• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.7 no.3
• /
• pp.48-55
• /
• 2004

본 연구는 중 저해상도 위성영상을 이용하여 하천주변 습지를 판별해내는 보다 개선된 기법을 개발해 내는데 그 목적이 있다. 중 저해상도 위성영상의 하나의 화소는 일반적으로 하나의 동질한 물체의 분광반사값을 나타내기보다는 다양한 분광값을 가진 물체들의 대표값으로 나타나게 된다. 특히 본 연구에서는 식생, 수문 및 토양요소의 혼합체인 습지의 판별을 위해서, 하나의 화소가 하나의 물체를 대표함을 전제로 하는 기존의 분석방법 보다는, 혼합화소 (mixed pixel)를 대상지 의 토지 피복을 가장 잘 반영 하는 순수한 화소값(endmember)들로 분해함으로써 보다 정확한 판별 및 분류를 가능케 하고자 하였다. 이를 위하여 일반적으로 극세분광 위성영상의 분석에 활용되는 기법인 분광혼합화소분석(Spectral Mixture Analysis)을 이용하였는데, 습지 각 화소의 식생, 수문 및 토양요소의 흔합정도를 분해한 후, 이들의 분할영상 (fraction images)을 추출해내고 이를 분석에 이용하였다. 팔당상수원보호구역의 소택형 습지를 대상으로 봄 가을의 Landsat 영상에 대한 분석을 수행하였으며, 도출된 결과는 다음과 같다. 첫째, 봄 가을 각각의 영상에 대하여 4개씩 endmember를 선정하였으며, 분할영상과 원자료 각각에 대하여 습지판별을 수행한 결과, 가을영상에 대하여 분할영상을 이용한 방법의 소택 형 습지 판별 정확도가 가장 높은 값을 보여주었다(생산자 정확도 : 83.3%, 사용자 정확도 : 86.5%). 둘째, 소택형 습지로 판별된 지역만을 대상으로 보다 세분화된 분류가 가능한 지 알아보기 위하여 소택형 습지로 판별된 지역의 영상에 대해 ISODATA 무감독분류를 수행한 결과 2개의 클러스터로 대별되었다. 현장조사, 기존 연구의 수심자료 및 식생에 대한 조사를 바탕으로 위의 2개의 클러스터를 조사한 결과, 수문조건에 따른 분류인 아계(subsystem) 단계의 '영구적 침수형 소택형 습지'와 '계절적 침수형 소택형 습지'로 분류할 수 있었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.7
• /
• pp.657-667
• /
• 2015

With development of technology and increase of commercial demand for unmanned aerial system(UAS), the related regulation has been prepared and complemented with the advanced countries such as Unite States and European Union(EU). However it is difficult for regulation to cover all areas of UASs practically since UASs have been developed in a variety of configurations and performance depending on their purpose. Therefore the reasonable criteria for the classification of UASs and their category should be suggested before development of the regulation. For this reason, many countries have been studying the standard for UASs classification and International Civil Aviation Organization(ICAO) makes an effort to prepare the international standards. In this paper, the new classification scheme which can complement domestic regulation is suggested based on investigation of the global trend of UAS classification and their researches.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5089-5096
• /
• 2010

Text categorization is one of important features in information searching system which classifies documents according to some criteria. The general method of categorization performs the classification of the target documents by eliciting important index words and providing the weight on them. Therefore, the effectiveness of algorithm is so important since performance and correctness of text categorization totally depends on such algorithm. In this paper, an enhanced method for text categorization by improving word weighting technique is introduced. A method called Okapi BM25 has been proved its effectiveness from some information retrieval engines. We applied Okapi BM25 and showed its good performance in the categorization. Various other words weights methods are compared: TF-IDF, TF-ICF and TF-ISF. The target documents used for this experiment is Reuter-21578, and SVM and KNN algorithms are used. Finally, modified Okapi BM25 shows the most excellent performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.652-657
• /
• 2015

BitTorrent is an innovative protocol related to file-sharing and file-transferring, which allows users to receive pieces of files from multiple sharer on the Internet to make the pieces into complete files. In reality, however, free distribution of illegal or copyright related video data is counted for crime. Difficulty of regulation on the copyright of data on BitTorrent is caused by the fact that data is transferred with the pieces of files instead of the complete file formats. Therefore, the classification process of file formats of the digital contents should take precedence in order to restore digital contents from the pieces of files received from BitTorrent, and to check the violation of copyright. This study has suggested SVM classifier for the classification of digital files, which has the feature vector of histogram differential on the pieces of files. The suggested classifier has evaluated the performance with the division factor by applying the classifier to three different formats of video files.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.293-300
• /
• 2011

The CGI(Computer-generated Image) techniques provide designers with an effective means of creating design artifacts in an automatic way. It has been pointed that two important activities while applying the CGI techniques are both image generation and managemental issues for the generated images. By applying automatic generation techniques for creation of images, designers can acquire benefits in that they can produce free style results in a simple way. Along with such benefits, it is also important for designer to identify and to establish well defined mechanisms for storing vast quantity of auto-generated CGIs. However, it is problematic to assign key-words and to classify abstract images mainly because they lack an analogy of the real world entities. This paper presents classification scheme for the abstract CGIs by applying classification and description criteria from the viewpoint of both design elements and emotional elements. Effective classification and specification can help designers build and retrieve desired images in an easy way, and make management process more simple and effective.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1210-1217
• /
• 2008

Sasang medicine is our country's unique traditional medicine based on the classification of individual physical constitution. In the Sasang medicine, what is considered the most important task is to categorize Sasang constitution exactly. Therefore, security of objective elements and diagnosis index is a problem awaiting solution in Sasang constitution classification. To this the paper abstracted result value from objectification, visualization, a fixed quantity of Sasang constitution to analyze face image signals and voice signals. And, comparing the differences constitution would like to develop system classification of Sasang constitution. Specially, image and voice signals are different because of gender, age, region so it composed Sasang constitution group to 40-50 years women in Seoul. To extract of these image and voice signals wanted to perform comparison, analysis in constitution. Finally, it would like to prove a significance of research result through experiment.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.133-138
• /
• 2012

Queries entered in a search box are the results of users' activities to actively seek information. Therefore, search logs are important data which represent users' information needs. The purpose of this study is to examine if there is a relationship between the results of queries automatically classified and the categories of documents accessed. Search sessions were identified in 2009 NDSL(National Discovery for Science Leaders) log dataset of KISTI (Korea Institute of Science and Technology Information). Queries and items used were extracted by session. The queries were processed using an automatic classifier. The identified queries were then compared with the subject categories of items used. As a result, it was found that the average similarity was 58.8% for the automatic classification of the top 100 queries. Interestingly, this result is a numerical value lower than 76.8%, the result of search evaluated by experts. The reason for this difference explains that the terms used as queries are newly emerging as those of concern in other fields of research.

• Journal of Information Technology and Architecture
• /
• v.9 no.2
• /
• pp.187-197
• /
• 2012

The investment on informatization has caused the increase in complexity of IT resources as well as inefficiency of Information system management and redundant investment. Thus, the idea of EA (Enterprise Architecture) was developed in order to manage the IT resources efficiently but the systematical guideline was insufficiently provided in data area.. Because of this, it is necessary to make full use of DRM (Data Reference Model) so we can enhance the sharing and reuse of data between several institutions in public sector by extracting and managing data behind processes. In this study, we recognize the necessity of improvement on data classification which is highly utilized and present the direction for the data classification rethesis.

• Journal of the Korea Institute of Building Construction
• /
• v.9 no.4
• /
• pp.147-155
• /
• 2009

Recently, the scale and technical complexity of agricultural production has been growing. Therefore, agricultural facilities are being gradually diversified, expanded, and made more complex. To furnish Korea's agricultural industry with international competitiveness, it is thus necessary to introduce new management techniques. The PCM (procurement-construction-maintenance) information management system for agricultural facilities is established by setting up its WBS (work breakdown structure). In this study, the WBS of a facility such as facility, space, element, works, and resources is analyzed. Following this analysts, a WBS of an agricultural facility that is appropriate for the PCM information system of an agricultural facility, is proposed by deriving it from actual WBS.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.63-70
• /
• 2009

BCI technology is to control communication systems or machines by brain signal among biological signals followed by signal processing. For the implementation of BCI systems, it is required that the characteristics of brain signal are learned and analyzed in real-time and the learned characteristics are applied. In this paper, we detect feature vector of EEG signal on left and right hand movements based on incremental approach and dimension reduction using the detected feature vector. In addition, we show that the reduced dimension can improve the classification performance by removing unnecessary features. The processed data including sufficient features of input data can reduce the time of processing and boost performance of classification by removing unwanted features. Our experiments using K-NN classifier show the proposed approach 5% outperforms the PCA based dimension reduction.