• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.1
• /
• pp.165-181
• /
• 2022

The fashion industry is creating innovative business models using artificial intelligence. To efficiently utilize artificial intelligence (AI), fashion data must be classified. Until now, such data have been classified focusing only on the objective properties of fashion products. Their subjective attributes, such as fashion brand sensibilities, are holistic and heuristic intuitions created by a combination of design elements. This study aims to improve the performance of collaborative filtering in the fashion industry by extracting fashion brand sensibility using computer vision technology. The image data set of fashion brand sensibility consists of high-end fashion brand photos that share sensibilities and communicate well in fashion. About 26,000 fashion photos of 11 high-end fashion brand sensibility labels have been collected from the 16FW to 21SS runway and 50 years of US Vogue magazines beginning from 1971. We use EfficientNet-B1 to establish the main architecture and fine-tune the network with ImageNet-ILSVRC. After training fashion brand sensibilities through deep learning, the proposed model achieved an F-1 score of 74% on accuracy tests. Furthermore, as a result of comparing AI machine and human experts, the proposed model is expected to be expanded to mass fashion brands.

• The Research Journal of the Costume Culture
• /
• v.31 no.5
• /
• pp.651-668
• /
• 2023

This study aims to help companies with efficient investment and marketing strategies by empirically verifying the impact on satisfaction and purchase intention for artificial intelligence-based digital technology supported shopping assistants introduced in e-commerce. Frequency, factor, SEM, and multiple group analysises were conducted using SPSS 26.0 and Amos 26.0. As a result, first, motivated consumer innovativeness elements of AI shopping assistant were derived into a total of four categories: functional, hedonic, rational, and reliable. Second, in the order of hedonic and rational, satisfaction with the AI shopping assistant was significantly affected, and in the order of rational and functional, purchase intention was significantly affected. The satisfaction with the AI shopping assistant did not affect the purchase intention. Third, in the case of hedonic, the AI-preferred group had a more significant effect on satisfaction than the human-preferred group, and in the case of rational, there was no difference by group in purchase intention. Thus, it was found that consumers prefer AI shopping helpers for e-commerce because they can shop reasonably and are functionally convenient. Therefore, when introducing AI shopping assistants, it is essential to include content that can compare and analyze fundamental information, such as product prices, as well as search functions and payment system compatibility that facilitate shopping.

• Journal of Fashion Business
• /
• v.27 no.5
• /
• pp.60-77
• /
• 2023

The scale of the industry utilizing the Metaverse platform is gradually growing around the world. Fashion brands are also starting to utilize the Metaverse platform as a new market to replace the next e-commerce platform by targeting new consumers, MZ generation, and even Alpha generation. In this study, a real K-fashion designer's outfit was made into a 3D outfit using CLO 3D program to express it in a new market, the Metaverse 3D platform. It was then compared with a real outfit. An avatar prototype was completed using Max program to simulate the 3D digital fashion outfit and produce an avatar through an optimization process. The 3D outfits showed the same level of results as the actual outfits in terms of fabric surface, material texture, drapability, overall outfit, details, and trimmings. In addition, we proposed a 2D work on total styling suggestion and modeling to secure data sets for future AI-based styling services. In conclusion, this study revealed that actual outfits and 3D outfits had the same results. It is significant that it can be a sample work to build a styling data set through styling suggestion and content production as a significant amount of styling DB construction will be required before AI styling automation services.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.138-147
• /
• 2022

Recently, chatbots have been applied in various fields and have shown good results, and many attempts to use chatbots in shopping mall product recommendation services are being conducted on e-commerce platforms. In this paper, for a conversation system that recommends a fashion that a user wants based on conversation between the user and the system and fashion image information, a transformer model that is currently performing well in various AI fields such as natural language processing, voice recognition, and image recognition. We propose a multimodal-based improved transformer model that is improved to increase the accuracy of recommendation by using dialogue (text) and fashion (image) information together for data preprocessing and data representation. We also propose a method to improve accuracy through data improvement by analyzing the data. The proposed system has a recommendation accuracy score of 0.6563 WKT (Weighted Kendall's tau), which significantly improved the existing system's 0.3372 WKT by 0.3191 WKT or more.

• 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.

• Fashion & Textile Research Journal
• /
• v.21 no.5
• /
• pp.640-655
• /
• 2019

Technology status was investigated by analyzing patents and development cases of wearable robots. Development direction of wearable robot for wearability was also suggested by understanding the problems of wearability from development cases through the FGI technique. The number of patents per technical field was the most in the field of strength support, but AI in the technology field was different in each country; Korea was found to be poor in the category of daily living assistance. The number of patents by technology category was the most in the category of muscular strength assistance. However, the values of AI in the technology category were different in each country; Korea was found to be poor in the category of daily living assistance. Development cases were focused on rehabilitation, so development is not fulfilled uniformly by use purpose. By wearing body parts, robots with single function type were mainly developed. Rigid material robots were mainly developed. It was confirmed that wearable robot technology is not developed evenly in the category of application because it is in the early stage of the technical proposal and centered on main performance improvement. We derived twelve wearable conditions for wearable robots: Shape and Size Appropriateness, Movement Appropriateness, Composition Appropriateness, Physiological Appropriateness, Performance Satisfaction, Ease of Operation, Safety, Durability, Ease of Dressing, Ease of Cleaning, Portability and Ease of Storage and Appearance Satisfaction. Finally, the development direction of a wearable robot for each wearable condition was suggested.

• Journal of Information Technology Services
• /
• v.23 no.2
• /
• pp.63-81
• /
• 2024

With the advancement of Information and Communication Technologies (ICT) and Artificial Intelligence (AI), the metaverse has emerged as a transformative model across various sectors, offering a three-dimensional virtual world where activities mirroring the real world occur. This study delves into the significant factors influencing fashion brand companies' investments in the metaverse, an evolved concept from Virtual Reality (VR) that extends beyond gaming to include real-life activities through avatars. This study highlights the surge in virtual fashion engagements, as evidenced by increased avatar updates and purchases of digital fashion items on platforms like Roblox. Luxury brands are steadily entering the metaverse indicating a new revenue stream within the fashion industry. This study employs a mixed-methods approach, integrating text mining and interviews to identify key factors for fashion companies considering metaverse investments. By proposing strategies based on these findings, this study not only enriches academic discourse in fashion, e-commerce, and information systems but also serves as a guideline for fashion companies aiming to navigate the burgeoning digital market, contributing to the generation of new revenue streams in the fashion sector.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.308-315
• /
• 2023

Russia invaded Ukraine in February 2022. Many military experts predicted that Russia could defeat Ukraine within a week, but the Ukraine-Russia War has not been going as expected. Indeed, Ukraine military has been defending well and seems to fight more efficiently than Russian military. There are many reasons for this unexpected situation and one apparent thing is due to artificial intelligence (AI) technologies. This study focused on AI-enabled combats that the Armed Forces of Ukraine has carried out around Siverskyi Donets River, the Crimean Peninsula, and suburbs of Kyiv. For more systematic analysis, the revolution in military affairs (RMA) theory was applied. There are four significant implications inferred by studying current Ukraine-Russia War. First, AI technologies are effective even in the current status and seems to be more influential. Second, hyper-connected network by satellite communications must be needed to enhance the AI weapon effects. Third, military AI technologies should be based on the civil-military cooperation to keep up with pace of technological innovation. Fourth, AI ethics in military should be seriously considered and established in the use of AI technologies. We expect that this study could help ROK Armed Forces to be modernized in the revolutionary fashion, especially for manned and unmanned teaming (MUM-T) system.

• Fashion & Textile Research Journal
• /
• v.25 no.5
• /
• pp.549-559
• /
• 2023

Along with the transition to the fourth industrial revolution, the possibility of metaverse-based innovation in the fashion field has been confirmed, and various applications are being sought. Therefore, this study performs meaning structure analysis and discusses the prospects of meta fashion using big data. From 2020 to 2022, data including the keyword "metaverse + fashion design" were collected from portal sites (Naver, Daum, and Google), and the results of keyword frequency, N-gram, and TF-IDF analyses were derived using text mining. Furthermore, network visualization and CONCOR analysis were performed using Ucinet 6 to understand the interconnected structure between keywords and their essential meanings. The results were as follows: The main keywords appeared in the following order: fashion, metaverse, design, 3D, platform, apparel, and virtual. In the N-gram analysis, the density between fashion and metaverse words was high, and in the TF-IDF analysis results, the importance of content- and technology-related words such as 3D, apparel, platform, NFT, education, AI, avatar, MCM, and meta-fashion was confirmed. Through network visualization and CONCOR analysis using Ucinet 6, three cluster results were derived from the top emerging words: "metaverse fashion design and industry," "metaverse fashion design and education," and "metaverse fashion design platform." CONCOR analysis was also used to derive differentiated analysis results for middle and lower words. The results of this study provide useful information to strengthen competitiveness in the field of metaverse fashion design.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.637-642
• /
• 2020

패션산업은 매년 1 조원씩 성장(연평균 2.1%)하며 많은 연구자들의 관심을 받고 있다. 전통적인 패션산업은 점차 디지털화되어 선진적인 컴퓨터 비전 기술을 적용해 소비자들에게 더 좋은 쇼핑 서비스를 제공하고 있다. 본 논문에서는 2014 년부터 2019 년 사이에 구축된 대표적인 패션 데이터셋을 연도별로 정리하고 각 데이터셋에 포함된 주석(annotation)의 특징을 정리했다. 또한 데이터셋이 패션 상품 검출(Fashion detection), 패션 이미지 생성(Fashion image generation), 가상 피팅(Virtual try-on) 그리고 패션 의류 분할(Fashion Clothing segmentation) 등 연구에서의 활용될 수 있는 여부에 대해 분석했다.