• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.182-183
• /
• 2018

Big data analysis is the process of discovering a meaningful correlation, pattern, and trends in large data set stored in existing data warehouse management tools and creating new values. In addition, by extracts new value from structured and unstructured data set in big volume means a technology to analyze the results. Most of the methods of Big data analysis technology are data mining, machine learning, natural language processing, pattern recognition, etc. used in existing statistical computer science. Global research institutes have identified Big data as the most notable new technology since 2011.

• Communications of Mathematical Education
• /
• v.32 no.4
• /
• pp.555-573
• /
• 2018

The purpose of this study is to identify the emotional language of math teachers in math class using text mining techniques. For this purpose, we collected the discourse data of the teachers in the class by using the excellent class video. The analysis of the extracted unstructured data proceeded to three stages: data collection, data preprocessing, and text mining analysis. According to text mining analysis, there was few emotional language in teacher's response in mathematics class. This result can infer the characteristics of mathematics class in the aspect of affective domain.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.563-567
• /
• 2023

본 연구는 한국 통계청이 수행하는 가계동향조사와 생활시간조사에서 자료처리 과정 및 방법을 혁신하려는 시도로, 기존의 통계 생산 방법론의 한계를 극복하고, 대규모 데이터의 효과적인 관리와 분석을 가능하게 하는 인공지능 기반의 통계 생산을 목표로 한다. 본 연구는 데이터 과학과 통계학의 교차점에서 진행되며, 인공지능 기술, 특히 자연어 처리와 딥러닝을 활용하여 비정형 텍스트 분류 방법의 성능을 검증하며, 인공지능 기반 통계분류 방법론의 확장성과 추가적인 조사 확대 적용의 가능성을 탐구한다. 이 연구의 결과는 통계 데이터의 품질 향상과 신뢰성 증가에 기여하며, 국민의 생활 패턴과 행동에 대한 더 깊고 정확한 이해를 제공한다.

• Journal of the Korean Society of Radiology
• /
• v.83 no.3
• /
• pp.632-644
• /
• 2022

Purpose To determine the incidence of atypical ductal hyperplasia (ADH) in needle biopsy and the upgrade rate to carcinoma, and to evaluate difference in findings between the upgrade and non-upgrade groups. Materials and Methods Among 9660 needle biopsies performed over 48 months, we reviewed the radiologic and histopathologic findings of ADH and compared the differences in imaging findings (mammography and breast US) and biopsy methods between the upgrade and non-upgrade groups. Results The incidence of ADH was 1.7% (169/9660). Of 112 resected cases and 30 cases followed-up for over 2 years, 35 were upgraded to carcinoma (24.6%, 35/142). The upgrade rates were significantly different according to biopsy methods: US-guided core needle biopsy (USCNB) (40.7%, 22/54) vs. stereotactic-vacuum-assisted biopsy (S-VAB) (16.0%, 12/75) vs. USguided VAB (US-VAB) (7.7%, 1/13) (p = 0.002). Multivariable analysis showed that only US-CNB (odds ratio = 5.19, 95% confidence interval: 2.16-13.95, p < 0.001) was an independent predictor for pathologic upgrade. There was no upgrade when a sonographic mass was biopsied by US-VAB (n = 7) Conclusion The incidence of ADH was relatively low (1.7%) and the upgrade rate was 24.6%. Surgical excision should be considered because of the considerable upgrade rate, except in the case of US-VAB.

• Journal of the Korea society of information convergence
• /
• v.7 no.2
• /
• pp.49-57
• /
• 2014

Recently, opinion mining is introduced to extract useful information from SNS data and to evaluate the true intention of users. Opinion mining are required several efficient techniques to collect and analyze a large amount of SNS data and extract meaningful data from them. Therefore in this paper, we propose a parallel HDFS(Hadoop Distributed File System) and emotion functions based on Mapreduce to extract some emotional information of users from various unstructured big data on social networks. The experiment results have verified that the proposed system and functions perform faster than O(n) for data gathering time and loading time, and maintain stable load balancing for memory and CPU resources.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.73-83
• /
• 2019

Since the emergence of the fourth industrial revolution, data analysis is being conducted in various fields. Distributed data processing has already become essential for the fast processing of large amounts of data. However, in the defense sector, simulation used cannot fully utilize the unstructured data which are prevailing at real environments. In this study, we propose a distributed data processing platform that can be applied to battalion level simulation models to provide visualized data for command decisions during training. 500,000 data points of strategic game were analyzed. Considering the winning factors in the data, variance processing was conducted to analyze the data for the top 10% teams. With the increase in the number of nodes, the model becomes scalable.

• Analytical Science and Technology
• /
• v.23 no.3
• /
• pp.261-268
• /
• 2010

This study was performed to evaluate the PCBs-containing wastes using official test method. Ninety samples of transformer oil and various solid waste were collected to assess the analytical results. In the analysis of PCBs-containing wastes, the PCBs levels were detected in the range of 7.6 mg/kg to 23.8 mg/kg for transformer oils, $0.02\sim0.54\;{\mu}g/100cm^2$ for plat solid wastes, and 0.01~0.071 mg/kg for amorphous solid waste. In the cupper wire waste of the transformer with oil concentration level of 23 mg/kg, the analytical result exceed PCBs regulation level of 0.04 mg/kg. The new proposed analytical method for PCBs containing waste can be forced to effective management of the wastes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.167-168
• /
• 2017

In this paper, we discuss the importance of what to analyze and what to predict using Big Data. The issue of how and where to apply a large amount of data that is accumulated in my daily life and which I am not aware of is a very important factor. There are many kinds of tasks that specify what to predict and how to use these data. Finding the most appropriate one is the way to increase the prediction probability. In addition, the data that are analyzed and predicted should be useful in real life to make meaningful data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.253-255
• /
• 2020

기업 및 기관 데이터는 워드프로세서, 프레젠테이션, 이메일, open api, 엑셀, XML, JSON 등과 같은 텍스트 기반의 비정형 데이터로 구성되어 있습니다. 텍스트 마이닝(Textmining)을 통해서 자연어 처리 및 기계학습 등의 기술을 이용하여 정보의 추출부터 요약·분류·군집·연관도 분석 등의 과정을 수행울 진행한다. 다양한 시각화 데이터를 보여줄 수 있는 다양한 모델 구축을 진행한 후 민원 신청 내용을 분석 및 변환 작업을 진행한다. 본 논문은 AI 기술과 빅데이터를 활용하여 민원을 분석을 하여 알맞은 부서에 민원을 자동으로 할당해 주는 기술을 다룬다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.101-104
• /
• 2023

본 연구는 현대 사회에서 빅데이터의 중요성이 강조되는 가운데, 온라인 시장의 확장과 소비자들의 다양한 소비 행태 변화를 반영한 가격지표 개발을 목표로 한다. 통계청의 기존 통계조사 방법론에 대한 한계를 극복하고, 온라인 쇼핑몰 데이터에서 필요한 정보를 추출하고 가공하기 위해 대규모 언어 모델(LLM)을 활용한 인공지능 기술을 적용해보고자 한다. 초기 연구 결과로 공개 Polyglot을 활용하여 비정형 자료 처리와 품목분류에 응용해 보았으며, 제한된 학습 데이터를 사용하여도 높은 정확도의 처리 결과를 얻을 수 있었으며, 현재는 적용 품목을 확장하여 더욱 다양한 품목에 방법론을 적용하는 연구를 진행 중이다.