• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.351-361
• /
• 2024

Satellite imagery contains various elements such as clouds, cloud shadows, and terrain shadows. Accurately identifying and eliminating these factors that complicate satellite image analysis is essential for maintaining the reliability of remote sensing imagery. For this reason, satellites such as Landsat-8, Sentinel-2, and Compact Advanced Satellite 500-1 (CAS500-1) provide Usable Data Masks(UDMs)with images as part of their Analysis Ready Data (ARD) product. Precise detection of clouds and their shadows is crucial for the accurate construction of these UDMs. Existing cloud and their shadow detection methods are categorized into threshold-based methods and Artificial Intelligence (AI)-based methods. Recently, AI-based methods, particularly deep learning networks, have been preferred due to their advantage in handling large datasets. This study aims to analyze the applicability of constructing UDMs for high-resolution satellite images through deep learning-based cloud and their shadow detection using open-source datasets. To validate the performance of the deep learning network, we compared the detection results generated by the network with pre-existing UDMs from Landsat-8, Sentinel-2, and CAS500-1 satellite images. The results demonstrated that high accuracy in the detection outcomes produced by the deep learning network. Additionally, we applied the network to detect cloud and their shadow in KOMPSAT-3/3A images, which do not provide UDMs. The experiment confirmed that the deep learning network effectively detected cloud and their shadow in high-resolution satellite images. Through this, we could demonstrate the applicability that UDM data for high-resolution satellite imagery can be constructed using the deep learning network.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.1-23
• /
• 2013

To discover significant social issues such as unemployment, economy crisis, social welfare etc. that are urgent issues to be solved in a modern society, in the existing approach, researchers usually collect opinions from professional experts and scholars through either online or offline surveys. However, such a method does not seem to be effective from time to time. As usual, due to the problem of expense, a large number of survey replies are seldom gathered. In some cases, it is also hard to find out professional persons dealing with specific social issues. Thus, the sample set is often small and may have some bias. Furthermore, regarding a social issue, several experts may make totally different conclusions because each expert has his subjective point of view and different background. In this case, it is considerably hard to figure out what current social issues are and which social issues are really important. To surmount the shortcomings of the current approach, in this paper, we develop a prototype system that semi-automatically detects social issue keywords representing social issues and problems from about 1.3 million news articles issued by about 10 major domestic presses in Korea from June 2009 until July 2012. Our proposed system consists of (1) collecting and extracting texts from the collected news articles, (2) identifying only news articles related to social issues, (3) analyzing the lexical items of Korean sentences, (4) finding a set of topics regarding social keywords over time based on probabilistic topic modeling, (5) matching relevant paragraphs to a given topic, and (6) visualizing social keywords for easy understanding. In particular, we propose a novel matching algorithm relying on generative models. The goal of our proposed matching algorithm is to best match paragraphs to each topic. Technically, using a topic model such as Latent Dirichlet Allocation (LDA), we can obtain a set of topics, each of which has relevant terms and their probability values. In our problem, given a set of text documents (e.g., news articles), LDA shows a set of topic clusters, and then each topic cluster is labeled by human annotators, where each topic label stands for a social keyword. For example, suppose there is a topic (e.g., Topic1 = {(unemployment, 0.4), (layoff, 0.3), (business, 0.3)}) and then a human annotator labels "Unemployment Problem" on Topic1. In this example, it is non-trivial to understand what happened to the unemployment problem in our society. In other words, taking a look at only social keywords, we have no idea of the detailed events occurring in our society. To tackle this matter, we develop the matching algorithm that computes the probability value of a paragraph given a topic, relying on (i) topic terms and (ii) their probability values. For instance, given a set of text documents, we segment each text document to paragraphs. In the meantime, using LDA, we can extract a set of topics from the text documents. Based on our matching process, each paragraph is assigned to a topic, indicating that the paragraph best matches the topic. Finally, each topic has several best matched paragraphs. Furthermore, assuming there are a topic (e.g., Unemployment Problem) and the best matched paragraph (e.g., Up to 300 workers lost their jobs in XXX company at Seoul). In this case, we can grasp the detailed information of the social keyword such as "300 workers", "unemployment", "XXX company", and "Seoul". In addition, our system visualizes social keywords over time. Therefore, through our matching process and keyword visualization, most researchers will be able to detect social issues easily and quickly. Through this prototype system, we have detected various social issues appearing in our society and also showed effectiveness of our proposed methods according to our experimental results. Note that you can also use our proof-of-concept system in http://dslab.snu.ac.kr/demo.html.

• Horticultural Science & Technology
• /
• v.32 no.1
• /
• pp.105-114
• /
• 2014

We established a high throughput screening system of African yam tuber lines which contain high contents of total carotenoids, flavonoids, and phenolic compounds using ultraviolet-visible (UV-VIS) spectroscopy and Fourier transform infrared (FT-IR) spectroscopy in combination with multivariate analysis. The total carotenoids contents from 62 African yam tubers varied from 0.01 to $0.91{\mu}g{\cdot}g^{-1}$ dry weight (wt). The total flavonoids and phenolic compounds also varied from 12.9 to $229{\mu}g{\cdot}g^{-1}$ and from 0.29 to $5.2mg{\cdot}g^{-1}$dry wt. FT-IR spectra confirmed typical spectral differences between the frequency regions of 1,700-1,500, 1,500-1,300 and $1,100-950cm^{-1}$, respectively. These spectral regions were reflecting the quantitative and qualitative variations of amide I, II from amino acids and proteins ($1,700-1,500cm^{-1}$), phosphodiester groups from nucleic acid and phospholipid ($1,500-1,300cm^{-1}$) and carbohydrate compounds ($1,100-950cm^{-1}$). Principal component analysis (PCA) and subsequent partial least square-discriminant analysis (PLS-DA) were able to discriminate the 62 African yam tuber lines into three separate clusters corresponding to their taxonomic relationship. The quantitative prediction modeling of total carotenoids, flavonoids, and phenolic compounds from African yam tuber lines were established using partial least square regression algorithm from FT-IR spectra. The regression coefficients ($R^2$) between predicted values and estimated values of total carotenoids, flavonoids and phenolic compounds were 0.83, 0.86, and 0.72, respectively. These results showed that quantitative predictions of total carotenoids, flavonoids, and phenolic compounds were possible from FT-IR spectra of African yam tuber lines with higher accuracy. Therefore we suggested that quantitative prediction system established in this study could be applied as a rapid selection tool for high yielding African yam lines.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• 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.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2004.08a
• /
• pp.104-117
• /
• 2004

Dmitri Donskoi, which went down during the Russo-Japanese War occurred 100 years ago, was found by using geophysical exploration techniques at the 400 m water depth of submarine valley off Jeodong of Ulleung Island. In the submarine area with the rugged seabed topography and volcanic seamounts, in particular, the reliable seabed images were acquired by using the mid-to-shallow Multibeam exploration technique The strength of corrosion (causticity) of the sunken Donskoi, measured by the electrochemical method, decreased to 2/5 compared with the original strength.

• Korean journal of food and cookery science
• /
• v.22 no.6 s.96
• /
• pp.875-881
• /
• 2006

This study was carried out to investigate work analysis and productivity of school foodservice systems through Questionnaire. The subjects Participated in this survey were 342 cook who engaged in school foodservice. The results were as follows : Average number of meal produced by a cook was 114 meals and 85 meals in conventional and commissary foodservice, respectively. Average lead time per meal were 7.65 and 9.37 minutes in conventional and commissary foodservice. It was no significant in average lead time per meal before noon were 2.86 and 3.35 minutes, as working time before dining and total working time of commissary foodservice required more time than conventional foodservice in conventional and commissary foodservice.

• Journal of KIISE:Databases
• /
• v.28 no.4
• /
• pp.529-544
• /
• 2001

Prefetching is an effective method to minimize the number of roundtrips between the client and the server in database management systems. In this paper we propose new notions of the type-level access pattern and the type-level access locality and developed an efficient prefetchin policy based on the notions. The type-level access patterns is a sequence of attributes that are referenced in accessing the objects: the type-level access locality a phenomenon that regular and repetitive type-level access patterns exist. Existing prefetching methods are based on object-level or page-level access patterns, which consist of object0ids of page-ids of the objects accessed. However, the drawback of these methods is that they work only when exactly the same objects or pages are accessed repeatedly. In contrast, even though the same objects are not accessed repeatedly, our technique effectively prefetches objects if the same attributes are referenced repeatedly, i,e of there is type-level access locality. Many navigational applications in Object-Relational Database Management System(ORDBMs) have type-level access locality. Therefore our technique can be employed in ORDBMs to effectively reduce the number of roundtrips thereby significantly enhancing the performance. We have conducted extensive experiments in a prototype ORDBMS to show the effectiveness of our algorithm. Experimental results using the 007 benchmark and a real GIS application show that our technique provides orders of magnitude improvements in the roundtrips and several factors of improvements in overall performance over on-demand fetching and context-based prefetching, which a state-of the art prefetching method. These results indicate that our approach significantly and is a practical method that can be implemented in commercial ORDMSs.

• Journal of agriculture & life science
• /
• v.46 no.5
• /
• pp.73-82
• /
• 2012

Allele information from the analysis of the 13 microsatellite (MS) markers, were classified into the $F_0$, $F_1$ and $F_2$ generations, and probabilities of the same individual emergency in each generation was calculated. As a result, the 13 MS markers showed an estimate of $3.84{\times}10^{-23}$ on the premise of the randomly mated group of $F_2$, which implies that the same individuals may emerge by the use of 37 kinds of SNP markers. In this study, the experimental pigs were intercross between only 2 breeds (Korean native pig and Landrace). In addition, the success rate of paternity tests was analyzed on the whole group, by the use of the 13 MS markers and 37 SNP markers. As regards the exclusionary power of the second parent ($PE_{pu}$), MS markers and SNP markers showed 0.97897 and 0.99149, respectively. In relation to the parent exclusion power of both parent (PE), MS markers and SNP markers showed 0.99916 and 0.99949, respectively. In the case of the estimate to identify parental candidates that had the highest probability ($PNE_{pp}$), the two showed 1.00000 all. The Korean pig industry tends to mass produce hogs with limited numbers of alleles in limited parents. Such being the case, there is a need to organize a marker, for which it is imperative to find markers with high efficiency and high economic feasibility of the characteristics of DNA markers, sample size, the accuracy and expenses of genotyping cost, the manageability of data and the compatibility among analysis systems.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.57-75
• /
• 2019

In this paper, we conducted a study focusing on the innovation direction of the documentary model on the Internet of Things industry, which is the most actively industrialized among the core technologies of the 4th Industrial Revolution. Policy, economic, social, and technical issues were derived using PEST analysis for global trend analysis. It also presented future prospects for the Internet of Things industry of ICT-related global research institutes such as Gartner and International Data Corporation. Global research institutes predicted that competition in network technologies will be an issue for industrial Internet (IIoST) and IoT (Internet of Things) based on infrastructure and platforms. As a result of the PEST analysis, developed countries are pushing policies to respond to the fourth industrial revolution through cooperation of private (business/ research institutes) led by the government. It was also in the process of expanding related R&D budgets and establishing related policies in South Korea. On the economic side, the growth tax of the related industries (based on the aggregate value of the market) and the performance of the entity were reviewed. The growth of industries related to the fourth industrial revolution in advanced countries overseas was found to be faster than other industries, while in Korea, the growth of the "technical hardware and equipment" and "communication service" sectors was relatively low among industries related to the fourth industrial revolution. On the social side, it is expected to cause enormous ripple effects across society, largely due to changes in technology and industrial structure, changes in employment structure, changes in job volume, etc. On the technical side, changes were taking place in each industry, representing the health and medical sectors and manufacturing sectors, which were rapidly changing as they merged with the technology of the Fourth Industrial Revolution. In this paper, various management methodologies for innovation of existing business model were reviewed to cope with rapidly changing industrial environment due to the fourth industrial revolution. In addition, four criteria were established to select a management model to cope with the new business environment: 'Applicability', 'Agility', 'Diversity' and 'Connectivity'. The expert survey results in an AHP analysis showing that Business Model Canvas is best suited for business model innovation methodology. The results showed very high importance, 42.5 percent in terms of "Applicability", 48.1 percent in terms of "Agility", 47.6 percent in terms of "diversity" and 42.9 percent in terms of "connectivity." Thus, it was selected as a model that could be diversely applied according to the industrial ecology and paradigm shift. Business Model Canvas is a relatively recent management strategy that identifies the value of a business model through a nine-block approach as a methodology for business model innovation. It identifies the value of a business model through nine block approaches and covers the four key areas of business: customer, order, infrastructure, and business feasibility analysis. In the paper, the expansion and application direction of the nine blocks were presented from the perspective of the IoT company (ICT). In conclusion, the discussion of which Business Model Canvas models will be applied in the ICT convergence industry is described. Based on the nine blocks, if appropriate applications are carried out to suit the characteristics of the target company, various applications are possible, such as integration and removal of five blocks, seven blocks and so on, and segmentation of blocks that fit the characteristics. Future research needs to develop customized business innovation methodologies for Internet of Things companies, or those that are performing Internet-based services. In addition, in this study, the Business Model Canvas model was derived from expert opinion as a useful tool for innovation. For the expansion and demonstration of the research, a study on the usability of presenting detailed implementation strategies, such as various model application cases and application models for actual companies, is needed.