• 정보관리연구
• /
• 제35권3호
• /
• pp.109-123
• /
• 2004

과학기술정보의 의미적 상호운용성 문제는 빈번하게 발생한다. 잘 만들어진 분류체계는 상이한 데이터베이스 간에 의미상 불일치 없이 정보를 교환하기 위한 도구로 사용될 것이다. 하지만 각 데이터베이스가 취하고 있는 분류체계가 상이함으로 인해서 여전히 현실적인 장벽이 존재한다. 따라서 분류체계간의 일치 및 조화는 매우 시급한 문제이다. 본 논문의 목표는 다른 분류체계('국가과학기술표준분류'와 'KISTI 표준 분류')를 갖는 데이터베이스간의 정보 교환 시에 발생할 수 있는 의미적 불일치를 해결하는 것이다. 이를 위해서 과학기술의 개념적 체계 분석을 수행하였고 다섯가지의 일치/불일치 유형을 사례에 기반하여 분석하였다.

• 방사선산업학회지
• /
• 제8권3호
• /
• pp.155-159
• /
• 2014

RI-Biomics is a new concept that combines radioisotopes (RI) and Biomics. For efficient collection of information, establishment of database for technical information system and its application to the system, there is an increasing need for constructing the standard classification system of technical information by its systematical classification. In this paper, we have summarized the development process of the standard classification system of technical information in the field of RI-Biomics and its application to the system. Constructing the draft version for the standard classification system of technical information was based on that standard classification one in national science and technology in Korea. The final classification system was then derived through the reconstruction and the feedback process based on the consultation from the 7 experts. These results were applied to the database of technical information system after transforming as standard code. Thus, the standard classification system were composed of 5 large classifications and 20 small classifications, and those classification are expected to establish the foundation of information system by achieving the circular structure of collection-analysis-application of information.

• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1809-1816
• /
• 2021

국가연구개발사업 관련 데이터를 이용한 최신 연구동향 파악, 의미 있는 정보의 생산과 활용을 위해 국가R&D 정보 서비스에도 자동 분류 기술 적용이 요구되어 R&D과제의 연구분야를 자동 분류하고 추천하기 위한 연구를 진행했다. 2013~2020년 국가R&D 과제 데이터 약 45만 건을 수집하여 학습과 평가에 사용했다. 수집 데이터 중 유효한 데이터를 대상으로 데이터 전처리 및 분석, 실험을 통한 성능 분석 후 모델을 선정했다. 최적의 모델 조합 도출을 목적으로 Word2vec, GloVe, fastText 성능을 비교했다. 실험 결과, 과제정보의 필수 항목으로 사용되는 소분류만의 정확도는 90.11%이다. 이 모델은 국가과학기술표준분류 연구분야와 유사한 계층 구조를 가진 다른 분류체계의 자동 분류 연구에 활용 가능할 것으로 기대한다.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.133-141
• /
• 2023

This work take deeper analysis of Adaptive Moment Estimation (Adam) and Adam with Weight Decay (AdamW) implementation in real world text classification problem (DGA Malware Detection). AdamW is introduced by decoupling weight decay from L2 regularization and implemented as improved optimizer. This work introduces a novel implementation of AdamW variant as AdamW+ by further simplifying weight decay implementation in AdamW. DGA malware detection LSTM models results for Adam, AdamW and AdamW+ are evaluated on various DGA families/ groups as multiclass text classification. Proposed AdamW+ optimizer results has shown improvement in all standard performance metrics over Adam and AdamW. Analysis of outcome has shown that novel optimizer has outperformed both Adam and AdamW text classification based problems.

• International Journal of Knowledge Content Development & Technology
• /
• 제2권1호
• /
• pp.51-65
• /
• 2012

While science and technology information service portals and heterogeneous databases produced in Korea and other countries are integrated, methods of connecting the unique classification systems applied to each database have been studied. Results of technologists' research, such as, journal articles, patent specifications, and research reports, are organically related to each other. In this case, if the most basic and meaningful classification systems are not connected, it is difficult to achieve interoperability of the information and thus not easy to implement meaningful science technology information services through information convergence. This study aims to address the aforementioned issue by analyzing mapping systems between classification systems in order to design a structure to connect a variety of classification systems used in the academic information database of the Korea Institute of Science and Technology Information, which provides science and technology information portal service. This study also aims to design a mapping system for the classification systems to be applied to actual science and technology information services and information management systems.

• 정보관리연구
• /
• 제37권4호
• /
• pp.125-139
• /
• 2006

인터넷의 등장은 과학기술정보의 생산과 유통에 많은 변화를 초래하고 있다. 기존 과학기술정보들은 주로 문헌위주로 생산되었다. 그러나, 인터넷이 대중화되면서 온라인 과학기술정보들이 대량으로 생산되고 있으며, 그 활용이나 중요도 또한 과학기술분야의 문헌에 뒤지지 않고 있다. 온라인 과학기술정보의 양적 질적 성장으로 인해, 정보서비스기관들은 이들 정보들의 체계적인 관리와 효율적인 서비스를 고민하고 있으며, 다양한 정보관리방법을 모색하고 있다. 효율적인 정보 관리를 위한 방법 중의 하나인 분류체계는 주요한 이슈이며, 지금까지는 문헌정보 중심의 분류체계나 일반 웹사이트의 분류체계를 벤치마킹하여 온라인 과학기술정보를 위해 도입되는 경우가 많았다. 본고에서는 국가 차원의 표준분류를 이용하여, 온라인 과학기술정보를 위한 분류체계 구성방안을 실천적으로 제시하여 보았다.

• ETRI Journal
• /
• 제43권2호
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• 한국도서관정보학회지
• /
• 제53권2호
• /
• pp.95-115
• /
• 2022

이 연구의 목적은 국가과학기술표준분류체계의 소분류 용어를 기계학습 알고리즘을 적용하여 기술키워드 변환하는 것이 목적이다. 이를 위해 본 연구에서는 주제어 추천에 적합한 학습 알고리즘으로 AttentionMeSH를 활용했다. 원천데이터는 한국과학기술기획평가원이 정제한 2017년부터 2020년까지 4개년 연구현황 파일을 사용하였다. 학습은 과제명, 연구목표, 연구내용, 기대효과와 같이 연구내용을 잘 표현하고 있는 4개 속성을 사용했다. 그 결과 임계치(threshold)가 0.5일 때 MiF 0.6377이라는 결과가 도출됨을 확인하였다. 향후 실제 업무에 기계학습을 활용하고, 기술키워드 확보를 위해서는 용어관리체계 구축과 다양한 속성들의 데이터 확보가 필요할 것으로 보인다.

• 농업과학연구
• /
• 제48권3호
• /
• pp.617-627
• /
• 2021

In the field of on-road motor vehicles, the level for autonomous driving technology is defined according to J3016, proposed by Society of Automotive Engineers (SAE) International. However, in the field of agricultural machinery, different standards are applied by country and manufacturer, without a standardized classification for autonomous driving technology which makes it difficult to clearly define and accurately evaluate the autonomous driving technology, for agricultural machinery. In this study, a method to classify the autonomy levels for autonomous agricultural machinery (ALAAM) is proposed by modifying the SAE International J3016 to better characterize various agricultural operations such as tillage, spraying and harvesting. The ALAAM was classified into 6 levels from 0 (manual) to 5 (full automation) depending on the status of operator and autonomous system interventions for each item related to the automation of agricultural tasks such as straight-curve path driving, path-implement operation, operation-environmental awareness, error response, and task area planning. The core of the ALAAM classification is based on the relative roles between the operator and autonomous system for the automation of agricultural machines. The proposed ALAAM is expected to promote the establishment of a standard to classify the autonomous driving levels of self-propelled agricultural machinery.

• Journal of the Korean Wood Science and Technology
• /
• 제47권1호
• /
• pp.101-109
• /
• 2019

This paper examines the classification of five coniferous species, including larch (Larix kaempferi), red pine (Pinus densiflora), Korean pine (Pinus koraiensis), cedar (Cryptomeria japonica), and cypress (Chamaecyparis obtusa), using near-infrared (NIR) spectra. Fifty lumber samples were collected for each species. After air-drying the lumber, the NIR spectra (wavelength = 780-2500 nm) were acquired on the wide face of the lumber samples. Soft independent modeling of class analogy (SIMCA) was performed to classify the five species using their NIR spectra. Three types of spectra (raw, standard normal variated, and Savitzky-Golay $2^{nd}$ derivative) were used to compare the classification reliability of the SIMCA models. The SIMCA model based on Savitzky-Golay $2^{nd}$ derivatives preprocessing was determined as the best classification model in this study. The accuracy, minimum precision, and minimum recall of the best model (PCA models using Savitzky-Golay $2^{nd}$ derivative preprocessed spectra) were evaluated as 73.00%, 98.54% (Korean pine), and 67.50% (Korean pine), respectively.