• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.1
• /
• pp.56-70
• /
• 2017

In this study, multi-image information for the central Taewha River basin was used to develop and analyze a distribution map of non-point pollution sources. The data were collected using a hyper-sensor (image), aerial photography, and a field spectro-radiometer. An image correction process was performed for each image to develop an ortho-image. In addition, the spectra from the field spectro-radiometer measurements were analyzed for each classification to create land cover and distribution maps of non-point pollutant sources. In the western region of the Taewha River basin, where most of the forest and agricultural land is distributed, the distribution map showed generated loads for BOD($kg/km^2{\times}day$) of 1.0 - 2.3, for TN($kg/km^2{\times}day$) of 0.06 - 9.44, and for TP($kg/km^2{\times}day$) of 0.03 - 0.24, which were low load distributions. In the eastern region where urbanization is in progress, the BOD, TN, and TP were 85.9, 13.69, and 2.76, respectively and these showed relatively high load distributions when the land use was classified by plot.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.141-166
• /
• 2018

Information technology improves the efficiency of humanities research. In humanities research, information technology can be used to analyze a given topic or document automatically, facilitate connections to other ideas, and increase our understanding of intellectual history. We suggest a method to identify and automatically analyze the relationships between arguments contained in unstructured data collected from humanities writings such as books, papers, and articles. Our method, which is called history mining, reveals influential relationships between arguments and the philosophers who present them. We utilize several classification algorithms, including a deep learning method. To verify the performance of the methodology proposed in this paper, empiricists and rationalism - related philosophers were collected from among the philosophical specimens and collected related writings or articles accessible on the internet. The performance of the classification algorithm was measured by Recall, Precision, F-Score and Elapsed Time. DNN, Random Forest, and Ensemble showed better performance than other algorithms. Using the selected classification algorithm, we classified rationalism or empiricism into the writings of specific philosophers, and generated the history map considering the philosopher's year of activity.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.4
• /
• pp.16-28
• /
• 2013

Recently the various applications and spectral indices development of airborne hyperspectral imagery(A-HSI) has been increased. Especially the vegetation indices (VIs) were used to verify stress and vigor of vegetation. The VIs needs two or more spectral bands selectively to calculate as NIR(near infrared) and red wavelength. The A-HIS has specific band characteristics as narrow, continues and many. The A-HIS has narrow, continues and many specific band characteristics. That could be make it confuse which of bands could be explained for appropriate vegetation characteristics. If the A-HIS bands is not the same the wavelength with VIs' development band setting, then it need a selection adequate for spectral characteristics of target vegetation. Therefore we set 4 substitute bands for NIR and red wavelength respectively and calculated two VIs combined with substitute bands such as NDVI(normalized difference vegetation index) and MSRI(modified simple ratio index). To consider the variation of each VIs, we adapted the image differencing method of change detection technique. Also, we used spectral derivative to identify appropriate bands for spectral characteristics of digital forest cover type map. The result of adequate bands for two VIs selected red #3 as 680.2nm and NIR #2 as 801.7nm. This wavelength was good for any forest type in low variations.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.155-160
• /
• 2014

This paper deals with comparison of classification accuracy between three land cover classification results having difference in resolution and they were classified with eight classes including building, road, forest, etc. Airborne hyperspectral image used in this study was acquired at 1000m, 2000m, 3000m elevation and had 24 bands(0.5m spatial resolution), 48 bands(1.0m), 96 bands(1.5m). Assessment of classification accuracy showed that the classification using 48 bands hyperspectral image had outstanding result as compared with other images. For using hyperspectral image, it was verified that 1m spatial resolution image having 48 bands was appropriate to classify land cover and qualitative improvement is expected in thematic map creation using airborne hyperspectral image.

• Korean Journal of Environmental Biology
• /
• v.36 no.1
• /
• pp.21-32
• /
• 2018

This study was carried out to define the characteristics of the identified ground-dwelling invertebrate communities at Nari basin and Tonggumi area in Ulleungdo Island, designated as a nationally important agricultural heritage. The habitat types were divided into the following categories: crop land, forest, and ecotone, and the soil-dwelling invertebrates were collected according to habitat type. The ground-dwelling invertebrates were collected using a pitfall trap, and a self-organizing map (SOM) was applied to the invertebrates dataset to define the characteristics in invertebrates distribution. The SOM clearly classified the relevant information into four clusters, and extracted ecological information from the invertebrates dataset. The cluster II was composed of invertebrate communities which are collected in the Tonggumi area. The Tonggumi area is where mountainous areas were developed for agricultural purposes, which has geographical features commonly observed in Ulleungdo Island. It is noted that the cluster II has different characteristics as compared other clusters. The results of this study are expected to be used for the preservation of agricultural environment and maintenance of biodiversity by providing basic data, on the biotope of Ulleungdo Island designated as a nationally important agricultural heritage and information on the characteristics of the applicable ground-dwelling invertebrate communities.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.3
• /
• pp.54-67
• /
• 2013

This study deals with the characteristics of view landscape in modern Daegu city which were analysed employing geographic information system(GIS). The view landscape analysis was performed by using GIS that enables to overlap land use map with the map of range of visibility, and the 3-D simulation. The results are as follows; First of all, the ratio of forest is enormously high in the range of visibility. The distribution of landscape components allows the dwellers to obtain a clear view towards forests from anywhere. The landscape components include west eroded lowlands, east open rolling lands, east eroded lowlands, and high mountain areas: Apsan(Mt.) in the south; Waryoungsan(Mt.) in the west; and Hamjisan(Mt.) and Hakbong(Mt.) in the north. On the tops of those, people are able to secure a clear vision from the viewpoint towards the surrounding mountains because of the rural areas continuing from the viewpoint to the mountains. A continuous view landscape has been formed by these natural environmental factors. Finally, there are multiple view targets with relatively high altitude that are covered with forests in the space between the urban area and the outer mountains that are higher than the view targets, which provides a scenery of mountains overlapped by higher mountains.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.1
• /
• pp.105-113
• /
• 2011

Since existing thematic maps have been made with medium- to low-resolution satellite images, they have several shortcomings including low positional accuracy and low precision of presented thematic information. Digital aerial photo image taken recently can express panchromatic and color bands as well as NIR (Near Infrared) bands which can be used in interpreting forest areas. High resolution images are also available, so it would be possible to conduct precision land cover classification. In this context, this paper implemented object-based land cover classification by using digital aerial photos with 0.12m GSD (Ground Sample Distance) resolution and IKONOS satellite images with 1m GSD resolution, both of which were taken on the same area, and also executed qualitative analysis with ortho images and existing land cover maps to check the possibility of object-based land cover classification using digital aerial photos and to present usability of digital aerial photos. Also, the accuracy of such classification was analyzed by generating TTA(Training and Test Area) masks and also analyzed their accuracy through comparison of classified areas using screen digitizing. The result showed that it was possible to make a land cover map with digital aerial photos, which allows more detailed classification compared to satellite images.

• 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 the Korean Association of Geographic Information Studies
• /
• v.19 no.3
• /
• pp.75-88
• /
• 2016

In this study, we used the CLUE-s model to predict the future land-use change based on the urban growth scenario in South Korea. The land-use maps of six classes (water, urban, rice paddy, upland crop, forest, and grass) for the year 2008 were obtained from the Ministry of Environment (MOE), and the land-use data for 5-year intervals between 1980 and 2010 were obtained from the Water Resources Management Information System (WAMIS), South Korea. For predicting the future land-use change, the MOE environmental conservation value assessment map (ECVAM) was considered for identifying the development-restricted areas, and various driving factors as location characteristics were prepared for the model. The predicted results were verified by comparing them with the land-use statistics of urban areas in each province for the year 2008. The prediction error rates were 9.47% in Gyeonggi, 9.96% in Gangwon, 10.63% in Chungbuk, 7.53% in Chungnam, 9.48% in Jeonbuk, 6.92% in Jeonnam, 2.50% in Gyeongbuk, and 8.09% in Gyeongnam. The sources of error might come from the gaps between the development of political decisions in reality with spatio-temporal variation and the mathematical model for urban growth rate in CLUE-s model for future scenarios. Based on the land-use scenario in 2008, the land-use predictions for the year 2100 showed that the urban area increased by 28.24%, and the rice paddy, upland crop, and forest areas decreased by 8.27, 6.72, and 1.66%, respectively, in South Korea.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.21-37
• /
• 2022

Drug repositioning, one of the methods of developing new drugs, is a useful way to discover new indications by allowing drugs that have already been approved for use in people to be used for other purposes. Recently, with the development of machine learning technology, the case of analyzing vast amounts of biological information and using it to develop new drugs is increasing. The use of machine learning technology to drug repositioning will help quickly find effective treatments. Currently, the world is having a difficult time due to a new disease caused by coronavirus (COVID-19), a severe acute respiratory syndrome. Drug repositioning that repurposes drugsthat have already been clinically approved could be an alternative to therapeutics to treat COVID-19 patients. This study intends to examine research trends in the field of drug repositioning using machine learning techniques. In Pub Med, a total of 4,821 papers were collected with the keyword 'Drug Repositioning'using the web scraping technique. After data preprocessing, frequency analysis, LDA-based topic modeling, random forest classification analysis, and prediction performance evaluation were performed on 4,419 papers. Associated words were analyzed based on the Word2vec model, and after reducing the PCA dimension, K-Means clustered to generate labels, and then the structured organization of the literature was visualized using the t-SNE algorithm. Hierarchical clustering was applied to the LDA results and visualized as a heat map. This study identified the research topics related to drug repositioning, and presented a method to derive and visualize meaningful topics from a large amount of literature using a machine learning algorithm. It is expected that it will help to be used as basic data for establishing research or development strategies in the field of drug repositioning in the future.