• Journal of Practical Engineering Education
• /
• v.11 no.2
• /
• pp.175-180
• /
• 2019

Existing fashion web sites show only the search results for one type of clothes in items such as tops and bottoms. As the fashion market grows, consumers are demanding a platform to find a variety of fashion information. To solve this problem, we devised the idea of linking image classification through deep learning with a website and integrating SNS functions. User uploads their own image to the web site and uses the deep learning server to identify, classify and store the image's characteristics. Users can use the stored information to search for the images in various combinations. In addition, communication between users can be actively performed through the SNS function. Through this, the plan to solve the problem of existing fashion-related sites was prepared.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.517-524
• /
• 2024

This study aims to train and implement a deep learning model for the fusion of website creation and artificial intelligence, in the era known as the AI revolution following the launch of the ChatGPT service. The deep learning model was trained using 3,000 collected web page images, processed based on a system of component and layout classification. This process was divided into three stages. First, prior research on AI models was reviewed to select the most appropriate algorithm for the model we intended to implement. Second, suitable web page and paragraph images were collected, categorized, and processed. Third, the deep learning model was trained, and a serving interface was integrated to verify the actual outcomes of the model. This implemented model will be used to detect multiple paragraphs on a web page, analyzing the number of lines, elements, and features in each paragraph, and deriving meaningful data based on the classification system. This process is expected to evolve, enabling more precise analysis of web pages. Furthermore, it is anticipated that the development of precise analysis techniques will lay the groundwork for research into AI's capability to automatically generate perfect web pages.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2013.08a
• /
• pp.175-178
• /
• 2013

웹의 발달과 전자정부의 지향으로, 행정기관의 웹사이트를 통한 민원처리가 증가하고 있다. 게시판을 통해 이용자가 민원을 제기하면, 각 기관에서는 담당자를 배정해 처리하지만 해당 게시물을 공기록으로 보존하지는 않는다. 공공사이트를 통한 투명한 행정을 위해서는 게시물도 공기록물로 보존하는 체계가 마련될 필요가 있다. 이를 위해, 정부기능연계모델(BRM)을 기준으로, 공공사이트의 게시글을 자동으로 분류하는 시스템을 구현하였다.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.443-451
• /
• 2021

The classification standards for hotels in Vietnam are different from many other hotel classification standards in the world. This study aims to analyze customer reviews on the TripAdvisor website to develop a new algorithm for hotel rating that is independent of Vietnam's hotel classification standards. This method can be applied to individual hotels, or hotels of a region or the whole country, while online booking sites only rate individual hotels. Data was crawled from TripAdvisor with 22,287 reviews of 5 cities in Vietnam. This study used a statistical model to analyze the review dataset and build an algorithm to rate hotels according to aspects or hotel overall. The results have less rating deviation when compared to the TripAdvisor system. This study also supports hotel managers to regularly update the status of their hotels using data from customer reviews, from which, managers can strategize long-term solutions to improve the quality of the hotel in all aspects and attract more travelers to Vietnam. Moreover, this method can be developed into an automatic system to rate hotels and update the status of service quality more quickly, thus, saving time and costs.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.71-76
• /
• 2021

Education is one of the pillars of sustainable development. For this reason, the discovery of useful information in its process of adaptation to new challenges is treated with care. This paper aims to present the initiation of a process of exploring the data collected from the results obtained by Romanian students at the BBaccalaureate (the Romanian high school graduation) exam, through data mining methods, in order to try an in-depth analysis to find and remedy some of the causes that lead to unsatisfactory results. Specifically, a set of public data was collected from the website of the Ministry of Education, on which several classification methods were tested in order to find the most efficient modeling algorithm. It is the first time that this type of data is subjected to such interests.

• Korean Journal of Community Nutrition
• /
• v.21 no.5
• /
• pp.440-450
• /
• 2016

Objectives: We previously developed a dish-based semi-quantitative food frequency questionnaire (FFQ) for Korean adolescents and reported that it had reasonable reliability and validity. The objective of the current study was to construct a web-based dietary evaluation system applying the FFQ for Korean adolescents and examine its applicability in the context of reliability and validity. Methods: A web-based food frequency questionnaire system was designed using a comprehensive approach, incorporating not only dietary data survey but also up-to-date nutrition information and individualized eating behavior guidelines. A convenience sample of 50 boys and girls aged 12~18 years agreed to participate in the study and completed the FFQ twice and 3 days of dietary recall on the developed website during a two-month period. The FFQ's reliability and validity was examined using correlation and cross classification analysis. We also measured participants' subjective levels of the web site's usability, visual effect, understanding, and familiarity. Results: Spearman correlation coefficients for reliability ranged from 0.74 (for vitamin A) to 0.94 (for energy). From cross-classification analyses, the proportion of subjects in the same intake quartile was highest for energy (82.0%) and lowest for vitamin A (56.0%). With regard to validity analysis, Spearman correlation coefficients ranged from 0.34 (for fiber) to 0.79 (for energy). The proportions of subjects in the opposite categories between the first FFQ and 3-day diet recall data were generally low from 0.00% (for fat) to 36.2% (for sodium). Average subjective levels of the website's usability, visual effect, understanding, and familiarity were all found to be over 4 points out of 5 points. Conclusions: The web-based dietary evaluation system developed can serve as a valid and attractive tool for administering FFQ to Korean adolescents.

• Archives of design research
• /
• v.16 no.1
• /
• pp.261-270
• /
• 2003

This paper focuses on the navigation methods which users select in different websites or for different tasks. Identifying the preferred navigation methods used for each case would help developers to construct the structure of website more effectively and confidently. To achieve the goal, this paper presents a framework on the classification of links as S_link and C_link. Then experiment is designed in order to evaluate the type of preferred link in each case. For the experiment, two different types of prototype websites such as news sites and shopping sites were constructed for which two different types of tasks such as goal-centered tasks and process-centered tasks were given to users. Particularly, to minimize the effects of visual elements and technical difference, prototype websites were produced with only HTML, not JavaScript nor Shockwave Flash. The result showed dearly that type of tasks had more significant effects on users navigation patterns than type of website. And users are more dependent on the S_link in the goal-centered task and on the C_link in the process-centered task. These findings were more apparent at the Qualitative test which was conducted for the comparative analysis between prototype site and real site.

• Spatial Information Research
• /
• v.18 no.2
• /
• pp.13-24
• /
• 2010

The purpose of this research is to explore the possibility of geographic education by implementing the map-based geographic education site which mashed up with Google earth by referring the various materials of geographic education which exist in on-line and off-line. In recent years map-based geographic education is required by the radical change of geoweb environments, but there have been few researches in this field. This research is folded up as follows: First, we designed the contents through the textbook analysis and then collect various data related to the contents such as pictures, video clips, conceptual map, etc. which are required to explain the concept. Second, we mashed up the collected data on the Google earth by using the Google's open API. Third, we implemented the geographic education website based on the classification of contents in textbook and the various collected data. This research is important in both that it explores the possibility of the map-based education rather than the text-based education in the geographic field which handles mainly the space and finds the best method to express the various concepts of the textbook on the geoweb environments.

• Fashion & Textile Research Journal
• /
• v.14 no.5
• /
• pp.778-790
• /
• 2012

This research categorizes and analyzes different online fashion store studies conducted over the past 10 years based on study type. The results are as follows. First, it was found that 116 studies out of 118 studies on online fashion stores conducted from 2000 to 2012 were based on PC web. Second, the studies on PC web-based fashion stores were reclassified into 9 different categories based on their topics: purchase behavior, word-of-mouth behavior, website, and product information presentation as well as products for sale, return behavior, customer service, system, present condition, marketing strategy, and promotions. However, mobile web-based studies were categorized into 2 categories of introduction of the fashion stores and purchase behavior. Third, we reclassified the studies chronologically to observe studies conducted at different times. In the early phase (in addition to studies on purchase behavior) studies on present condition, marketing strategy, and website constituted the majority of studies conducted because the field research was just starting to grow; however, studies conducted in the latter phase showed new patterns of study, such as word-of-mouth effect, and return behavior. Future studies conducted on competitive PC web-based fashion stores require a more specific classification of studies (according to their purpose) to develop an effective marketing strategy.

• Economic and Environmental Geology
• /
• v.56 no.1
• /
• pp.65-73
• /
• 2023

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.