 decision tree model by comparing their experimental results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.139-147
• /
• 2003

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as signal prediction. This paper proposes the hybrid network, composed of locally(LRNN) and globally recurrent neural networks(GRNN), to improve dynamics of multilayered recurrent networks(RNN) and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The hybrid network consists of IIR-MLP and Elman RNN as LRNN and GRNN, respectively. The proposed network is evaluated in nonlinear signal prediction and compared with Elman RNN and IIR-MLP networks for the relative comparison of prediction performance. Experimental results show that the hybrid network performs better with respect to convergence speed and accuracy, indicating that the proposed network can be a more effective prediction model than conventional multilayered recurrent networks in nonlinear prediction for nonstationary signals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1802-1808
• /
• 2003

In this paper, we propose a method about the extraction of the pedestrian tracking trajectory in the road and we used the method of mosaic background extraction and adaptive neural network for automatic pedestrian tracking system. We used mosaic background extraction to overcome ghost phenomenon. And we detected pedestrian using differential image analysis. We used adaptive neural network for multiple pedestrian tracking that non­rigid form moving. The ART2 network is capable of detecting the mass­centers of moving objects within one frame. The history of neurons positions in the sequential frames approximates the traces of the targets. The experiments done with the network in simulated environment show promising results.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.26-31
• /
• 2014

In this paper, we present performance analysis of video smoke detection based on BPN-Network that is using multi-smoke feature, and Neural Network. Conventional smoke detection method consist of simple or mixed functions using color, temporal, spatial characteristics. However, most of all, they don't consider the early fire conditions. In this paper, we analysis the smoke color and motion characteristics, and revised distinguish the candidate smoke region. Smoke diffusion, transparency and shape features are used for detection stage. Then it apply the BPN-Network (Back-Propagation Neural Network). The simulation results showed 91.31% accuracy and 2.62% of false detection rate.

• Journal of the Korean Society of Tobacco Science
• /
• v.17 no.1
• /
• pp.5-14
• /
• 1995

Efficient algorithms for the automatic classification of flue-cured tovacco ripeness and grading have been developed The ripeness of the tobacco was classified into 4 levels vased on the color. The lab-built simple RGB color measuring system was utilized for detecting the light reflectance of the tobacco leaves. The measured data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The spectrophotometer was used to detect the light reflectance and absorption of the graded tobacco leaves in the frequency ranges of the visible light The measured data and the statistical analysis was performed to investigate the light characteristics of the graded samples. The measured data were obtained from samples of 5 different grades directly without considering the leaf positions. Those data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The neural network based sensor information processing showed successful results for grading of tobacco leaves.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.