• Journal of the Korean Society for Railway
• /
• v.13 no.2
• /
• pp.214-221
• /
• 2010

The transitional zone between tunnel and earthwork is one of the most vulnerable areas site for railway lines and because of differential settlement due to different stiffness of each supporting layer, it has to conducted a maintenance work constantly. In this study, it is conducted to compare the effect of reinforcement by wheel load and displacement of the sleepers after existing sleepers are replaced with the large sleepers for 20m long in-field transitional zone. Also, numerical parametric study using multi-layer elastic method has been performed to compare rail force, settlement and stresses of ballast while varying size and space of the sleeper. The field test and numerical results show that replacing the large sleepers improves about 10% of total settlement and coefficient of wheel force than conventional sleepers. Effectiveness of improvement is about 9.3%, 4%, 14.5% for rail seat force, settlement of sleepers and ballast pressure respectively with size of sleepers.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.409-416
• /
• 2006

In this paper, we propose an algorithm for extracting text regions from spam-mail images using color layer. The CLTE(color layer-based text extraction) divides the input image into eight planes as color layers. It extracts connected components on the eight images, and then classifies them into text regions and non-text regions based on the component sizes. We also propose an algorithm for recovering damaged text strokes from the extracted text image. In the binary image, there are two types of damaged strokes: (1) middle strokes such as 'ㅣ' or 'ㅡ' are deleted, and (2) the first and/or last strokes such as 'ㅇ' or 'ㅁ' are filled with black pixels. An experiment with 200 spam-mail images shows that the proposed approach is more accurate than conventional methods by over 10%.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.2 s.20
• /
• pp.39-47
• /
• 2002

For the purpose of data construction for the systematic management and sight-seeing guidance of the natural park, the Kumoh Mt. Province Park was selected as a pilot area. Digital topographic maps, thematic maps and satellite imagery covering the object area were processed and then landform analysis for elevation, slope, aspect and so on was conducted through DEM generation, and the landcover map and NDVI maP were extracted from Landsat TM data. The database was then constructed with these spatial data for GSIS. The image map was generated from IKONOS satellite data, which cover the pilot area data, with one meter resolution and also 3D visualization which was overlaid with main paths up a mountain were conducted. And the moving image files were produced along main paths up including main natural spectacular sights, cultural assets and management facilities. It is expected that the research result can be utilized as the fundamental data for re-assessing suitable land use and constructing Web-based guidance system.

• Journal of Advanced Navigation Technology
• /
• v.4 no.1
• /
• pp.23-35
• /
• 2000

In this paper, the design for a PCS base station antenna which is using broadband method by a stacked structure has been studied. The sensitive parameters, such as the parasitic elements, the height of air layer between the upper and lower patch, and the variation of feed point, of the microstrip antenna that has stacked structure in a characteristics variation situation are classified and the characteristics has been investigated through the simulations. A designed antenna has following characters. Impedance bandwidth is Z57.5MHz(VSWR${\leq}$2), horizontal beamwidth is $64.1^{\circ}$, and gain is 14.7dBi. Therefore, it is confirmed the characteristics is good. In this paper, through the designing of a stacked microstrip antenna, we has investigated the availability for Korea PCS base station antenna.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.5B
• /
• pp.794-800
• /
• 2010

It is necessary to accurate and efficient management for measured digital data from various sensors in digital marine vessel. It is not efficient that sensor network process input stream data of mass storage stored in database the same time. In this paper, We propose to improve the processing performance of multidimensional stream data continuous incoming from multiple sensor. We propose that we arrange some sensors (temperature, humidity, lighting, voice) and process query based on sliding window for efficient input stream and found multiple query plan to Mjoin method and we reduce stored data using SVM algorithm. We automatically delete that it isn't necessary to the data from the database and we used to ship diagnosis system for available data. As a result, we obtained to efficient result about 18.3% reduction rate of database using 35,912 data sets.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.27 no.1
• /
• pp.167-177
• /
• 1997

타액선 병변의 일반적인 영상진단법으로는 타액선조영술, 전산화단층촬영술, 자기공명 영상, 타액선 스캔, 초음파 촬영술이 있다. 이중 초음파촬영술은 타액선내 종양의 유무를 평가하는데 있어서 매우 우수하여, 전산화단층촬영이나 자기공명영상과 더불어 이용되고 있으나, 염증을 진단하는데 있어서는 타액선조영술보다 민감도가 떨어지는 단점이 있다. 일반적으로 타액선의 염증반응시 초음파상은 반향이 정상보다 낮아지며, 내부의 균질성이 떨어지는 양상을 보여 이를 진단의 기준으로 이용해왔으나 정상타액선에서도 반향이 편차가 심할 뿐만 아니라 연령에 따른 정상 타액선의 반향성에 대한 연구가 부족하여 진단에 어려움이 있었다. 이에 저자는 우선적으로 타액선에 병적인 증상이 없는 남녀 90명을 연령별(20-35세 : 청년군, 36~55세 : 중년군, 55-70세 노년군),성별에 따라 분류하여 정상 타액선의 초음파상을 얻었다. 이의 반향을 측정하고, 비만한 정도를 나타내는 체격지수를 구하여 다음과 같은 결과를 얻었다. 1. 이하선과 악하선 모두에서 연령군극_ 따라 반향성이 증가하는 양상을 보였으며, 청년군과 노년군 사이에는 유의한 차이가 있었다(p<0.05). 2. 이하선과 악하선 모두에서 성에 따른 반향성의 유의한 차이는 없었다. 3. 성에 관계없이 악하선의 반향성이 이하선의 반향성보다 높았으며, 남자에 있어서는 유의한 차이가 있었다(p<0.05). 4. 동일한 타액선에서 좌우측 타액선의 반향성의 평균 차이값은 유의한 차이가 없었다. 5. 이하선과 악하선의 반향성은 중등도의 양의 상관관계를 보였다(남자 : r=0.56, 여자 : r=0.54). 6. 체격지수와 타액선의 반향성은 약한 양의 상관관계를 보였다.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.475-485
• /
• 2020

Recently, a crowdsensing system that provides a new sensing service with real-time sensing data provided from a user's device including a sensor without installing a separate sensor has attracted attention. In the crowdsensing system, meaningless data may be provided due to a user's operation error or communication problem, or false data may be provided to obtain compensation. Therefore, the detection and removal of the abnormal data determines the quality of the crowdsensing service. The proposed methods in the past to detect these anomalies are not efficient for the fast-changing environment of crowdsensing. This paper proposes an anomaly data detection method by extracting the characteristics of continuously and rapidly changing sensing data environment by using machine learning technology and modeling it with an appropriate algorithm. We show the performance and feasibility of the proposed system using deep learning binary classification model of supervised learning and autoencoder model of unsupervised learning.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.11
• /
• pp.1307-1314
• /
• 2015

This study proposed a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. The algorithm proposed detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). Also, by applying the feature vector obtained for SVM, face areas can be tested. After the testing, the feature vector is applied to LDA and using Euclidean distance in the 2nd dimension, the final analysis and matching is performed. The algorithm proposed in this study could increase the stability and accuracy of recognition rates and as a large amount of calculation was not necessary due to the use of two dimensions, real-time recognition was possible.

• Journal of the Korean Applied Science and Technology
• /
• v.29 no.1
• /
• pp.159-173
• /
• 2012

UV-Curing technology can be classified into two categories for radical curing and cation curing. It also has mainly focused on surface finishing technology to improve functionality of various substrates such as plastics and metals. On the other hand, EB technology has dealt with cross-linking reactions as well as polymerization process to create novel functional materials. Both technologies have advantages in energy utilizing efficiency and environmental friendly when compared to conventional thermoset coatings. Consequently, UV cured coatings also permits a reduction in the $CO_2$ and VOCs emitted in the drying and curing process. This review mainly shows radical curing technology which is commonly used in UV curing coatings and also describes the technology trends of cation curing which has been attracted attention recently.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.539-548
• /
• 2020

Deep learning technology is currently being used and applied in many different fields. Convolution neural network (CNN) is a method of artificial neural networks in deep learning, which is commonly used for analyzing different types of images through classification. In the conventional classification of histopathology images of prostate carcinomas, the rating of cancer is classified by human subjective observation. However, this approach has produced to some misdiagnosing of cancer grading. To solve this problem, CNN based classification method is proposed in this paper, to train the histological images and classify the prostate cancer grading into two classes of the benign and malignant. The CNN architecture used in this paper is based on the VGG models, which is specialized for image classification. However, color normalization was performed based on the contrast enhancement technique, and the normalized images were used for CNN training, to compare the classification results of both original and normalized images. In all cases, accuracy was over 90%, accuracy of the original was 96%, accuracy of other cases was higher, and loss was the lowest with 9%.