• Korean Journal of Food Science and Technology
• /
• v.27 no.4
• /
• pp.525-531
• /
• 1995

Three quality factors of bread during baking process were measured to develop neural network models for bread baking process. Firstly, volume and browning changes during bread baking process were measured using image processing technique and temperature changes inside the bread during process were measured by K-type thermocouples. Relationships among them showed nonlinearity. Secondly, multilayer perception structure with error back propagation learning was used to construct neural network models. Three neural network models for volume, browning, and bread temperature were developed respectively. Developed models showed good performance with predictive error of 4.62% for volume and browning changes after 30 seconds, 7.38% for volume and browning changes after 2 minutes, and 1.09% for temperature change inside the bread respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.230-235
• /
• 2008

Recently, LG chemical corporation developed new material called HYPERIER, which has an excellent barrier characteristic. It has many layers which are made of nano-composite within LDPE(Low-Density Poly Ethylene). In order to guarantee the quality of the final product from the production line, a certain test equipment is required to investigate the existence of layers inside the HYPERIER. In this work, ultrasonic sensor based test equipment for investigating the existence of inner layers is proposed. However, it is a tedious job for human operators to check the existence by just looking at the resounding waveform from ultrasonic sensor. Therefore, to enhance the performance of the ultrasonic test equipment, Fast Fourier Transform(FFT) and Principle Components Analysis(PCA) and Back-Propagation Neural Network(BPNN) are utilized which is used for classification of Quality. To verily the feasibility of the proposed scheme, some experiments are executed.

• Geophysics and Geophysical Exploration
• /
• v.3 no.2
• /
• pp.70-75
• /
• 2000

In the seismic migration, Kirchhoff and reverse time migration are used in general. In the reverse time migration using wave equation, two-way and one-way wave equation are applied. The approach of one-way wave equation uses approximately computed downward continuation extrapolator, it need tess amounts of calculations and core memory in compared to that of two-way wave equation. In this paper, we applied one-way wave equation to pre-stack reverse time migration. In the frequency-space domain, forward propagation of source wavefield and back propagration of measured wavefield were executed by using monochromatic one-way wave equation, and zero-lag cross correlation of two wavefield resulted in the image of subsurface. We had implemented prestack migration on a massively parallel processors (MPP) CRAYT3E, and knew the algorithm studied here is efficiently applied to the prestck migration due to its suitability for parallelization.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.1.2-24
• /
• 2000

The field of neural networks has been a recent surge in activity as a result of progress in developments of efficient training algorithms. For this reason, and coupled with the widespread availability of powerful personal computer hardware for running simulations of networks, there is increasing focus on the potential benefits this field can offer. The neural network may be viewed as an advanced pattern recognition technique and can be applied in many areas such as financial time series forecasting, medical diagnostic expert system and etc.. The intention of this study is to build and implement one simple artificial neural networks hereinafter called ANN. For this purpose, some literature survey was undertaken to understand the structures and algorithms of ANN theoretically. Based on the review of theories about ANN, the system adopted 3-layer back propagation algorithms as its learning algorithm to simulate one case of medical diagnostic model. The adopted ANN algorithm was performed in PC by using turbo PASCAL and many input parameters such as the numbers of layers, the numbers of nodes, the number of cycles for learning, learning rate and momentum term. The system output more or less successful results which nearly agree with goals we assumed. However, the system has some limitations such as the simplicity of the programming structure and the range of parameters it can dealing with. But, this study is useful for understanding general algorithms and applications of ANN system and can be expanded for further refinement for more complex ANN algorithms.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.6
• /
• pp.47-52
• /
• 2002

The wavelet functions are originated from scaling functions and can be used as activation function in the hidden node of the network by deciding two parameters such as scale and center. In this paper, we would like to propose the mixed structure. When we compose the WNN using wavelet functions, we propose to set a single scale function as a node function together. The properties of the proposed structure is that while one scale function approximates the target function roughly, the other wavelet functions approximate it finely. During the determination of the parameters, the wavelet functions can be determined by the global search algorithm such as genetic algorithm to be suitable for the suggested problem. Finally, we use the back-propagation algorithm in the learning of the weights.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.65-74
• /
• 2009

In optimizing the neural network structure, there are two methods of the pruning scheme and the constructive scheme. In this paper we use the pruning scheme to optimize neural network structure, and the genetic algorithm to find out its optimum node pruning. In the conventional researches, the input and hidden layers were optimized separately. On the contrary we attempted to optimize the two layers simultaneously by encoding two layers in a chromosome. The offspring networks inherit the weights from the parent. For teaming, we used the existing error back-propagation algorithm. In our experiment with various databases from UCI Machine Learning Repository, we could get the optimal performance when the network size was reduced by about $8{\sim}25%$. As a result of t-test the proposed method was shown better performance, compared with other pruning and construction methods through the cross-validation.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.87-97
• /
• 2020

In this paper, we propose a novel neural relighting that infers a relighted rendering image based on the user-guided specular highlight map. The proposed network utilizes a pre-trained neural renderer as a backbone network learned from the rendered image of a 3D scene with various lighting conditions. We jointly optimize a 3D light position and its associated relighted image by back-propagation, so that the difference between the base image and the relighted image is similar to the user-guided specular highlight map. The proposed method has the advantage of being able to explicitly infer the 3D lighting position, while providing the artists' preferred 2D screen-space interface. The performance of the proposed network was measured under the conditions that can establish ground truths, and the average error rate of light position estimations is 0.11, with the normalized 3D scene size.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.211-214
• /
• 2000

This paper describes a lateral guidance system of an autonomous vehicle, using a neural network model of magneto-resistive sensor and magnetic fields. The model equation was compared with experimental sensing data. We found that the experimental result has a negligible difference from the modeling equation result. We verified that the modeling equation can be used in simulations. As the neural network controller acquires magnetic field values(B$\sub$x/, B$\sub$y/, B$\sub$z/) from the three-axis, the controller outputs a steering angle. The controller uses the back-propagation algorithms of neural network. The learning pattern acquisition was obtained using computer simulation, which is more exact than human driving. The simulation program was developed in order to verify the acquisition of the teaming pattern, learning itself, and the adequacy of the design controller. Also, the performance of the controller can be verified through simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.842-848
• /
• 2008

This paper deal with uncertainty problem by using Type-2 fuzzy logic set for nonlinear system modeling. We design Type-2 fuzzy logic system in which the antecedent and the consequent part of rules are given as Type-2 fuzzy set and also analyze the performance of the ensuing nonlinear model with uncertainty. Here, the apexes of the antecedent membership functions of rules are decided by C-means clustering algorithm and the apexes of the consequent membership functions of rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The proposed model is demonstrated with the aid of two representative numerical examples, such as mathematical synthetic data set and Mackey-Glass time series data set and also we discuss the approximation as well as generalization abilities for the model.