• Journal of the Korean association of regional geographers
• /
• v.13 no.3
• /
• pp.301-320
• /
• 2007

In Korean academic societies, old maps has not yet been properly investigated in terms of their genealogy, classification, detailed place names, historical backgrounds and the other aspects. With publication of the bibliographies and papers on old maps reserved in museum and library, the scope of research enlarged gradually its scope from 1970s. In 1980s, with the development of theoretical geography, scientific analysis were applied to investigate the projection method of Daedongyeo-jido. The 1990s proved a prominent decade for researches. The photo-copies of old maps enabled researchers to investigate the in-depth comparative study. The more important thing is that old maps became to be powerful instrument in the research of historical geography, such as territorial disputes and marine name(東海). And county old maps compiled by region became to be regional-cultural contents of local areas. Important issues in old map research in Korean academic societies are about Cheonha-do which is unique old world map in Korea, grid-system projection in old county maps and the genealogy of Daedongyeo-jido(manuscript and block print edition). This study shows that bibliography of all old maps preserved in each library and museum should be standardized. This could enable the exchange of information of old maps between institutes. The more important thing is that conciliation of human, social and natural sciences should be applied in the research of old maps.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.5
• /
• pp.661-678
• /
• 2006

Products developed in this research is a software which can transfer the type of shape(.shp) into the type of ascii using the land cover data and the topography data in the metropolitan area of Seoul. In addition, it can calculate the $CO_2$ flux according to distribution of plants within the land cover data. The $CO_2$ flux is calculated by the experimental equation which is compose of the meteorological parameters such as the solar radiation and the air temperature. The net flux was shown in about $-19ton/km^2$ by removing $CO_2$ through the photosynthesis during daytime, and in 2 ton/km2 by producing it through the respiration during nighttime on 10 August 2004, the maximum day of air temperature during the period of 3yr(2001 to 2004), in the metropolitan area of Seoul. Spatial distribution of the air temperature and the wind field is simulated by substituting the middle classification of the land cover map data, upgraded by the Korean Ministry of Environment(KME), for the land-use data of the United States Geological Survey(USGS) within the Meteorological Mesoscale Model Version 5(MM5) on 10 August 2006 in the metropolitan area of Seoul. Difference of the air temperature between both data was shown in the maximum range of $-2^{\circ}C\;to\;2.9^{\circ}C$, and the air temperature due to the land use data of KME was higher than that of USGS in average $0.4^{\circ}C$. Also, those of wind vectors were meanly lower than that of USGS in daytime and nighttime. Furthermore, the hourly time series of Volatile Organic Components(VOCs) is calculated by using the Biosphere Emission and Interaction System Version 2(BEIS2) including the new land cover data and the meteorological parameters such as the air temperature and so]ar insolation. It is possible to calculate the concentration of ozone due to the biogenic emission of VOCs.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.1
• /
• pp.113-126
• /
• 2017

This study aimed to quantitatively analyze the trends in environmental research that utilize environmental geospatial information through text mining, one of the big data analysis technologies. The analysis was conducted on a total of 869 papers published in the Republic of Korea, which were collected from the National Digital Science Library (NDSL). On the basis of the classification scheme, the keywords extracted from the papers were recategorized into 10 environmental fields including "general environment", "climate", "air quality", and 20 environmental geospatial information fields including "satellite image", "numerical map", and "disaster". With the recategorized keywords, their frequency levels and time series changes in the collected papers were analyzed, as well as the association rules between keywords. First, the results of frequency analysis showed that "general environment"(40.85%) and "satellite image"(24.87%) had the highest frequency levels among environmental fields and environmental geospatial information fields, respectively. Second, the results of the time series analysis on environmental fields showed that the share of "climate" between 1996 and 2000 was high, but since 2001, that of "general environment" has increased. In terms of environmental geospatial information fields, the demand for "satellite image" was highest throughout the period analyzed, and its utilization share has also gradually increased. Third, a total of 80 correlation rules were generated for environmental fields and environmental geospatial information fields. Among environmental fields, "general environment" generated the highest number of correlation rules (17) with environmental geospatial information fields such as "satellite image" and "digital map".

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.525-532
• /
• 2021

In the ocean, it is difficult to separate the effects of one cause due to the multiple causes, but the self-organizing map can be analyzed by adding other factors to the cluster result. Therefore, in this study, the results of the clustering of sea level data were applied to sea surface temperature. Sea level data was clustered into a total of 6 nodes. The difference between sea surface temperature and sea level height has a one-month delay, which applied sea surface temperature data a month ago to the clustered results. As a result of comparing the mean of sea surface temperature of 140 to 150°E, where the sea surface temperature was variously distributed, in the case of nodes 1, 3, and 5, it was possible to find a meandering sea surface temperature distribution that is clearly distinguished from the sea level data. While nodes 2, 4 and 6, the sea surface temperature distribution was smooth. In this study, sea surface temperature data were applied to the clustered results of sea level data, but later it is necessary to apply wind or geostrophic velocity data to compare.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.3
• /
• pp.1-16
• /
• 2022

Areas developed through land reclamation projects have huge economic advantages in terms of supplying lands that can be used for farmlands, urban areas and etc., however have relatively small areas of grasslands and densely located buildings compared to inland cities. Hence, an urban heat island is occurring in these areas due to this characteristic, and in particular, the urban heat island in Cheongna International City is getting serious. In this study, the urban heat island in Cheongna International City was evaluated and analyzed by classified into the three periods after the reclamation project: farmland(2001-2008), development(2009-2013) and artificial grassland(2014-2020). The land cover map and Landsat time-series imagery were utilized for measuring the differences of the land surface temperatures between the urbanized areas and the grassland/forest areas in Cheongna International City. The statistical results showed that the differences in the land surface temperature between these areas were calculated to be at most 0℃ during the period of farmland, at most 3.60℃ during the period of development, and at most 2.51℃ during the period of grassland. This study proved that the urban heat island phenomenon increased when the urbanized areas increased, and the urban heat island phenomenon decreased when the artificial grassland areas increased in Cheongna International City where the reclamation project was carried out. The statistical results derived through this research can be used as the reference data for identifying the urban heat island problem in urban planning and establishing the reduction plan.

• Journal of Korean Society of Forest Science
• /
• v.111 no.3
• /
• pp.345-356
• /
• 2022

Yokjido is a 15-km² inhabited island located at the tip of the southeastern coast of the Korean Peninsula. Its forest is mostly composed of substitutional vegetation. Our aim was to provide basic information necessary for the conservation and management of the forest vegetation in Yokjido. We classified the types of existing vegetation using methods of the Zurich-Montpellier school of phytosociology. The resulting vegetation map shows the dominant tree species in the top canopy-layer. A total of 8 vegetation types were identified, which were arranged into a vegetation unit hierarchy of 2 communities, 4 sub-communities, 6 variants, and 2 subvariants. Evaluations of each type showed large and small differences in floristic composition, which reflect anthropogenic influences, site conditions, succession stages, and the establishment period. Moreover, vegetation types differed significantly in terms of species diversity indices; in particular, overall species richness, species diversity, and species evenness tended to increase significantly as the elevation increased. The herbaceous plant species showed the highest positive (+) correlation to x. These results were consistent with those of McCain, who reported that species diversity increases in mountainous areas with relatively low elevations due to the mid-domain effect. The forest succession in Yokjido will potentially enter a mixed-forest stage and then proceed to become an all-evergreen broad-leaved forest.

• The Journal of Society for e-Business Studies
• /
• v.26 no.4
• /
• pp.133-154
• /
• 2021

Today smart phone is the most common media with a vehicle called 'application'. In order to understand how media users select applications and build their repertoire, this study conducted two-step approach using big data from smart phone log for 4 weeks in November 2019, and finally classified 8 media repertoire groups. Each of the eight media repertoire groups showed differences in time spent of mobile application category compared to other groups, and also showed differences between groups in demographic distribution. In addition to the academic contribution of identifying the mobile application repertoire with large scale behavioral data, this study also has significance in proposing a two-step approach that overcomes 'outlier issue' in behavioral data by extracting prototype vectors using SOM (Sefl-Organized Map) and applying it to k-means clustering for optimization of the classification. The study is also meaningful in that it categorizes customers using e-commerce services, identifies customer structure based on behavioral data, and provides practical guides to e-commerce communities that execute appropriate services or marketing decisions for each customer group.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.267-279
• /
• 2023

This research assessed the feasibility of using high-resolution aerial images and deep learning algorithms for estimating the land-use and land-cover areas at the Approach 3 level, as outlined by the Intergovernmental Panel on Climate Change. The results from different sampling densities of high-resolution (51 cm) aerial images were compared with the land-cover map, provided by the Ministry of Environment, and analyzed to estimate the accuracy of the land-use and land-cover areas. Transfer learning was applied to the VGG16 architecture for the deep learning model, and sampling densities of 4 × 4 km, 2 × 4 km, 2 × 2 km, 1 × 2 km, 1 × 1 km, 500 × 500 m, and 250 × 250 m were used for estimating and evaluating the areas. The overall accuracy and kappa coefficient of the deep learning model were 91.1% and 88.8%, respectively. The F-scores, except for the pasture category, were >90% for all categories, indicating superior accuracy of the model. Chi-square tests of the sampling densities showed no significant difference in the area ratios of the land-cover map provided by the Ministry of Environment among all sampling densities except for 4 × 4 km at a significance level of p = 0.1. As the sampling density increased, the standard error and relative efficiency decreased. The relative standard error decreased to ≤15% for all land-cover categories at 1 × 1 km sampling density. These results indicated that a sampling density more detailed than 1 x 1 km is appropriate for estimating land-cover area at the local level.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.250-258
• /
• 2007

Current speech recognition technology s achieved high performance with the development of hardware devices, however it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. For the system which aims to operate powered wheelchairs safely by voice in real environment, we need to consider that non-voice commands such as user s coughing, breathing, and spark-like mechanical noise should be rejected and the wheelchair system need to recognize the speech commands affected by disability, which contains specific pronunciation speed and frequency. In this paper, we propose non-voice rejection method to perform voice/non-voice classification using both YIN based fundamental frequency(F0) extraction and reliability in preprocessing. We adopted a multi-template dictionary and acoustic modeling based speaker adaptation to cope with the pronunciation variation of inarticulately uttered speech. From the recognition tests conducted with the data collected in real environment, proposed YIN based fundamental extraction showed recall-precision rate of 95.1% better than that of 62% by cepstrum based method. Recognition test by a new system applied with multi-template dictionary and MAP adaptation also showed much higher accuracy of 99.5% than that of 78.6% by baseline system.