• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.58-65
• /
• 2023

Bankruptcy is a significant risk for start-up companies, but with the help of cutting-edge artificial intelligence technology, we can now predict bankruptcy with detailed explanations. In this paper, we implemented the Category Boosting algorithm following data cleaning and editing using OpenRefine. We further explained our model using the Shapash library, incorporating domain knowledge. By leveraging the 5C's credit domain knowledge, financial analysts in banks or investors can utilize the detailed results provided by our model to enhance their decision-making processes, even without extensive knowledge about AI. This empowers investors to identify potential bankruptcy risks in their business models, enabling them to make necessary improvements or reconsider their ventures before proceeding. As a result, our model serves as a "glass-box" model, allowing end-users to understand which specific financial indicators contribute to the prediction of bankruptcy. This transparency enhances trust and provides valuable insights for decision-makers in mitigating bankruptcy risks.

• Journal of Information Science Theory and Practice
• /
• v.12 no.2
• /
• pp.36-48
• /
• 2024

For consumers making health decisions, Wikipedia is a popular source for health information. This study investigated major factors influencing consumer satisfaction with Wikipedia medical/health articles. Using a crowdsourcing method, data were collected from 322 adults who read/edit English Wikipedia medical/health articles and reside in the US. The results showed that the presentation of information was the most influential factor. Trustworthiness was the second most important factor for consumer satisfaction with the quality of information, followed by reliability, and topic coverage. Study participants did not consider other factors such as accuracy and currency to be crucial factors. Moderating effects of the control variables such as editing experience with Wikipedia articles, gender, and age were also examined to enhance the internal validity of the study. Implications for the Wikipedia editor community and researchers, and directions of future research are presented.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.28 no.1
• /
• pp.1-21
• /
• 2024

This review comprehensively explores the evolution, theoretical underpinnings, variations, and applications of diffusion models. Originating as a generative framework, diffusion models have rapidly ascended to the forefront of machine learning research, owing to their exceptional capability, stability, and versatility. We dissect the core principles driving diffusion processes, elucidating their mathematical foundations and the mechanisms by which they iteratively refine noise into structured data. We highlight pivotal advancements and the integration of auxiliary techniques that have significantly enhanced their efficiency and stability. Variants such as bridges that broaden the applicability of diffusion models to wider domains are introduced. We put special emphasis on the ability of diffusion models as a crucial foundation model, with modalities ranging from image, 3D assets, and video. The role of diffusion models as a general foundation model leads to its versatility in many of the downstream tasks such as solving inverse problems and image editing. Through this review, we aim to provide a thorough and accessible compendium for both newcomers and seasoned researchers in the field.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.67-79
• /
• 2023

In the image field, data augmentation refers to increasing the amount of data through an editing method such as rotating or cropping a photo. In this study, a generative adversarial network (GAN) image was created using CycleGAN, and various colors of dogs were reflected through data augmentation. In particular, dog data from the Stanford Dogs Dataset and Oxford-IIIT Pet Dataset were used, and 10 breeds of dog, corresponding to 300 images each, were selected. Subsequently, a GAN image was generated using CycleGAN, and four learning groups were established: 2,000 original photos (group I); 2,000 original photos + 1,000 GAN images (group II); 3,000 original photos (group III); and 3,000 original photos + 1,000 GAN images (group IV). The amount of data in each learning group was augmented using existing data augmentation methods such as rotating, cropping, erasing, and distorting. The augmented photo data were used to train the MobileNet_v3_Large, ResNet-152, InceptionResNet_v2, and NASNet_Large frameworks to evaluate the classification accuracy and loss. The top-3 accuracy for each deep neural network model was as follows: MobileNet_v3_Large of 86.4% (group I), 85.4% (group II), 90.4% (group III), and 89.2% (group IV); ResNet-152 of 82.4% (group I), 83.7% (group II), 84.7% (group III), and 84.9% (group IV); InceptionResNet_v2 of 90.7% (group I), 88.4% (group II), 93.3% (group III), and 93.1% (group IV); and NASNet_Large of 85% (group I), 88.1% (group II), 91.8% (group III), and 92% (group IV). The InceptionResNet_v2 model exhibited the highest image classification accuracy, and the NASNet_Large model exhibited the highest increase in the accuracy owing to data augmentation.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.491-497
• /
• 2022

In this study, we tried to secure basic data to create an environment necessary for distance learning through a survey on professor demand. Among the 184 full-time faculty members of the university, 73 (39.89%) respondents in 2021 and 87 (47.28%) in 2022 were included. As a result of the research on professor demand, in the 2021 school year, 27 people (37%) were classified as LMS improvement items when checking attendance, 38 people (23.3%) were pin-mics as content development support items, and 26 people (35.6%), 33 people (45.2%) of GOM Mix and 25 people (34.2%) of the distance education support center wanted to learn video editing program as the item of video editing program they are currently using. In the 2022 school year, 27 people (31.03%) said mobile upgrade as an LMS improvement item, 52 people (59.8%) of pin-microphone as a content development support item, 33 people (37.9%), but currently using the content creation intention using a studio. As for the video editing program they are working on, 47 people (54%) of GOM Mix Pro and 23 people (26.4%) of the distance education support center want to learn content creation method. In addition, the intention to produce content using the studio for the 2021 and 2022 academic year and the desired educational topic of the distance education support center in the future appeared insignificant (p > 0.05). In this distance education support center, we are working to solve the class of LMS attendance, upgrade mobile, and plan to distribute pin microphones. We are planning to increase the usability of the studio and provide training on how to use video editing programs and how to create video content. In order for a smooth class to take place in a university distance class, the university authorities should seek ways to support the instructor so that he/she does not have difficulties in performing his/her role as a teaching designer, such as setting learning goals, organizing and organizing content, motivating learning, and establishing effective class participation plans. there is a need

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3943-3957
• /
• 2016

As digital evidence has a highly influential role in proving the innocence of suspects, methods for integrity verification of such digital evidence have become essential in the digital forensic field. Most surveillance camera systems are not equipped with proper built-in integrity protection functions. Because digital forgery techniques are becoming increasingly sophisticated, manually determining whether digital content has been falsified is becoming extremely difficult for investigators. Hence, systematic approaches to forensic integrity verification are essential for ascertaining truth or falsehood. We propose an integrity determination method that utilizes the structure of the video content in a Video Event Data Recorder (VEDR). The proposed method identifies the difference in frame index fields between a forged file and an original file. Experiments conducted using real VEDRs in the market and video files forged by a video editing tool demonstrate that the proposed integrity verification scheme can detect broken integrity in video content.

• Journal of Nutrition and Health
• /
• v.20 no.6
• /
• pp.442-455
• /
• 1987

The purpose of the study were to assist foodservice managers in complex decision making by utilizing computerized cost accounting system and to relieve managers from repetitive and routine tasks so that more adequate patient care and consultation can be provided. The scope of the computer-assisted cost accounting system consists of budget, menu planning, purchasing, inventory, cost control and financial reporting. The content of the computerized system are summarized as follows ; 1) For budgeting monthly income was estimated by calculating unit cost of each meal and forecasting serving numbers. The actual serving numbers for patients and employees were totaled everyday, and utilized as the basic data base for estimating income and planning menu. The monthly lists of meal sensus were generated. 2) for menu planning concersion factors were computed based on the standarized recipe for 50 servings. Daily menus for patients and employees which include total amounts of each ingredient and cost analyzed information were generated. 3) Daily and monthly purchasing report for each food item classified by patient and employee meals were generated. 4) Inventory transactions such as recipts and issues were totalized daily for each stocked item, and monthly inventory reports were generated. 5) Cost analysis reports for each menu item were generated into two ways based on the budget coat as well as the purchasing cost. 6) Editing new recipes and updating food costs change to the data base were carried out. 7) Financial reports were generated monthly, first-half and second-half of the year, and yearly basis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.325-329
• /
• 2011

We are developing a minimized integrated public address system that has facilities such as external input, Mic., CD, MP3 and Radio. In this paper, developing an integrated public address system with operational MICOM will make it possible to control the facilities of digital devices centrally. The operational MICOM is composed of 3 layers which are a control layer, a processing layer and a user interface layer. The control layer controls digital devices in the integrated public address and the processing layer is for processing voice data editing, controlling signals of devices and providing status information of the device. The user interface layer displays the status of control devices and the data processing of a user. A remote control is used for the central control.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.7
• /
• pp.1160-1168
• /
• 2008

The purpose of the study was to examine the effect of motif categories and motif colors on evaluating impressions of dress wearers. The research was conducted on a quasi experimental basis, with subjects numbering 187 male and 207 female college students. Data were collected in the period from march 19th to march 31st, 2007. A set of stimuli of dress wearers and semantic differential scales were developed. The stimuli were thirteen photographs editing by Youngwoo CAD system. Variables included; (a) motif colour(red, blue, achromatic and white) (b) motif categories(flower, paisley, stripes, zebra effect and plain). The semantic differential scale to measure impressions of dress wearer stimuli included 22 sets of hi-polar adjectives. The data were analysed by factor analysis and ANOVA and the major finding were as follows. Four factors emerged to account for dimension of impression. There were salience, attractiveness, comfort and femininity. The motif category effected on the four impression dimensions while the motif color effected on salience, comfort and softness sensory dimensions, and the results supported the gestalt theory of the impression perception.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.2
• /
• pp.223-235
• /
• 1999

본 논문에서는 HDTV 데이터를 입출력할 수 있는 고속 실시간 데이터 저장 시스템을 제안한다. 이 시스템은 ⅰ) 방대한 크기를 HDTV 데이터를 고속으로 입출력할 수 있어야 한다. ⅱ)데이타를 연속적으로 입출력할 수 있는 것 외에 데이터를 비선형적으로 랜덤하게 억세스 할 수 있어야 한다. ⅲ)실시간으로 데이터를 재생하기 위해 일정하게 주어진 시스템 입출력 속도를 항상 만족할수 있어야 한다. 이러한 조건을 만족시키기 위해서 여러 개의 하드디스크를 병렬로 연결하고 데이터들을 각각의 하드디스크에 나누어 저장하였다. 하드디스크의 입출력 성능은 하드디스크 아암의 탐색 동작에 의해 크게 좌우되므로 탐색 동작을 효과적으로 제어할 수 있는 방법이 설계되었다. 제안된 시스템은 주제어부, 데이터 분배부, 종제어부로 나뉘며 각각의 하드디스크는 독립도니 종제어부에 의해 제어된다. 제안된 시스템이 주어진 요구사항을 만족하는지를 확인하기 위하여, 제안된 시스템을 DEVS 형식론을 이용하여 구현하고 시뮬레이션 하였다. DEVS 형식론은 이산사건 시스템을 계층적이고 모듈화된 형태로 기술한다. 시뮬레이션 과정에서 발생된 사건들을 분석하였다. 그 결과 제안된 시스템이 주어진 요구사항을 잘 만족함을 보았다.