• 정보처리학회논문지A
• /
• 제10A권3호
• /
• pp.269-278
• /
• 2003

웹 기반 교육의 대중화로 학습 보조 도구를 이용한 다양한 웹 학습 방법들이 제시되고 있으며 또한 이틀 시스템의 운용 환경, 컨텐츠명세 그리고 활용 등의 상호 운용성 지원을 위한 표준화에 대한 연구가 국제표준기관 등을 통해 활발히 이루어지고 있다. 특히 e-learning 개발 환경을 위한 Learning Technology Standard Architecture(LTSA)를 기능별 5계층을 IEEK에서 제정하였다. 이 LTSA의 학습 보조 도구 표준화 영역에서 학습과정 피드백을 제공하는 질의 응답 학습 방법에 대한 표준규약기능을 명세하지 않고 있다. 본 논문에서는 국제표준화 기술인 ITSA 시스템 구성중 제 3계층을 기반한 질의 응답 학습 도구에 대해 연구한다. 데이터 중심으로 작성된 LTSA 컴포넌트를 객체지향 또는 컴포넌트 패라다임으로 재 정의하는 모델을 제안하고 기존의 Loaming Object Meatdata(LOM)을 참조하여 질의 응답 메타 데이터인 Query Answer Metadata(QAM)를 서술한다. 이들 재정의 모델과 QAM을 통합한 Query Answer Learning Tool(QALT)를 분석, 설계하여 프로토타이핑시스템으로 구현한다. 이를 통해 웹 기반 교육의 효율성 및 관련 도구 개발의 품질 및 생산성 효율을 가진다.

• Journal of Korea Trade
• /
• 제23권7호
• /
• pp.96-112
• /
• 2019

Purpose - "Trade Facilitation" aims the easier flow of trade across borders, driven not only by effective customs administration, the efficiency of appropriate authorities, but also by telecommunications, the quality of infrastructures and competent logistics. Facilitating trade will help lower trade development costs as well as improve economic development and enhance economic benefits for emerging economies at a time when imports and exports are sent in and out across borders several times in the form of intermediate and final products. Not only that, globalization is being accelerated, which in turn increases competitiveness and this makes logistics one of the key factors when it comes to international trade. Highly efficient logistics services promote product movement, ensure product safety and delivery speed, and reduce trade costs between countries. The purpose of this study is, by using the LPI indices based on gravity model estimates, to analyze the impact of each LPI component on trade with the 20 biggest exporting countries of Northeast Asian countries-Korea, Japan, and China-which account for 19.05% of global exports. Design/methodology - Also, this study statistically analyzes the impact of trade on Northeast Asian countries' top 20 exporting countries, using the LPI indices relevant to Trade Facilitation based on the gravity model estimates. Findings - As a result, it was turned out that the distance, GDP, and the LPI components have relevant impact on the trade exports of all three countries but demonstrated little relation to the demographic perspective. Originality/value - The study also found we can increase the trade volume by improving three countries' trade partners' LPI indices since Korea, Japan, and China share most of their 20 biggest trade partners.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.174-180
• /
• 2022

Emotion recognition is an essential component of complete interaction between human and machine. The issues related to emotion recognition are a result of the different types of emotions expressed in several forms such as visual, sound, and physiological signal. Recent advancements in the field show that combined modalities, such as visual, voice and electroencephalography signals, lead to better result compared to the use of single modalities separately. Previous studies have explored the use of multiple modalities for accurate predictions of emotion; however the number of studies regarding real-time implementation is limited because of the difficulty in simultaneously implementing multiple modalities of emotion recognition. In this study, we proposed an emotion recognition system for real-time emotion recognition implementation. Our model was built with a multithreading block that enables the implementation of each modality using separate threads for continuous synchronization. First, we separately achieved emotion recognition for each modality before enabling the use of the multithreaded system. To verify the correctness of the results, we compared the performance accuracy of unimodal and multimodal emotion recognitions in real-time. The experimental results showed real-time user emotion recognition of the proposed model. In addition, the effectiveness of the multimodalities for emotion recognition was observed. Our multimodal model was able to obtain an accuracy of 80.1% as compared to the unimodality, which obtained accuracies of 70.9, 54.3, and 63.1%.

• Journal of Korea Trade
• /
• 제26권7호
• /
• pp.109-126
• /
• 2022

Purpose - Based on the relevant panel data for China and 13 of the RCEP countries from 2008-2019, this paper conducts an in-depth study on the impact of trade facilitation levels on China's cross-border e-commerce exports using the expanded trade gravity model. Design/methodology - This study constructs a trade facilitation index (TFI) system, and uses the principal component analysis method to measure the trade facilitation levels of RCEP countries in 2008-2019. This result is then introduced into the extended gravity model to explore the effect of trade facilitation in RCEP countries on China's cross-border e-commerce export. Findings - It is found that the overall trade facilitation level has a significant effect on China's cross-border e-commerce exports. Among the primary indicators, with the exception of infrastructure, the other four indicators demonstrate a significant impact. The findings show that China should strengthen its cooperation with RCEP countries in trade facilitation and cross-border e-commerce to better achieve complementary regional economic development. Originality/value - This paper has three contributions: first, this paper builds a TFI system that includes five primary indicators based on the characteristics of cross-border e-commerce. Second, we explore the impact of trade facilitation levels of RCEP countries on China's cross-border e-commerce exports, which helps to fill the gap in existing studies of the impact of cross-border e-commerce exports. Third, this paper further analyzes the impact of five primary indicators on cross-border e-commerce exports; this thus provides more targeted measures to improve trade facilitation levels.

• 산경연구논집
• /
• 제9권11호
• /
• pp.39-54
• /
• 2018

Purpose - To success, in spite of deficient resources, a start-up company has to check various circumstances. Many researchers proposed different appraisal methods for technology commercialization. But everybody agrees Merrifield is the first one, who is a pioneer of an appraisal model of technology commercialization. After he proposed it, many researchers and field workers developed a more complicated model, which called a BMO model. In this research, considering the circumstances of start-ups that lack available resources, it proposes a new appraisal method for technology commercialization, which is named a weighted-BMO model. Research design, data, and methology - For the new BMO-model, it studied the preceding studies. And it found that the success factors for start-ups were correlated with technology commercialization. After comparing the success factors for technology commercialization of start-ups with BMO appraisal factor, it withdraws the net BMO appraisal model: which we are calling the weighted-BMO model. Results - This study found a few things. First, actually, the BMO appraisal factors related with the success factors of technology commercialization. Second, the weighted-BMO model, which included the entrepreneur ability factor, was more accurately estimated the success of technology-based start-ups than the BMO model. Third, it overcame the weakness of the BMO-model, which did not include quantitative factors. In addition to evaluating the feasibility of the BMO model, we also presented a strategy for the future direction. But, still, it included a few shortcomings, which we are calling the arbitrage of weighted value. Sometimes, the intentional weighted value can deliberate the different valuation. Conclusitons - Due to this study, the weighted-BMO model included appraisal factors related with the success factors of technology commercialization and the entrepreneur ability factor, and quantitative factors. When evaluating the combined score of the existing Merrified BMO components, 35 points of the first pass criterion accounted for 29.17% of the total score, and 80 points of the merit score of the second rank criterion were 66.67% Considering that the weighted sum is taken into account, the baseline score of the weighted summing method for each component of the modified BMO model is 2.92 points, which is 29.17% of the weighted sum total of 10 points. The evaluation score was 6.67 points, 66.67% of the weighted total score of 10 points.

• 산업경영시스템학회지
• /
• 제43권4호
• /
• pp.15-22
• /
• 2020

Economic indicators are a factor that affects air cargo volume. This study analyzes the different factors affecting air cargo volume by each Chinese cities according to the main characteristics. The purpose of this study is to help companies related to China, airlines, and other stakeholders predict and prepare for the fluctuations in air cargo volume and make optimal decisions. To this end, 20 economic data were used, and the entire data was reduced to 5 dimensions through factor analysis to build a dataset necessary and evaluated the influencing factors by multi regression. The result shows that Macro-Economic Indicators, Production/Service indicators are significant for every cities and Chinese manufacture/Customer indicators, Korean manufacture/Oil Price indicators, Trade/Current indicators are significant for each other city. All adjusted R2 values are high enough to explain our model and the result showed excellent performance in terms of analyzing the different factors which affects air cargo volume. If companies that are currently doing business with China can identify factors affecting China's cargo volume, they can be flexible in response to changes in plans such as plans to enter China, production plans and inventory management, and marketing strategies, which can be of great help in terms of corporate operations.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• 한국전자거래학회:학술대회논문집
• /
• 한국전자거래학회 1997년도 한국전자거래학회 종합학술대회지
• /
• pp.263-268
• /
• 1997

Functional Modeling methodology, IDEF0 is widely used for modeling, analysis and description of enterprise system. The limitation of modeling components restricts applicability and give rise to confusion about model. In this paper, we propose new method to extend IDEF0. The first is adding modeling components which are semantic representations. In addition to ICOMs, we add the time and cost component which is required to execute the function. The second is tracing mechanism. When we need some information, we drive the functions related with the information by reverse tracing of the function which produces the information as a output and input. Through the tracing, we find out the bottleneck process or high cost process. Finally, we suggest the final decomposition level. We call the final decomposed function into unit function which has only one output data. We can combine and reconstruct some of functions because an unit function is similar to ‘lego block’. To reach the integrated system, the main problem to be solved is the integration of information produced by different functional subsystem. This can be resolved when the creation of data must be dependent on only one function. Through view integration of function output, we can guarantee the integrity of data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.