• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.763-764
• /
• 2013

A three-dimensional image capturing device and its signal processing algorithm and apparatus are presented. Three dimensional information is one of emerging differentiators that provides consumers with more realistic and immersive experiences in user interface, game, 3D-virtual reality, and 3D display. It has the depth information of a scene together with conventional color image so that full-information of real life that human eyes experience can be captured, recorded and reproduced. 20 Mega-Hertz-switching high speed image shutter device for 3D image capturing and its application to system prototype are presented[1,2]. For 3D image capturing, the system utilizes Time-of-Flight (TOF) principle by means of 20MHz high-speed micro-optical image modulator, so called 'optical resonator'. The high speed image modulation is obtained using the electro-optic operation of the multi-layer stacked structure having diffractive mirrors and optical resonance cavity which maximizes the magnitude of optical modulation[3,4]. The optical resonator is specially designed and fabricated realizing low resistance-capacitance cell structures having small RC-time constant. The optical shutter is positioned in front of a standard high resolution CMOS image sensor and modulates the IR image reflected from the object to capture a depth image (Figure 1). Suggested novel optical resonator enables capturing of a full HD depth image with depth accuracy of mm-scale, which is the largest depth image resolution among the-state-of-the-arts, which have been limited up to VGA. The 3D camera prototype realizes color/depth concurrent sensing optical architecture to capture 14Mp color and full HD depth images, simultaneously (Figure 2,3). The resulting high definition color/depth image and its capturing device have crucial impact on 3D business eco-system in IT industry especially as 3D image sensing means in the fields of 3D camera, gesture recognition, user interface, and 3D display. This paper presents MEMS-based optical resonator design, fabrication, 3D camera system prototype and signal processing algorithms.

• Journal of Welding and Joining
• /
• v.28 no.2
• /
• pp.32-38
• /
• 2010

In shipbuilding industry, welding position are usually flat and vertical position at the erection stage. Application of SAW and EGW for these positions makes it possible to achieve enhanced productivity and high quality. But owing to their large size and weight it is difficult to apply these techniques in short and narrow regions. To overcome this problem, our company developed light weight and compact size 4-axis welding carriage which perform 3D weaving. The purpose of this study is to explain the development and application of intelligent welding carriage using 3D weaving pattern that can fill a large amount of welds and thereby making it possible to achieve high quality of welding. This study shows 3D weaving pattern, development of weaving database, and skill of adaptive control response for the variable gap. Also, it shows the results of procedure qualification test for the AH-grade steel when applied to the intelligent welding carriage.

• Journal of the Korean Solar Energy Society
• /
• v.33 no.4
• /
• pp.23-30
• /
• 2013

This paper presents the determination method of the hybrid energy storage capacity for compensating the output of wind power when disconnecting from the grid. In the wind power output compensation, a lot of charging and discharging time with lithium-ion battery will be deteriorated the life time. And also, this fluctuation will cause some problems of the power quality and power system stability. To solve these kind of problems, many researchers in the world have been studied with BESS(Battery Energy Storage System) in the wind farm. But, BESS has the limitation of its output during very short term period, this means that it is difficult to compensate the very short term output of wind farm. Using the EDLC (Electric Double Layer Capacitor), it is possible to solve the problem. Installing the battery system in the wind farm, it will be possible to decrease the total capacity of BESS consisting of HESS (Hybrid Energy Storage System). This paper shows simulation results when not only BESS is connected to wind farm but also to HESS. To verify the proposed system, results of computer simulation using PSCAD/EMTDC program with actual output data of wind farms of Jeju Island will be presented.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.257-278
• /
• 2021

As the definition of the vendor-oriented implementation method, which was utilized in adopting an ERP system, has been centered around the project construction business, it was difficult for the EPR adopting organization to systematically prepare ERP projects and have enough deliberative opportunities to change-related policies. Furthermore, this method does not have a fully standardized construction process. Accordingly, by defining an organization that wants to adopt an ERP system as a customer, this paper develops the customer-based ERP construction process framework that assists both customers and developers who construct the system. For this purpose, this paper reviews the previous research and collects the construction processes of the commercial ERP SW vendor and ERP construction cases while proposing the three-layer process framework to construct ERP through the KJ method. The ERP process framework consists of 7 processes, 32 activities, 141 tasks while providing definitions for concepts of each component. Furthermore, the proposed processes and phases were set in order of the recommended execution, while the activities were suggested as an open-ended type so that the application and usability can be increased and polished by reflecting experts' opinions. The contribution of this study is to standardize the ERP project process by transforming the previous supplier-based ERP construction method into the customer-based one while providing important procedure and activity frameworks that apply to diverse ERP solutions per vendor. At the same time, this study provides an theoretical foundation to develop the construction process for the customer -based Cloud ERP. In practice, At the beginning of the ERP system construction project, it provides communication or process tailoring tools for the stakeholder.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.1
• /
• pp.74-78
• /
• 2019

As software becomes larger and network technology develops, the management of distributed data becomes more popular. Therefore, it is becoming increasingly important to use blockchain technology that can guarantee the integrity of data in various fields by utilizing existing infrastructure. Blockchain is a distributed computing technology that ensures that servers participating in a network maintain and manage data according to specific agreement algorithms and rules to ensure integrity. As smart contracts are applied, not only passwords but also various services to be applied to the code. In order to reinforce existing research on smart contract applied to the blockchain, we proposed a dynamic conditional rule of smart contract that can formalize rules of smart contract by introducing ontology and SWRL and manage rules dynamically in various situations. In the previous research, there is a module that receives the upper rule in the blockchain network, and the rule layer is formed according to this module. However, for every transaction request, it is a lot of resources to check the top rule in a blockchain network, or to provide it to every blockchain network by a reputable organization every time the rule is updated. To solve this problem, we propose to separate the module responsible for the upper rule into an independent server. Since the module responsible for the above rules is separated into servers, the rules underlying the service may be transformed or attacked in the middleware. Therefore, the security mechanism using TLS and PKI is added as an agent in consideration of the security factor. In this way, the benefits of computing resource management and security can be achieved at the same time.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.85-98
• /
• 2021

The pandemic of COVID-19 further promoted the imbalance in the volume of imports and exports among countries using containers, which worsened the shortage of empty containers. Since it is important to secure as many empty containers as the appropriate demand for stable and efficient port operation, measures to predict demand for empty containers using various techniques have been studied so far. However, it was based on long-term forecasts on a monthly or annual basis rather than demand forecasts that could be used directly by ports and shipping companies. In this study, a daily and weekly prediction method using an actual artificial neural network is presented. In details, the demand forecasting model has been developed using multi-layer perceptron and multiple linear regression model. In order to overcome the limitation from the lack of data, it was manipulated considering the business process between the loaded container and empty container, which the fully-loaded container is converted to the empty container. From the result of numerical experiment, it has been developed the practically applicable forecasting model, even though it could not show the perfect accuracy.

• The Journal of Fisheries Business Administration
• /
• v.4 no.1_2
• /
• pp.19-57
• /
• 1973

Laver io one of the most necessary and seasonal items in Korean food from oldtimes. Laver is lagely eaten in dried form, and its supply depends entirely upon culture weeds. The history of laver culture in Korea about sixty or seventy years is older than in Japan. Significance of laver culture is divided into two aspects, one is food supply in the nation, and the other is export to other countries. Houses engaged in laver culture are about foully thousands, and laver production in 1972 is estimated as 1, 3 bitten sheets. (1 sheet is a dried laver of 20 cm sq, in the shape of paper) Especcially meaning of layer production is the concentration of labour input, and systematic management of labour. From around 1920, the method of laver culture was introduced by Japanese Imperialism for mono culture in shallow seas, and mass products of laver is provided to Japan market, DOMESTIC MARKET Fundamental consume function calculates at below, $D_{(68_71)}$=16354 $Y^{0.471}$ $P^{-1.0662}$ where D is total layer demand, Y income variable, P price variable. It means income elasticity is 476. in the whole country, and price elasticity is 1, 07. But generally income elasticity is higher in urban area than in rural area, as shown at 1, 3 in Seoul city. Expence of laver in house expenditure is mutually correlated with another expence, See Table 12 about the relative function. See Table 14 and 16 about the relation between the gathering and the changes of price in auction, wholesale and retail price support system is for two effects, one of which is constraint of the upper price, the other is rise of the lower price. Before the system control, the equation in three year average calculated as below, $Y_{b}$ ＝18, 907.7455＋15435.9364 t (r=0.89) where the origin t＝0 is the November and the units are month. Post the system control, $Y_{p}$ =30, 047.9636+1, 631.1721t (r＝0.97) therefore, this system has an effect only on the rise of lower price, Average annual margins of laver products at four market levels according to the consumer spent is below. EXPORTING MARKET Japanese demand function of laver products is, Log D=5, 289+1, 108 Log Y-1, 395 Log P (r=0.987) where D is Japanese laver demand, Y income variable, P price variable. according to which income elasticity is 1. 1 and price elasticity is 1.4. Laver production in 1970 tile highest record till then, is estimated as six billion sheets. But the recent improvement of laver culture techniques, the production of seeds and freezing storage of seeds has been stabilized. Futher new culture farms have been developed by means of break- water fences or by floating culture method. These improvements have been backed up with increased demand of laver products. Import quantity and price of Korean laver products are restrained by three organizations, that is producer, distributor and consumer. This relationship calculated by regression equation shows that import is influenced only producer organization, at the sacrifice of consumer profit. For increase to export of laver products, we urgently require to open foreign trade of laver products for Japanese consumer, .and Japan has political responsibility to solve Korean laver structure. But with long run timeseries, as regards Japanese production and import quantity, importing function shows increasing trend as below, 250 million sheets ＜3, 947.1674+0.005 $L_{g}$ ＞) 600 million sheets where $L_{q}$ is relative production quantity of laver in Japan. (unit; 100 thousand sheets) Our Export effort should be put on the highly processed products whithin the restraind quote.ote.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.