• Journal of Ecology and Environment
• /
• v.38 no.4
• /
• pp.405-413
• /
• 2015

We classified the streamside plant community by phyto-sociological method and analyzed the relationship between environment factors and vegetation structure by using the classification and ordination method. We found that twenty one plant communities were classified according to dominant species at the natural streamside valley forest with surveying the 65 quadrats (10 m × 10 m). From the survey results, the hardwood plant communities were classified as streamside valley forest and the softwood plant communities as riparian forest according to the degree of flooding. The valley forest had a distribution of 17 plant communities which was 65% (42 quadrats) of 65 quadrats: Maackia amurensis community, Betula davurica community, Quercus variabilis community, Pinus densiflora community, Q. serrata community, Prunus sargentii community, and Meliosma oldhamii community etc. The riparian forest had a distribution of four plant communities which was 35% (23 quadrats) of 65 quadrats: Salix koreensis community, S. rorida community, S. purpurea var. japonica community, and S. glandulosa community, etc. From the two-way indicator species analysis (TWINSPAN) analysis, we found indicator species Oplismenus undulatifolius and Lindera obtusiloba for the streamside valley forest and Humulus japonicus, Phragmites japonica, and S. koreensis for the riparian forest. From the results of the canonical correspondence analysis (CCA), coordinates, altitude, and stream structure showed low correlation to the distribution of the plant community. Therefore, it seemed that valley forest and riparian forest were distinguished by the stream gradient and waterway width which determined by the stream water level.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.201-206
• /
• 2018

Recently, as technologies for realizing artificial intelligence have become more common, machine learning is widely used. Machine learning provides insight into collecting large amounts of data, batch processing, and taking final action, but the effects of the work are not immediately integrated into the learning process. In this paper proposed an adaptive learning model to improve the performance of real-time stream analysis as a big business issue. Adaptive learning generates the ensemble by adapting to the complexity of the data set, and the algorithm uses the data needed to determine the optimal data point to sample. In an experiment for six standard data sets, the adaptive learning model outperformed the simple machine learning model for classification at the learning time and accuracy. In particular, the support vector machine showed excellent performance at the end of all ensembles. Adaptive learning is expected to be applicable to a wide range of problems that need to be adaptively updated in the inference of changes in various parameters over time.

• Journal of Wetlands Research
• /
• v.13 no.1
• /
• pp.67-77
• /
• 2011

To classify the relationship between riparian vegetation type and bird habitat, we studied the vegetation and avian species in the three streams(Anyang Stream, Gap Stream, Seom River), located in middle province. Five different vegetation types - Woodland type, Shrub type, Tall and wet grassland type, Low and dry grassland type and Cropland - were identified. The habitats of avian species were highly correlated with vegetation type. Streptopelia orientalis and Hypsipetes amaurotis were found in woodland. Both Paradoxornis webbiana and Phoenicurus auroreus were mainly found in shrub. Tall and wet grassland were preference habitats of Ixobrychus sinensis, Acrocephalus arundinaceus, while, low and dry grassland were occupied by Phasianus colchicus, Falco tinnunculus. Cropland were used as breeding and feeding sites for Egretta alba modesta, Anas poecilorhyncha, Anthus spinoletta. Distribution patterns of avian species were clearly divided by vegetation type and site characteristics in the stream.

• Journal of the Korean association of regional geographers
• /
• v.8 no.3
• /
• pp.281-294
• /
• 2002

Inhabitants make a specific cultural landscape in various ways according to his culture. In this paper, I consider the characteristics of cultural landscapes distributed in Sangju. I divide Sangju-City Area owing to physical criteria(relief and drainage basin}, appreciate them according to human criteria(administrative district of Joseon Period, dialects, periodical market area} and classify into 6 small regions: (1) Nakyang Region is the traditionally central place based on alluvial plain marginal to Byeongseong stream and Dong stream, and on hills of Sabeol. (2) Nakdong Region is the traffic center which the water transport of Nakdong river and the land transport of Yeongnamdaero cross each other. (3) The upstream region of Byungseong stream is the agricultural region connected with Nakyang Region. (4) Jungmo Region is a intermontane basin where grape cultivation using its specific climate flourish. (5) Wharyeong Region is a mountainous sightseeing district based on the beautiful scenery and Gyeonwhueon's remains of Sogni mountains and Yongyu valley. (6) Hamnyeong Region is the district of Goryeonggaya realm where 3 whites(cocoon, dried persimmon, rice) are abundant.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.

• Journal of Environmental Impact Assessment
• /
• v.25 no.6
• /
• pp.384-401
• /
• 2016

The vegetation assessment indicator has been developed recently as a biological part of the integrated assessment system for river environment to improve the efficiency of river restoration projects. This study carried out to test the vegetation assessment indicator and to reset its grade criteria on experimental streams. We classified and mapped vegetation communities at the level of physiognomic-floristic composition by each assessment unit. A total of 204 sampling quadrats were set up on the 68 assessment units at 5 experimental streams. By analyzing the vegetation data collected, we examined the appropriate numbers of sampling quadrats, the criteria of vegetation index score, classification of vegetation community, and grade criteria for vegetation assessment. The developed vegetation assessment indicator composed with the vegetation complexity index (VCI), the vegetation diversity index (VDI), and the vegetation naturalness index (VNI) was proved to reflect the current conditions of the streams sufficiently. The contribution of vegetation naturalness index to grading by vegetation assessment indicator was larger, but three indexes were closely correlated to each other. Also there was more clearer discrimination of grading with the application of adjusted criteria of vegetation assessment indicator and the standardized classification of vegetation community, but the stream segment type did not influence the vegetation assessment grade significantly.

• Journal of Environmental Science International
• /
• v.15 no.4
• /
• pp.349-357
• /
• 2006

The purpose of this study is to evaluate the water pollution degree in the Mid-Nakdong River watershed regarding to landcover types using GIS method. As a result of landcover classification, rate of urban appeared highly on Daegu Metropolitan city. Also, rate of agriculture showed highly in the riparian zones of the Nakdong and Guemho River and rate of forest appeared highly in the borders of the study area. To identify the groups of watershed with similar landcover patterns using the Cluster Analysis. According to the cluster analysis, the fifty sub-watersheds were grouped in three clusters, 'Urban watershed', 'Agriculture watershed', 'Forest watershed'. The proportion of urban area in each cluster had a positive correlation with water pollution degree. Otherwise, the proportion of agriculture in the Agriculture watershed had a high positive correlation with water pollution degree. Therefore, it is necessary to estimate environmental capacity of water duality considering ecological and environmental characteristics of watershed ecosystem and expand water duality monitoring systems to small stream.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.1-11
• /
• 2006

In this paper, we propose the novel video retrieval algorithm using non-parametric based motion classification in the shot-based video indexing structure. The proposed system firstly gets the key frame and motion information from each shot segmented by scene change detection method, and then extracts visual features and non-parametric based motion information from them. Finally, we construct real-time retrieval system supporting similarity comparison of these spatio-temporal features. After the normalized motion vector fields is created from MPEG compressed stream, the extraction of non-parametric based motion feature is effectively achieved by discretizing each normalized motion vectors into various angle bins, and considering a mean, a variance, and a direction of these bins. We use the edge-based spatial descriptor to extract the visual feature in key frames. Experimental evidence shows that our algorithm outperforms other video retrieval methods for image indexing and retrieval. To index the feature vectors, we use R*-tree structures.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.17 no.1
• /
• pp.65-79
• /
• 2014

This study selected Nakdong River basin zone in Daegu as an example area to conduct landscapetope classification and aesthetic value assessment of landscape according to the classified landscapetope. The main result of this research can be summed up as following. First, the result of landscapetope type classification showed 28 types of landscapetope including complex residential area (AA), natural stream type with copious vegetation (BA), forest type centered on mixed forest of soft and hardwood (EB) along with 129 types of imputed specific landscapetope. The result of the total first assessment using B-VAT showed the first grade 10 types, II grade 4 types, III grade6 types, IV grade 3 types, 5 types for V grade with the lowest value. The second assessment conducted toward the landscapetope types with the grade higher than the average (including III grade) in the result of the first assessment showed that there are 66 spaces for the sites (1a, 1b) with special meaning for aesthetic landscape evaluation. And also, there were 69 spaces for those (2a, 2b, 2c) with meaning for aesthetic landscape evaluation. The design model of this research is largely divided into improvement goal and specific execution plan. First, the improvement goal is divided into 6 categories including conservation area, complementary area, and restoration area, and the specific execution plan is divided into 14 categories including special landscape management area, general landscape management area, conservation of hill areas with optically good condition. A comprehensive master plan was suggested by directly applying the set landscape planning model to the subject place of this research.

• Korean Journal of Environment and Ecology
• /
• v.25 no.5
• /
• pp.691-709
• /
• 2011

This study was performed to classify habitat types depending on environmental factors and to find out distribution characteristics of functional feeding groups of aquatic insects which were collected at that habitat types. Field survey was conducted twice in a year for every spring and fall from 2007 to 2008 for 38 sites in the Geum River. During the field survey 15 environmental factors were measured at each 38 sites and analyzed by similarity analysis method to classify habitat types. The result of similarity analysis showed that the 38 sites could be grouped into 7 classes like as C1 and C3 class belong to Head water(HD), C2 and C4 and C5 class belong to Middle stream(MS), C6 and C7 class belong to Large River(LR) based on euclidean distances 4. And also, we could extract the main environmental factors affecting the classification of habitat types such as Stream Width and Elevation of physical environmental factors, Water Temperature, Conductivity and DO of chemical environmental factors, percentages of Sand, Silt and Gravel of substrate factors. Total 142 species of aquatic insects in 46 families, 9 orders were collected during the field surveys and the occurrence number of species and individuals showed high correlation with the Velocity factor and the percentage of Sand factor of each habitat types. In addition, correlation analysis between functional feeding groups and environmental factors represented that (1) Filtering-collectors(FC) affected by Velocity, Stream Width and Silt, (2) Gathering-collector(GC) affected by Velocity, (3) Predator(P) affected by Elevation, Velocity, Boulder, Conductivity and Sand, (4) Plant-piecer(PP) affected by Water Width and Silt, (5) Scraper(SC) affected by Elevation and Conductivity, (6) Shredder(SH) affected by Elevation, Boulder, DO, pH, Conductivity and Water Temperature respectively. As a result of this study, Elevation, Stream Width, Velocity, Conductivity, Water Temperature and percentage of Sand factors which were deduced by stepwise multiple regression analysis had correlations($r{\geqq}0.600$, p<0.01) with biota community inhabitation. Therefore these six environmental factors were regarded as major environmental factors that might affect highly the distribution of functional feeding groups in stream ecosystem of the Geum River.