• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.920-926
• /
• 2004

The human being receives a new information from outside and the information shows gradual oblivion with time. But the information remains in memory and isn't forgotten for a long time if the information is read several times over. For example, we assume that we memorize a telephone number when we listen and never remind we may forget it soon, but we commit to memory long time by repeating. If the human being received new information with strong stimulus, it could remain in memory without recalling repeatedly. The moments of almost losing one's life in an accident or getting a stroke of luck are rarely forgiven. The human being can keep memory for a long time in spite of the limit of memory for the mechanism mentioned above. In this paper, we propose a model to explain the mechanism mentioned above using a neural network and fuzzy.

• Geomechanics and Engineering
• /
• v.12 no.3
• /
• pp.441-464
• /
• 2017

The determination of the mixture parameters of stabilization has become a great concern in geotechnical applications. This paper presents an effort about the application of artificial intelligence (AI) techniques including radial basis neural network (RBNN), multi-layer perceptrons (MLP), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) in order to predict the unconfined compressive strength (UCS) of silty soil stabilized with bottom ash (BA), jute fiber (JF) and steel fiber (SF) under different freeze-thaw cycles (FTC). The dosages of the stabilizers and number of freeze-thaw cycles were employed as input (predictor) variables and the UCS values as output variable. For understanding the dominant parameter of the predictor variables on the UCS of stabilized soil, a sensitivity analysis has also been performed. The performance measures of root mean square error (RMSE), mean absolute error (MAE) and determination coefficient ($R^2$) were used for the evaluations of the prediction accuracy and applicability of the employed models. The results indicate that the predictions due to all AI techniques employed are significantly correlated with the measured UCS ($p{\leq}0.05$). They also perform better predictions than nonlinear regression (NLR) in terms of the performance measures. It is found from the model performances that RBNN approach within AI techniques yields the highest satisfactory results (RMSE = 55.4 kPa, MAE = 45.1 kPa, and $R^2=0.988$). The sensitivity analysis demonstrates that the JF inclusion within the input predictors is the most effective parameter on the UCS responses, followed by FTC.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.3
• /
• pp.95-106
• /
• 2000

The load frequency control of power system is one of important subjects in view of system operation and control. That is even though the rapid load disturbances were applied to the given power system, the stable and reliable power should be supplied to the users, converging unconditionally and rapidly the frequency deviations and the tie-line power flow one on each area into allowable boundary limits. Nonetheless of such needs, if the internal parameter perturbation and the sudden load variation were given, the unstable phenomenal of power system can be often brought out because of the large frequency deviation and the unsuppressible power line one. Therefore, it is desirable to design the robust neuro-fuzzy controller which can stabilize effectively the given power system as soon as possible. In this paper the robust neuro-fuzzy controller was proposed and applied to control of load frequency over multi-area power system. The architecture and algorithm of a designed NFC(Neuro-Fuzzy Controller) were consist of fuzzy controller and neural network for auto tuning of fuzzy controller. The adaptively learned antecedent and consequent parameters of membership functions in fuzzy controller were acquired from the steepest gradient method for error-back propagation algorithm. The performances of the resultant NFC, that is, the steady-state deviations of frequency and tie-line power flow and the related dynamics, were investigated and analyzed in detail by being applied to the load frequency control of multi-area power system, when the perturbations of predetermined internal parameters. Through the simulation results tried variously in this paper for disturbances of internal parameters and external stepwise load stepwise load changes, the superiorities of the proposed NFC in robustness and adaptive rapidity to the conventional controllers were proved.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.267-275
• /
• 2022

Using a nonconforming mesh in enrichment methods results in several numerical issues induced by discontinuities and singularities found within the solution spaces, including the computational overhead during integration. In this study, we present a novel enrichment technique based on the selective expansion technique of moment fitting (Düster and Allix, 2020). In particular, two modifications are proposed to address the inefficiency during the integration process. First, a feedforward artificial neural network is introduced to correlate the implicit functions and integration moments. Through numerical examples, it is shown that the efficiency of the method is greatly improved when compared with existing expansion techniques, whereas the solution accuracy is maintained. Additionally, the finite element and domain representation grids are separated, which in turn improves the solution accuracy even for coarse mesh conditions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• Computers and Concrete
• /
• v.18 no.1
• /
• pp.1-16
• /
• 2016

In this study, an Artificial Neural Network (ANN) and Adaptive Network-based Fuzzy Inference Systems (ANFIS) prediction models for flexural strength of the cement mortars have been developed. For purpose of constructing this models, 12 different mixes with 144 specimens of the 2, 7, 28 and 90 days flexural strength experimental results of cement mortars containing pure Portland cement (PC), blast furnace slag (BFS), waste tire rubber powder (WTRP) and BFS+WTRP used in training and testing for ANN and ANFIS were gathered from the standard cement tests. The data used in the ANN and ANFIS models are arranged in a format of four input parameters that cover the Portland cement, BFS, WTRP and age of samples and an output parameter which is flexural strength of cement mortars. The ANN and ANFIS models have produced notable excellent outputs with higher coefficients of determination of $R^2$, RMS and MAPE. For the testing of dataset, the $R^2$, RMS and MAPE values for the ANN model were 0.9892, 0.1715 and 0.0212, respectively. Furthermore, the $R^2$, RMS and MAPE values for the ANFIS model were 0.9831, 0.1947 and 0.0270, respectively. As a result, in the models, the training and testing results indicated that experimental data can be estimated to a superior close extent by the ANN and ANFIS models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2020

Effective jamming in electronic warfare depends on proper jamming technique selection and jamming parameter estimation. For this purpose, this paper proposes a new method of estimating jamming parameters using Gaussian kernel function networks. In the proposed approach, a new method of determining the optimal structure and parameters of Gaussian kernel function networks is proposed. As a result, the proposed approach estimates the jamming parameters in a reliable manner and outperforms other methods such as the DNN(Deep Neural Network) and SVM(Support Vector Machine) estimation models.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.15-17
• /
• 2018

VVC(Versatile Video Coding)는 입력된 영상을 CTU(Coding Tree Unit) 단위로 분할하여 코딩하며, 이를 다시 QTBTT(Quadtree plus binary tree and triple tree)로 분할하고, TU(Transform Unit)도 이와 같은 단위로 분할된다. 따라서 TU의 크기는 $4{\times}4$, $4{\times}8$, $4{\times}16$, $4{\times}32$, $8{\times}4$, $16{\times}4$, $32{\times}4$, $8{\times}8$, $8{\times}16$, $8{\times}32$, $16{\times}8$, $32{\times}8$, $16{\times}16$, $16{\times}32$, $32{\times}16$, $32{\times}32$, $64{\times}64$의 17가지 종류가 있다. 기존의 VVC 참조 Software인 VTM에서는 디블록킹필터와 SAO(Sample Adaptive Offset)로 이루어진 인루프필터를 이용하여 에러를 복원하는데, 본 논문은 TU 크기에 따라서 원본블록과 복원블록의 차이(에러)가 통계적으로 다름을 이용하여 서로 다른 CNN(Convolution Neural Network)을 구축하고 에러를 복원하는 방법으로 VTM의 인루프 필터를 대체한다. 복원영상의 에러를 감소시키기 위하여 TU 블록크기에 따라 DenseNet의 Dense Block기반 CNN을 구성하고, Hyper Parameter와 복잡도의 감소를 위해 네트워크 간에 일부 가중치를 공유하는 모양의 Network를 구성하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.526-537
• /
• 1999

In the paper. we propose an evaluation model based the adaptive fuzzy systems, which can transform the physical features of a color pattern to the emotional features. The model is motivated by the Soen's psychological experiments, in which he found the physical features such as average hue, saturation, intensity and the dynamic components of the color patterns affects to the emotional features represented by a pair of adjective words having the opposite meanings. Our proposed model consists of two adaptive fuzzy rule-bases and the y-model, a l i r ~ r ys et operator, to fuze the evaluation values produced by them. The model shows con~parablep erformances to the neural network for the approximation of the nonlinear transforms, and it has the advantage to obtain the linbwistic interpretation from the trained results. We believe the evaluated results of a color pattern can be used to the emotion-based color image retrievals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1853-1858
• /
• 2021

O-rings fill the gaps between mechanical parts. Until now, the sorting of defective products has been performed visually and manually, so classification errors often occur. Therefore, a camera-based defect classification system without human intervention is required. However, a binarization process is required to separate the required region from the background in the camera input image. In this paper, an adaptive binarization technique that considers the surrounding pixel values is applied to solve the problem that single-threshold binarization is difficult to apply due to factors such as changes in ambient lighting or reflections. In addition, the convex hull technique is also applied to compensate for the missing pixel part. And the learning model to be applied to the separated region applies the residual error-based deep learning neural network model, which is advantageous when the defective characteristic is non-linear. It is suggested that the proposed system through experiments can be applied to the automation of O-ring defect detection.