스트리트 패션을 통한 인도네시아 무슬림 여성의 패션 디자인 특성 연구 : 서부 자바(West Java) 반둥시(Bandung City)를 중심으로

The purpose of this study is to analyze types of roles and fashion of the Chinese first ladies and provide basic data for fashion image-making of first ladies. As for the research methods, the concepts, role types, and fashion of the first ladies were considered by referring to the precedent studies and relevant literature. Then, the fashion images according to role types were analyzed by collecting the photos of Chinese first ladies from the period of the Republic of China until today. The results were as follows: First, when the roles of Chinese first ladies were categorized based on ceremonial, political, and policy roles, Zhuo Lin and Wang Yeping played a ceremonial role; Wang Guangmei, Liu Yongqing, and Peng Liyuan played a political role; and Soong Qingling, Soong Mayling, and Jiang Qing played a policy role while they were first ladies. While the first ladies of the Republic of China often wore classic Chinese styles like traditional qipao as well as western clothes which contained a western influence, the first ladies of the People's Republic of China wore more colorful clothes and more accessories in the later period, and also often wore clothes that combined traditional and western elements. Second, first ladies who played a ceremonial role showed mannish and classic images; those who played a political role showed elegant, classic, and diverse images according to T.P.O; and those who played a policy role showed feminine, modern, and mannish images. Fashion images of the first ladies varied according to the level of political involvement, the sociocultural background of China at that time, and their personality and preference.

Traditional fashion design relies on the designer's experience, and there are limitations in fashion trend analysis and user demand response. Combining the characteristics of fashion design with Deep Learning, this paper constructs a multi-module intelligent model integrating trend prediction, key point detection, and design generation. The results show that Convolutional Neural Networks are superior to other models in the task of trend prediction on two fashion image data sets. Back Propagation Neural Networks combined with Principal Component Analysis dimension reduction significantly improves the training efficiency and model generalization ability. The model proposed in this study improves the scientificity of fashion trend analysis and design decision-making. It also provides technical support for a personalized clothing customization system based on communication networks and intelligent terminals, which embodies the deep integration of Artificial Intelligence, fashion design, and information technology and has a good interdisciplinary application prospect.

: The "AI-Powered Virtual Try-On System for Fashion Designing" is an innovative solution aimed at transforming the fashion retail and design industry through advanced technologies such as artificial intelligence (AI), computer vision, deep learning, and augmented reality (AR). This platform enables customers and designers to digitally visualize garments on real-time human models, reducing dependency on physical trials and enhancing personalization. The system leverages body measurement extraction, 3D garment simulation, and generative AI to provide realistic fitting experiences. It significantly minimizes production costs, reduces return rates in online shopping, and improves customer satisfaction. With features such as personalized recommendations, real-time fabric simulation, and cross-platform accessibility, the system sets a new benchmark in virtual fashion innovation. The rapid growth of e-commerce and digital fashion has increased the demand for interactive and personalized shopping experiences. This paper/project proposes an AI-powered Virtual Try-On (VTO) system that enables users to visualize how garments would appear on them without physical trials. The system integrates advanced computer vision and deep learning techniques, including human body segmentation, pose estimation, and garment warping, to generate realistic try-on results. By leveraging state-of-the-art models such as CP-VTON and pose-guided networks, the proposed solution accurately aligns and overlays clothing items onto user images while preserving fabric details, body shape, and occlusions. Additional features such as size adjustment, color and pattern customization, and designer-oriented garment uploads enhance flexibility for both consumers and fashion designers. The system aims to reduce product return rates, improve customer satisfaction, and accelerate the design-to-market pipeline in the fashion industry. Keywords – AI in fashion, virtual try-on, computer vision, 3D garment simulation, augmented reality, generative AI, fashion design technology.

Fashion design is a challenging and complex process. Recent works on fashion generation and editing are all agnostic of the actual fashion design process, which limits their usage in practice. In this paper, we propose a novel hierarchical diffusion-based framework tailored for fashion design, coined as HieraFashDiff. Our model is designed to mimic the practical fashion design workflow, by unraveling the denosing process into two successive stages: 1) an ideation stage that generates design proposals given high-level concepts and 2) an iteration stage that continuously refines the proposals using low-level attributes. Our model supports fashion design generation and fine-grained local editing in a single framework. To train our model, we contribute a new dataset of full-body fashion images annotated with hierarchical text descriptions. Extensive evaluations show that, as compared to prior approaches, our method can generate fashion designs and edited results with higher fidelity and better prompt adherence, showing its promising potential to augment the practical fashion design workflow.

Big cities in Indonesia, including in West Java, such as Bandung, are attractive markets for both national and international drug dealers and dealers. With the condition of the rapid growth and development of drug distribution in the city of Bandung, including on campuses today, campuses are competing to create and carry out drug prevention and eradication programs, with the aim of cleaning campuses from the influence of psychotropic substances. Of course, this spirit will be carried out with a handling that combines all the potential of both the BNN, the campus/ARTIPENA, the Central and Regional Government, the Media, the Ministry of Defense, Advocates/PERADI, the police and NGOs such as GRANATE by jointly coordinating and develop strategies in the prevention and treatment of drug addicts both physically and psychologically, what is the most appropriate strategy in realizing a drug-free campus on campuses in the city of Bandung. Eradicating drugs is not an easy thing, it is important but requires the cooperation of many parties synergistically which is then referred to as the pentahelix synergy. The goals to be achieved include: Describing the motives of the pentahelix synergy phenomenon through online media in realizing a clean drug campus in Bandung City, Identifying Actions for the pentahelix synergy phenomenon through online media in realizing a clean drug campus in Bandung City, Identifying the Meaning of the pentahelix synergy phenomenon through social media in realizing a clean campus for drugs in the city of Bandung. The research method used is a qualitative method with a phenomenological research approach from Alfred Schutz. This study will identify what are the phenomena in the handling of drug eradication on campuses in the city of Bandung. The results of the research and discussion in this study are to produce five categories of pentahelix synergy so that the realization of a drug-free campus in the city of Bandung is as follows: Law Enforcement / Tightening of Rules, Soft skills / training on motivation, Spiritual Touch / using Islamic boarding school education or mentoring, Having a Fun Approach / Social Approach and Persuasion Through Social Media.

This purpose of this study is to analyze the pursuit of current fashion trends and fashion image types of middle-aged women in Korea. This study attempted to investigate the standards and properties of these different types of fashion images. The overall characteristics of middle-aged women and the concepts of personal image and fashion image were investigated through literature research. Survey and analysis based on Q methodology was conducted. Factors of personal image, fashion image and components of fashion image were analyzed by collecting information from in-depth workshops and focus group interview of an expert group. The results of this study are as follows: 1) The main factors influencing the current fashion image of women in their forties and fifties in Korea are classified into six types. 2) The elements of fashion image that Korean women in their 40s and 50s pursue are divide into four types. 3) Each type can be recognized by specific fashion image components and colors. 4) This shows that middle-aged Korean women are highly conscious of how others perceive them and have a desire to not stand out from others. It also shows that they are very active in pursuing fashion and following trends, which is the image of an active and dignified woman. This study provides the framework that enables sorting of the fashion images types that middle-aged Korean women want to pursue. The results from analyzing the factors can be used to recognize specific fashion images, and can be used in the planning and designing of fashion items for middle-aged Korean women.

The deep convolutional generative adversarial network (DCGAN) model can be applied to personalized fashion design. Determining the best design from fashion sketches that is of interest to customers is an important research field. In this study, we propose a rapid evaluation method based on Kansei engineering to evaluate personalized fashion images generated by DCGAN. The degree of customer interest in the generated fashion images is determined by tracking the eye movements and facial expressions of customers. Images with high number of fixations are added to the training data for iterative training; this aims to improving customer satisfaction. The method was verified in an interaction design of personalized black dresses. After several iterations, the customers’ satisfaction rating of the generated images by DCGAN improved. This method can be applied to other styles of fashion design.

Before the start of every season, fashion forecasting companies predict upcoming fashion colors. They cater to modern consumers, who are very sensitive to fashion trends. Therefore, to satisfy the trendy consumer with a fashion product, the fashion design must first be found, since image matters. Then the design must be followed by an analysis of each design element's effect on the total image composition. Previous studies of fashion image have found a significant correlation between fashion design elements and the fashion image. The effects of each element were studied, but few studies dealt with compound elements. In this thesis, two fashion design elements, color and fabric, are simultaneously considered to classify the fabric image. For color variables, 10 hues were selected from Munsell system of color notation, and 12 tones currently used in the domestic fashion industry were selected from PCCS color notation. Texture variables used in this survey were classified by luster, prominence‐depression of surface, thickness, and density of fabric. Graduate students ranging from 20‐ to 50 years old and specialists in fashion companies participated in the survey. The results of this survey show that: 1) Fashion fabric image is classified into 5 main descriptive image categories: ‘elegant,’ ‘comfortable,’ ‘characteristic,’ ‘light’ and ‘simple.’ 2) The influence of hue, tone, and texture are significant in fashion fabric image. Colors, such as yellow‐red and red hues, and light grayish and dark grayish tones convey an elegant image. The texture property for an elegant image is luster‐thin fabric of low density. Properties of fabric conveying a comfortable image are yellow‐red and green‐yellow hues, softness, light tones, matte finish, and high density. Hue, however, turned out to be an insignificant variable for a unique image, whereas dark grays, grayish tones, luster and prominent texture conveyed a unique image. For the light image, fabric properties are blue‐green and purple hues, light and bright tones, and thin, low‐density textures. Properties of fabric conveying a simple image are blue‐green, purple‐blue, green‐yellow hues, and strong, vivid tones, with luster and flat texture. © 2003 Wiley Periodicals, Inc. Col Res Appl, 28, 221–226, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.10147

This study derives evaluation terms by analyzing the semantic relationship between design elements and sentiment terms in regards to fashion design. As for research methods, a total of 38,225 texts from Daum and Naver Blogs from November 2015 to October 2016 were collected to analyze the parts, frequency, centrality and semantic networks of the terms. As a result, design elements were derived in the form of a noun while fashion image and user''s emotional responses were derived in the form of adjectives. The study selected 15 noun terms and 52 adjective terms as evaluation terms for men''s striped shirts. The results of semantic network analysis also showed that the main contents of the users of men''s striped shirts were derived as characteristics of expression, daily wear, formation, and function. In addition, design elements such as pattern, color, coordination, style, and fit were classified with evaluation results such as wide, bright, trendy, casual, and slim.

Automatic understanding of the product images, particularly the image attributes such as pattern, color, category, material, department, etc., has become a prerequisite for many downstream applications in the e-commerce ecosystem such as visually similar product retrieval and recommendation, publisher website image content monetization. With the recent advancement of deep learning techniques, multi-task deep neural networks (MTDNN) have been widely adopted for multi-class multi-label fashion image classification tasks. In this work, we propose a training technique Multi-Task Generative Adversarial Network (MT-GAN) to improve fashion image classification performance with an additional image translation task. We evaluated the proposed technique on two real-world fashion image datasets and experimental results show that both image classification and image translation benefit from this joint training setting. Specifically the image classifier, even though trained with a smaller amount of data and fewer types of labeled information, manages to outperform existing image classification models such as WTBI and DARN by 54% and 20% respectively for category classification on DeepFashion benchmark. Two main contributors to the superior performance of the image classifier trained as the discriminator in the proposed MT-GAN framework are: 1) the classifier leverages additional amount of data and the regularization effect by taking on the task of a traditional discriminator. 2) The classifier takes not only the RGB image but also the conditional input image shared between the generator and itself as its input, boosting the classification accuracy and recall by 18%. The proposed MT-GAN training technique is GAN-agnostic and can be applied to various state-of-the-art designs of generator and discriminator as well.

This research aims to investigate the impact of customer trust and commitment on the purchase intentions of consumers regarding electronic products in Bandung, West Java. The respondents for this study consisted of 100 consumers of electronic products in the city of Bandung, West Java, selected through convenience sampling. The analytical model employed in this research is multiple linear regression. The findings of the regression analysis reveal a positive influence of both trust and commitment on the purchase intentions of consumers of electronic products in the city of Bandung, West Java. Moreover, it is observed that both trust and commitment significantly contribute to purchase intentions individually, with a significance level of α= 0.05.

Bulan Imunisasi Anak Nasional or BIAN is an Health Ministry of Republic Indonesia program that aims to enhance the children’s health by immunize them with a mass Complete Immunization and Follow-Up Immunization in Indonesia especially for the children that did not have immunize yet since the pandemic in 2020. Bandung City which is included in West Java Province has the lowest coverage of BIAN Immunization among the other City/Districts in West Java. This research is aimed to figure out what factors affected the low coverage of BIAN Immunization in Bandung City and analyze the situation regarding the field report in the implementation phase and how to solve it by applying better strategies in upcoming BIAN events. The analysis that was conducted are External and Internal Analysis to find what factors that related to the issue. In the External Analysis, the author uses Customer Analysis, Stakeholder Analysis, and PESTEL Analysis to indicate any external factors that affected the low coverage of BIAN Immunization. In the Internal Analysis, the author uses Tangible Analysis, Intangible Analysis, and Interview Data from stakeholders that hold the event. There are several findings in External and Internal Analysis especially in Advertisement and Public Relation became the strong factor that affected the main issue because of low awareness of the target audience. From several analyses and the findings, there are four proposed strategies to increase the awareness of the target audience to participate in the event to enhance the coverage of the immunization in Bandung City. The first one is improvement in Public Relation strategy that needs to be more organized and comprehensive especially with external parties. The second strategy is improvement in Advertisement strategy, especially in social media activation and Advocacy Advertisement. The third strategy is collaboration with brands that have a strong family image in the health sector. The fourth strategy is initiation in having Key Opinion (KOL) as the face of BIAN in Bandung City. In academic recommendation, the next author should consider the current situation of the target audience especially in their awareness towards the event and the current coverage of the immunization.

Abstract.As one of the best online shopping platforms in Indonesia, Shopee can maintain its position in intense competition, through the phenomenon of online information dissemination and the important role of websites for online shopping platforms. This study was conducted to analyze the effect of website quality and electronic word of mouth (e-WOM) on the purchase intention of Shopee consumers in the City of Bandung, West Java. The research method used is a quantitative approach. The data collection technique was carried out through a questionnaire distributed to Shopee consumers. The research sample consisted of 100 respondents who were active Shopee consumers in the City of Bandung. The collected data were analyzed using multiple linear regression analysis techniques to determine the effect of the independent variable on the dependent variable. The results showed that website quality and e-WOM had a positive and significant influence on purchase intention with a contribution of 68.5%. Partially, website quality has an effect of 53,1%, while e-WOM has an effect of 56,3% on purchase intention. These findings emphasize the importance of continuous improvement in website quality and e-WOM strategies to increase consumer purchase intention. Abstrak. Sebagai salah satu platform belanja online terbaik di Indonesia Shopee mampu mempertahankan posisinya di tengah persaingan yang ketat, melalui fenomena penyebaran informasi secara online dan peran penting website bagi platform belanja online. Penelitian ini dilakukan untuk menganalisis pengaruh kualitas website dan electronic word of mouth (e-WOM) terhadap purchase intention konsumen Shopee di Kota Bandung, jawa barat. Metode penelitian yang digunakan adalah pendekatan kuantitatif. Teknik pengumpulan data dilakukan melalui kuesioner yang dibagikan kepada konsumen Shopee. Sampel penelitian terdiri dari 100 responden yang merupakan konsumen aktif Shopee di Kota Bandung. Data yang terkumpul dianalisis menggunakan teknik analisis regresi linier berganda untuk mengetahui pengaruh variabel independen terhadap variabel dependen. Hasil penelitian menunjukkan bahwa kualitas website dan e-WOM memiliki pengaruh positif dan signifikan terhadap purchase intention dengan kontribusi sebesar 68,5%. Secara parsial, kualitas website memberikan pengaruh sebesar 53,1%, sementara e-WOM memberikan pengaruh sebesar 56,3% terhadap purchase intention. Temuan ini menekankan pentingnya perbaikan berkelanjutan dalam kualitas website dan strategi e-WOM untuk meningkatkan minat beli konsumen. Dengan meningkatkan kualitas interaksi layanan di website dan memanfaatkan e-WOM secara efektif, Shopee dapat memperkuat posisi mereka dalam persaingan pasar e-commerce yang ketat ini

Dengue hemorrhagic fever (DHF) is a health problem in Indonesia. The region in Indonesia that has the highest number of cases in West Java with the highest ranking with 10,772 cases. The city of Bandung is recorded to have the highest number of cases at this time, namely 4,424 cases. Dengue fever can be caused by high rainfall. Judging from the high number of cases and fluctuations that occur, it is necessary to predict the spread of the disease so that in the future it can be anticipated by the government. Prediction of the spread of dengue fever in the city of Bandung using various classification algorithms has been done. Therefore, the author wants to make a new breakthrough by using hybrid ensemble learning using a hard voting method from three classification methods, namely Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Decision Tree (DT). Using the Bandung City DHF disease dataset from 2012 to 2018. The results obtained using the Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Decision Tree (DT) were 84%, 87%, 79%. to improve the classification accuracy of the three methods using a hybrid classification with the hard voting method to get 91% results.

This PPM activity aimed to provide literacy through socialization and direction regarding the use of various online media to culinary MSME actors in the district and city of Bandung, West Java in an effort to increase product sales in the midst of the Covid-19 pandemic and during the recovery period from pandemic conditions. The decline in economic levels in various sectors was one of the most serious impacts of the COVID-19 pandemic, as experienced by culinary MSME entrepreneurs in Indonesia, including culinary MSME entrepreneurs in the district and city of Bandung. The decline in sales levels for culinary MSME business actors had resulted in a decline in income and welfare levels. The presence of online media as a technology that could help and facilitate culinary MSME business actors as a strategy to carry out promotions with the aim of increasing sales in the midst and the recovery period of the Covid-19 pandemic. The method in this PPM activity was through literacy for culinary MSMEs through socialization activities, briefings, and sharing pamphlets. This PPM activity was expected to produce output to provide solutions for culinary MSME actors to be able to increase sales of their products through the use of online media in the midst and the recovery period of the Covid-19 pandemic. From this PPM activity, it is suggested that culinary MSMEs be more active in participating in activities such as workshops or training to improve their ability to do business digitally or online.