• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.5C
• /
• pp.422-434
• /
• 2002

We propose 3-layered hierarchical fiber-optic backbone transmission network composed of B-DCS, Backbone ring, Edge ring for efficient transmission of high capacity traffic and consider design method to ensure network survivability of each layer at affordable cost. Mathematical ring-construction cost minimization using MIP(Mixed Integer Programming) models results in NP-complete problem. So, it is hard to solve it within reasonable computing time. on a large-scale network. Therefore we develop heuristic algorithms solving WSCAP(Working and Spared Channel Assignment Problem) for B-DCS, MRLB(Multi-Ring Load Balancing) problem for Backbone ring, and ORLB(Overlayed Ring Load Balancing) problem for Edge ring and show their usefulness through case study.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• The Korean Journal of Applied Statistics
• /
• v.36 no.1
• /
• pp.1-19
• /
• 2023

The purpose of this study was to find out what attributes are valid for the edge between students through longitudinal network analysis, and the results of TERGM (temporal exponential random graph model) and SAOM (stochastic actor-oriented model) statistical models were compared. The TERGM model interprets the research results based on the edge formation of the entire network, and the SAOM model interprets the research results on the surrounding networks formed by specific actors. The TERGM model expressed the influence of a previous time through a time term, and the SAOM model considered temporal dependence by implementing a network that evolves by an actor's opportunity as a ratio function.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.643-657
• /
• 2020

Sixth generation will exploit satellite, aerial, and terrestrial platforms jointly to improve radio access capability and unlock the support of on-demand edge cloud services in three-dimensional (3D) space, by incorporating mobile edge computing (MEC) functionalities on aerial platforms and low-orbit satellites. This will extend the MEC support to devices and network elements in the sky and forge a space-borne MEC, enabling intelligent, personalized, and distributed on-demand services. End users will experience the impression of being surrounded by a distributed computer, fulfilling their requests with apparently zero latency. In this paper, we consider an architecture that provides communication, computation, and caching (C3) services on demand, anytime, and everywhere in 3D space, integrating conventional ground (terrestrial) base stations and flying (non-terrestrial) nodes. Given the complexity of the overall network, the C3 resources and management of aerial devices need to be jointly orchestrated via artificial intelligence-based algorithms, exploiting virtualized network functions dynamically deployed in a distributed manner across terrestrial and non-terrestrial nodes.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.3
• /
• pp.492-507
• /
• 2008

Many classical network analysis methods approach networks in aspatial perspectives. Measuring network reliability and finding critical nodes in particular, the analyses consider only network connection topology ignoring spatial components in the network such as node attributes and edge distances. Using local network autocorrelation measure, this study handles the problem. By quantifying similarity or clustering of individual objects' attributes in space, local autocorrelation measures can indicate significance of individual nodes in a network. As an application, this study analyzed internet backbone networks in the United States using both classical disjoint product method and Getis-Ord local G statistics. In the process, two variables (population size and reliability) were applied as node attributes. The results showed that local network autocorrelation measures could provide local clusters of critical nodes enabling more empirical and realistic analysis particularly when research interests were local network ranges or impacts.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.387-396
• /
• 2024

Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms,such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically,we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.37.4-37
• /
• 2002

$\textbullet$ Feature extraction method for robot application $\textbullet$ Using ultrasonic sensor arrays $\textbullet$ Differentiate the target as plane, corner and edge $\textbullet$ Neural network approach

• Industrial Engineering and Management Systems
• /
• v.12 no.1
• /
• pp.9-15
• /
• 2013

An inverse minimum spanning tree problem makes the least modification on the edge weights such that a predetermined spanning tree is a minimum spanning tree with respect to the new edge weights. In this paper, the concept of uncertain ${\alpha}$-minimum spanning tree is initiated for minimum spanning tree problem with uncertain edge weights. Using different decision criteria, two uncertain programming models are presented to formulate a specific inverse minimum spanning tree problem with uncertain edge weights involving a sum-type model and a minimax-type model. By means of the operational law of independent uncertain variables, the two uncertain programming models are transformed to their equivalent deterministic models which can be solved by classic optimization methods. Finally, some numerical examples on a traffic network reconstruction problem are put forward to illustrate the effectiveness of the proposed models.

• Journal of Korea Multimedia Society
• /
• v.7 no.12
• /
• pp.1692-1699
• /
• 2004

Many researchers have developed various techniques for detection of human faces in ordinary still images. Face detection is the first imperative step of human face recognition systems. The two main problems of human face detection are how to cutoff the running time and how to reduce the number of false positives. In this paper, we present frontal and near-frontal face detection algorithm in still gray images using a thick edge image and neural network. We have devised a new filter that gets the thick edge image. Our overall scheme for face detection consists of two main phases. In the first phase we describe how to create the thick edge image using the filter and search for face candidates using a whole face detector. It is very helpful in removing plenty of windows with non-faces. The second phase verifies for detecting human faces using component-based eye detectors and the whole face detector. The experimental results show that our algorithm can reduce the running time and the number of false positives.

• Journal of Astronomy and Space Sciences
• /
• v.33 no.4
• /
• pp.313-318
• /
• 2016

Communication, Ocean And Meteorological Satellite (COMS) Meteorological Imager (MI) images are processed for radiometric and geometric correction from raw image data. When intermediate image data are matched and compared with reference landmark images in the geometrical correction process, various techniques for edge detection can be applied. It is essential to have a precise and correct edged image in this process, since its matching with the reference is directly related to the accuracy of the ground station output images. An edge detection method based on neural networks is applied for the ground processing of MI images for obtaining sharp edges in the correct positions. The simulation results are analyzed and characterized by comparing them with the results of conventional methods, such as Sobel and Canny filters.