• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.9-15
• /
• 2018

Policy polls, which investigate the degree of support that the policy has for policy implementation, play an important role in making decisions. As the number of Internet users increases, the public is actively commenting on their policy news stories. Current policy polls tend to rely heavily on phone and offline surveys. Collecting and analyzing policy articles is useful in policy surveys. In this study, we propose a method of analyzing comments using deep learning technology showing outstanding performance in various fields. In particular, we designed various models based on the recurrent neural network (RNN) which is suitable for sequential data and compared the performance with the support vector machine (SVM), which is a traditional machine learning model. For all test sets, the SVM model show an accuracy of 0.73 and the RNN model have an accuracy of 0.83.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.7-13
• /
• 2018

Recent advancement in data gathering technique improves the capability of information collecting, thus allowing the learning process between gathered data patterns and application sub-tasks. A pattern can be associated with multiple labels, demanding multi-label learning capability, resulting in significant attention to multi-label feature selection since it can improve multi-label learning accuracy. However, existing evolutionary multi-label feature selection methods suffer from ineffective search process. In this study, we propose a evolutionary search process for the task of multi-label feature selection problem. The proposed method creates large set of offspring or new feature subsets and then retains the most promising feature subset. Experimental results demonstrate that the proposed method can identify feature subsets giving good multi-label classification accuracy much faster than conventional methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.853-854
• /
• 2014

서비스 산업에 있어 효율적인 경영을 위해서는 시시각각으로 변하는 고객의 니즈를 파악하기 위해 그 어느 때 보다도 고객피드백이 필요한 시대이다. 기존의 설문조사를 이용한 방법은 자발적이고 즉각적인 고객의 의견을 수집하는데 한계가 있어 최근에는 서비스의 즉각적이고 사실적인 피드백을 얻기 위해서 조사에 대한 인지 없이 능동적이고 자발적으로 작성한 소셜미디어 상의 게시글을 수집하고 분석하는 방법을 이용하여 고객의 피드백을 파악하고 있다. 본 연구에서는 이러한 소셜 미디어상의 빅데이터 정보를 분석하는 기술의 적합성을 평가하는 방법을 제안한다. 수집 적합성 평가는 사전 설정된 수집규칙에 의해 수집된 수집데이터에 대한 검증방안을 수립하고 샘플링 조사를 수행하여 목표 수준의 정확도가 이루어지지 않을 경우 수집엔진에 대한 기능 보완 및 수집 주기 재설정 등 수집 규칙을 재설정하고 샘플조사 범위를 확대하여 평가하는 일련의 과정 반복을 통해 수집 정확도를 향상시킨다.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1663-1672
• /
• 2021

There are various typing practice applications. In addition, research cases on learning applications that support typing practice have been reported. These services are usually provided in a way that utilizes their own built-in text. Learners collect various contents through web services and use them a lot for learning. Therefore, this paper proposes a learning application to increase the learning effect by collecting vast amounts of web content and applying it to typing practice. The proposed application is implemented using Tkinter, a GUI module of Python. BeautifulSoup module of Python is used to extract information from the web. In order to process the extracted data, the NLTK module, which is an English data preprocessor, and the KoNLPy module, which is a Korean language processing module, are used. The operation of the proposed function is verified in the implementation and experimental results.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.219-225
• /
• 2021

This study was a cross-sectional reaserch that analyzed the factors that most affect COVID-19 knowledge in nursing college students who are relatively at high risk for recent prevalence of COVID-19 exposure in relation to clinical practice of nursing college students. A total of 249 nursing students participated in this study, 93 male students and 156 female students. The period for collecting data from structured questionnaires was from October 1 to October 20, 2021. The collected data were frequency analysis, Pearson correlation analysis, simple regression analysis, and hierarchical regression analysis using SPSS 18.0. As a result of the analysis, infection prevention behavior(𝛽=0.06, p=0.006) had the most influence on COVID-19 knowledge, and the second was professional intuition(𝛽=-.162, p=0.018). Based on the results of this study, in order to improve the knowledge of COVID-19 among nursing students, it is proposed to develop an infection prevention behavior education program and a professional intuition improvement program.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.815-818
• /
• 2009

USN 환경에서의 센서는 일반적으로 많은 제약사항을 가지고 있다. 센서의 제한된 전원의 문제는 센서의 동작 수명과 관련된 것으로 최근의 연구들에서 중요 이슈가 되고 있다. 본 논문에서는 고도화되는 USN 환경에서 발생되는 다차원 스트림데이터를 수집하는데 있어서 센서의 전원 문제를 해결하고 데이터를 효율적으로 수집하기 위한 기법을 제안한다. 제안하는 기법은 센서에 이상 이벤트를 정의하고 이상 이벤트에 해당하는 데이터를 수집하는 경우에만 데이터를 전송하도록 하여 센서의 통신 빈도를 줄여 센서의 전원 문제를 해결하고 스트림 데이터를 기호화 하여 처리함으로써 스트림 데이터를 효율적으로 수집할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.361-364
• /
• 2020

소셜 네트워크 서비스의 사용자가 늘어나면서, 소셜 네트워크 서비스상에서 발생하는 빅데이터를 활용한 서비스가 늘어나고 있다. 소셜 네트워크 서비스 데이터는 실시간으로 생성되며, 따라서 데이터 수집 시스템 역시 자동화하여 준 실시간으로 데이터를 수집할 필요가 있다. 본 논문에서는 대표적인 소셜 네트워크 서비스인 트위터의 데이터를 지속적으로 수집하기 위한 자동 수집 시스템을 제안한다. 수집 시스템은 Twitter API 를 활용하는 Python 라이브러리를 통해 내용 및 메타데이터를 수집하며, 수집된 데이터를 재 검증한 뒤 저장한다. 또한 구현된 시스템에 환경 데이터를 주제로 하는 쿼리를 입력하여 실제 트위터 데이터를 수집하며 구현된 시스템을 검증해보았다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.103-104
• /
• 2023

In this study, the correlation between the rheolog y parameter of fresh concrete and the rheology parameter of wet sieving mortar was analyzed for analyzing to possibility predicting the rheology parameter of fresh concrete. Through the experiment, the dynamic yield stress and plastic viscosity of concrete and wet sieving mortar show a direct proportional relationship, and the two data had a correlation. Therefore, it is thought that it is possible to predict the rheology parameter of fresh concrete through the rheology parameter of wet sieving mortar. However, in order to more accurately predict the rheology parameter of fresh concrete, it is need additional relationship analysis by collecting more rheology parameter data of fresh concrete and wet sieving mortar.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.13 no.1
• /
• pp.15-23
• /
• 2014

With introduction of amended educational curriculum in 2007, optimizing project of educational environment to accomplish its purposes and goals includes expanding educational facilities and supplying eco-friendly school facilities. However, while the focus of optimizing project of educational environment is quality improvement of educational facilities, aging of these facilities built at th times of quantitative expansion and its management become serious problems. Higher concerns on studies and jobs on management of building caused by serious aging of facilities, management cost of building becomes a very crucial issue. Therefore, this study aims to analyze environment improvement budget of school facilities through building and using data warehouse, by investigating and analyzing the current status of environment improvement budget of school facilities and its cost through questionnaire and interview surveys on officers who are in charge of environment improvement budget of school facilities in educational administrations. This study thus analyzed environment improving budget of school facilities by using data warehouse technology collecting related data to the topic and setting levels by region, school class, establishment year, school facility types and others.

• Journal of Korea Multimedia Society
• /
• v.18 no.9
• /
• pp.1131-1139
• /
• 2015

The purpose of this research is creating the visualization platform of the user interface to make able to be provide the demanded service while users communication with surrounding space in a smart city environment. This comes from the latest enhanced interface technology and social media, and it uses the shares information to support the proper interface environment according to a life style and spatial properties. "EzCity" which is the user interface platform suggested in this research, can control the enormous amount of public data for the smart city. The core module of user platform is made up with Public data module, Interface module, Visualization module and Service module. The role of this platform is to be provide "Geo-Intelligent Interface Service" for space users to access the data in easier and more practical interface environment. This reinforces the visualization process for data collecting, systematization, visualization and providing service. Also this will be expected to be the base to solve the problem which complexity and rapidly increasing amount of data.