• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1651-1669
• /
• 2023

Sea ice currently covers approximately 7% of the world's ocean area, primarily concentrated in polar and high-altitude regions, subject to seasonal and annual variations. It is very important to analyze the area and type classification of sea ice through time series monitoring because sea ice is formed in various types on a large spatial scale, and oil and gas exploration and other marine activities are rapidly increasing. Currently, research on the type and area of sea ice is being conducted based on high-resolution satellite images and field measurement data, but there is a limit to sea ice monitoring by acquiring field measurement data. High-resolution optical satellite images can visually detect and identify types of sea ice in a wide range and can compensate for gaps in sea ice monitoring using Geostationary Ocean Color Imager-II (GOCI-II), an ocean satellite with short time resolution. This study tried to find out the possibility of utilizing sea ice monitoring by training a rule-based machine learning model based on learning data produced using high-resolution optical satellite images and performing detection on GOCI-II images. Learning materials were extracted from Liaodong Bay in the Bohai Sea from 2021 to 2022, and a Random Forest (RF) model using GOCI-II was constructed to compare qualitative and quantitative with sea ice areas obtained from existing normalized difference snow index (NDSI) based and high-resolution satellite images. Unlike NDSI index-based results, which underestimated the sea ice area, this study detected relatively detailed sea ice areas and confirmed that sea ice can be classified by type, enabling sea ice monitoring. If the accuracy of the detection model is improved through the construction of continuous learning materials and influencing factors on sea ice formation in the future, it is expected that it can be used in the field of sea ice monitoring in high-altitude ocean areas.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.69-94
• /
• 2017

Recently, increase of demand for big data analysis has been driving the vigorous development of related technologies and tools. In addition, development of IT and increased penetration rate of smart devices are producing a large amount of data. According to this phenomenon, data analysis technology is rapidly becoming popular. Also, attempts to acquire insights through data analysis have been continuously increasing. It means that the big data analysis will be more important in various industries for the foreseeable future. Big data analysis is generally performed by a small number of experts and delivered to each demander of analysis. However, increase of interest about big data analysis arouses activation of computer programming education and development of many programs for data analysis. Accordingly, the entry barriers of big data analysis are gradually lowering and data analysis technology being spread out. As the result, big data analysis is expected to be performed by demanders of analysis themselves. Along with this, interest about various unstructured data is continually increasing. Especially, a lot of attention is focused on using text data. Emergence of new platforms and techniques using the web bring about mass production of text data and active attempt to analyze text data. Furthermore, result of text analysis has been utilized in various fields. Text mining is a concept that embraces various theories and techniques for text analysis. Many text mining techniques are utilized in this field for various research purposes, topic modeling is one of the most widely used and studied. Topic modeling is a technique that extracts the major issues from a lot of documents, identifies the documents that correspond to each issue and provides identified documents as a cluster. It is evaluated as a very useful technique in that reflect the semantic elements of the document. Traditional topic modeling is based on the distribution of key terms across the entire document. Thus, it is essential to analyze the entire document at once to identify topic of each document. This condition causes a long time in analysis process when topic modeling is applied to a lot of documents. In addition, it has a scalability problem that is an exponential increase in the processing time with the increase of analysis objects. This problem is particularly noticeable when the documents are distributed across multiple systems or regions. To overcome these problems, divide and conquer approach can be applied to topic modeling. It means dividing a large number of documents into sub-units and deriving topics through repetition of topic modeling to each unit. This method can be used for topic modeling on a large number of documents with limited system resources, and can improve processing speed of topic modeling. It also can significantly reduce analysis time and cost through ability to analyze documents in each location or place without combining analysis object documents. However, despite many advantages, this method has two major problems. First, the relationship between local topics derived from each unit and global topics derived from entire document is unclear. It means that in each document, local topics can be identified, but global topics cannot be identified. Second, a method for measuring the accuracy of the proposed methodology should be established. That is to say, assuming that global topic is ideal answer, the difference in a local topic on a global topic needs to be measured. By those difficulties, the study in this method is not performed sufficiently, compare with other studies dealing with topic modeling. In this paper, we propose a topic modeling approach to solve the above two problems. First of all, we divide the entire document cluster(Global set) into sub-clusters(Local set), and generate the reduced entire document cluster(RGS, Reduced global set) that consist of delegated documents extracted from each local set. We try to solve the first problem by mapping RGS topics and local topics. Along with this, we verify the accuracy of the proposed methodology by detecting documents, whether to be discerned as the same topic at result of global and local set. Using 24,000 news articles, we conduct experiments to evaluate practical applicability of the proposed methodology. In addition, through additional experiment, we confirmed that the proposed methodology can provide similar results to the entire topic modeling. We also proposed a reasonable method for comparing the result of both methods.

• Strategy21
• /
• s.31
• /
• pp.251-293
• /
• 2013

해적은 공해상 해상안전을 위협 한다는 점에서 '인류공동의 적'으로 규정되어 모든 국가가 이를 규제할 수 있는 보편적 관할권이 행사되는 범죄이다. 한국을 포함한 아시아 지역 국가들은 말라카해협 통항에 관해 깊은 이해관계를 갖고 있어 해적 소탕에 대한 의지가 강한 편이다. 이러한 의지는 2006년 '아시아해적퇴치정보공유센터(ReCAAP ISO)'의 창설에 밑거름이 되었으며, 아시아 지역에서 해적이 출현하면 동 센터를 통해 17개국 회원국으로 즉시 통보되고, 주변국의 해경과 해군이 유기적인 작전을 통해 해적을 효율적으로 퇴치하고 있는 모범사례다. 그러나 2009년 소말리아 내란에 따른 무정부 상태가 지속되면서 소말리아 및 아덴만에서의 해적활동이 극성을 부리기 시작했으며, 선박납치 행위가 급증하자 세계 각국에서 함정과 항공기를 파견하여 해적퇴치 활동을 전개하고 있으나 근절되지 않을 뿐만 아니라 해적의 활동해역이 확대되고 있다. 이러한 배경 하에 시작된 본 연구는 연구결과를 중심으로 다음과 같은 대응 방안을 제시한다. 첫째, 소말리아 해적의 근본원인은 국가의 붕괴에서 비롯된 치안부재와 열악한 경제사정 등 내부적인 요인이 크기 때문에 다국적 해군 활동으로 인한 근본적인 해적퇴치에는 한계가 있다. 따라서 국제적인 차원에서 '지역협력협정'체결은 물론, 소말리아 국가재건을 위한 노력이 함께 이루어지는 종합적인 대책이 필요하다. 그러나 보다 더 근본적인 해결책은 유엔차원에서 빠른 시간 내에 소말리아가 정치적 안정을 유지할 수 있도록 정치적 차원에서의 지원이 필요하며, 해적과 테러리스트가 연계됨으로써 국제문제로 확대되지 않도록 하는 노력도 병행되어야 한다. 둘째, 해적문제는 특정국가에만 해당되는 것이 아니라 초국가적인 문제임을 감안하여 유엔안전보장이사회 결의 제1851호에서 '지역 센터' 설립을 권고하고 있는 것처럼 2006년 아시아 국가들이 설치한 ReCAAP ISO와 같은 형태의 지역국가 간 협력기구 또는 유엔 차원의 해적 전담기구를 설치하여 국제사회 공조 하에 해적에 대처하는 방안을 추진하는 것이 필요하다. 셋째, 최근 발생하고 있는 해적행위는 주로 항구 등 내수, 영해 등 연안국의 관할권이 행사되는 지역에서 발생하고 있어 유엔해양법상의 규정은 이러한 '해적' 퇴치에 더 이상 효율적이지 못하다. 국제사회는 이러한 문제점을 인식하여 국제해사기구 (IMO) 등 국제기구를 통해 영해내의 해적 처벌을 위해 최선의 노력을 기울이고 있다. 향후 궁극적으로는 유엔해양법협약의 개정을 통해 법적인 문제점이 개선되어야 한다. 넷째, 전술적인 측면에서도 지상에 기지를 두고 있는 해적들의 지도부가 그 동안 쌓아 놓은 네트워크를 이용하여 다국적 해군에 대한 정보를 수집하고 대응방안을 강구함으로써 나름대로의 생존전략을 구사할 것으로 예상된다. 특히, 선박을 납치한 후 소말리아 연안으로 이동하면서 해군함정과 대치하는 과정에서 해적들이 살상을 당하는 사례가 증가함에 따라 지금까지는 피랍된 선박의 선원을 단순히 해적활동에 참여시키거나, 항해지원을 위한 목적 등으로만 활용했는데, 앞으로는 해적들의 인명피해를 최소화하기 위해서라도 선원들을 방패막이로 활용할 가능성이 더욱 높아질 것으로 예상된다. 따라서 참가하는 해군함정 또는 부대간 해적들의 활동 관련 정보를 공유하는 등 사전에 정보를 획득하기 위한 협력을 강화해야 한다. 다섯째, 한국군함이 삼호주얼리호를 납치했던 소말리아 해적을 한국까지 대리고 와서 처벌하는 것은 불합리하고, 많은 문제점을 야기할 수 있기 때문에 향후 해적처벌을 위한 국제사법기구의 설치가 요구된다. 회원국 분담금으로 운영되는 유엔에 산하기관을 설치하여 소말리아 인접국에서 해결하도록 적극적인 노력을 경주할 필요가 있다. 마지막으로, 선박회사에서도 자국 선박이 위험구역으로 지정된 해역을 항해할 경우를 대비해서 선박자동식별 시스템 구축을 확대하고, 해적이 선박에 승선했을 경우를 대비해서 안전구역(citadel)을 설치하여 선원의 안전을 확보하는 등의 대책이 필요하다. 본 연구를 통해 해양안보는 어느 특정국가에게만 주어진 것이 아니며, 해적행위도 특정 국가의 선박을 대상으로 하는 것이 아니므로 각국 정부간 공동의 협력과 국제사회의 공조가 반드시 실현될 때 해적의 위협으로부터 선박의 안전과 국제사회의 평화가 실현될 수 있다는 것을 강조하고자 한다.

• Journal of Korean Society of Forest Science
• /
• v.103 no.3
• /
• pp.339-352
• /
• 2014

The study was carried out to analyze vegetation structure of Pinus densiflora and Quercus mongolica forests located in Jochimryeong to Shinbaeryeong of the Baekdudaegan mountain range. The survey for 50 plots was conducted from April 2012 to August 2013 in the permanent plots ($100m{\times}100m$) using phytosociological analysis. As a result, the vegetations were classified into five vegetation units. In species composition, they were classified into Q. mongolica community group divided into 2 community such as Fraxinus rhynchophylla community and Carpinus cordata community, F. rhynchophylla community was subdivided Pinus densiflor group (into Euonymus sachalinensis subgroup, Vitis coignetiae subgroup) and Juglans mandshurica group. C. cordata community was subdivided Acer komarovii group and Betula ermanii group. In terms of importance value, P. densiflora and Q. mongolica were more than 20% respectively. P. densiflora was found to have the highest relative coverage. Analysis of interspecific association showed four types which were coincident with differential species and character species on the constancy table. Based on the diameter class distribution, P. densiflora forest presented a normal distribution pattern except for other species which showed a reverse Jshaped distribution pattern, therefore P. densiflora forest would likely be replaced by Q. mongolica forests. While in Q. mongolica forest, diameter class distribution of all species population presented a reverse J-shaped distribution pattern, therefore Q. mongolica forest could likely remain in the future.

• Journal of Dairy Science and Biotechnology
• /
• v.32 no.1
• /
• pp.17-29
• /
• 2014

GRAS probiotics can be used to modulate intestinal microbiota and to alleviate various gastrointestinal disorders. In several recent studies, researchers have explored the potential expansion and usability of probiotics to reduce the risk factors associated with diseases, including obesity, hypercholesterolemia, arterial hypertension, hyperhomocysteinemia, and oxidative stress. In this review, our aim was to clarify the mechanism underlying interactions between hosts (animal or human) and probiotics and the beneficial effects of probiotics on human health.

• Journal of Plant Biotechnology
• /
• v.45 no.3
• /
• pp.250-256
• /
• 2018

To determine whether metabolite fingerprinting for whole cell extracts based on Fourier transform infrared spectroscopy (FT-IR) can be used to discriminate and compare metabolic equivalence, standard medicinal parts of Cynanchum wilfordii (Maxim.) Hemsl. and their adventitious roots were subjected to FT-IR. The principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) from FT-IR spectral data showed that whole metabolic pattern from the adventitious root of Cynanchum wilfordii was highly similar to its standard medicinal parts. These results clearly showed that mass proliferation of adventitious roots could be applied for the novel supply of standard medicinal parts of medicinal plants. Furthermore, FT-IR spectroscopy combined with multivariate analysis established in this study could be applied as an alternative tool for discriminating of whole metabolic equivalence from standard medicinal parts. Thus, it is proposed that these metabolic discrimination systems from the adventitious root of Cynanchum wilfordii could be applied for metabolic standardization of in vitro grown Cynanchum wilfordii.

• Korean Security Journal
• /
• no.21
• /
• pp.155-175
• /
• 2009

RFID that provide automatic identification by reading a tag attached to material through radio frequency without direct touch has some specification, such as rapid identification, long distance identification and penetration, so it is being used for distribution, transportation and safety by using the frequency of 125KHz, 134KHz, 13.56MHz, 433.92MHz, 900MHz, and 2.45GHz. Also it is one of main part of Ubiquitous that means connecting to net-work any time and any place they want. RFID is expected to be new growth industry worldwide, so Korean government think it as prospective field and promote research project and exhibition business program to linked with industry effectively. RFID could be used for access control of person and vehicle according to section and for personal certify with password. RFID can provide more confident security than magnetic card, so it could be used to prevent forgery of register card, passport and the others. Active RFID could be used for protecting operation service using it's long distance date transmission by application with positioning system. And RFID's identification and tracking function can provide effective visitor management through visitor's register, personal identification, position check and can control visitor's movement in the secure area without their approval. Also RFID can make possible of the efficient management and prevention of loss of carrying equipments and others. RFID could be applied to copying machine to manager and control it's user, copying quantity and It could provide some function such as observation of copy content, access control of user. RFID tag adhered to small storage device prevent carrying out of item using the position tracking function and control carrying-in and carrying-out of material efficiently. magnetic card and smart card have been doing good job in identification and control of person, but RFID can do above functions. RFID is very useful device but we should consider the prevention of privacy during its application.

• Journal of Korea Spatial Information System Society
• /
• v.3 no.2 s.6
• /
• pp.21-43
• /
• 2001

The environment to development information system including a GIS has been drastically changed in recent years in the perspectives of the complexity and diversity of the software, and the distributed processing and network computing, etc. This leads the paradigm of the software development to the CBD(Component Based Development) based object-oriented technology. As an effort to support these movements, OGC has released the abstract and implementation standards to enable approaching to the service for heterogeneous geographic information processing. It is also common trend in domestic field to develop the GIS application based on the component technology for municipal governments. Therefore, it is imperative to adopt the component technology considering current movements, yet related research works have not been made. This research is to propose a component-based GIS development methodology-ATOM(Advanced Technology Of Methodology)-and to verify its adoptability through the case study. ATOM can be used as a methodology to develop component itself and enterprise GIS supporting the whole procedure for the software development life cycle based on conventional reusable component. ATOM defines stepwise development process comprising activities and work units of each process. Also, it provides input and output, standardized items and specs for the documentation, detailed instructions for the easy understanding of the development methodology. The major characteristics of ATOM would be the component-based development methodology considering numerous features of the GIS domain to generate a component with a simple function, the smallest size, and the maximum reusability. The case study to validate the adoptability of the ATOM showed that it proves to be a efficient tool for generating a component providing relatively systematic and detailed guidelines for the component development. Therefore, ATOM would lead to the promotion of the quality and the productivity for developing application GIS software and eventually contribute to the automatic production of the GIS software, the our final goal.

• 한국해양학회지
• /
• v.8 no.1
• /
• pp.33-45
• /
• 1973

Plankton samples used for the present study were collected by the NORPAC net during the CSK cruises in the Korean waters in March and August, 1967. Regional and seasonal variations in the zooplankton biomass (wet weight, mg/㎥) were noticed in the Korean waters. In March the highest biomass, 130mg/㎥ on the average, occurred in the southern part of Japan Sea, but the lowest biomass of less than 50mg/㎥ occurred in the Yellow Sea and the western sea of Cheju Island Contrally, in August, the average biomass of 120mg/㎥ was measured in the Yellow Sea, the western sea of Cheju Island and the coastal waters of southern Korea, while the biomass of Japan Sea was the lowest of the regions surveyed. In comparison with the zooplankton biomass, total number of zooplankton per cubic meter of water strained also showed regional and seasonal fluctuations. In general, variations in the number of zooplankton specimens follows the same trend as in the biomass. The largest number, up to 800mg/㎥ on the average, occurred in the southern part of Japan Sea in March and the lowest number, less than 200mg/㎥ occurred in the Yellow Sea and the western sea of Cheju Island. In August, as shown by the biomass fluctuations, the largest number of zooplankton 850mg/㎥ on the average occurred in the Yellow Sea, the western sea of Cheju Island and the coastal region of southern Korea. But the lowest number of less than 500mg/㎥ was found in the Japan Sea. Among the various groups of zooplankton examined, the following were dominant components of the zooplankton population: Copepoda, Chaetognatha, Siphonophora, Euphausiacea, Cladocera, Appendicularia, and Amphipoda. The zooplankton conposition was significantly differed between the Japan Sea and Yellow Sea. Copepods which usually occupied over 66% in the Japan Sea and thd Korean Strait samples occupied only 42% of the catches in August, while cladocerans and chaetognaths were relatively abundant, i. e., 15 and 18% of the total organisms. The most dominant species of copepods and chaetognaths were Paracalanus parvus, Oithona similis, Acartia clausi, Calanus helgolandicus, Sagitta enflata, S. bedoti, S. elegans and S. crassa.