• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2948-2966
• /
• 2014

To promote recommendation services through prediction quality, some privacy-preserving collaborative filtering solutions are proposed to make e-commerce parties collaborate on partitioned data. It is almost probable that two parties hold ratings for the same users and items simultaneously; however, existing two-party privacy-preserving collaborative filtering solutions do not cover such overlaps. Since rating values and rated items are confidential, overlapping ratings make privacy-preservation more challenging. This study examines how to estimate predictions privately based on partitioned data with overlapped entries between two e-commerce companies. We consider both user-based and item-based collaborative filtering approaches and propose novel privacy-preserving collaborative filtering schemes in this sense. We also evaluate our schemes using real movie dataset, and the empirical outcomes show that the parties can promote collaborative services using our schemes.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.43 no.6
• /
• pp.808-824
• /
• 2019

This study analyzes the values of vintage in Korean fashion prosumer's activities and elevates the values as one characteristic of Korean modern fashion. The methodology included literary and empirical studies as well as prosumer and modern Korean vintage fashion literary studies. In-depth interviews were done to analyze the values of vintage in fashion prosumer's activities. The values of vintage fashion for Millennials are creative activities based on public interest, expanded reproducing through sharing daily looks and self-expression through the scarcity of vintage clothing. Prosumer characteristics are self-satisfaction and sharing. Fashion prosumer's vintage trends are new-tro, communication, cultural complex, and sharing of daily life. The formativeness in fashion prosumer's activities are heritage, text, activity and image. The meanings are creation, communication, experience and sharing. Fashion prosumers are developing the new genre of 'vintage fashion activity'; in addition, values towards vintage fashion activity are also drawing international interest.

• The Research Journal of the Costume Culture
• /
• v.18 no.1
• /
• pp.205-215
• /
• 2010

In modern society as people adapt to social and cultural changes, people prefer high-scarcity designed products rather than standardized ones. Consequently, this adaptation lays a foundation in art and cultural domains to express uniqueness and individuality. The purpose of this study is to develop fashion designs by fusing fashion painting and handicraft techniques through creative and various artistic expressions. The researchers studied the sociocultural background of modern handicraft fashion using document-based research methods. Based on the characteristics of modern handicraft, we produced six garments that applied fashion painting techniques. In this study, the origin of fashion painting was found in ornaments such as tattoo or body-painting. We determined that modern designers were using various fashion painting techniques and motives as unique and advanced ornamentary skills. Harmonizing various handicraft techniques(dyeing, embroidery, quilt, patchwork, beads, fashion painting, etc.) centered on fashion painting enabled creation of unique fashion design through varieties of artistic expressions.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.42 no.3
• /
• pp.486-502
• /
• 2018

Mass-production caused by industrialization has led to environmental pollution; however, a potential solution to this problem is the Up-cycling fashion design belonging to the sustainable design category. This study analyzed the material characteristics of each brand fashion product by selecting 21 domestic Up-cycling fashion brands. The product types manufactured by domestic Up-cycling fashion brands could be divided into fashion clothing, bag, and fashion accessories. The materials used for each item included special material, waste fiber, waste leather, waste paper, and others. In the results of analyzing the material characteristics into the external characteristics and internal characteristics, the external characteristics included the durability with less abrasiveness and deformation as well as a mixture with other different materials, while the internal characteristics included a story arousing consumers' empathy, and scarcity without the same design due to the limitation of material.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.867-878
• /
• 2021

In context awareness and user intention tasks, dataset construction is expensive because specific domain data are required. Although pretraining with a large corpus can effectively resolve the issue of lack of data, it ignores domain knowledge. Herein, we concentrate on data domain knowledge while addressing data scarcity and accordingly propose a multi-channel long short-term memory (LSTM). Because multi-channel LSTM integrates pretrained vectors such as task and general knowledge, it effectively prevents catastrophic forgetting between vectors of task and general knowledge to represent the context as a set of features. To evaluate the proposed model with reference to the baseline model, which is a single-channel LSTM, we performed two tasks: voice phishing with context awareness and movie review sentiment classification. The results verified that multi-channel LSTM outperforms single-channel LSTM in both tasks. We further experimented on different multi-channel LSTMs depending on the domain and data size of general knowledge in the model and confirmed that the effect of multi-channel LSTM integrating the two types of knowledge from downstream task data and raw data to overcome the lack of data.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.167-179
• /
• 2024

This study addresses the challenge of objectively evaluating the performance of early-stage startups amidst limited information and uncertainty. Focusing on companies selected by TIPS, a leading private sector-driven startup support policy in Korea, the research develops a new indicator to assess technological efficiency. By analyzing various input and output variables collected from Crunchbase and KIND (Korea Investor's Network for Disclosure System) databases, including technology use metrics, patents, and Crunchbase rankings, the study derives technological efficiency for TIPS-selected startups. A prediction model is then developed utilizing machine learning techniques such as Random Forest and boosting (XGBoost) to classify startups into efficiency percentiles (10th, 30th, and 50th). The results indicate that prediction accuracy improves with higher percentiles based on the technical efficiency index, providing valuable insights for evaluating and predicting startup performance in early markets characterized by information scarcity and uncertainty. Future research directions should focus on assessing growth potential and sustainability using the developed classification and prediction models, aiding investors in making data-driven investment decisions and contributing to the development of the early startup ecosystem.

• Korean Journal of Child Studies
• /
• v.29 no.4
• /
• pp.43-63
• /
• 2008

This study developed an experience-based economic education program and examined its effects on young children's economic concepts and purchasing behavior. Subjects were 60 5-year-old kindergarteners assigned to an experimental or a control group. Instruments for pre- and post-tests were the Economic Concept Task (Laney, 1995) and the Purchasing Behavior Task (Jang, 2004). Experimental group children participated in the economic education program for 5 weeks; control group children listened to economic stories. Differences between pre- and post-test in the experimental group showed that the economic education program was effective in development of concepts of scarcity, opportunity cost, resource/production, goods/services, and complements/substitutes. Children's purchasing behavior changed partially after application of the program.

• International Journal of Costume and Fashion
• /
• v.15 no.2
• /
• pp.49-62
• /
• 2015

The purpose of the study was to investigate jean consumption among middle-aged Korean women and the characteristics of consumers as potential jean consumers. The data were collected from the survey of 238 Korean women aged 45 to 64 years old. The respondents prefer outlet store to other retail outlets and wear jeans mainly for travel, grocery shopping, and outing. The main reason for not wearing jeans is body change, which leads to poor fit in abdomen and waist area. The sample was clustered into two groups based on interest in jeans: high-interest and low-interest group. From the examination of group differences, the high-interest group rated conformity/brand reputation, scarcity, and attractiveness of appearance significantly higher compared to the low-interest group among the five clothing benefits pursued. No difference was found in obesity and body satisfaction. Group differences were found in recent purchase, price, number of jeans owned, and frequency of wearing jeans. The results suggest the characteristics of the potential jean market among middle-aged women in Korea. Implications are discussed.

• Journal of the Korea Safety Management & Science
• /
• v.10 no.4
• /
• pp.309-314
• /
• 2008

Many studies on predicting and recommending information and products have been studying to meet customers' preference. Unnecessary information should be removed to satisfy customers' needs in massive information. The some information filtering methods to remove unnecessary information have been suggested but these methods have scarcity and scalability problems. Therefore, this paper explores a personalized recommendation system based on artificial neural network (ANN) to solve these problems. The insurance product recommendation is adapted as an example to demonstrate the proposed method. The proposed recommendation system is expected to recommended a suitable and personalized insurance products for customers' satisfaction.