• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.57-63
• /
• 2009

Object recognition technologies using PCA(principal component analysis) recognize objects by deciding representative features of objects in the model image, extracting feature vectors from objects in a image and measuring the distance between them and object representation. Given frequent recognition problems associated with the use of point-to-point distance approach, this study adopted the k-nearest neighbor technique(class-to-class) in which a group of object models of the same class is used as recognition unit for the images in-putted on a continual input image. However, the robustness of recognition strategies using PCA depends on several factors, including illumination. When scene constancy is not secured due to varying illumination conditions, the learning performance the feature detector can be compromised, undermining the recognition quality. This paper proposes a new PCA recognition in which database of objects can be detected under different illuminations between input images and the model images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.5B
• /
• pp.274-286
• /
• 2005

In this paper, we propose a new power-efficient and reliable connected dominating set based routing protocol in the mobile ad hoc networks. Gateway nodes must be elected in consideration of residual energy and mobility because frequent reconstruction of connected dominating set result in transmission error for route losses. If node density is high, it results in a lot of contentions and more delays for network congestion. Therefore, in this paper, we propose a new construction method of connected dominating set that supports reliable and efficient data transmission through minimizing reconstruction of connected dominating set by delaying neighbor set advertisement message broadcast in proportion to weighted sum of residual energy, mobility, and the number of neighbor nodes. The performance of the proposed protocol is proved by simulation of various conditions.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.327-332
• /
• 2015

Constructing a k-nearest neighbor (k-NN) graph is a primitive operation in the field of recommender systems, information retrieval, data mining and machine learning. Although there have been many algorithms proposed for constructing a k-NN graph, either the existing approaches cannot be used for various types of similarity measures, or the performance of the approaches is decreased as the number of nodes or dimensions increases. In this paper, we present a novel algorithm for k-NN graph construction based on "balanced" canopy clustering. The experimental results show that irrespective of the number of nodes or dimensions, our algorithm is at least five times faster than the brute-force approach while retaining an accuracy of approximately 92%.

• Bulletin of the Korean Chemical Society
• /
• v.12 no.5
• /
• pp.544-554
• /
• 1991

Using the Huckel method, we obtain the analytical expressions for eigenvalues and eigenvectors of s.c., f.c.c. and b.c.c. clusters of rectangular parallelepiped shape, and of an arbitrary size. Our formula converage to those derived from the Bloch sum, in the limit of infinite extension. DOS and LDOS reveal that the major contribution of the states near Fermi level originates from the surface atoms, also symmetry of DOS curves disappears by the introduction of 2nd nearest neighbor interactions, in all the cubic lattices. An accumulation of the negative charges on surface of cluster is observed.

• Journal of Korea Port Economic Association
• /
• v.34 no.4
• /
• pp.1-16
• /
• 2018

The standard shift-share analysis decomposes a region's sectoral growth into three components: national, industry-mix, and regional-shift effects. Nevertheless, the three components of the traditional shift-share are not related to the behavior of the regional economies that are neighbors of the region under analysis. We incorporate a spatial structure within this basic formulation, and consider spatial interaction in the decomposition analysis. Daesan Port's export grew steadily at an annualized average rate of 4.0% during 2011-2017, and its rank, in terms of export performance, was 13 in 2010; this rose to 6 in 2016, then declined slightly to 7 in 2017 before reaching 6 as of June, 2018. However, not all ports have a similar growth path. The Onsan Port's share declined from 27.4% in 2011 to 21.0% to 2017, whereas the share of petroleum product exports of Daesan Port increased rapidly, from approximately 8.5% in 2011 to 16.0% in 2017. The standard shift-share analysis shows that petroleum products and basic petrochemicals have a positive regional in dustry-mix effect, but petrochemistry materials and synthetic resins have a negative sign, indicating that the former's exports grow faster than national export, while the increase of the latter's export is slower than national one. The spatial shift-share model indicates that for both petroleum products and basic petrochemicals, Incheon and Ulsan Ports have a positive value for the neighbor-nation regional shift effect and a positive value for the region-neighbor regional shift effect. This paper also shows that Yeosu Port for petroleum products; Ulsan Port for basic petrochemicals; Ulsan, Onsan and Yeosu Ports for petrochemistry materials; and Ulsan, Busan, and Incheon Ports for synthetic resins have a positive value for the neighbor-nation regional shift effect but a negative value for the region-neighbor regional shift effect.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.145-150
• /
• 2015

Needs about safety of residents are important in urbanized society, elderly and small-size family. People are looking for safety information system and device of CPTED. That is, Needs and Installations of CCTV increased steadily. But, scientific analysis about validity, systematic plan and location of security CCTV is nonexistent. It is simply put these devised in more demanded areas. It has limits to look for safety of residents by increasing density of CCTVs. One of the characteristics of crime is clustering and stong interconnectivity. So, exploratory spatial data of crime is geo-coded using 2 years data and carried out cluster analysis and space statistical analysis through GIS space analysis by dividing 18 variables into social economy, urban space, crime prevention facility and crime occurrence index. The result of analysis shows cluster of 5 major crimes, theft, violence and sexual violence by Nearest Neighbor distance analysis and Ripley's K function. It also shows strong crime interconnectivity through criminal correlation analysis. In case of finding criminal cluster, you can find criminal hotspot. So, in this study I found concept of hotspot and considered technique about selection of hotspot. And then, selected hotspot about 5 major crimes, theft, violence and sexual violence through Nearest Neighbor Hierarchical Spatial Clustering.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.311-320
• /
• 2009

This study was carried out to estimate forest biomass and to produce forest biomass thematic map for Muju county by combining field data from the 5$^{th}$ National Forest Inventory (2006-2007) and satellite data. For estimating forest biomass, two methods were examined using a Landsat TM-5(taken on April 28th, 2005) and field data: multi-variant regression modeling and t-Nearest Neighbor (k-NN) technique. Estimates of forest biomass by the two methods were compared by a cross-validation technique. The results showed that the two methods provide comparatively accurate estimation with similar RMSE (63.75$\sim$67.26ton/ha) and mean bias ($\pm$1ton/ha). However, it is concluded that the k-NN method for estimating forest biomass is superior in terms of estimation efficiency to the regression model. The total forest biomass of the study site is estimated 8.4 million ton, or 149 ton/ha by the k-NN technique.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2A
• /
• pp.99-106
• /
• 2009

In this paper, we propose UCA algorithms that are applied to the unified inter-cell interference mitigation through frequency plannings in OFDMA cellular systems. Under three frequency plannings, UCA algorithms allocate frequency channels to UEs(User Equipments). Proposed UCA algorithms require the information of received signal power from home sector and neighbor sectors respectively. We compare all possible combinations of UCA algorithms and frequency plannings through compute simulation. A primary performance measure is the low 5th percentile of SINR at UEs. The proposed UCA algorithms can avoid the interference to neighbor cells by allocating relatively low transmit power to centrally-located UEs and cancel inter-cell interference at cell-edge UEs by a coordinated symbol repetition. We show that UCA algorithm 2 applied in frequency planning 1 is promising among other combinations of UCA algorithms and frequency palnnings in terms of the low 5th percentile of SINR at UEs.

• Journal of Korean Society of Transportation
• /
• v.26 no.2
• /
• pp.101-107
• /
• 2008

Traffic speed data may be missed due to detector malfunction or network problems. In this paper we have proposed effective methods to estimate the data which could not be collected through loop detectors. Our proposed algorithm has three steps. First step is to find the most similar neighbor data record by coefficient of correlation. Second step is to make some data records which is calculated by the 5 kinds of estimation methods. Third step is to compare the data records with history data record of observation link and thus the best method is selected. The proposed method is useful for estimating travel time.

• Journal of Korea Multimedia Society
• /
• v.7 no.4
• /
• pp.459-466
• /
• 2004

In this paper, an effective skeleton method is proposed in order to obtain an enhanced digital image of skeleton line. The binary image using the threshold values is applied in the preprocessing stage and then the modified parallel processing method is applied to obtain the improved image of skeleton line. The existing skeleton methods are Rutovitz, Steiabelli and other five skeleton methods. In the digital process of skeleton line, the major problem caused by these methods is elongated lines and noise branches of the processed image. In this study, however, such noises are deleted first by the modified parallel processing step of the proposed method. Then a pixel is compared to its eight neighbor pixels. if its neighbor pixels are in one of the eight conditions, the central pixel is deleted. As a result, the quality of the skeleton is better then those produced by the existing skeleton methods.