• Smart Media Journal
• /
• v.13 no.4
• /
• pp.57-64
• /
• 2024

Attributes such as material, color, and fit in fashion images are important factors for consumers to purchase clothing. However, the process of classifying clothing attributes requires a large amount of manpower and is inconsistent because it relies on the subjective judgment of human operators. To alleviate this problem, there is a need for research that utilizes artificial intelligence to classify clothing attributes in fashion images. Previous studies have mainly focused on classifying clothing attributes for either tops or bottoms, so there is a limitation that the attributes of both tops and bottoms cannot be identified simultaneously in the case of full-body fashion images. In this study, we propose a deep learning model that can distinguish between tops and bottoms in fashion images and classify the category of each item and the attributes of the clothing material. The deep learning models ResNet and EfficientNet were used in this study, and the dataset used for training was 1,002,718 fashion images and 125 labels including clothing categories and material properties. Based on the weighted F1-Score, ResNet is 0.800 and EfficientNet is 0.781, with ResNet showing better performance.

• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.351-360
• /
• 2008

The purpose of this study is to segment visitors for beer franchise restaurants. Total of 308 questionnaires were distributed to the beer franchise restaurant customers of Kangnam area, Seoul. To accomplish the aim of this study, author took the following three steps. Firstly, literature review was done to find out selective attributes for restaurant and bar and market segmentation. secondly, Selective attributes of beer franchise were analyzed and five factors, -'additional service', 'side dish quality', 'service class', 'accessibility' and 'outlet image'- were extracted. Lastly, customers of beer franchise shop were divided into two groups by the selective attributes, -'simple visiting group' and 'active lover group'. Those variables-loyalty, intent to recommend and overall satisfaction- have significant influence on 'active lover group'. Other than that, other variables -demographic characteristics and customer's behavior characteristics- didn't play important role to distinct two groups. As a result, only basic information for setting up marketing strategy of each market was provided.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.107-121
• /
• 2005

Recently, many researches on recommendation systems and collaborative filtering have been proceeding in both research and practice. However, although product items may have multi-valued attributes, previous studies did not reflect the multi-valued attributes. To overcome this limitation, this paper proposes new methodology for recommendation system. The proposed methodology uses multi-valued attributes based on clustering technique for items and applies the collaborative filtering to provide accurate recommendations. In the proposed methodology, both user clustering-based CBR and item attribute clustering-based CBR technique have been applied to the collaborative filtering to consider correlation of item to item as well as correlation of user to user. By using multi-valued attribute-based clustering technique for items, characteristics of items are identified clearly. Extensive experiments have been performed with MovieLens data to validate the proposed methodology. The results of the experiment show that the proposed methodology outperforms the benchmarked methodologies: Case Based Reasoning Collaborative Filtering (CBR_CF) and User Clustering Case Based Reasoning Collaborative Filtering (UC_CBR_CF).

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1339-1353
• /
• 2004

< TABLE > tags in HTML documents are widely used for formatting layout of Web documents as well as for describing genuine tables with relational information. As a prerequisite for information extraction from the Web, this paper presents an efficient method for sophisticated table detection. The proposed method consists of two phases: preprocessing and attribute-value relations extraction. For the preprocessing where genuine or ungenuine tables are filtered out, appropriate rules are devised based on a careful examination of general characteristics of < TABLE > tags. The remaining is detected at the attribute-value relations extraction phase. Specifically, a value area is extracted and checked out whether there is a syntactic coherency Futhermore, the method looks for a semantic coherency between an attribute area and a value area of a table that may be inappropriate for the syntactic coherency checkup. Experimental results with 11,477 < TABLE > tags from 1,393 HTML documents show at the method has performed better compared with previous works, resulting in a precision of 97.54% and a recall of 99.22% in average.

• Journal of Korean Library and Information Science Society
• /
• v.46 no.3
• /
• pp.27-49
• /
• 2015

The purpose of this study is to suggest the ways to apply describing attributes and relationships of families to Korean Cataloging Rules. In order to achieve the objective of this study, the FRAD conceptual model, and the cataloging rules such as RDA, DACS2 and KCR2 were analyzed. For describing attributes of families, this study analyzed name, type, date, place, prominent member, hereditary title, language, history, and identifier of families. For describing relationships of families, this study investigated describing relationships to families associated with each resource, such as a work, an expression, a manifestation, and an item, and describing relationships between families, relationships between families and persons, and relationships between families and corporate bodies. Based on these analyses, this study suggested the application methods of describing attributes and relationships of families in Korean Cataloging Rules.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.8
• /
• pp.1597-1605
• /
• 2015

Password authenticated key exchange (PAKE) is a protocol that a client stores its password to a server, authenticates itself using its password and shares a session key with the server. In multi-server PAKE, a client splits its password and stores them to several servers separately. Unless all the servers are compromised, client's password will not be disclosed in the multi-server setting. In attribute-based encryption (ABE), a sender encrypts a message M using a set of attributes and then a receiver decrypts it using the same set of attributes. In this paper, we introduce multi-server PAKE protocol that utilizes a set of attributes of ABE as a client's password. In the protocol, the client and servers do not need to create additional public/private key pairs because the password is used as a set of public keys. Also, the client and the servers exchange only one round-trip message per server. The protocol is secure against dictionary attacks. We prove our system is secure in a proposed threat model. Finally we show feasibility through evaluating the execution time of the protocol.

• Journal of Korea Port Economic Association
• /
• v.35 no.4
• /
• pp.67-84
• /
• 2019

In order to suggest ways to enhance service competitiveness in cruise and destination, this study developed a measure of cruise tour service and analyzed the impact and relative importance on customer satisfaction. Specifically, for the service quality analysis, based on the SERVPERF model, the specialty of the industry was reflected through the arguments of tourism and transport logistics, and the three factors of cruise service quality and destination service quality were derived and utilized as measurement tools. As an analysis method, factor and reliability analysis were conducted using data collected via a survey. Next, correlation analysis was conducted to analyze the relationship between variables and regression analysis was performed to check the impact of cruise tour service quality on customer satisfaction. The study found that both cruise service attributes and destination service attributes had a positive effect on customer satisfaction and that the relative importance of service attributes was identified. Accordingly, it was found that the service quality should be formed by reflecting arguments in the tourism and transport logistics sectors and that the service should be further improved and developed according to the importance of the service attributes so as to enhance cruise tour products.

• Journal of Digital Contents Society
• /
• v.16 no.5
• /
• pp.749-756
• /
• 2015

This study focused on smartphone adoption of foreign students who are studying in Korea in digital media era. Smartphone is not only new media but also social media. Based on former research, factor for smartphone adoption of foreign students will be analyzed. Based on TAM theory technological attribute, individual attribute and social attribute were taken out as independent variables. Perceived ease of use and perceived usefulness are applied as mediator variables. In conclusion, some hypotheses for example service quality and individual attribute are rejected as variables which influence positively to mediator variable perceived easy of use. For the next research more various variables and nationwide sampling will be needed.

• Proceedings of the KOR-KST Conference
• /
• 1999.10a
• /
• pp.29-34
• /
• 1999

• Journal of KSNVE
• /
• v.12 no.5
• /
• pp.334-341
• /
• 2002