• Journal of Global Scholars of Marketing Science
• /
• v.14
• /
• pp.125-144
• /
• 2004

The purpose of this study is to classify customer bye-mailing responsiveness on time-series analysis and RFM module and testify the effectiveness of grouping by ROI analysis. RFM (Recency, Frequency, Monetary Value) analysis are used for customer classification that is fundamental process of e-CRM application. ROI analysis were consisted of open, click-through, duration time, conversion rate, personalization and e-mail loyalty index. Major findings are as follows; Customer segmentation were loyal customer, odds customer, dormant customer, secession customer and observation customer by Activity email module. And Loyal, dormant and secession customer are segregated by RFM module. Loyal customer group have higher point of all ROI index than other groups. These results indicated that customer responsiveness of e-mailing and RFM analysis were appropriate methods to grouping the customer. Mid-small Internet Biz adapted marketing strategy by optimization of consumer information.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.440-445
• /
• 2017

Due to the advance of e-commerce systems, the number of people using online shopping and products has significantly increased. Therefore, the need for an accurate recommendation system is becoming increasingly more important. Recurrent neural network is a deep-learning algorithm that utilizes sequential information in training. In this paper, an evaluation is performed on the application of recurrent neural networks to recommendation systems. We evaluated three recurrent algorithms (RNN, LSTM and GRU) and three optimal algorithms(Adagrad, RMSProp and Adam) which are commonly used. In the experiments, we used the TensorFlow open source library produced by Google and e-commerce session data from RecSys Challenge 2015. The results using the optimal hyperparameters found in this study are compared with those of RecSys Challenge 2015 participants.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.11 s.158
• /
• pp.1519-1530
• /
• 2006

This study has surveyed and analyzed in 2005 S/S domestic men's street fashion by using the Web-SFAS system that was developed and completed in the earlier research. Total of 270 men who were sensitive to fashion were surveyed around 5 nationwide cities and 9 commercial zones. The analysis results of the questionnaire and image survey in 2005 S/S for each commercial zone was shown as follows. 1. The most interest in producing fashionable shape when they go out was in the order of clothes>hair style>shoes and it was found that the proper reason for visiting the commercial zone was to meet with friends>watching movies>shopping etc. 2. T-shirts were most preferred as upper garments and as for bottoms, blue jeans were preferred. Black, gray, and white colors were most preferred and blue color was most preferred primarily due to the preference for blue jeans. The color image was proven mainly modem and light tone, comfortable and casual items were preferred. An active comfort casual image emphasized with activeness by coordinating comfortable T-shirts or shirts with blue jeans were most preferred in 9 areas. 3. A clear difference was confirmed in color by commercial area. Blackish color was most prevalent in Daehakro whereas simple color was mostly shown around Hongik University area. Bright and unique colors such as green and violate were dominant at Dae-Gu Dongseongro, and basic colors such as white and black were preferred in Masan Hapseong-dong and Changwon Sangnam-dong. Through the results of nationwide street fashion survey, the each commercial zone has unique characteristics in fashion trend even in the same city, rather than the regional difference in Seoul and local city.

• Journal of Distribution Research
• /
• v.6 no.2
• /
• pp.91-108
• /
• 2002

While a lot of research has been done in the area of the B2C e-commerce, heavily on the Internet shopping, a study on the B2B e-commerce has not been improved enough to be competitive for its importance and practical use. We have studied to build an effective database, attempting to complement and further replace in the long term the off-line distribution channel which has yet to be fully evolve with respect to effectiveness and efficiency. For the building of the effective database, we have gathered information from the related institutions and characterized a fishery channel, and surveyed existing literatures and consumers for deriving factors affecting their purchase intentions and satisfactions. Based upon this survey we constructed the entity-relationship diagram(ERD) which possibly provided some perspectives for the future application. This study focuses on the improvement in the distributional efficiency not only minimizing the intra-organizational conflict and resistance but also maximizing the role function of each party of the organization.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.254-262
• /
• 2009

As the trend of e-business activities develop, customers come into contact with products through on-line shopping sites and lots of customers refer product reviews before the purchasing on-line. However, as the volume of product reviews grow, it takes a great deal of time and effort for customers to read and evaluate voluminous product reviews. Lately, attention is being paid to Opinion Mining(OM) as one of the effective solutions to this problem. In this paper, we propose an efficient method for opinion sentiment classification of product reviews using product specific context information of words occurred in the reviews. We define the context information of words and propose the application of context for sentiment classification and we show the performance of our method through the experiments. Additionally, in case of word corpus construction, we propose the method to construct word corpus automatically using the review texts and review scores in order to prevent traditional manual process. In consequence, we can easily get exact sentiment polarities of opinion words in product reviews.

• Journal of Satellite, Information and Communications
• /
• v.12 no.1
• /
• pp.49-53
• /
• 2017

In this paper we present the combination of location based mobile advertisement services and dynamic digital signage markets has been developing recent days to provide consumer admired visual mobile advertisement on all kind transportation vehicles. In spite of that, the digital signage advertisement content management is still not that easy to manage the content dynamically as well operation is most time consuming to handle the contents dynamically in digital signage business. As location based services is most impactful service in shopping, the location responsive advertisement on vehicle signage will be most desirable mobile advertisement to help people migrate from one place to another place for travel or stay. This paper propose a mobile location responsive digital signage system for vehicles using the GPS and wireless infrastructure integrated with digital signage system. This proposed research use the centralized digital signage system architecture for the mobile advertisement application and this system can be expanded to different vehicles for digital advertisement including buses, trucks, train, air vehicle and any other form of mobile advertising vehicles. Also, this present an effective advertisement recommendation algorithm, by which the advertisement can be selected broadcasted for the right advertisement ventures more effectively as the service requested from advertiser. This paper present the emulated experimental result to evidence the proposed dynamic vehicle signage system performed better than compared with traditional signage random advertising. The emulated result proves that the advertisement recommendation algorithm can effectively works out the targeted key audiences in location responsive region the algorithm evaluated.

• Journal of Satellite, Information and Communications
• /
• v.12 no.1
• /
• pp.101-106
• /
• 2017

In this paper, we present Emergency exit signs are installed to provide escape routes or ways in buildings like shopping malls, hospitals, industry, and government complex, etc. and various other places for safety purpose to aid people to escape easily during emergency situations. In case of an emergency situation like smoke, fire, bad lightings and crowded stamped condition at emergency situations, it's difficult for people to recognize the emergency exit signs and emergency doors to exit from the emergency building areas. This paper propose an automatic emergency exit sing recognition to find exit direction using a smart device. The proposed approach aims to develop an computer vision based smart phone application to detect emergency exit signs using the smart device camera and guide the direction to escape in the visible and audible output format. In this research, a CAMShift object tracking approach is used to detect the emergency exit sign and the direction information extracted using template matching method. The direction information of the exit sign is stored in a text format and then using text-to-speech the text synthesized to audible acoustic signal. The synthesized acoustic signal render on smart device speaker as an escape guide information to the user. This research result is analyzed and concluded from the views of visual elements selecting, EXIT appearance design and EXIT's placement in the building, which is very valuable and can be commonly referred in wayfinder system.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.337-343
• /
• 2014

There have been many efforts to find a new way to combine software reuse and agile software development methods. This paper studies the integration of software reuse techniques in agile methods, such as Scrum. Agile methods have the advantage of accepting frequent requirement changes, while software reuse reduces development time. Despite the rapid acceptance of the Scrum method in industry, not much emphasis has been placed on active reuse in the Scrum method, and most studies have focused on introducing agile practices into software product line engineering. However, the iterative development and backlog refinement activities of the Scrum method present the advantage of facilitating software reuse. In this paper, we identify sprint characteristics and components for reuse and suggest extended backlog refinement steps. Based on the results of this research, we integrate a backlog factoring technique into backlog refinement to support reuse in agile methods. In addition, we apply the proposed technique and demonstrate a prototype of product backlog reuse in backlog refinement for an Internet shopping mall application.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.65-72
• /
• 2020

In this paper, a USB module with fingerprint recognition was designed as a distributed node of blockchain on distributed ID (DID, distributed ID) for user identification. This biometric-linked fingerprint recognition device was verified for the real-time authentication process of authentication transaction with FIDO(Fast IDentity Online) server. Blockchain DID-based services were proposed like as a method of individual TV rating survey, and recommending service for customized shopping channels, and crypto-currency, too. This DID based remote service can be improved by recognizing of channel-changing information through personal identification. The proposed information of production purchase can be shared by blockchain. And customized service can be provided for the utilization of purchase history in shoppingmall using distributed ID. As a result, this blockchain node-device and Samsung S10 Key-srore with FIDO service can be certified for additional transactions through various biometric authentication like fingerprint, and face recognition.

• Journal of the Korean Society of Safety
• /
• v.30 no.6
• /
• pp.78-84
• /
• 2015

In order to increase the utilization of limited space in urban area, it can be a good solution to make use of underground space. For the last few decades, underground space systems, such as underground passages, subway stations, and underground shopping arcades, have been constructed in many cities all over the country. Despite of the advantages on the utilization of space in urban area, underground space systems have always been exposed to the risk of inundations resulted from severe rain storms. In this study, it has been examined to apply 2-D flow models (TUFLOW and FLUMEN) to establishing the preventive measures to the risk of flood. For the part with relatively complex configuration, such as a corridor junction, 2-D flow models present the detailed information about the effect of geometry on the inundation events and the temporal and spatial distribution of inundation over the space. From the result, it can be concluded that the 2-D flow model can be the effective implement for establishing the proper measure to the inundation on underground space systems, which generally have relatively long and narrow geometry with complex inner configuration.