• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of Distribution Science
• /
• v.15 no.1
• /
• pp.123-130
• /
• 2017

Purpose - This research aims to examine the effect of e-business adoption on firm's growth and profitability in the distribution industry. The value added from the distribution industry acts as the cost of other industries. As the distribution industry develops, its stage becomes shorter and the distribution margin becomes smaller. Therefore, e-business is expected to have a different effect on the distribution industry than other industries. Research design, data and methodology - The previous research generally used e-business adoption as an independent variable and firm's performance as a dependent variable. This study elaborated the model using a dynamic panel model that includes the performance variable of the previous year as an independent variable. By employing system GMM (Generalized Method of Moments), the endogeneity problem in the dynamic panel model can be solved. For the analysis, I extracted the distribution companies as the raw data in the National Statistical Office's Business Activity Survey over the period 2006 to 2012. Results - The growth rate of firms adopting e-business was 0.299%p higher than that of the non-adopter. However, only ERP (Enterprise Resource Planning), KMS (Knowledge Management System) and SCM (Supply Chain Management) contributed positively to the growth rate. In the case of profitability, it was 0.04%p higher than the distribution companies that did not adopt e-business. ERP and LMS (Learning Management System) improve profitability, while SCM reduces profitability. Consequently, while ERP improves both growth and profitability, SCM improves growth but reduces profitability. In addition, KMS improves firm's growth only, and LMS does only profitability, showing that each e-business has a differentiated effect. Conclusions - Since the distribution industry has different characteristics from manufacturing and other service industries, the introduction of e-business may not guarantee the growth and profitability of distribution companies. Careful introduction considering the characteristics of the distribution industry is required. In particular, it is necessary to select an e-business meeting the characteristics and needs of a distribution company, and thereafter, it is required for the company's own efforts to internalize it within the system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.489-498
• /
• 2023

Advancements in hardware performance and computing technology have facilitated the progress of climate prediction models to address climate change. The Korea Meteorological Administration employs the GloSea6 model with supercomputer technology for operational use. Various universities and research institutions utilize the Low-GloSea6 model, a low-resolution coupled model, on small to medium-scale servers for weather research. This paper presents an analysis using Intel VTune Profiler on Low-GloSea6 to facilitate smooth weather research on small to medium-scale servers. The tri_sor_dp_dp function of the atmospheric model, taking 1125.987 seconds of CPU time, is identified as a hotspot. Nonlinear regression models, a machine learning technique, are applied and compared to existing functions conducting numerical operations. The K-Nearest Neighbors regression model exhibits superior performance with MAE of 1.3637e-08 and SMAPE of 123.2707%. Additionally, the Light Gradient Boosting Machine regression model demonstrates the best performance with an RMSE of 2.8453e-08. Therefore, it is confirmed that applying a nonlinear regression model to the tri_sor_dp_dp function during the execution of Low-GloSea6 could be a viable alternative.

• Journal of Korean Society of Transportation
• /
• v.22 no.5
• /
• pp.111-122
• /
• 2004

The driver's decision making (e.g. route choice) is a typical decision making with an uncertainty. In this paper, we investigate the effect of route guidance information on driver's route choice and learning behavior and analyse the potential of information system in a road network in which traffic flows follow random walk. A Simulation performed focuses on the relationship among the network wide performance, message receiving rates and driver's learning mechanism. We know that at high levels of message receiving rates, the network-wide performance may get worse. However, at low levels of receiving rates, we found that the travel time when guidance information is provided decrease compared to the cases when no pubic information is provided. Also, we found that the learning parameter of the learning mechanism model always changes under nonstationary traffic condition. In addition, learning process of drivers does not converge on any specific value. More investigation is needed to enlarge the scope of the study and to explore more deeply driver's behavior.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.25-31
• /
• 2008

It is important for users to be confirming in e-Leaning system, because legitimate learner should be joined to the system for teaming and testing Thus, most system for authentication was verified using id and password with learner's id and password. In this case, It can be easy for hackers to steal learner's id and password. In addition, soma learner gets another to sit for the examination for one with another person id and password. For the solution like this problem it needs a biometrics authentication for complement. This method is required so much extra cost as well as are an unwanted concern. Therefore, we proposed keystroke technique to decide which learners are righteous or unlawful in this paper. In addition, we applied statistics and neural network for the performance of keystroke system. As a result, the performance of FAR and FRR in keystroke authentication was increased by proposed method.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.188-198
• /
• 2018

With recent development of high-speed wide-area wireless networks and wide spread of highperformance wireless devices, the demand on seamless video streaming services in Long Term Evolution (LTE) network environments is ever increasing. To meet the demand and provide enhanced Quality of Experience (QoE) with mobile users, the Dynamic Adaptive Streaming over HTTP (DASH) has been actively studied to achieve QoE enhanced video streaming service in dynamic network environments. However, the existing DASH algorithm to select the quality of requesting video segments is based on a procedural algorithm so that it reveals a limitation to adapt its performance to dynamic network situations. To overcome this limitation this paper proposes a novel quality selection mechanism based on a Deep Q-Network (DQN) model, the DQN-based DASH ABR($DQN_{ABR}$) mechanism. The $DQN_{ABR}$ mechanism replaces the existing DASH ABR algorithm with an intelligent deep learning model which optimizes service quality to mobile users through reinforcement learning. Compared to the existing approaches, the experimental analysis shows that the proposed solution outperforms in terms of adapting to dynamic wireless network situations and improving QoE experience of end users.

• Journal of Information Technology Applications and Management
• /
• v.22 no.1
• /
• pp.109-130
• /
• 2015

This study aims to provide the results of a case study, based on the action research approach, in which an user-oriented management system for enterprise information systems operational performance is successful developed and applied. This study performs the research and summarizes the results by adopting 5-step approach of action research, i.e., diagnosing, action planning, action taking, evaluating and specifying learning. The most important lessons learned from the study include (1) operation performance measures should be established to be shared by the management and users; (2) evaluation and improvement activities should be performed continually; and (3) formula to calculate the measure should be evolved so that improvement initiatives can be identified. The results of the study are expected to provide the companies intending to develop a management system for enterprise information systems operational performance with the practical and useful information. In addition, it is expected to suggest the research results that can be utilized as a basis for future research in this area.

• Korean Medical Education Review
• /
• v.25 no.2
• /
• pp.114-118
• /
• 2023

Multiple cohorts (e.g., current students and graduates) were formed to collect information on the entire educational process from admission to graduation regarding students' educational performances at Kosin University College of Medicine. Data that had already been collected and analyzed by different committees for different purposes were grouped into a more systematic and comprehensive system called the cohort system, enabling the necessary data to be collected promptly and analyzed in accordance with the purpose of providing meaningful information in each area of the educational process. Therefore, comprehensive cohort data that can be used for mission statement revision, curriculum development and improvement, student counseling, and student selection were established and utilized. The cohort data were collected from performance evaluation indicators including self-evaluation surveys, evaluation tools for learning outcomes, academic achievement, results of the Korean Medical Licensing Examination, and career placement. Based on the results obtained by analyzing cohort data, a comprehensive cohort report has been published. The data analyzed through the cohort were reported to each committee and used in various ways. Currently, however, only some data have been analyzed and used. In the future, after complete data collection, the cohort data can be used as meaningful basic data for achieving the institution's mission and educational goals, developing and improving the curriculum, counseling students, and selecting students through the analysis of learning performance data from student admission to graduation and after graduation.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.924-935
• /
• 2023

Purpose: The central aim of this study is to leverage machine learning techniques for the classification of Intrusion Detection System (IDS) data, with a specific focus on identifying the variables responsible for enhancing overall performance. Method: First, we classified 'R2L(Remote to Local)' and 'U2R (User to Root)' attacks in the NSL-KDD dataset, which are difficult to detect due to class imbalance, using seven machine learning models, including Logistic Regression (LR) and K-Nearest Neighbor (KNN). Next, we use the SHapley Additive exPlanation (SHAP) for two classification models that showed high performance, Random Forest (RF) and Light Gradient-Boosting Machine (LGBM), to check the importance of variables that affect classification for each model. Result: In the case of RF, the 'service' variable and in the case of LGBM, the 'dst_host_srv_count' variable were confirmed to be the most important variables. These pivotal variables serve as key factors capable of enhancing performance in the context of classification for each respective model. Conclusion: In conclusion, this paper successfully identifies the optimal models, RF and LGBM, for classifying 'R2L' and 'U2R' attacks, while elucidating the crucial variables associated with each selected model.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.177-185
• /
• 2024

Web science, a general discipline of learning is presently at high demand of expertise with ideas to develop software-based WebApps and MobileApps to facilitate user or customer demand e.g. shopping etc. electronically with the access at their smartphones benefitting the business enterprise as well. A worldwide-computerized reservation network is used as a single point of access for reserving airline seats, hotel rooms, rental cars, and other travel related items directly or via web-based travel agents or via online reservation sites with the advent of social-web, e-commerce, e-business, from anywhere-on-earth (AoE). This results in the accumulation of large and diverse distributed databases known as big data. This paper describes a novel intelligent web-based electronic booking framework for e-business with distributed computing and data mining support with the detail of e-business system flow for e-Booking application architecture design using the approaches for distributed computing and data mining tools support. Further, the importance of business intelligence and data analytics with issues and challenges are also discussed.