• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.770-781
• /
• 2022

Korea's aging population is rapidly increasing, but there has been little research into senior-friendly foods. Therefore, this study aimed to provide basic data for the development of senior-friendly Home Meal Replacement(HMR) foods by conducting a survey among elderly and middle-aged persons highly likely to purchase senior-friendly foods in the near future. Study findings showed that the level of HMR purchase was higher among the middle-aged, many subjects preferred products requiring simple cooking, and a higher proportion of subjects purchased them offline. Five HMR selection attributes were identified, and dietary lifestyles were classified into four categories. Through a cluster analysis, 3 groups based on level of involvement were identified: high-level, mid-level, and low-level. Napping^® analysis showed that subjects classified food products into HMR and meal kits, and into products with a clear broth and products with a thicker broth. The study findings are expected to help suggest a differentiating approach in developing senior-friendly HMR foods.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.383-388
• /
• 2022

This study is about the elements of cosmetic's package design which MZ generation prefer and the effect on purchase. Naming, brand logo, color, typography, layout, illustration, matter & finish, and meaningful are classified 8 visual elements through the pilot study. After that this study analyzes specific visual elements which MZ generation prefer through online survey and In-depth interview based on the 8 visual elements. As a result of study, MZ generation prefer tidy and neat design to decorated style, and they feel brand logo is the most important thing of all 8 visual elements. In additional, meaningful of brand is barley able to compare with price, although it is significant visual element. This study may help to develop the way of the cosmetic's package design for MZ generation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.1-8
• /
• 2022

Recently, Google MedeiaPipe presents a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Though neural network related to hair segmentation is relatively small size, it produces a high-quality hair segmentation mask that is well suited for AR effects such as a realistic hair recoloring. However, it has undesirable segmentation effects according to hair styles or in case of containing noises and holes. In this study, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood function. It is further optimized according to graph cuts algorithm and initial hair region is obtained. Finally, clustering algorithm and image post-processing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. The proposed method is applied to MediaPipe hair segmentation pipeline.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.2-5
• /
• 2022

With the advent of deep learning and the rapid development of ICT (Information and Communication Technology), research using artificial intelligence is being actively conducted in various fields of society such as politics, economy, and culture and so on. Deep learning-based artificial intelligence technology is subdivided into various domains such as natural language processing, image processing, speech processing, and recommendation system. In particular, as the industry is advanced, the need for a recommendation system that analyzes market trends and individual characteristics and recommends them to consumers is increasingly required. In line with these technological developments, this paper extracts and classifies attribute information from structured or unstructured text and image big data through deep learning-based technology development of 'language processing intelligence' and 'image processing intelligence', and We propose an artificial intelligence-based 'customized fashion advisor' service integration system that analyzes trends and new materials, discovers 'market-consumer' insights through consumer taste analysis, and can recommend style, virtual fitting, and design support.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• Culinary science and hospitality research
• /
• v.16 no.3
• /
• pp.14-31
• /
• 2010

Lifestyle has the largest influence on purchasing intention. Currently, consumers have to be adjusted to dynamic environmental change, therefore they are demanding more and more on bakery items and functional food products. It is important to understand the trend of customers' eating habits and the effect of this trend on purchasing intention as well as the development of special characteristics in purchase, viewpoints, and behaviors. Based on this fact, this study was conducted to classify the types of lifestyle according to the consumer's behavior and to examine how the variety and quality of bakery products affect consumer's purchasing pattern. The subjects of this survey were housewives in thirties and forties at the national capital region. AIO(activities, interests, opinions) analysis was used to classify lifestyle and to investigate the effect or relationship between lifestyle, variety and quality of bakery products. Lifestyle was classified into the pursuit of rationality, the pursuit of utility and the pursuit of convenience. The information was the most concerning area in the pursuit of rationality, the taste in the pursuit of utility, and convenience in the pursuit of convenience. The purchasing intention was not affected by the quality of the bakery product itself but by the satisfaction with the service of the bakery.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1682-1688
• /
• 2008

The Counterpropagation algorithm(CP) is a combination of Kohonen competition network as a hidden layer and the outstar structure of Grossberg as an output layer. CP has been used in many real applications for pattern matching, classification, data compression and statistical analysis since its learning speed is faster than other network models. However, due to the Kohonen layer's winner-takes-all strategy, it often causes instable learning and/or incorrect pattern classification when patterns are relatively diverse. Also, it is often criticized by the sensitivity of performance on the learning rate. In this paper, we propose an enhanced CP that has multiple Kohonen layers and dynamic controlling facility of learning rate using the frequency of winner neurons and the difference between input vector and the representative of winner neurons for stable learning and momentum learning for controlling weights of output links. A real world application experiment - pattern recognition from passport information - is designed for the performance evaluation of this enhanced CP and it shows that our proposed algorithm improves the conventional CP in learning and recognition performance.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.35 no.2
• /
• pp.65-84
• /
• 2024

As the number of Instagram users continues to grow, an increasing number of public libraries are establishing and maintaining accounts on the Instagram platform. The objective of this study is to classify and analyze the content of Instagram posts from 14 public libraries that are actively engaged on the platform. A classification of post types, divided into seven large, 16 medium, and 76 small categories, was employed to analyze the content of posts on each library's Instagram account from the account's inception to the end of December 2023. The analysis revealed that library posts focused on a few items, including book recommendations, library introductions and news, and event announcements of literary and arts programs. Program event announcements and reviews, book recommendations and reading programs were found to be highly correlated with user engagement and teen reading programs. Based on these findings, it is recommended that future Instagram posts should be more user-centered and interactive, and that libraries should actively promote their events on Instagram and other social media platforms.

• Journal of Fashion Business
• /
• v.11 no.4
• /
• pp.183-203
• /
• 2007

This study aims at providing useful fundamental information to re-establish the theories of modern fashion by examining the origination and genealogy of street style. The street styles focusing on caucasoid have a variety of genealogies such as western type, beat, teddy boy, hippie, skinhead, punk, neuron-mantic, indie kid, riot grrrl, grunge and techno cyber punk. In the same period, on the contrary, the streets styles focusing on negroid are zootie, hipster, modernist, rude boy, two-tone, rastafarian, funky, B-boy, fly girl, raggamuffine, bhangra, and acid jazz, which are seen as the culture of the large cities formed along Atlantic Ocean and Caribbean sea like England, America and Jamaica. These have root as the main fashion in western society. Ironically, most of the subculture concentrated on the whites were racists. Because of such a reason, the street styles have been formed as resistance culture that was unable to sympathize with their society and characteristics by distinguishing the whites and the colored people. Zootie or hipster that is one of the street fashion styles was formed in the 1940-50s, while the colored people who lived in the west Indies migrated to England or America. As a minimal modernist style called Ivy look in US, in that time, anti-culture formed by teenagers in whitey, teddy boy and mods fashion can be strictly different from the zootie and hipster. The colored people's street styles of the 1960s developed into aggressive and hard forms from the rude boy and two-tone while their resistance toward the whites was stronger. The rastafarian style researched the peak as the colored people's traditional ethnic characteristics or resistance intention for their freedom in the 1970s. In that time, The colored people's street styles of the 1960s developed into aggressive and hard forms from the rude boy and two-tone while their resistance toward the whites was stronger. The rastafarian style researched the peak as the colored people's traditional ethnic characteristics or resistance intention for their freedom in the 1970s. In that time, the street styles of the whites were mostly the skinhead or hippie. Most of them were racists toward the colored people. The punk type on shown on the whites focused on luxury and exaggerative costume. On the contrary, the funky style of the colored people focused on aggressive nihilism and form. With B-boy, fly girl, reggae, rap music, and break dancing in the 1980s, the subculture gradually told on the high fashion as well as the culture between the whites and the colored people. From such aspects, the colored people tried to maintain their unique traditional characteristics. However, their individual values surged by the coming young generation excluded the colored people's characteristic street styles. Focusing on gender, violence and private success among their major concerns, the raga muffin style that represents multi-races and multi-cultures was formed. The jazz style in the 1990s showed cold post-modernistic eclecticism different from that of the 1940s-50s. Simultaneously, the various classes appeared their street styles by emphasizing on each personality. Now that we are living in multi-cultural society, a human race or nationalism concept is getting obscurer. There is no obvious boundary line in the differences between human race and its fashion.

• The Journal of Korean Philosophical History
• /
• no.25
• /
• pp.381-410
• /
• 2009

It is a very important book about painting theory, that "Xuanhehuapu"(宣和畵譜) was wrote by Emperor Huizhong(徽宗) in Song Dynasty. Fundamental discussions and studies in the relation of socio-economical base in Song Dynasty are still more needed. And accordingly, it is necessary to advent upgraded aesthetical articles. Li xue(理?) deeply influenced upon paintings and its theories in Song Dynasty. Similarly, Taoism(道家) and Zen Buddhism(?宗) also did. But some people who have not found "Xuanhehuapu" important meaning and rich and complicated aesthetic thought, gave low and even negative valuation to it. There is rich aesthetic in "Xuanhehuapu", which is not as simple and narrow as some people imagined. It was deeply influenced by the aesthetic thought of Confucianism(Lixue 理學), Taoism(Zhuangzi 莊子) and "Zhouyi"({周易}). I will be analytical in a few aspects "Xuanhehuapu" of aesthetics thought. 1. The calligraphy and painting is one flesh. 2. learn a good lesson from painting. 3. The handicrafts(Art, 藝) and Tao(道) unify. 4. It is a Art taxology. 5. It use a new art criticism methods.