• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1192-1200
• /
• 2019

Recently, artificial intelligence techniques have been widely used in the computer science field, such as the Internet of Things, big data, cloud computing, and mobile computing. In particular, resource management is of utmost importance for maintaining the quality of services, service-level agreements, and the availability of the system. In this paper, we review and analyze various ways to meet the requirements of cloud resource management based on artificial intelligence. We divide cloud resource management techniques based on artificial intelligence into three categories: fog computing systems, edge-cloud systems, and intelligent cloud computing systems. The aim of the paper is to propose an intelligent resource management scheme that manages mobile resources by monitoring devices' statuses and predicting their future stability based on one of the artificial intelligence techniques. We explore how our proposed resource management scheme can be extended to various cloud-based systems.

• 한국안전학회지
• /
• 제31권6호
• /
• pp.121-128
• /
• 2016

Social Media transformed the mass media based information traffic, and it has become a key resource for finding value in enterprises and public institutions. Particularly, in regards to disaster management, the necessity for public participation policy development through the use of social media is emphasized. National Disaster Management Research Institute developed the Social Big Board, which is a system that monitors social Big Data in real time for purposes of implementing social media disaster management. Social Big Board collects a daily average of 36 million tweets in Korean in real time and automatically filters disaster safety related tweets. The filtered tweets are then automatically categorized into 71 disaster safety types. This real time tweet monitoring system provides various information and insights based on the tweets, such as disaster issues, tweet frequency by region, original tweets, etc. The purpose of using this system is to take advantage of the potential benefits of social media in relations to disaster management. It is a first step towards disaster management that communicates with the people that allows us to hear the voice of the people concerning disaster issues and also understand their emotions at the same time. In this paper, Korean language text mining based Social Big Board will be briefly introduced, and disaster issue detection model, which is key algorithms, will be described. Disaster issues are divided into two categories: potential issues, which refers to abnormal signs prior to disaster events, and occurrence issues, which is a notification of disaster events. The detection models of these two categories are defined and the performance of the models are compared and evaluated.

• 한국의류학회지
• /
• 제30권5호
• /
• pp.788-799
• /
• 2006

The purpose of this study was to analyze fashion merchandising process, to apply customer information in merchandising process and to examine customer management strategies of fashion industry in on-line and off-line channel. In depth, face to face interviews with structured questionnaires were conducted with MD and customer managers from selected 4 brands, one from each categories of men's, women's, casual and sports wear. Key findings of the study were as follows: First, they followed fashion merchandising process of 18 steps and collected trend information and sales data were applied to planning, selling/promoting process to plan season concept, design, and promotion activity. Second, commonly applied customer information types in fashion merchandising process were all from indirect information collected from sales data and forecasting companies. However, casual and sports wear conducted consumer monitoring activity f3r collecting customer data directly from customer participation. Third, in off-line channel, customers are segmented by amount of purchase they make in a specific time period and all the categories show high interest in valuable customers. However, only men's and woman's wear conducted promotion activities for valuable customers as a differentiated marketing strategy. In on-line channel, companies were interacting with the customers through internet web site to determine their demands. In conclusion, this study has significance in that it propose the necessity and strategy of differentiated customer management approaching by analyzing and comparing fashion merchandising activity process cases.

• 디지털융복합연구
• /
• 제17권10호
• /
• pp.321-327
• /
• 2019

본 연구의 목적은 언어장애 환자군의 의사소통 능력 향상을 위하여 스마트 기기 기반의 언어재활 프로그램 개발에 있다. 이를 위하여 기존에 개발된 다양한 국내외 의사소통 언어훈련 프로그램을 비교분석하여 구체적인 의사소통 범위 및 훈련 과제, 문항 등을 검토하여 과제 구성에 필요한 콘텐츠를 선별하였다. 다양한 의미범주와 문법요소를 포함하고 언어학적 단위에 기초하여 단어수준, 의미범주, 문장수준, 담화수준의 이해산출 능력 향상을 위하여 17개의 의미범주를 추출하고 29개의 훈련과제와 3780개의 훈련 문항을 제작하였으며, 윈도우를 기반으로 하는 관리 프로그램과 안드로이드 기반 재활 훈련 애플리케이션을 개발하였다. 본 언어재활 프로그램은 가정에서 쉽고 편리하게 홈 프로그램으로 사용되어 언어훈련 효과를 증대시킬 수 있으며, 환자 관리 및 훈련 결과 데이터베이스 구축 등 언어장애 환자군의 치료에 유용하게 사용될 것으로 기대된다. 향후 언어장애 환자군 별 언어재활 효과 검증 등의 후속 연구가 진행될 예정이다.

• Safety and Health at Work
• /
• 제12권3호
• /
• pp.339-345
• /
• 2021

Background: Some researchers state that they are not yet able to provide a deep understanding of the underlying causes of unsafe behaviors (UBs). Therefore, the present study was conducted to investigate the attitudes and experiences of Iranian workers of UBs. Methods: This present study was conducted in 35 industries using a semistructured interview based on grounded theory. Forty participants were interviewed, including 13 industrial safety and health experts and 27 workers and supervisors. The analysis of the present study consisted of a three-step coding process including open, axial, and selective coding. Results: The results showed that the factors affecting UBs could be classified into three categories: organizational, individual, and socioeconomic factors. Organizational factors were divided into 6 parts: procedure and environmental conditions, communications, monitoring, organizational safety culture, resource allocation, and human resources. Socioeconomic factors had three subcategories: community safety culture, type of organizational ownership, and economic problems. Finally, the individual factors were classified into two categories of personality traits and individual competence. Conclusion: The results showed that organizational factors were the most categorized, and it is estimated that this factor has a more important role in the UBs. Of course, to better understand the close relationship between these factors and find the weight and importance of each factor, it needs to measure it with multicriteria decision systems.

• Healthcare Informatics Research
• /
• 제24권4호
• /
• pp.253-262
• /
• 2018

Objectives: We reviewed digital epidemiological studies to characterize how researchers are using digital data by topic domain, study purpose, data source, and analytic method. Methods: We reviewed research articles published within the last decade that used digital data to answer epidemiological research questions. Data were abstracted from these articles using a data collection tool that we developed. Finally, we summarized the characteristics of the digital epidemiological studies. Results: We identified six main topic domains: infectious diseases (58.7%), non-communicable diseases (29.4%), mental health and substance use (8.3%), general population behavior (4.6%), environmental, dietary, and lifestyle (4.6%), and vital status (0.9%). We identified four categories for the study purpose: description (22.9%), exploration (34.9%), explanation (27.5%), and prediction and control (14.7%). We identified eight categories for the data sources: web search query (52.3%), social media posts (31.2%), web portal posts (11.9%), webpage access logs (7.3%), images (7.3%), mobile phone network data (1.8%), global positioning system data (1.8%), and others (2.8%). Of these, 50.5% used correlation analyses, 41.3% regression analyses, 25.6% machine learning, and 19.3% descriptive analyses. Conclusions: Digital data collected for non-epidemiological purposes are being used to study health phenomena in a variety of topic domains. Digital epidemiology requires access to large datasets and advanced analytics. Ensuring open access is clearly at odds with the desire to have as little personal data as possible in these large datasets to protect privacy. Establishment of data cooperatives with restricted access may be a solution to this dilemma.

• 한국임상약학회지
• /
• 제30권4호
• /
• pp.243-249
• /
• 2020

Background: Despite the increased use of direct-acting oral anticoagulants, warfarin is still recommended as first-line therapy in patients with mechanical valves or moderate to severe mitral stenosis. Anticoagulation management services (AMSs) are warranted for patients receiving warfarin therapy due to the complexity of warfarin dosing and large interpatient variability. To overcome limited health care resources, we developed a messenger app-based chatbot that provides information to patients taking warfarin. Methods: We developed "WafarinTalk" as an add-on to the open-source messenger app KakaoTalk. We developed the prototype chatbot after building a database containing seven categories: 1) dosage and indications, 2) drug-drug interactions, 3) drug-food interactions, 4) drug-diet supplement interactions, 5) monitoring, 6) adverse events, and 7) precautions. We then surveyed 30 pharmacists and 10 patients on chatbot reliability and on participant satisfaction. Results: We found that 80% of the pharmacists agreed on the consistency of chatbot responses and 44% agreed on the appropriateness of chatbot. Furthermore, 47% of pharmacists said that they were willing to recommend the chatbot to patients. Of the seven categories, information on drug-food interaction was the most useful; 90% of patients said they were satisfied with the chatbot and 100% of patients said they were willing to use it when they were unable to see a pharmacist. We updated the prototype chatbot with feedback from the survey. Conclusion: This study showed that warfarin-related information could be provided to patients through a messenger application-based chatbot.

• 농촌계획
• /
• 제27권1호
• /
• pp.9-20
• /
• 2021

In order to develop practical indicator that can diagnose the regional conditions and characteristics of fishing villages, this study reviewed domestic and foreign researches and selected the diagnostic indicator of fishing villages by spatial unit. The major categories are divided into population and society, economic conditions, and living conditions. The middle categories consists of population, household, industry, tourism, settlement, environment, safety, health and welfare, education, and culture and leisure. The indicator were selected with reference to the existence of statistical data officially provided according to the spatial range(Si/Gun, eup/myeon, village). Based on the selected indicator, the test evaluation was conducted in Jindo-gun, Jeollanam-do by applying data that can be obtained from KOSIS and web GIS. It is judged that the diagnostic indicator developed through this research can be used in various ways from the planning stage to the implementation stage of the regional development project, such as grasping the current conditions, setting improvement targets, promotion and evaluation/monitoring of the project. In addition, it is expected that it will be possible to carry out regional diagnosis for each spatial unit and to plan and implement regional development projects by giving priority to areas where the level of each department is insufficient.

• 보건행정학회지
• /
• 제32권3호
• /
• pp.304-316
• /
• 2022

Background: As prevention of coronavirus disease 2019 (COVID-19) transmission in healthcare settings has become a critical component in its effective management, COVID-19 specific infection prevention and control (IPC) guidelines were developed and implemented by numerous countries. Although largely based on the current evidence-base, guidelines show much heterogeneity, as they are influenced by respective health system capacities, epidemiological risk, and socioeconomic status. This study aims to analyze the variations and concurrences of these guidelines to draw policy implications for COVID-19 response and future guidelines development. Methods: The contents of the COVID-19 IPC guidelines were analyzed using the categories and codes developed based on "World Health Organization guidelines on core components." Data analysis involved reviewing, appraising and synthesizing data from guidelines, which were then arranged into categories and codes. Selection of countries was based on the country income level, availability of COVID-19 specific IPC guideline developed at a national or district level. Results: The guidelines particularly agreed on IPC measures regarding application of standard precautions and providing information to patients and visitors, monitoring and audit of IPC activities and staff illnesses, and management of built environment/equipments. The guidelines showed considerable differences in certain components, such as workplace safety measures and criteria for discontinuation of precautions. Several guidelines also contained unique features which enabled a more systematic response to COVID-19. Conclusion: The guidelines generally complied with the current evidence-based COVID-19 management but also revealed variances stemming from differences in local health system capacity. Several unique features should be considered for benchmark in future guidelines development.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.80-80
• /
• 2022

Estimation of heading date of paddy rice is laborious and time consuming. Therefore, automatic estimation of heading date of paddy rice is highly essential. In this experiment, deep learning classification models were used to classify two difference categories of rice (vegetative and reproductive stage) based on the panicle initiation of paddy field. Specifically, the dataset includes 444 slanted view images belonging to two categories and was then expanded to include 1,497 images via IMGAUG data augmentation technique. We adopt two transfer learning strategies: (First, used transferring model weights already trained on ImageNet to six classification network models: VGGNet, ResNet, DenseNet, InceptionV3, Xception and MobileNet, Second, fine-tuned some layers of the network according to our dataset). After training the CNN model, we used several evaluation metrics commonly used for classification tasks, including Accuracy, Precision, Recall, and F1-score. In addition, GradCAM was used to generate visual explanations for each image patch. Experimental results showed that the InceptionV3 is the best performing model in terms of the accuracy, average recall, precision, and F1-score. The fine-tuned InceptionV3 model achieved an overall classification accuracy of 0.95 with a high F1-score of 0.95. Our CNN model also represented the change of rice heading date under different date of transplanting. This study demonstrated that image based deep learning model can reliably be used as an automatic monitoring system to detect the heading date of rice crops using CCTV camera.