• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.3
• /
• pp.257-264
• /
• 2005

This paper suggests a heuristic algorithm for the clustering problem. Clustering involves grouping similar objects into a cluster. Clustering is used in a wide variety of fields including data mining, marketing, and biology. Until now there are a lot of approaches using Self-Organizing Feature Maps(SOFMs). But they have problems with a small output-layer nodes and initial weight. For example, one of them is a one-dimension map of k output-layer nodes, if they want to make k clusters. This approach has problems to classify elaboratively. This paper suggests one-dimensional output-layer nodes in SOFMs. The number of output-layer nodes is more than those of clusters intended to find and the order of output-layer nodes is ascending in the sum of the output-layer node's weight. We can find input data in SOFMs output node and classify input data in output nodes using Euclidean distance. We use the well known IRIS data as an experimental data. Unsupervised clustering of IRIS data typically results in 15 - 17 clustering error. However, the proposed algorithm has only six clustering errors.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.4
• /
• pp.803-809
• /
• 2007

This study suggests a computational model to inquire the roles of phonological information and orthography information in the process of visual word recognition among the courses of language information processing, and the representation types of the mental lexicon. The model that this study is presenting here was designed as a feed forward network structure which is comprised of input layer which uses two Korean syllables as its input value, hidden layer, and output layer which express meanings. As the result of the study, the computational model showed the phonological and orthographic neighborhood effect among language phenomena which are shown in Korean word recognition, and showed proofs which implies that the mental lexicon is represented as phonological information in the process of Korean word recognition.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3317-3323
• /
• 2022

Half Value Layer calculations theoretically need prior specification of linear attenuation calculations, since the HVL value is derived by dividing ln(2) by the linear attenuation coefficient. The purpose of this study was to establish a direct computational model for determining HVL, a vital parameter in nuclear radiation safety studies and shielding material design. Accordingly, a typical gamma-ray transmission setup has been modeled using MCNPX (version 2.4.0) general-purpose Monte Carlo code. The MCNPX code's INPUT file was designed with two detection locations for primary and secondary gamma-rays, as well as attenuator material between those detectors. Next, Half Value Layer values of some well-known gamma-ray shielding materials such as lead and ordinary concrete have been calculated throughout a broad gamma-ray energy range. The outcomes were then compared to data from the National Institute of Standards and Technology. The Half Value Layer values obtained from MCNPX were reported to be highly compatible with the HVL values obtained from the NIST standard database. Our results indicate that the developed INPUT file may be utilized for direct computations of Half Value Layer values for nuclear safety assessments as well as medical radiation applications. In conclusion, advanced simulation methods such as the Monte Carlo code are very powerful and useful instruments that should be considered for daily radiation safety measures. The modeled MCNPX input file will be provided to the scientific community upon reasonable request.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.166-174
• /
• 2010

Based on the theoretical results that multi-layer feedforward neural networks with enough hidden nodes are universal approximators, we usually use three-layer MLP's(multi-layer perceptrons) consisted of input, hidden, and output layers for many application problems. However, this conventional three-layer architecture of MLP shows poor generalization performance in some applications, which are complex with various features in an input vector. For the performance improvement, this paper proposes a hierarchical architecture of MLP especially when each part of inputs has a special information. That is, one input vector is divided into sub-vectors and each sub-vector is presented to a separate MLP. These lower-level MLPs are connected to a higher-level MLP, which has a role to do a final decision. The proposed method is verified through the simulation of protein disorder prediction problem.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.5
• /
• pp.25-34
• /
• 2010

By introducing additional nodes called Steiner points, the problem of Steiner Minimum Tree whose length can be shorter than Minimum Spanning Tree and which connects all input terminal nodes belongs to Non-Polynomial Complete domain. Though diverse heuristic methods can be applied to the problem, most of them may meet serious pains in computing and waiting for a solution of the problem with numerous input nodes. For numerous input nodes, an efficient PTAS approximation method producing candidate unit steiner trees with portals in most bottom layer, merging them hierarchically to construct their parent steiner trees in upper layer and building swiftly final approximation Steiner tree in most top layer is suggested in this paper. The experiment with 16,000 input nodes and designed 16 unit areas in most bottom layer shows 85.4% execution time improvement in serial processing and 98.9% in parallel processing comparing with pure Steiner heuristic method, though 0.24% overhead of tree length. Therefore, the suggested PTAS Steiner tree method can have a wide range applications to build a large scale approximation Steiner tree quickly.

• Journal of Welding and Joining
• /
• v.13 no.2
• /
• pp.139-149
• /
• 1995

Many pressure vessels for the power plants are fabricated from low alloy ferritic steels. The inner sides of the pressure vessels are commonly weld_cladded with austenitic stainless steels to minimize problems of corrosive attack. The submerged-arc welding(SAW) process is now used in preference to other processes because of the possibilities open to automation to reduce the overaII welding times. The most reliable way to avoid underclad cracks(UCC) which are often detected at the overlap of the clad beads is to use nonsusceptible steels such as SA508 class 3. At present domestically developed forging steel of SA508 cl.S is now being cladded with single layer by using 90mm wide strip, which transfers higher heat input into the base metal compared to the conventional two layers strip cladding which has been in wide use with 30-60 mm wide strip. But the current indices for the influence of heat input on crack susceptibility are not accurate enough to express the subtle difference in crack susceptibility of the steel. Therefore, the purpose of this present study is: l) To determine UCC susceptibility on domestic forging steel, SA508 cl.S cladded with single layer by using submerged arc 90mm strip and, 2) To optimize heat input range by which the crack susceptibility could be eliminated.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.363-363
• /
• 2023

Artificial Neural Networks (ANN) is a powerful tool for addressing various practical problems and it has been extensively applied in areas of water resources. In this study, Artificial Neural Networks (ANNs) were developed for flood forecasting at specific locations on the Han River. The Partial Mutual Information (PMI) technique was used to select input variables for ANNs that are neither over-specified nor under-specified while adequately describing the underlying input-output relationships. Historical observations including discharges at the Paldang Dam, flows from tributaries, water levels at the Paldang Bridge, Banpo Bridge, Hangang Bridge, and Junryu gauge station, and time derivatives of the observed water levels were considered as input candidates. Lagged variables from current time t to the previous five hours were assumed to be sufficient in this study. A three-layer neural network with one hidden layer was used and the neural network was optimized by selecting the optimal number of hidden neurons given the selected inputs. Given an ANN architecture, the weights and biases of the network were determined in the model training. The use of PMI-based input variable selection and optimized ANNs for different sites were proven to successfully predict water levels during flood periods.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1493-1496
• /
• 2016

This paper proposes a system for reducing the standby power consumption in using the consumer electronic devices such as a television, a home theater, a set-top box, or a DVD player. The system is consisted of a flyback converter, monitoring circuits, a relay and a micro-processor. The proposed system can reduce the standby power consumption by disconnecting the AC input and the consumer devices can be turned on with a remote control. The proposed standby power system consumes the low power to receive the infrared signal from the remote controller. Furthermore, a electronic double layer capacitor is used to store the energy with high efficiency. The proposed power system can operate the 플라이백 converter to charge the electronic double layer capacitor and connect the AC input to the consumer electronic devices. The proposed power circuit can reduce the standby power consumption in AV devices without increasing the cost. The prototype is implemented to verify the system with the commercialized products.

• Earthquakes and Structures
• /
• v.8 no.5
• /
• pp.1241-1254
• /
• 2015

Spatially variable ground motions can be significant on the seismic response of a structure due to the incoherency of the incident wave. Incoherence of the incident wave is resulted from wave passage and wave scattering. In this study, wave passage effect on the response spectrum of a building structure built on a soft soil layer was investigated utilizing a finite element program of P3DASS (Pseudo 3-dimensional Dynamic Analysis of a Structure-soil System). P3DASS was developed for the axisymmetric problem in the cylindrical coordinate, but it is modified to apply anti-symmetric input earthquake motions. Study results were compared with the experimental results to verify the reliability of P3DASS program for the shear wave velocity of 250 m/s and the apparent shear wave velocities of 2000-3500 m/s. Studied transfer functions of input motions between surface mat foundation and free ground surface were well-agreed to the experimental ones with a small difference in all frequency ranges, showing some reductions of the transfer function in the high frequency range. Also wave passage effect on the elastic response spectrum reduced the elastic seismic response of a SDOF system somewhat in the short period range.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.25-34
• /
• 2017

Autoencoder is a type of deep learning method where input layer and output layer are the same, and effectively extracts and restores characteristics of input vector using constraints of hidden layer. In this paper, we propose methods of Autoencoders to remove a natural background image which is a noise to the CAPTCHA and recover only a numerical images by applying various autoencoder models to a region where one number of CAPTCHA images and a natural background are mixed. The suitability of the reconstructed image is verified by using the softmax function with the output of the autoencoder as an input. And also, we compared the proposed methods with the other method and showed that our methods are superior than others.