• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.

• 수산경영론집
• /
• 제38권2호
• /
• pp.1-24
• /
• 2007

The improvement and richness of research in a particular domain are fundamentally based on their own various research topics and scientific or systematic research methodology. Especially considering fisheries business administration as a branch of business administration, the interdisciplinary concept will be a important factor in the research of fisheries business administration. This study analyzes fisheries business administration research through bibliometric analysis and meta-analysis to examine meta-data including research trends, researcher characteristics, and keywords. The 225 source articles are all papers published from 1990 to 2006 in the Journal of Fisheries Business Administration Society of Korea. Comparing previous research from the 80s, the major areas of Korean fisheries business administration research have changed and the rate of co-researched papers has also increased. In keyword-based meta-analysis, the topics of recent research are well balanced and diversified but some structural and editorial problems still remain. The result from meta-data and bibliometric information gathered in this study will help create guidelines for carrying out further rigorous research and enhancing the quality of research in fisheries business administration.

• 산업융합연구
• /
• 제17권3호
• /
• pp.17-22
• /
• 2019

빅데이터의 가치가 중요하게 인식되면서 기존의 방대한 데이터들과 비정형 데이터들을 분석할 수 있는 JAVA 및 R 프로그램들이 개발되고 활용도가 높아짐에 따라 정부를 비롯한 공공기관, 민간기업 등에 실질적으로 도입 및 개선 할 수 있어 의사결정의 고도화가 가능하게 되었다. 본 연구에서는 소비자의 항공사 선호도에 따른 마케팅 전략을 수립하기 위해 뉴스 데이터를 클롤링하고 이를 텍스트 마이닝 기법을 통해 분석을 수행하였다. 본 연구는 과거 빅데이터에서 얻기 어려웠던 데이터들을 고도의 빅데이터 활용 프로그램 기법으로 소비자의 항공사 선호도를 분석하여 분석 결과에 따른 마케팅 전략을 수립하는데 의의가 있다.

• 정보화정책
• /
• 제30권3호
• /
• pp.29-48
• /
• 2023

디지털전환과 AI·데이터시대가 심화되면서 데이터의 원활한 흐름과 활용을 위한 데이터 정책, 그리고 그 의사결정 구조로서의 데이터 거버넌스에 대한 관심이 증대되고 있다. 기존의 데이터 거버넌스 연구들을 살펴보면, 데이터 거버넌스 자체의 측정이나 사례 분석은 많이 이루어지고 있으나 실증연구가 부족한 것으로 보인다. 이 논문에서는 데이터 거버넌스의 구성요소 간 구조적 관계와 그것이 목표로 하는 데이터 융합이나 데이터기반행정 등에 미치는 영향을 실증하고자 하였다. 첫째, 데이터 거버넌스에 대한 다양한 정의와 구성요소 및 유형화의 방식, 이를 적용한 선행연구들을 살펴보고, 공공 부문에 특화된 데이터 정책 관점의 정의를 개발하여 적용하였다. 둘째, 분석틀과 가설을 설정하고, 검증을 위해 한국행정연구원의 '공공데이터 정책 활용 실태조사' 자료를 분석하였다. 분석 결과, 데이터 거버넌스 구성요소 중 조직 요소가 제도 요소와 기술 요소 사이에서 매개적 효과를 나타내었고, 제도 요소와 기술 요소가 데이터 융합이나 데이터기반행정에 통계적으로 유의한 긍정적 영향을 미치는 것으로 나타났다. 셋째, 데이터 거버넌스에서 법제도의 개선과 개발에 대한 관심과 투자, 데이터 기술의 수단과 목적에 대한 명확화, 데이터 조직과 인력에 대한 관심과 실제적으로 작동할 수 있는 메커니즘의 개발 등, 몇 가지 중요한 정책적 시사점을 제시하였다.

• Journal of Astronomy and Space Sciences
• /
• 제35권3호
• /
• pp.175-183
• /
• 2018

Many recent satellites have mission periods longer than 10 years; thus, satellite-based local space weather monitoring is becoming more important than ever. This article describes the instruments and data applications of the Korea Space wEather Monitor (KSEM), which is a space weather payload of the GeoKompsat-2A (GK-2A) geostationary satellite. The KSEM payload consists of energetic particle detectors, magnetometers, and a satellite charging monitor. KSEM will provide accurate measurements of the energetic particle flux and three-axis magnetic field, which are the most essential elements of space weather events, and use sensors and external data such as GOES and DSCOVR to provide five essential space weather products. The longitude of GK-2A is $128.2^{\circ}E$, while those of the GOES satellite series are $75^{\circ}W$ and $135^{\circ}W$. Multi-satellite measurements of a wide distribution of geostationary equatorial orbits by KSEM/GK-2A and other satellites will enable the development, improvement, and verification of new space weather forecasting models. KSEM employs a service-oriented magnetometer designed by ESA to reduce magnetic noise from the satellite in real time with a very short boom (1 m), which demonstrates that a satellite-based magnetometer can be made simpler and more convenient without losing any performance.

• Asia pacific journal of information systems
• /
• 제32권3호
• /
• pp.496-513
• /
• 2022

Artificial intelligence or big data technologies can benefit finance companies such as those in the insurance sector. With artificial intelligence, companies can develop better customer segmentation methods and eventually improve the quality of customer relationship management. However, the application of AI-based customer segmentation in the insurance industry seems to have been unsuccessful. Findings from our interviews with sales agents and customer service managers indicate that current customer segmentation in the Korean insurance company relies upon individual agents' heuristic decisions rather than a generalizable data-based method. We propose guidelines for AI-based customer segmentation for the insurance industry, based on the CRISP-DM standard data mining project framework. Our proposed guideline provides new insights for studies on AI-based technology implementation and has practical implications for companies that deploy algorithm-based customer relationship management systems.

• 디지털융복합연구
• /
• 제12권1호
• /
• pp.89-97
• /
• 2014

빅데이터의 가치가 인식되고 정부 3.0이 발표되면서 빅데이터에 대한 관심이 증가하고 있다. 그러나 각 부처나 지방자치단체에 구체적인 추진 대안이나 전략이 취약한 상황에서 빅데이터를 체계적으로 활용하고 성과를 낸다는 것은 그리 쉬운 일이 아닐 것이다. 이에 본 연구는 지방자치단체의 빅데이터 활용 영역을 정리한 다음, 빅데이터 활용 전략을 제안하고자 하였다. 연구 결과 지방행정의 빅데이터 활용 영역은 크게 이상 현상 감지 및 대응, 가까운 미래 예측 및 대응, 분석된 상황 대응 및 새로운 정책(행정 서비스) 개발, 시민 맞춤형 서비스 등 네 가지로 구분되었다. 또한 빅데이터 활용 전략은 단계적 접근, 사용자의 요구분석, 주요성공요소 기반 추진, 시범사업, 성과평가, 성과에 따른 인센티브, 공통기반 구축 등으로 정리하였다.

• 수산경영론집
• /
• 제31권1호
• /
• pp.55-71
• /
• 2000

Being Changed the international fisheries situation to begin the WTO, it is important to increase the international competition power in fisheries environment to related our country. One of most important work is to build the Fisheries Information Systems(FIS), FIS should give to increase the efficiency of fisheries policies, to share the fisheries informations, and to increase the competitive power of international fisheries environment. On the conclusion, this paper has four expect effects to build the FIS. First, fisheries information will be supplied the clean fisheries policies based on FIS. Second, The Data Warehouse of FIS will be contributed to improve the criterion and statistics of fisheries data. Third, Fisheries Administration will increase the service between fisheries institutes using the FIS. Finally, fisheries administration will use the fisheries data efficiently as integrating the fisheries data into information systems.

• 지능정보연구
• /
• 제6권1호
• /
• pp.73-82
• /
• 2000

This study examined the characteristicso f the knowledge discovery and data mining algorithms to demonstrate how they can be used to predict health outcomes and provide policy information for hypertension management using the Korea Medical Insurance Corporation database. Specifically this study validated the predictive power of data mining algorithms by comparing the performance of logistic regression and two decision tree algorithms CHAID (Chi-squared Automatic Interaction Detection) and C5.0 (a variant of C4.5) since logistic regression has assumed a major position in the healthcare field as a method for predicting or classifying health outcomes based on the specific characteristics of each individual case. This comparison was performed using the test set of 4,588 beneficiaries and the training set of 13,689 beneficiaries that were used to develop the models. On the contrary to the previous study CHAID algorithm performed better than logistic regression in predicting hypertension but C5.0 had the lowest predictive power. In addition CHAID algorithm and association rule also provided the segment characteristics for the risk factors that may be used in developing hypertension management programs. This showed that data mining approach can be a useful analytic tool for predicting and classifying health outcomes data.

• 대기
• /
• 제33권1호
• /
• pp.33-47
• /
• 2023

In this study, for the application of observation errors to the Korean Integrated Model (KIM) to utilize the Constellation Observing System for Meteorology, Ionosphere & Climate-2 (COSMIC-2) new satellites, the observation errors were diagnosed based on the Desroziers method using the cost function in the process of variational data assimilation. We calculated observation errors for all observational species being utilized for KIM and compared with their relative values. The observation error of the calculated the Global Navigation Satellite System Radio Occultation (GNSS RO) was about six times smaller than that of other satellites. In order to balance with other satellites, we conducted two experiments in which the GNSS RO data expanded by about twice the observation error. The performance of the analysis field was significantly improved in the tropics, where the COSMIC-2 data are more available, and in the Southern Hemisphere, where the influence of GNSS RO data is significantly greater. In particular, the prediction performance of the Southern Hemisphere was improved by doubling the observation error in global region, rather than doubling the COSMIC-2 data only in areas with high density, which seems to have been balanced with other observations.