통계적 기법을 이용한 빅데이터 기술 분석

박상성 청주대학교 산업과학연구소 2021 産業科學硏究 Vol.39 No.1

Patents are a system that protects the rights of inventors by document. Recently, with the start of the 4th Industrial Revolution, various technologies are being developed. Patent analysis can be used to identify trends prior to technology development. As the number of patent applications has increased, a lot of time and cost are being consumed. Therefore, many studies have been conducted on data-based patent analysis. This study proposes a method to find out the correlation between the top applicant and the technology code in patent big data. The methodology has the advantage of being able to grasp the insights in the technology domain. The experiment was conducted with 10,077 patents related to healthcare technology. As a result, there is a high possibility that medical-type technology will develop into healthcare informatics.

슬러리형 돈사 폐기물의 혐기성 최종 생분해도

박상성,김병욱,한동준,임재명 대한환경공학회 1999 대한환경공학회 학술발표논문집 Vol.1999 No.8

추론모델 기반 성과지표 네트워크를 이용한 특허 빅데이터 시각화에 관한 연구

박상성 한국지능시스템학회 2020 한국지능시스템학회논문지 Vol.30 No.1

특허는 빠르게 생성되며 축적된 양이 방대하고 다양한 형태의 정보를 포함하는 빅데이터이다. 특허 빅데이터의 정성분석은많은 시간과 비용이 소모된다. 또한, 전문가 기반 특허 분석은 전문가 의견에 편향된 결과가 도출될 수 있다. 이를 개선하기위해 데이터 기반 특허 분석이 필요하다. 그리고 특허에 존재하는 많은 질적 지표 및 텍스트 정보를 사용할 필요가 있다. 따라서 본 논문은 추론모델을 통해 특허의 텍스트 정보와 특허의 질적 성과지표와의 관계를 파악하기 위한 모델을 제안한다. 추론모델의 변수 중요도를 통해 성과지표와 특허의 서지정보 간의 관계를 도출한다. 도출된 특허의 성과지표와 서지정보의관계를 활용하여 네트워크 분석을 실시하며 이를 시각화하여 분석 결과를 가시성 높게 제공한다. 제안된 방법을 사용하면, 특정 기술의 비전문가도 분석 결과를 통해 특허 빅데이터의 내용을 쉽게 파악하는 것이 가능할 것으로 기대된다. 제안된방법은 스마트 카 특허를 사용하여 실제 적용 가능성을 검토하였다. 실험을 통해 성과지표와 텍스트 정보 간의 관계를추론하고 시각화하는 것이 가능하였다.

특허빅데이터 분석을 이용한 R&D전략수립

박상성 청주대학교 산업과학연구소 2020 産業科學硏究 Vol.37 No.2

Smart cars are the next generation of intelligent cars that combine automobile manufacturing technology with electric · electronic, information and communication technologies. Smart cars, which are complicated by various technologies, are not far away from commercial vehicles of the future. In this study, the trend of smart car technology is identified through trend analysis. Trend analysis is conducted on top smart car applicants and international patent classification codes. Patents were collected and modeled for trend analysis. As a result of trend analysis by top applicants, trends of GM, Google, Ford and Intel will continue to increase at the significance level of 0.1. Therefore, they are likely to be technology leaders in the future of smart car technology. In the trend analysis of IPC codes, it was predicted that hybrid vehicle control systems, measurement techniques and steering technologies would continue to be developed at the significance level of 0.1.

대학 빅데이터 기반 학생 취업 로드맵 추천에 관한 연구

박상성 (사)디지털산업정보학회 2021 디지털산업정보학회논문지 Vol.17 No.3

The number of new students at many domestic universities is declining. In particular, private universities, which are highly dependent on tuition, are experiencing a crisis of existence. Amid the declining school-age population, universities are striving to fill new students by improving the quality of education and increasing the student employment rate. Recently, there is an increasing number of cases of using the accumulated big data of universities to prepare measures to fill new students. A representative example of this is the analysis of factors that affect student employment. Existing employment-influencing factor analysis studies have applied quantitative models such as regression analysis to university big data. However, since the factors affecting employment differ by major, it is necessary to reflect this. In this paper, the factors affecting employment by major are analyzed using the data of University C and the decision tree model. In addition, based on the analysis results, a roadmap for student employment by major is recommended. As a result of the experiment, four decision tree models were constructed for each major, and factors affecting employment by major and roadmap were derived.

CTI를 이용한 콜센터 시스템 개발 : 대리운전 시스템

박상성,정원교,신영근,장동식 대한산업공학회 2007 산업공학 Vol.20 No.3

By an explosive increase of proxy driving, customers require the quick and correct services of call center. But because most call centers have an unsystematic management system, grievance of customers is continually increasing. To solve these problem, we constructed a call center system of proxy driving that is based on CTI (Computer Telephony Integration) in this paper. The proposed system is constructed using CID (Caller Identify Display) terminal, SMS (Short Message Service) and call center management program etc. Customer service level could be improved through efficient customer management by using the proposed system. Also it could be convenient and easy to implement customer management, order management, staff management, SMS and settlement of accounts.

앙상블 기법을 활용한 대학생 중도탈락 예측 모형 개발

박상성 (사)디지털산업정보학회 2021 디지털산업정보학회논문지 Vol.17 No.1

The number of freshmen at universities is decreasing due to the recent decline in the school-age population, and the survival of many universities is threatened. To overcome this situation, universities are seeking ways to use big data within the school to improve the quality of education. A study on the prediction of dropout students is a representative case of using big data in universities. The dropout prediction can prepare a systematic management plan by identifying students who will drop out of school due to reasons such as dropout or expulsion. In the case of actual on-campus data, a large number of missing values are included because it is collected and managed by various departments. For this reason, it is necessary to construct a model by effectively reflecting the missing values. In this study, we propose a university student dropout prediction model based on eXtreme Gradient Boost that can be applied to data with many missing values and shows high performance. In order to examine the practical applicability of the proposed model, an experiment was performed using data from C University in Chungbuk. As a result of the experiment, the prediction performance of the proposed model was found to be excellent. The management strategy of dropout students can be established through the prediction results of the model proposed in this paper.

특허분류 체계를 활용한 유망기술 예측에 관한 연구

박상성 한국지능시스템학회 2023 한국지능시스템학회논문지 Vol.33 No.2

Global markets and technologies are rapidly changing together. The prediction ofpromising technologies is attracting attention as a tool for the survival of nationaltechnologies beyond universities and companies. In previous studies, promisingtechnology predictions were conducted mainly based on expert discussions inrelated fields. However, as the organic relationship between technologies becomesincreasingly complex, the need for data-based predictions of emerging technologiesis increasing. This paper proposes a methodology for predicting promisingtechnologies based on patents. The proposed method discovers promisingtechnologies by discovering key nodes and key rules through social networkanalysis and association rule mining. The experiment was conducted with 92,898patents related to materials. As a result, it is expected that chemical methods forprocessing fibrous materials and technologies for post-processing of fibrousmaterials will be promising. 글로벌 시장이 급변함에 따라 기술은 빠르게 변화하고 있다. 유망기술의 예측은 대학과 기업을 넘어 국가 기술의 생존을 위한 도구로 주목받고 있다. 종래의 유망기술 예측은 주로 관련 분야의 전문가 토의에 기반해 진행되었다. 그러나 기술 간의 유기적인 관계가 점차 복잡해짐에 따라 데이터 기반의 유망기술 예측에 대한 필요성이 증가하고 있다. 본 논문은 특허를 기반으로 한 유망기술 예측 방법론을 제안한다. 제안된 방법은 사회네트워크분석과 연관규칙마이닝을 통해 핵심 노드와 핵심 규칙을 발굴하여 유망기술을 발굴한다. 실험은 소재관련 특허 92,898건으로 진행했다. 실험 결과, 섬유질 소재를 처리하기 위한 화학적 방법과섬유질 소재의 사후 처리에 관한 기술이 유망할 것으로 기대된다.

퍼지 ART 신경망을 이용한 내용기반 영상검색

박상성,이만희,장동식,김재연 한국융합신호처리학회 2003 융합신호처리학회 논문지 (JISPS) Vol.4 No.2

본 논문은 퍼지 ART 신경망 알고리즘을 이용하여 내용기반 영상을 검색하는 연구를 제시한다. 대용량의 영상 데이터베이스를 검색할 때, 클러스터링은 빠른 검색을 위해 중요하다. 그러나 많은 양의 영상 데이터를 적절하게 클러스터링 하는 것은 상당히 어렵다. 기존의 유사도에 따른 검색 방법은 검색의 정확도가 떨어지고 검색시간이 많이 걸리는 단점이 있기 때문에 이러한 단점을 보완하는 방법이 필요하다. 본 논문에서는 앞서 언급한 문제점을 보완하기 위하여 신경망 알고리즘을 사용한 내용기반 영상검색 시스템을 제안한다. 퍼지 ART 신경망 알고리즘을 사용한 본 검색 시스템에서는 색상과 질감을 검색에 필요한 특징치로 잡아 데이터를 0과 1사이의 데이터로 정규화 하여 신경망 알고리즘의 입력 데이터로 넣어서 영상을 클러스터링 한 후 검색을 실시하였다 300개의 영상을 가지고 실험한 결과 약 87%의 검출률을 보여 주었다. This paper proposes content-based image retrieval system with fuzzy ART neural network algorithm. Retrieving large database of image data, the clustering is essential for fast retrieval. However, it is difficult to cluster huge image data pertinently, Because current retrieval methods using similarities have several problems like low accuracy of retrieving and long retrieval time, a solution is necessary to complement these problems. This paper presents a content-based image retrieval system with neural network in order to reinforce abovementioned problems. The retrieval system using fuzzy ART algorithm normalizes color and texture as feature values of input data between 0 and 1, and then it runs after clustering the input data. The implemental result with 300 image data shows retrieval accuracy of approximately 87%.

Technological cognitive diagnosis model for patent keyword analysis

박상성,Sunghae Jun 한국통신학회 2020 ICT Express Vol.6 No.1

Patent analysis has been performed in various areas of technology management to understand technology such as research and development planning, new product development, technology innovation, sustainable technology etc. In the patent analysis, the analysis of patent keywords with technological information is very popular and meaningful. So we study on a method for patent keyword analysis, and use the cognitive diagnosis model (CDM) to construct the proposed method. We call our method technological cognitive diagnosis model (TCDM), this provides significant technology structure for understanding target technology using the result of patent keyword analysis by TCDM. We illustrate the performance of the TCDM by the experiments using the patent documents related to artificial intelligence (AI) technology. The final goal of these experiments is to find the relationship between core technologies for AI.