• Korean Management Science Review
• /
• v.21 no.3
• /
• pp.55-69
• /
• 2004

This study analyzes customer buying-behavior patterns in a department store as time goes on, and predicts moving patterns of its customers. Through them, it suggests in this paper short-term and long-term marketing promotion strategies. RFM techniques are utilized for customer segmentation. Customers are clustered by using the Kohonen's Self Organizing Map as a method of data mining techniques. Then C5.0, a decision tree analysis technique, is used to predict moving patterns of customers. Using real world data, this study evaluates the prediction accuracy of predictive models.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.11a
• /
• pp.70-73
• /
• 2003

Although there has been an upcoming recognition in the repairing reinforcement and remodeling of currently existing buildings with a regard to economic and resource saving effects of buildings roughly exposed to the open air for a long-term period, followed by a number of problems with the construction business operations that support economy-oriented projects within the limits of their short-term period durability, it is true that reasonable decisions of concrete performance are insufficient owing to the lack of proper history management for those existing buildings. This research attempted to comparatively analyze the compression strength together with investigation of carbonization depth and alkali concentration according to the passage of years on the subjects of aged buildings, and to provide basic data for remodeling and/or reconstruction of future construction structures by indirectly estimating durability lifetime expectancy according to carbonization phenomenon.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.1
• /
• pp.52-57
• /
• 2005

In the foe of global competition, the requirements for the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a mai or change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved. In this paper, an on-line training neural network for both long-term teaming and short-term teaming was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.124-129
• /
• 2003

In the face of global competitor the requirements flor the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a major change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models fir simulation and quantitative description of the industrial operations involved. In this paper, a on-line training neural network for both long-term teaming and short-term teaming was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

• Proceedings of the CALSEC Conference
• /
• 2004.02a
• /
• pp.223-226
• /
• 2004

Several studies have shown that the trust is a significant barrier for realizing the potential of e-commerce. Trust is not only a short-term issue but also the most significant long-term barrier for realizing the potentials of e-commerce. Because digital contents which have been used in e-commerce are easy to be duplicated, the enforcement of digital copyright protection is an important issue. Watermarking is a technique for labeling digital pictures by hiding secret information in the image. In this paper, a discrete wavelet transform(DWT) based technique for embedding digital watermark into image is proposed. The performance of the proposed watermarking is robust to a variety of signal distortions, such as JPEG and image processing operations.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.255-256
• /
• 2016

In this paper, we analyze the operations and/or status of our structure which builds the management structure measuring integrated monitoring system based on linked open data in a short term or long term bases. We have applied a novel analyzing method of linked open data to expect what movements can be occurred in the structure, and we improve the monitoring system using an integrated design to solve the drawbacks of conventional types of monitoring. And collecting data through cloud and their reliability can be proved by evaluation of soundness of data amount and their confidence.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.299-309
• /
• 2022

Recently, The sea water temperature around Korean Peninsula is steadily increasing. Water temperature changes not only affect the fishing ecosystem, but also are closely related to military operations in the sea. The purpose of this study is to suggest which model is more suitable for the field of water temperature prediction by attempting short-term water temperature prediction through various prediction models based on deep learning technology. The data used for prediction are water temperature data from the East Sea (Goseong, Yangyang, Gangneung, and Yeongdeok) from 2016 to 2020, which were observed through marine observation by the National Fisheries Research Institute. In addition, we use Long Short-Term Memory (LSTM), Bidirectional LSTM, and Gated Recurrent Unit (GRU) techniques that show excellent performance in predicting time series data as models for prediction. While the previous study used only LSTM, in this study, the prediction accuracy of each technique and the performance time were compared by applying various techniques in addition to LSTM. As a result of the study, it was confirmed that Bidirectional LSTM and GRU techniques had the least error between actual and predicted values at all observation points based on 1 hour prediction, and GRU was the fastest in learning time. Through this, it was confirmed that a method using Bidirectional LSTM was required for water temperature prediction to improve accuracy while reducing prediction errors. In areas that require real-time prediction in addition to accuracy, such as anti-submarine operations, it is judged that the method of using the GRU technique will be more appropriate.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1422-1431
• /
• 2015

The reliability of power system components can be affected by a numbers of factors such as the health level of components, external environment and operation environment of power systems. These factors also affect the electrical parameters of power system components for example the thermal capacity of a transmission element. The relationship of component reliability and power system is, therefore, a complex nonlinear function related to the above-mentioned factors. Traditional approaches for reliability assessment of power systems do not take the influence of these factors into account. The assessment results could not, therefore, reflect the short-term trend of the system reliability performance considering the influence of the key factors and provide the system dispatchers with enough information to make decent operational decisions. This paper discusses some of these important operational issues from the perspective of power system reliability. The discussions include operational reliability of power systems, reliability influence models for main performance parameters of components, time-varying reliability models of components, and a reliability assessment algorithm for power system operations considering the time-varying characteristic of various parameters. The significance of these discussions and applications of the proposed techniques are illustrated by case study results using the IEEE-RTS.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.12
• /
• pp.5077-5081
• /
• 2014

To clarify whether gastric cancer patients can benefit from laparoscopy-assisted surgery completed by junior surgeons under supervision of expert surgeons, data of 232 patients with gastric cancer underwent operation performed by inexperienced junior surgeons were reviewed. Of the 232 patients, 137 underwent laparoscopy-assisted resection and in 118 cases this approach was successful. All of these 118 patients were assigned to laparoscopic group in this study, 19 patients who were switched to open resection were excluded. All laparoscopic operations were performed under the supervision of expert laparoscopic surgeons. Some 95 patients receiving open resection were assigned to the open group. All open operations were completed independently by the same surgeons. Short-term outcomes including oncologic outcomes, operative time intra-operative blood loss, time to first flatus, time to first defecation, postoperative hospital stay and perioperative complication were compared between the two groups. The numbers of lymph nodes harvested in the laparoscopic and open groups were $21.1{\pm}9.6$ and $18.2{\pm}9.7$ (p=0.029). There was no significant difference in the length of margins. The mean operative time was $215.9{\pm}32.2$ min in laparoscopic group and $220.1{\pm}34.6min$ in the open group (p=0.866), and the mean blood loss in laparoscopic group was obviously less than that in open group ($200.9{\pm}197.0ml$ vs $291.1{\pm}191.4ml$; p=0.001). Time to first flatus in laparoscopic and open groups was $4.0{\pm}1.0$ days and $4.3{\pm}1.2$ days respectively and the difference was not significant (p=0.135). Similarly no statically significant difference was noted for time to first defecation ($4.7{\pm}1.6$ vs $4.8{\pm}1.6$, p=0.586). Eleven patients in the laparoscopic group and 19 in the open group suffered from peri-operative complications and the difference between the two groups was significant (9.3% vs 20.0%, p=0.026). The conversion rate for laparoscopic surgery was 13.9%. Patients with gastric cancer can benefit from laparoscopy-assisted operations completed by inexperienced junior surgeons under supervision of expert laparoscopic surgeons.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.666-671
• /
• 2019

The flight controller(FC) used in small-sized drone was developed as simple structure does not perform complex operations because it uses different MCU with large-sized drone. Also, the balance control of small-sized drone should be simpler than Kalman filter using complex filter and the method using Complementary filter has relatively more operations. So, the method to realize the balance control on small-sized drone effectively using two-track control operating as proper method for above is suggested in this research. This method is a system maintaining effective balance with simple structure and less operations by operating adaptively for the unbalance of the drone with the acceleration sensor with the advantage which performing accurate correction by data processing for long term change and gyroscope sensor maintaining the balance of the drone by data processing for short term change. It is confirmed that stable operation was performed mostly based on the test result for repeatable test more than 100 times using two-track control and it maintained normal state operation more than 98% excluding the difficulty of maintaining normal operation when meets sudden and rapid wind yet.