• Title/Summary/Keyword: Data Clustering

Search Result 2,747, Processing Time 0.037 seconds

Reconstruction of 3D Building Model from Satellite Imagery Based on the Grouping of 3D Line Segments Using Centroid Neural Network (중심신경망을 이용한 3차원 선소의 군집화에 의한 위성영상의 3차원 건물모델 재구성)

  • Woo, Dong-Min;Park, Dong-Chul;Ho, Hai-Nguyen;Kim, Tae-Hyun
    • Korean Journal of Remote Sensing
    • /
    • v.27 no.2
    • /
    • pp.121-130
    • /
    • 2011
  • This paper highlights the reconstruction of the rectilinear type of 3D rooftop model from satellite image data using centroid neural network. The main idea of the proposed 3D reconstruction method is based on the grouping of 3D line segments. 3D lines are extracted by 2D lines and DEM (Digital Elevation Map) data evaluated from a pair of stereo images. Our grouping process consists of two steps. We carry out the first grouping process to group fragmented or duplicated 3D lines into the principal 3D lines, which can be used to construct the rooftop model, and construct the groups of lines that are parallel each other in the second step. From the grouping result, 3D rooftop models are reconstructed by the final clustering process. High-resolution IKONOS images are utilized for the experiments. The experimental result's indicate that the reconstructed building models almost reflect the actual position and shape of buildings in a precise manner, and that the proposed approach can be efficiently applied to building reconstruction problem from high-resolution satellite images of an urban area.

Rotation Invariant 3D Star Skeleton Feature Extraction (회전무관 3D Star Skeleton 특징 추출)

  • Chun, Sung-Kuk;Hong, Kwang-Jin;Jung, Kee-Chul
    • Journal of KIISE:Software and Applications
    • /
    • v.36 no.10
    • /
    • pp.836-850
    • /
    • 2009
  • Human posture recognition has attracted tremendous attention in ubiquitous environment, performing arts and robot control so that, recently, many researchers in pattern recognition and computer vision are working to make efficient posture recognition system. However the most of existing studies is very sensitive to human variations such as the rotation or the translation of body. This is why the feature, which is extracted from the feature extraction part as the first step of general posture recognition system, is influenced by these variations. To alleviate these human variations and improve the posture recognition result, this paper presents 3D Star Skeleton and Principle Component Analysis (PCA) based feature extraction methods in the multi-view environment. The proposed system use the 8 projection maps, a kind of depth map, as an input data. And the projection maps are extracted from the visual hull generation process. Though these data, the system constructs 3D Star Skeleton and extracts the rotation invariant feature using PCA. In experimental result, we extract the feature from the 3D Star Skeleton and recognize the human posture using the feature. Finally we prove that the proposed method is robust to human variations.

Interspecific Relationships within the Fungal Genus Pleurotus by Isozyme Analysis (동위효소 분석에 의한 느타리속의 종간 유연관계)

  • Lee, Hee-Kyung;Yoo, Young-Bok;Cha, Dong-Yeul;Min, Kyung-Hee
    • The Korean Journal of Mycology
    • /
    • v.26 no.2 s.85
    • /
    • pp.163-172
    • /
    • 1998
  • Thirty six strains of Pleurotus spp., from world-wide nations, were examined for interspecific isozyme variation. A comparison of isozymes in mycelial extracts of the fungal genus Pleurotus was made by polyacrylamide gel isoelectric focusing. A total of one hundred and sixty six bands was resolved from six isozymes. A cluster analysis was done based on the zymograms for esterase, glucosephosphate isomerase, leucine aminopeptidase, malate dehydrogenase, peroxidase, and phosphoglucomutase. From the isozyme analysis, esterase showed higher degree of variability, while it was observed less variability for the enzymes such as glucosephosphate isomerase, malate dehydrogenase, and phosphoglucomutase. The species P. ostreatus, whose taxon is controversial, was discriminated from P. pulmonarius, while P. florida was classified as a distinct taxon. The clustering of P. sapidus and P. spodoleucus strains appeared to be more difficult. It was found that some strains were included to another cluster based on electrophoretic banding patterns. These results show that this lack of congruence among data sets may help explain the taxonomic difficulty within the genus Pleurotus. A dendrogram of genetic similarities was presented, and applications of isozyme data to the systematics of these commercially important fungi was discussed.

  • PDF

Competition - Ecological Classification of the Prominent Paddy Weed Species around Bulrush(Scirpus juncoides) (올챙고랭이(Scirpus juncoides)를 중심으로 한 주요(主要) 논 잡초종(雜草種)의 벼 경합생태적(競合生態的) 분류(分類))

  • Guh, J.O.;Heo, S.M.
    • Korean Journal of Weed Science
    • /
    • v.5 no.2
    • /
    • pp.96-102
    • /
    • 1985
  • A study on the competition-ecological classification of the 10 prominent paddy weed species around bulrush (Scirpus juneoides) to simplify the weed problem concept for the rice production. A serial assessments on the competition ability in space and dry matter production(nutrient depletion) of respective weed species and paddy rice, and the data were used to compute the phenotypic similarity by Single Link Clustering method. Both growth response of weed species in mono- and under the paddy rice standing was very similar (r = 0.969), but the reduction rate as affected by paddy rice standing was negatively correlated with the ability in space-competition(r=-0.513). Dendrogram of 10 weed species based on the phenotypic similarity computed in 4 characters in mono- and under the paddy rice standing was also similar, as Echinochloa c., Ludwigia p., Cyperus s., and Scirpus m. in I-group, Eleocharis k., Scirpus j, in II-group, and Juncus e., Potamogeton d. in III-group, respectively. Also, that of paddy rice to 10 weed species showed Fimbristylis m., Scirpus j., Eleocharis k., Scirpus m., Juncus e. in I-group, and Ludwigia p., Potamogeton d., Monochoria v. in II-group, respectively. The integrated dendrogram by the above two data indicate the I-group with Fimbristylis m., Scirpus j., Eleocharis k. and Juncus e., as higher growth response with relatively lower competition ability to paddy rice, II-group with Cyperus s., Echinochloa c., Potamogeton d., and Ludwigia p., as higher both in growth and competition, and the last, III-group with Monochoria v., and Scirpus m., as lower growth but higher competition, respectively.

  • PDF

Analysis of dimensions and shapes of maxillary and mandibular dental arch in Korean young adults

  • Park, Su-Jung;Leesungbok, Richard;Song, Jae-Won;Chang, Se Hun;Lee, Suk-Won;Ahn, Su-Jin
    • The Journal of Advanced Prosthodontics
    • /
    • v.9 no.5
    • /
    • pp.321-327
    • /
    • 2017
  • PURPOSE. The aim of this study was to investigate dental arch dimensions and to classify arch shape in Korean young adults. MATERIALS AND METHODS. The sample included 50 Koreans with age ranging from 24 to 32 years. Maxillary and mandibular casts were fabricated using irreversible hydrocolloid and type III dental stones. Incisor-canine distance, $incisor-1^{st}$ molar distance, $incisor-2^{nd}$ molar distance, intercanine distance, $inter-1^{st}$ molar distance, and $inter-2^{nd}$ molar distance in both the maxillary and mandibular arch were measured using a three-dimensional measuring device. The dental arch was classified into three groups using five ratios from the measured values by the K-means clustering method. The data were analyzed with one-way analysis of variance. RESULTS. Arch lengths (IM2D, $incisal-2^{nd}$ molar distance) were 44.13 mm in the maxilla and 40.40 mm in the mandible. Arch widths (M2W, inter $2^{nd}$ molar width) were 64.12 mm in the maxilla and 56.37 mm in the mandible. Distribution of the dental arch form was mostly ovoid shape (maxilla 52% and mandible 56%), followed by the V-shape and the U-shape. The arch width for the U-shape was broader than for the other forms. CONCLUSION. This study establishes new reference data for dental arch dimensions for young Korean adults. The most common arch form is the ovoid type in the maxilla and mandible of Koreans. Clinicians should be aware of these references and classify arch type before and during their dental treatment for effective and harmonized results in Koreans.

A Study on the Next VWorld System Architecture: New Technology Analysis for the Optimal Architecture Design (차세대 브이월드 시스템 아키텍처 구성에 관한 연구: 최적의 아키텍처 설계를 위한 신기술 분석)

  • Go, Jun Hee;Lim, Yong Hwa;Kim, Min Soo;Jang, In Sung
    • Spatial Information Research
    • /
    • v.23 no.4
    • /
    • pp.13-22
    • /
    • 2015
  • There has been much interest in the VWorld open platform with the addition of a variety of contents or services such as 2D map, 3D terrain, 3D buildings, and thematic map since 2012. However, the VWorld system architecture was not stable for the system overload. For example, the system was stopped due to the rapidly increasing user accesses when the 3D terrain service of the North Korea and the Baekdu mountain was launched at September 2012 and September 2013, respectively. It was because the system architect has just extended the server system and the network bandwidth whenever the rapid increase of user accesses occurs or new service starts. Therefore, this study proposes a new VWorld system architecture that can reliably serve the huge volume of National Spatial Data by applying the new technologies such as CDN, visualization and clustering. Finally, it is expected that the results of this study can be used as a basis for the next VWorld system architecture being capable of a huge volume of spatial data and users.

Analysis of crown size and morphology, and gingival shape in the maxillary anterior dentition in Korean young adults

  • Song, Jae-Won;Leesungbok, Richard;Park, Su-Jung;Chang, Se Hun;Ahn, Su-Jin;Lee, Suk-Won
    • The Journal of Advanced Prosthodontics
    • /
    • v.9 no.4
    • /
    • pp.315-320
    • /
    • 2017
  • PURPOSE. The aim of this investigation was to analyze the dimensions of clinical crowns and to classify the crown and the gingival type in the anterior teeth in Korean young adults. MATERIALS AND METHODS. Casts were obtained from 50 subjects ranging in age from 24 to 32. Measurements of length and width were made on the casts using a pair of digital calipers on the entire dentition. Crown thickness and papilla height were also measured and MDW/CL (mesiodistal width to clinical length) and CW/CL (cervical width to clinical length) ratios of the maxillary anterior teeth were calculated. The K-clustering method was used for CW/CL to classify the anterior tooth shape into three groups (tapered, ovoid, and square), and one-way analysis of variance and Duncan's post-hoc comparison were used to evaluate statistical significance between the groups. Pearson's correlation analysis was performed between tooth shape and papillary height (PH) to demonstrate the correlation between tooth shape and gingival morphological characteristics. RESULTS. The average length of the maxillary central incisors was 9.89 mm; the mesio-distal width was 8.54 mm; and the ratio of width/length was 0.86 in Korean young adults. The average bucco-palatal thickness of the central incisor was 3.14 mm at the incisal 1/3 aspect. Ovoid type was the most common tooth shape (48%), followed by square type (29%) and taper type (23%) in the central incisors of Korean young adults. Tooth shape and gingival type were correlated with each other. CONCLUSION. New reference data were established for tooth size in Korean young adults and the data show several patterns of tooth shape and gingival type. Clinicians should diagnose and treat based on these characteristics for better results in the Korean population.

A Study on the Stepwise Benchmarking Method for Efficient Operation of Student Education Support (학생 교육지원의 효율적 운영에 대한 단계적 벤치마킹 방안 연구)

  • Jeong, Kyu-Han;Lee, Jang-Hee
    • Journal of Practical Engineering Education
    • /
    • v.12 no.1
    • /
    • pp.213-230
    • /
    • 2020
  • Until now, various educational budgets, facilities, and programs have been put into school education, but the results have not been clearly evaluated. This study presents a model to analyze the effectiveness of educational support for students in high schools across the country. In this model, we first use EM cluster analysis to make clusters with similar inputs for school operation, and then calculate the relative efficiency in each cluster by using Network DEA analysis. The Network DEA analysis has a two-stage structure where the first stage uses six inputs in terms of school infrastructure to generate outputs such as the number of academic persistence. In the Network DEA analysis, the second stage uses 10 inputs in terms of school programs to generate outputs such as the number of enrollees to higher learning and the number of employees and per capita usage of library as the connection variable. Based on the efficiency analysis results, Tier analysis is performed by applying the Euclidean distance to select targets for benchmarking. In this study, we applied the model to analyze the efficiency of educational support by collecting data regarding student education support in general and vocational high school nationwide. The stepwise benchmarking method proposed that the target be selected for efficiency improvement step by step, taking into account inefficient school elements to complement the problem of the choice of benchmarking targets. Based on this study, it is expected that schools with low efficiency of educational support for students will be used as basic data for stepwise benchmarking for efficient operation of educational support for students.

A Study on the Characteristics of Firm Agglomeration of Green Energy Industry in Daegyeong Region (대경권 친환경에너지산업 집적 특성에 관한 연구)

  • Yoon, Chil-Seok
    • Journal of the Korean association of regional geographers
    • /
    • v.16 no.6
    • /
    • pp.689-705
    • /
    • 2010
  • The purpose of this study is to examine the geographical distribution and the clustering characteristics as an industrial cluster in order to provide alternative fundamental data for the preparation of the policies to facilitate the development of the Green Energy Industry. The main source of the data in this study is the outcome of a survey conducted to the firms and environment specialist from June 21st, 2010 to July 23rd, 2010. The Green Energy related companies in Daegyeong region are clustered around Pohang and Gumi, Gyeongbuk, and Dalseo District of Daegu Metropolitan City. The core element of the sustainability of the Green Energy Industry in the region is the inducement of the large-scale corporate presence in the region as well as the technical and geographical proximity. That is, the fact that there are sister companies established by the large scale corporate Daegyeong region as they have chosen this field for their new drive for growth. The major location factors are proximity, higher quality expectations from the local demands, technical availability, and competition with other companies of the same industry in the region, rather than the availability of the raw material. And the choke points for these companies are the financial support of R&D and the policy support of specialist training. The policy to facilitate the development of the industry in question in Daegyeong region, therefore, should shift from its previous focuses on infrastructure building and taxation benefits to financial supports for the technical research, human resource development in response to the needs of the companies. Also, programs to support the proficiency training for the already-hired work forces and development of new policies for the Green Energy Industry are needed to be introduced for the development of the Green Energy Industry in Daegyeong region.

  • PDF

Hotspot Analysis of Urban Crime Using Space-Time Scan Statistics (시공간검정통계량을 이용한 도시범죄의 핫스팟분석)

  • Jeong, Kyeong-Seok;Moon, Tae-Heon;Jeong, Jae-Hee
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.13 no.3
    • /
    • pp.14-28
    • /
    • 2010
  • The aim of this study is to investigate crime hotspot areas using the spatio-temporal cluster analysis which is possible to search simultaneously time range as well as space range as an alternative method of existing hotspot analysis only identifying crime occurrence distribution patterns in urban area. As for research method, first, crime data were collected from criminal registers provided by official police authority in M city, Gyeongnam and crime occurrence patterns were drafted on a map by using Geographic Information Systems(GIS). Second, by utilizing Ripley K-function and Space-Time Scan Statistics analysis, the spatio-temporal distribution of crime was examined. The results showed that the risk of crime was significantly clustered at relatively few places and the spatio-temporal clustered areas of crime were different from those predicted by existing spatial hotspot analysis such as kernel density analysis and k-means clustering analysis. Finally, it is expected that the results of this study can be not only utilized as a valuable reference data for establishing urban planning and crime prevention through environmental design(CPTED), but also made available for the allocation of police resources and the improvement of public security services.