• Journal of Information Processing Systems
• /
• 제20권2호
• /
• pp.215-225
• /
• 2024

With the rapid development of Internet of Things (IoT) and big data technology, a large amount of data will be generated during the operation of related industries. How to classify the generated data accurately has become the core of research on data mining and processing in IoT industry chain. This study constructs a classification model of IoT industry chain based on improved random forest algorithm and text analysis, aiming to achieve efficient and accurate classification of IoT industry chain big data by improving traditional algorithms. The accuracy, precision, recall, and AUC value size of the traditional Random Forest algorithm and the algorithm used in the paper are compared on different datasets. The experimental results show that the algorithm model used in this paper has better performance on different datasets, and the accuracy and recall performance on four datasets are better than the traditional algorithm, and the accuracy performance on two datasets, P-I Diabetes and Loan Default, is better than the random forest model, and its final data classification results are better. Through the construction of this model, we can accurately classify the massive data generated in the IoT industry chain, thus providing more research value for the data mining and processing technology of the IoT industry chain.

• 경영과학
• /
• 제26권3호
• /
• pp.101-115
• /
• 2009

In this paper, we propose a technology mining framework for mobile communication industry. We develop a two phase approach of new technology identification and service enhancement. The new technology identification process consists of R&D issues analysis, technology theme design, and emerging technology sampling. On the other hand, existing service enhancement process has technology landscaping, keyword based search, and technological growth analysis. By implementing these two phase frameworks, we develop a technology portfolio for mobile communication industry.

• 한국산학기술학회논문지
• /
• 제11권11호
• /
• pp.4489-4495
• /
• 2010

본 연구에서는 강원지역 석탄 산업을 중심으로 현재 이루어지고 있는 안전교육 현황을 분석하고, 그에 따른 문제점과 개선방안을 제시하였다. 문헌연구를 통하여 이론적 배경을 수립하였으며, 일반 근로자를 대상으로 설문조사를 실시하여 분석하는 연구를 병행하였다.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.157-161
• /
• 2022

The coffee industry continues to grow steadily due to the spread of coffee and changes in consumer awareness. Once upon a time, instant coffee was common, People today have distinct personal preferences As consumption needs for favorite foods are segmented, ways to enjoy coffee are diversifying. This study was conducted through analysis of consumption changes for specialty coffee as a changed issue of COVID-19 The goal is to present a vision for the future of the specialty coffee industry. As a research method, text mining through big data analysis was conducted to extract and analyze factors affecting the change in specialty coffee consumption. As a result of the study, we judged that specialty coffee is consumed by using a drip tool that allows you to easily enjoy coffee at home after Corona 19. Therefore, hand drips used in home cafes were found to play a central role in the change in specialty coffee consumption.

• 한국정보통신학회논문지
• /
• 제23권7호
• /
• pp.764-770
• /
• 2019

본 연구에서는 "4차 산업"과 관련된 논문들의 세부 연구 주제를 파악하기 위하여 텍스트 마이닝 기법을 이용하여 논문들을 분석하였다. 이를 위하여 2016년부터 2019년까지 한국학술지인용색인(KCI)에서 "4차 산업"이라는 키워드로 논문을 검색하여 총 685편의 논문을 수집하였다. 논문 수집을 위해서는 Python 기반의 웹 스크랩핑 프로그램을 사용하였으며, 자료 분석을 위해서는 R 언어로 구현된 LDA 알고리즘 기반의 토픽 모델링 기법들을 활용하였다. 수집된 논문들에 대한 Perplexity 분석 결과, 9가지 토픽이 최적으로 결정되었고 수집된 논문들의 9가지 대표 토픽들을 Gibbs 샘플링 방법을 사용하여 추출하였다. 분석 결과, 인공지능, 빅데이터, 사물인터넷, 디지털, 네트워크 등이 상위 주요 기술들로 나타났으며, 산업, 정부, 교육 현장, 일자리 등 4차 산업과 관련한 다양한 분야에서 주요 기술들로 인한 변화에 대한 연구들이 이루어져 왔음을 확인할 수 있었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.118-122
• /
• 2005

Data mining is the process of autonomously extracting useful information or knowledge from large data stores or sets. For analyzing data of manufacturing processes obtained from database using data mining, source data should be collected form production process and transformed to appropriate form. To extract those data from database, a computer program should be made for each database. This paper presents a program to extract easily data form database in industry. The advantage of this program is that user can extract data from all types of database and database table and interface with Teamcenter Manufacturing.

• 대한산업공학회지
• /
• 제41권1호
• /
• pp.86-96
• /
• 2015

A lot of research works in the BPM area focuses on the development of new techniques in process mining. Even though the application of process mining to analyze real life process logs is important, only few case studies are available. Thus, in this paper, we conduct a case study on how to analyze a real life process log which comes from a Korean company in the heavy industry area. We analyze a customer service process that consists of a series of activities to enhance the level of customer satisfaction. In this case study, five research questions are derived based on collected questions from the company. Then we focus on bottleneck analysis, basic performance analysis and pattern analysis that are selected in order to answer the research questions. The analysis shows some abnormal behaviors in the process and possible ways to improve current processes are suggested.

• 지능정보연구
• /
• 제9권2호
• /
• pp.135-154
• /
• 2003

Credit scoring system (CSS) starts from an analysis of delinquency trend of each individual or industry. This paper conducts a research on credit card delinquency of bank customers as a preliminary step for building effective credit scoring system to prevent excess loan or bad credit status. To serve this purpose, we use association rules as a rule generating data mining technique. Specifically, we generate sets of rules of customers who are in bad credit status because of delinquency by association rule mining. We expect that the sets of rules generated by association rule mining could act as an estimator of good or bad credit status classifier and basic component of early warning system.

• Journal of Information Technology Applications and Management
• /
• 제11권1호
• /
• pp.161-174
• /
• 2004

This study is intended to suggest1 the optimized data mining model for the efficient customer credit evaluation in the capital finance industry. To accomplish the research objective, various data mining models for the customer credit evaluation are compared and analyzed. Furthermore, existing models such as Multi-Layered Perceptrons, Multivariate Discrimination Analysis, Radial Basis Function, Decision Tree, and Logistic Regression are employed for analyzing the customer information in the capital finance market and the detailed data of capital financing transactions. Finally, the data from the integrated model utilizing a genetic algorithm is compared with those of each individual model mentioned above. The results reveals that the integrated model is superior to other existing models.

• 터널과지하공간
• /
• 제30권1호
• /
• pp.29-38
• /
• 2020

본 연구에서는 최근 10여 년 간 북한 광업 및 암반공학 분야의 발전 동향 및 최신 연구현황을 파악하기 위해, 2008-2017년 기간 출판된 북한 내 광업 관련 주요 학술지인 '채굴공학', '지질 및 지리과학', '기술혁신'을 대상으로 광업 및 암반공학 분야 연구논문의 투고 현황 및 연구 방법론을 분석하였다. 먼저 각 학술지에 수록된 연구논문의 서지정보 및 초록 자료를 정리하여 기초자료 데이터베이스를 작성하였다. 그리고 작성한 기초자료 데이터베이스를 활용하여 연구 분야별 학술지 투고 경향을 분석하였으며, 그 방법론 및 성과가 뛰어나다고 판단되는 연구논문에 대한 추가조사를 수행하여 북한 광업 및 암반공학 분야의 동향을 분석하였다. 연구동향 분석 결과, 최근 북한의 과학기술정책 변동 및 광업환경의 악화에 따른 정량화·자동화 경향성을 확인할 수 있었다. 본 연구결과는 향후 북한 광물자원 개발 전략 수립 및 경제성 평가를 위해 활용 가능할 것으로 판단되며, 향후 남북 기술협력 및 북한 현지 조사를 통해 보완될 수 있을 것이다.