• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.193-203
• /
• 2009

Snow cover is one of the important parameters since it determines surface energy balance and its variation. To classify snow and cloud from satellite data is very important process when inferring land surface information. Generally, misclassified cloud and snow pixel can lead directly to error factor for retrieval of surface products from satellite data. Therefore, in this study, we perform algorithm for detecting snow cover area with remote sensing data. We just utilize visible reflectance, and infrared channels rather than using NDSI (Normalized Difference Snow Index) which is one of optimized methods to detect snow cover. Because COMS MI (Meteorological Imager) channels doesn't include near infra-red, which is used to produce NDSI. Detecting snow cover with visible channel is well performed over clear sky area, but it is difficult to discriminate snow cover from mixed cloudy pixels. To improve those detecting abilities, brightness temperature difference (BTD) between 11 and 3.7 is used for snow detection. BTD method shows improved results than using only visible channel.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2021

An Automated Industry and Occupation Coding System assigns statistical classification code to the enormous amount of natural language data collected from people who write about their industry and occupation. Unlike previous studies that applied information retrieval, we propose a system that does not need an index database and gives proper code regardless of the level of classification. Also, we show our model, which utilized KoBERT that achieves high performance in natural language downstream tasks with deep learning, outperforms baseline. Our method achieves 95.65%, 91.51%, and 97.66% in Occupation/Industry Code Classification of Population and Housing Census, and Industry Code Classification of Census on Basic Characteristics of Establishments. Moreover, we also demonstrate future improvements through error analysis in the respect of data and modeling.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.1-6
• /
• 2023

Morphological analysis is a branch of natural language processing, is now a rapidly growing field. The fundamental tenet of morphological analysis is that it can establish the roots or stems of words and enable comparison to the original term. Arabic is a highly inflected and derivational language and it has a strong structure. Each root or stem can have a large number of affixes attached to it due to the non-concatenative nature of Arabic morphology, increasing the number of possible inflected words that can be created. Accurate verb recognition and extraction are necessary nearly all issues in well-known study topics include Web Search, Information Retrieval, Machine Translation, Question Answering and so forth. in this work we have designed and implemented an algorithm to detect and recognize Arbic Verbs from Arabic text.The suggested technique was created with "Python" and the "pyqt5" visual package, allowing for quick modification and easy addition of new patterns. We employed 17 alternative patterns to represent all verbs in terms of singular, plural, masculine, and feminine pronouns as well as past, present, and imperative verb tenses. All of the verbs that matched these patterns were used when a verb has a root, and the outcomes were reliable. The approach is able to recognize all verbs with the same structure without requiring any alterations to the code or design. The verbs that are not recognized by our method have no antecedents in the Arabic roots. According to our work, the strategy can rapidly and precisely identify verbs with roots, but it cannot be used to identify verbs that are not in the Arabic language. We advise employing a hybrid approach that combines many principles as a result.

• The KIPS Transactions:PartD
• /
• v.16D no.4
• /
• pp.475-486
• /
• 2009

Data cube plays an important role in multi-dimensional, multi-level data analysis. Meeting on-line analysis requirements of data stream, several cube structures have been proposed for OLAP on data stream, such as stream cube, flowcube, S-cube. Since it is costly to construct data cube and execute ad-hoc OLAP queries, more research works should be done considering efficient data structure, query method and algorithms. Stream cube uses H-cubing to compute selected cuboids and store the computed cells in an H-tree, which form the cuboids along popular-path. However, the H-tree layoutis disorderly and H-cubing method relies too much on popular path.In this paper, first, we propose $H^*$-tree, an improved data structure, which makes the retrieval operation in tree structure more efficient. Second, we propose an improved cubing method, $H^*$-cubing, with respect to computing the cuboids that cannot be retrieved along popular-path when an ad-hoc OLAP query is executed. $H^*$-tree construction and $H^*$-cubing algorithms are given. Performance study turns out that during the construction step, $H^*$-tree outperforms H-tree with a more desirable trade-off between time and memory usage, and $H^*$-cubing is better adapted to ad-hoc OLAP querieswith respect to the factors such as time and memory space.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.8 no.2
• /
• pp.67-78
• /
• 2013

Objectives : The present study examines the domestic trend of Osteoporosis studies in Korea. Method : We reviewed oriental medicine papers published in last ten years (2003-2012). Korean literature search was used for domestic Internet search portal. 'Naver specialized information retrieval', 'Korea Traditional Knowledge Portal', 'Korea Medical Information Portal (OASIS)',' Scientific and Technological Information Integration Services (NDSL)',' Academic Research Information Service (RISS)'as the primary destination of the search were. Since 2003 until 2012, the thesis o'f osteoporosis'and found 92 papers with the search term '(golwi)' to the search terms found in 3 papers Korean medical target of on going research trends in osteoporosis about investigated. Results : 1. We researched 95 papers in 15 journals and patterns of study were as follows : experimental studies were 79(83%), clinical studies were 12(13%), reviewed studies were 3(3%) and etc. were 1(1%). 2. The experimental studies(79) were divided into papers on efficiency testing of herbal medications(67) and herbal acupuncture(12). 3. The clinical studies(12) showed that research has been carried out in the fields of follow up surveys for the herbal medication efficiency testing, basic research, case report, the relativity of osteoporosis to age and sex, and the perception about osteoporosis and korean medicine treatment. 4. The reviewed studies showed that research has been carried out in the fields of osteoporosis about acient literature and domestic studies about herbal medication of osteoporosis. Conclusion : Reviewing the domestic trend of Osteoporosis studies and examining the strong and weak points of those treatments are essential for the future studies. It is anticipated that this review benefits the future in-depth study on the treatments for osteoporosis in Korean medicine.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.43-61
• /
• 2019

Development of technologies in artificial intelligence has been rapidly increasing with the Fourth Industrial Revolution, and researches related to AI have been actively conducted in a variety of fields such as autonomous vehicles, natural language processing, and robotics. These researches have been focused on solving cognitive problems such as learning and problem solving related to human intelligence from the 1950s. The field of artificial intelligence has achieved more technological advance than ever, due to recent interest in technology and research on various algorithms. The knowledge-based system is a sub-domain of artificial intelligence, and it aims to enable artificial intelligence agents to make decisions by using machine-readable and processible knowledge constructed from complex and informal human knowledge and rules in various fields. A knowledge base is used to optimize information collection, organization, and retrieval, and recently it is used with statistical artificial intelligence such as machine learning. Recently, the purpose of the knowledge base is to express, publish, and share knowledge on the web by describing and connecting web resources such as pages and data. These knowledge bases are used for intelligent processing in various fields of artificial intelligence such as question answering system of the smart speaker. However, building a useful knowledge base is a time-consuming task and still requires a lot of effort of the experts. In recent years, many kinds of research and technologies of knowledge based artificial intelligence use DBpedia that is one of the biggest knowledge base aiming to extract structured content from the various information of Wikipedia. DBpedia contains various information extracted from Wikipedia such as a title, categories, and links, but the most useful knowledge is from infobox of Wikipedia that presents a summary of some unifying aspect created by users. These knowledge are created by the mapping rule between infobox structures and DBpedia ontology schema defined in DBpedia Extraction Framework. In this way, DBpedia can expect high reliability in terms of accuracy of knowledge by using the method of generating knowledge from semi-structured infobox data created by users. However, since only about 50% of all wiki pages contain infobox in Korean Wikipedia, DBpedia has limitations in term of knowledge scalability. This paper proposes a method to extract knowledge from text documents according to the ontology schema using machine learning. In order to demonstrate the appropriateness of this method, we explain a knowledge extraction model according to the DBpedia ontology schema by learning Wikipedia infoboxes. Our knowledge extraction model consists of three steps, document classification as ontology classes, proper sentence classification to extract triples, and value selection and transformation into RDF triple structure. The structure of Wikipedia infobox are defined as infobox templates that provide standardized information across related articles, and DBpedia ontology schema can be mapped these infobox templates. Based on these mapping relations, we classify the input document according to infobox categories which means ontology classes. After determining the classification of the input document, we classify the appropriate sentence according to attributes belonging to the classification. Finally, we extract knowledge from sentences that are classified as appropriate, and we convert knowledge into a form of triples. In order to train models, we generated training data set from Wikipedia dump using a method to add BIO tags to sentences, so we trained about 200 classes and about 2,500 relations for extracting knowledge. Furthermore, we evaluated comparative experiments of CRF and Bi-LSTM-CRF for the knowledge extraction process. Through this proposed process, it is possible to utilize structured knowledge by extracting knowledge according to the ontology schema from text documents. In addition, this methodology can significantly reduce the effort of the experts to construct instances according to the ontology schema.

• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.189-194
• /
• 2012

In this paper, we propose a query expansion method based on word graphs using pseudo-relevant and pseudo non-relevant documents to achieve performance improvement in information retrieval. The initially retrieved documents are classified into a core cluster when a document includes core query terms extracted by query term combinations and the degree of query term proximity. Otherwise, documents are classified into a non-core cluster. The documents that belong to a core query cluster can be seen as pseudo-relevant documents, and the documents that belong to a non-core cluster can be seen as pseudo non-relevant documents. Each cluster is represented as a graph which has nodes and edges. Each node represents a term and each edge represents proximity between the term and a query term. The term weight is calculated by subtracting the term weight in the non-core cluster graph from the term weight in the core cluster graph. It means that a term with a high weight in a non-core cluster graph should not be considered as an expanded term. Expansion terms are selected according to the term weights. Experimental results on TREC WT10g test collection show that the proposed method achieves 9.4% improvement over the language model in mean average precision.

• Journal of KIISE:Software and Applications
• /
• v.35 no.1
• /
• pp.1-11
• /
• 2008

This paper detected the characteristics of motion vector to support efficient content -based video search of video. Traditionally, the present frame of a video was divided into blocks of equal size and BMA (block matching algorithm) was used, which predicts the motion of each block in the reference frame on the time axis. However, BMA has several restrictions and vectors obtained by BMA are sometimes different from actual motions. To solve this problem, the foil search method was applied but this method is disadvantageous in that it has to make a large volume of calculation. Thus, as an alternative, the present study extracted the Spatio-Temporal characteristics of Motion Vector Spatio-Temporal Correlations (MVSTC). As a result, we could predict motion vectors more accurately using the motion vectors of neighboring blocks. However, because there are multiple reference block vectors, such additional information should be sent to the receiving end. Thus, we need to consider how to predict the motion characteristics of each block and how to define the appropriate scope of search. Based on the proposed algorithm, we examined motion prediction techniques for motion compensation and presented results of applying the techniques.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.8
• /
• pp.697-705
• /
• 2009

An unsupervised (blind) method is proposed aiming at extracting rhythmic sources from commercial polyphonic music whose number of channels is limited to one. Commercial music signals are not usually provided with more than two channels while they often contain multiple instruments including singing voice. Therefore, instead of using conventional modeling of mixing environments or statistical characteristics, we should introduce other source-specific characteristics for separating or extracting sources in the under determined environments. In this paper, we concentrate on extracting rhythmic sources from the mixture with the other harmonic sources. An extension of nonnegative matrix factorization (NMF), which is called nonnegative matrix partial co-factorization (NMPCF), is used to analyze multiple relationships between spectral and temporal properties in the given input matrices. Moreover, temporal repeatability of the rhythmic sound sources is implicated as a common rhythmic property among segments of an input mixture signal. The proposed method shows acceptable, but not superior separation quality to referred prior knowledge-based drum source separation systems, but it has better applicability due to its blind manner in separation, for example, when there is no prior information or the target rhythmic source is irregular.