PowerPoint Presentation
|
|
- 용주 감
- 5 years ago
- Views:
Transcription
1 철도궤도결함탐지를위한영역기반및픽셀기반딥러닝기법적용사례 Detection of track defects by region- and pixel-based deep learning approaches 한국철도기술연구원 / 첨단궤도토목본부황성호선임연구원 2015 The MathWorks, Inc. 1
2 목차 1. 회사및발표자소개 2. 철도및궤도소개 3. 프로젝트개요 4. 연구내용. 영역기반결함탐지. 픽셀기반결함탐지. Network 수정 5. 기술적어려움 6. 향후연구방향 7. MATLAB 에대한소감 2
3 한국철도기술연구원은? Korea Railroad Research Institute - 소속및소재지 : 과학기술정보통신부산하정부출연연구기관 / 경기도의왕 - 임무 : 철도, 대중교통, 물류등공공교통분야의연구개발및성과확산을통해국가및산업계 발전에기여 - 주요기능및역할. 고속철도, 일반철도, 도시철도및경량전철시스템연구개발. 차세대대중교통시스템연구개발. 철도안전, 표준화, 철도정책및물류기술연구개발. 남북철도및대륙철도연계기술연구개발. 철도, 대중교통, 물류등공공교통시스템핵심원천기술연구개발. 중소 중견기업등관련산업계협력 지원및기술사업화등 3
4 발표자황성호선임연구원은? 이름 : 황성호부서 : 첨단궤도토목본부, 궤도노반연구팀경력 : ~ 현재한국철도기술연구원전공 : 토목공학주요연구분야 : 궤도공학, 차량궤도상호작용 forever7@krri.re.kr 4
5 철도란?
6 궤도란? - 궤도의역할 : 차량을직접지지 (support) 정해진길로유도 (guide) - 기본궤도의구성 :. 레일 (rail). 체결장치 (fastener). 침목 (sleeper, tie). 자갈도상 (ballast) Spacing ~ 0.6m f t = 800(KS) ~ 900N/mm²(UIC). 노반 (roadbed) concrete or wood (steel or plastic fo special cases) Modern Railway Track 6
7 아스팔트도로포장의파손 - 균열 [ 거북등균열 ] [ 단부균열 ] 7
8 아스팔트도로포장의파손 - 균열 [ 차로와길어깨줄눈균열 ] [ 세로방향균열 ] 8
9 아스팔트도로포장의파손 - 변형 [ 러팅 ] [ 코러게이션 ] 9
10 아스팔트도로포장의파손 - 탈리 [ 포트홀 ] [ 박리 ] 10
11 궤도구성품의파손 - 레일 RailCorp Engineering Manual - Track Surface Defects in Rails [ 레일파단 ] [ 레일스쿼트 ] 11
12 궤도구성품의파손 - 레일 RailCorp Engineering Manual - Track Surface Defects in Rails [ 레일코러게이션 ] [ 헤드체크 ] RailCorp Engineering Manual - Track Surface Defects in Rails 12
13 궤도구성품의파손 - 체결장치 [ 파손 ] [ 탈락 ] 13
14 궤도구성품의파손 - 침목 [ 균열 ] [ 침목파손 ] 14
15 궤도구성품의파손 - 자갈도상 : 침하, 궤도틀림 [ 도상침하 ] [ 궤도틀림 ] 15
16 궤도유지보수의사결정체계 16
17 과업개요 - 과업목표 : 궤도결함주 ) 탐지를위한이미지프로세싱 Deep Learning 기법도입및적용 - 과업기간 : ~ (3년) - 진행방향 :. Network : 기존 trained network(segnet) 을이용하여 transfer learning 수행. 영역기반결함탐지우선수행 [1]. 픽셀기반결함탐지를통해세부적인결함탐지 [2]. 정확도를높이기위해 Network 수정 [3] - MATLAB 2018b or 2019a의 machine learning 및 deep learning toolbox를이용 주 ) 궤도결함 : 다양한외부환경및열차하중에따라궤도구성품에발생되는결함을의미. 예 ) 레일표면결함, 침목균열및파손, 체결구탈락등 17
18 SegNet - A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation Vijay Badrubarayanan, Alex Kendall, etc 18
19 1. 영역기반결함탐지 - input - Bounding Box(BB) - 개체구분 : 나뭇가지, 솔잎 [ 당초이미지 ] [ 영역지정이미지 ] 19
20 1. 영역기반결함탐지 method - RCNN : selective searching 기법주1) - FCNN : Fast RCNN 주2) 영역기반가속심층학습 - FFCNN : Faster RCNN 주3) 주 1) Girshick, R., et al. Rich feature hierarchies for accurate object detection and semantic segmentation, Proc. IEEE, CVPR, , 주 2) Girshick, R. Fast R-CNN, Proc. IEEE ICCV, , 주 3) Ren, S., et al. Faster R-CNN: Towards real-time object detection with region proposal networks, arxiv: ,
21 1. 영역기반결함탐지 결과 [RCNN] [FCNN] [FFCNN] Method RCNN FCNN FFCNN Pr (leaf) Pr (branch)
22 2. 픽셀기반결함탐지 method - Semantic Segmentation(SS) 주 ). 기존 DCNN 모형에적용한계층구조를적용하여 encoder를구성 pooling 층에대응하는 upsampling 층을도입 decoder 모형을작성하는동시에픽셀단위의 softmax 함수를통해대상물을구분. Decoder는 encoder에서 max pooling 층을사용하여구축한특성맵의해상도를다시향상시키는과정으로이해할수있으며, 이때 pooling층에서사용한인수를기억한후 upsampling 층에서다시사용함으로써원하는특성맵을획득. 따라서균열등과같이길이대비폭이작은대상물의검지에 RCNN 대비상대적으로우월한결과획득가능 주 ) Badrinarayanan, V., et al. SegNet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Transactions on pattern Analysis and Machine Intelligence, 39(12), pp , Garcia-Garcia, A, et al. A review on deep learning techniques applied to semantic segmentation, arxiv: ,
23 2. 픽셀기반결함탐지 1 - input [ 당초이미지 ] [ 픽셀지정이미지 ] - 개체구분 : 자갈, 침목, 체결장치, 레일, 나뭇가지, 솔잎 23
24 2. 픽셀기반결함탐지 1 Image Labeller 24
25 Polygon Brush digitizer 25
26 2. 픽셀기반결함탐지 1 - 결과 [ 입력이미지 ] [ 결과이미지 ] Model Leaf Branch Pr IoU Pr IoU SS DCNN
27 2. 픽셀기반결함탐지 2 [ 입력이미지 ] [ 결과이미지 ] Object avg. Pr IoU Object avg. Pr IoU Ballast Crack Sleeper Branch Rail Stone E-clip Leaf
28 3. 정확도향상을위한방안 Kernel size 변화 - Concept ReLU1 ReLU2 BN1 BN2 ReLU1 ReLU2 Conv1 (h w) Conv2 (w h) Pooling BN1 Conv1 (3 3) BN2 Conv2 (3 3) Pooling [Model 1] ReLU1 ReLU2 [SegNet] BN1 Conv1-2 (w h) Conv1-1 (h w) BN2 Conv2-2 (h w) Conv2-1 (w h) Pooling [Model 2] 28
29 Kernel size 입력 Layer 치환 / 삭제 / 추가 Layer 구성 29
30 3. 정확도향상을위한방안 Kernel size 변화 - Concept 30
31 3. 정확도향상을위한방안 결과 [Segnet(2017)] [Model 2] 31
32 Trouble - 균열검지의어려움. 균열은 bounding box 로 labelling 하기에는실제균열의면적비가작음 Gahyun Suh, Young-Jin Cha, "Deep faster R-CNN-based automated detection and localization of multiple types of damage," Proc. SPIE 10598, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, T (27 March 2018); doi: /
33 Trouble - 균열검지의어려움. Pixel labelling의경우도 labelling의정밀도에따라결과가달라짐. 균열의경계를찾기가난해 33
34 34
35 Trouble - Ground Truth Data 확보의어려움. Bounding Box의경우는 box 지정이용이한편임. Semantic Segmentation은 image labelling 작업이어렵고시간소요가많음. 비록 MATLAB에서제공하는자동 labelling tool이있지만, 아직실효성은낮으며, 균열과같은특이한부분을자동으로해주지못함 Image Labeler App에서 Custom algorithm을넣어서자동화가능 35
36 36
37 진행중인연구방향 - 대량의데이터확보. Ground Truth Data 확보가정밀도향상에가장지름길이라판단. Time-consuming한작업이지만균열검지, 균열폭확인을위해서는필요한작업 - Augmentation 을통한정밀도향상. 균열은방향성을가지고있기때문에직사각형 kernel 을사용할경우 augmentation 에따른 정밀도향상을기대할수있음 - Edge detection. 균열폭을검지하기위해서는 edge detection 이필수. how? 37
38 MATLAB 을활용한 Deep Learning 적용은? - 사용자 interface 우수. Deep learning, Image processing, Machine learning, Statistics 등다양한 toolbox를동시에활용할수있어상호보완적인효과 ex) 기구축된 DB를활용할경우 Label에대한전처리를손쉽게수행가능. Embedded app 을통해사용자편의성고려 ex) Image labeler 를활용하여별도의 image tool 없이도작업가능 (automated tool 등 ) - Trained network 수정용이. 기존의 network 를불러와서 custom layer 를추가하고삭제하는부분이용이 38
39 경청해주셔서 감사합니다. Q&A 2015 The MathWorks, Inc. 39
<4D6963726F736F667420576F7264202D20B1E2C8B9BDC3B8AEC1EE2DC0E5C7F5>
주간기술동향 2016. 5.18. 컴퓨터 비전과 인공지능 장혁 한국전자통신연구원 선임연구원 최근 많은 관심을 받고 있는 인공지능(Artificial Intelligence: AI)의 성과는 뇌의 작동 방식과 유사한 딥 러닝의 등장에 기인한 바가 크다. 이미 미국과 유럽 등 AI 선도국에서는 인공지능 연구에서 인간 뇌 이해의 중요성을 인식하고 관련 대형 프로젝트들을
More informationPowerPoint 프레젠테이션
Visual Search At SK-Planet sk-planet Machine Intelligence Lab. 나상일 1. 개발배경 2. 첫접근방법 3. 개선된방법 A. Visual recognition technology B. Guided search C. Retrieval system 개발배경 개발배경 상품검색을좀더쉽게 Key-word 트렌치코트버튺벨트
More information2 : (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, (JBE
2: (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, 2019 7 (JBE Vol. 24, No. 4, July 2019) https://doi.org/10.5909/jbe.2019.24.4.623
More information(JBE Vol. 24, No. 2, March 2019) (Special Paper) 24 2, (JBE Vol. 24, No. 2, March 2019) ISSN
(Special Paper) 24 2, 2019 3 (JBE Vol. 24, No. 2, March 2019) https://doi.org/10.5909/jbe.2019.24.2.234 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) SIFT a), a), a), a) SIFT Image Feature Extraction
More information(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN
(Special Paper) 23 2, 2018 3 (JBE Vol. 23, No. 2, March 2018) https://doi.org/10.5909/jbe.2018.23.2.186 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a) Robust Online Object Tracking via Convolutional
More information6 : (Gicheol Kim et al.: Object Tracking Method using Deep Learing and Kalman Filter) (Regular Paper) 24 3, (JBE Vol. 24, No. 3, May 2019) http
(Regular Paper) 24 3, 2019 5 (JBE Vol. 24, No. 3, May 2019) https://doi.org/10.5909/jbe.2019.24.3.495 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a), a), b), b), b), a) Object Tracking Method using
More informationMicrosoft Word - KSR2015A223
2015 년도한국철도학회추계학술대회논문집 KSR2015A223 콘크리트-아스팔트궤도연결접속부내광폭침목거동평가 Performance Evaluation of Wide Sleeper of the Connection Area Between Concrete and Asphalt Trackbed 전선표 *, 이성혁 **, 정우영 *, 박성민 *, 손호영 * SeonPyo
More informationHigh Resolution Disparity Map Generation Using TOF Depth Camera In this paper, we propose a high-resolution disparity map generation method using a lo
High Resolution Disparity Map Generation Using TOF Depth Camera In this paper, we propose a high-resolution disparity map generation method using a low-resolution Time-Of- Flight (TOF) depth camera and
More information정보기술응용학회 발표
, hsh@bhknuackr, trademark21@koreacom 1370, +82-53-950-5440 - 476 - :,, VOC,, CBML - Abstract -,, VOC VOC VOC - 477 - - 478 - Cost- Center [2] VOC VOC, ( ) VOC - 479 - IT [7] Knowledge / Information Management
More information09권오설_ok.hwp
(JBE Vol. 19, No. 5, September 2014) (Regular Paper) 19 5, 2014 9 (JBE Vol. 19, No. 5, September 2014) http://dx.doi.org/10.5909/jbe.2014.19.5.656 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a) Reduction
More information김기남_ATDC2016_160620_[키노트].key
metatron Enterprise Big Data SKT Metatron/Big Data Big Data Big Data... metatron Ready to Enterprise Big Data Big Data Big Data Big Data?? Data Raw. CRM SCM MES TCO Data & Store & Processing Computational
More informationexample code are examined in this stage The low pressure pressurizer reactor trip module of the Plant Protection System was programmed as subject for
2003 Development of the Software Generation Method using Model Driven Software Engineering Tool,,,,, Hoon-Seon Chang, Jae-Cheon Jung, Jae-Hack Kim Hee-Hwan Han, Do-Yeon Kim, Young-Woo Chang Wang Sik, Moon
More informationSchoolNet튜토리얼.PDF
Interoperability :,, Reusability: : Manageability : Accessibility :, LMS Durability : (Specifications), AICC (Aviation Industry CBT Committee) : 1988, /, LMS IMS : 1997EduCom NLII,,,,, ARIADNE (Alliance
More information(JBE Vol. 24, No. 4, July 2019) (Special Paper) 24 4, (JBE Vol. 24, No. 4, July 2019) ISSN
(JBE Vol. 24, No. 4, July 2019) (Special Paper) 24 4, 2019 7 (JBE Vol. 24, No. 4, July 2019) https://doi.org/10.5909/jbe.2019.24.4.580 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) Sensor Fusion a), b),
More informationDelving Deeper into Convolutional Networks for Learning Video Representations - Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville arXiv:
Delving Deeper into Convolutional Networks for Learning Video Representations Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville arxiv: 1511.06432 Il Gu Yi DeepLAB in Modu Labs. June 13, 2016 Il Gu Yi
More information,. 3D 2D 3D. 3D. 3D.. 3D 90. Ross. Ross [1]. T. Okino MTD(modified time difference) [2], Y. Matsumoto (motion parallax) [3]. [4], [5,6,7,8] D/3
Depth layer partition 2D 3D a), a) 3D conversion of 2D video using depth layer partition Sudong Kim a) and Jisang Yoo a) depth layer partition 2D 3D. 2D (depth map). (edge directional histogram). depth
More information딥러닝 첫걸음
딥러닝첫걸음 4. 신경망과분류 (MultiClass) 다범주분류신경망 Categorization( 분류 ): 예측대상 = 범주 이진분류 : 예측대상범주가 2 가지인경우 출력층 node 1 개다층신경망분석 (3 장의내용 ) 다범주분류 : 예측대상범주가 3 가지이상인경우 출력층 node 2 개이상다층신경망분석 비용함수 : Softmax 함수사용 다범주분류신경망
More information19_9_767.hwp
(Regular Paper) 19 6, 2014 11 (JBE Vol. 19, No. 6, November 2014) http://dx.doi.org/10.5909/jbe.2014.19.6.866 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) RGB-Depth - a), a), b), a) Real-Virtual Fusion
More information(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN
(Special Paper) 23 2, 2018 3 (JBE Vol. 23, No. 2, March 2018) https://doi.org/10.5909/jbe.2018.23.2.246 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) CNN a), a), a) CNN-Based Hand Gesture Recognition
More information<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB>
주간기술동향 2016. 2. 24. 최신 ICT 이슈 인공지능 바둑 프로그램 경쟁, 구글이 페이스북에 리드 * 바둑은 경우의 수가 많아 컴퓨터가 인간을 넘어서기 어려움을 보여주는 사례로 꼽혀 왔 으며, 바로 그런 이유로 인공지능 개발에 매진하는 구글과 페이스북은 바둑 프로그램 개 발 경쟁을 벌여 왔으며, 프로 9 단에 도전장을 낸 구글이 일단 한발 앞서 가는
More informationJournal of Educational Innovation Research 2019, Vol. 29, No. 2, pp DOI: * The Effect of Paren
Journal of Educational Innovation Research 2019, Vol. 29, No. 2, pp.95-116 DOI: http://dx.doi.org/10.21024/pnuedi.29.2.201906.95 * The Effect of Parent Education Program Using Action Learning on Family
More information02(848-853) SAV12-19.hwp
848 정보과학회논문지 : 소프트웨어 및 응용 제 39 권 제 11 호(2012.11) 3차원 객체인식을 위한 보완적 특징점 기반 기술자 (Complementary Feature-point-based Descriptors for 3D Object Recognition) 장영균 김 주 환 문 승 건 (Youngkyoon Jang) (Ju-Whan Kim) (Seung
More informationVertical Probe Card Technology Pin Technology 1) Probe Pin Testable Pitch:03 (Matrix) Minimum Pin Length:2.67 High Speed Test Application:Test Socket
Vertical Probe Card for Wafer Test Vertical Probe Card Technology Pin Technology 1) Probe Pin Testable Pitch:03 (Matrix) Minimum Pin Length:2.67 High Speed Test Application:Test Socket Life Time: 500000
More informationDBPIA-NURIMEDIA
한국소음진동공학회 2015추계학술대회논문집년 Study of Noise Pattern and Psycho-acoustics Characteristic of Household Refrigerator * * ** ** Kyung-Soo Kong, Dae-Sik Shin, Weui-Bong Jeong, Tae-Hoon Kim and Se-Jin Ahn Key Words
More informationJournal of Educational Innovation Research 2017, Vol. 27, No. 2, pp DOI: * Review of Research
Journal of Educational Innovation Research 2017, Vol. 27, No. 2, pp.79-102 DOI: http://dx.doi.org/10.21024/pnuedi.27.2.201706.79 * Review of Research Trends on Curriculum for Students with Severe and multiple
More informationuntitled
전방향카메라와자율이동로봇 2006. 12. 7. 특허청전기전자심사본부유비쿼터스심사팀 장기정 전방향카메라와자율이동로봇 1 Omnidirectional Cameras 전방향카메라와자율이동로봇 2 With Fisheye Lens 전방향카메라와자율이동로봇 3 With Multiple Cameras 전방향카메라와자율이동로봇 4 With Mirrors 전방향카메라와자율이동로봇
More information(JBE Vol. 21, No. 1, January 2016) (Regular Paper) 21 1, (JBE Vol. 21, No. 1, January 2016) ISSN 228
(JBE Vol. 1, No. 1, January 016) (Regular Paper) 1 1, 016 1 (JBE Vol. 1, No. 1, January 016) http://dx.doi.org/10.5909/jbe.016.1.1.60 ISSN 87-9137 (Online) ISSN 16-7953 (Print) a), a) An Efficient Method
More informationKAKAO AI REPORT Vol.01
KAKAO AI REPORT Vol.01 2017.03 import kakao.ai.dataset.daisy import kakao.ai.image import kakao.ai.classifier import mxnet as mx def Conv(data, num_filter, kernel=(1, 1), stride=(1, 1), pad=(0, 0), name=none,
More information다중 곡면 검출 및 추적을 이용한 증강현실 책
1 딥러닝기반성별및연령대 추정을통한맞춤형광고솔루션 20101588 조준희 20131461 신혜인 2 개요 연구배경 맞춤형광고의필요성 성별및연령별주요관심사에적합한광고의필요성증가 제한된환경에서개인정보획득의한계 맞춤형광고의어려움 영상정보기반개인정보추정 연구목표 딥러닝기반사용자맞춤형광고솔루션구현 얼굴영상을이용한성별및연령대추정 성별및연령대를통합네트워크로학습하여추정정확도향상
More information°í¼®ÁÖ Ãâ·Â
Performance Optimization of SCTP in Wireless Internet Environments The existing works on Stream Control Transmission Protocol (SCTP) was focused on the fixed network environment. However, the number of
More information°¡°Ç6¿ù³»ÁöÃÖÁ¾
J 2007. 6 J J J J J J J J Special J Special J J Special 01 02 03 04 05 06 07 J J Special J J Special J Special J J Special J J Special J J Special J J Special J J J J J J J J J J J J J J J J J J J J
More information<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB>
최신 ICT 이슈 최신 ICT 이슈 알파고의 심층강화학습을 뒷받침한 H/W 와 S/W 환경의 진화 * 알파고의 놀라운 점은 바둑의 기본규칙조차 입력하지 않았지만 승리 방식을 스스로 알아 냈다는 것이며, 알파고의 핵심기술인 심층강화학습이 급속도로 발전한 배경에는 하드웨 어의 진화와 함께 오픈소스화를 통해 발전하는 AI 관련 소프트웨어들이 자리하고 있음 2014
More information09È«¼®¿µ5~152s
Korean Journal of Remote Sensing, Vol.23, No.2, 2007, pp.45~52 Measurement of Backscattering Coefficients of Rice Canopy Using a Ground Polarimetric Scatterometer System Suk-Young Hong*, Jin-Young Hong**,
More informationMicrosoft Word - KSR2016A215.
2016 년도한국철도학회추계학술대회논문집 KSR2016A215 비개착공사에있어철도노반자동화계측관리사례분석 Case Study of the Automatic Measurement System around Railway roadbed on the Non-open Cut Method 이재호 *, 이근수 **, 천승우 ***, 엄진현 *** Jaeho Lee *,
More information2 : (Juhyeok Mun et al.: Visual Object Tracking by Using Multiple Random Walkers) (Special Paper) 21 6, (JBE Vol. 21, No. 6, November 2016) ht
(Special Paper) 21 6, 2016 11 (JBE Vol. 21, No. 6, November 2016) http://dx.doi.org/10.5909/jbe.2016.21.6.913 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a), a) Visual Object Tracking by Using Multiple
More information(JBE Vol. 7, No. 4, July 0)., [].,,. [4,5,6] [7,8,9]., (bilateral filter, BF) [4,5]. BF., BF,. (joint bilateral filter, JBF) [7,8]. JBF,., BF., JBF,.
: 565 (Special Paper) 7 4, 0 7 (JBE Vol. 7, No. 4, July 0) http://dx.doi.org/0.5909/jbe.0.7.4.565 a), b), a) Depth Map Denoising Based on the Common Distance Transform Sung-Yeol Kim a), Manbae Kim b),
More information<BACFC7D1B3F3BEF7B5BFC7E22D3133B1C733C8A3504446BFEB2E687770>
북한의 주요 농업 관련 법령 해설 1) 이번 호와 다음 호에서는 북한의 주요 농업 관련 법령을 소개하려 한다. 북한의 협동농장은 농업협동조합기준규약초안 과 농장법 에 잘 규정되어 있다. 북한 사회주의 농업정책은 사회 주의농촌문제 테제 2), 농업법, 산림법 등을 통해 엿볼 수 있다. 국가계획과 농업부문의 관 계, 농산물의 공급에 관해서는 인민경제계획법, 사회주의상업법,
More information1 9 2 0 3 1 1912 1923 1922 1913 1913 192 4 0 00 40 0 00 300 3 0 00 191 20 58 1920 1922 29 1923 222 2 2 68 6 9
(1920~1945 ) 1 9 2 0 3 1 1912 1923 1922 1913 1913 192 4 0 00 40 0 00 300 3 0 00 191 20 58 1920 1922 29 1923 222 2 2 68 6 9 1918 4 1930 1933 1 932 70 8 0 1938 1923 3 1 3 1 1923 3 1920 1926 1930 3 70 71
More informationfull paper_철도교량_강덕만.hwp
궤도구조를 고려한 철도교량의 동적거동 분석 Dynamic Behavior Analysis of Railway Bridge considering Track Stiffness 강덕만 안해영* 성덕룡** 김성일*** 박용걸**** Kang, Duck-Man An, Hea-Young Sung, Deok-Yong Kim, Sung-Il Park, Yong-Gul ------------------------------------------------------------------------------------
More informationÀ±½Â¿í Ãâ·Â
Representation, Encoding and Intermediate View Interpolation Methods for Multi-view Video Using Layered Depth Images The multi-view video is a collection of multiple videos, capturing the same scene at
More information09 ½ÅÇù3¿ùb63»ÁöÃÖÁ¾FFš
2009 +03 Special Story 04 06 08 In Happy 10 14 17 18 20 22 With 24 27 28 30 31 32 34 2009. 03 Vol.423 Story 1 Story 2 Story 3 04 Special Story1 MARCH 2009 05 Special Story 2 01 06 02 03 MARCH 2009 07
More information2017 년 6 월한국소프트웨어감정평가학회논문지제 13 권제 1 호 Abstract
2017 년 6 월한국소프트웨어감정평가학회논문지제 13 권제 1 호 Abstract - 31 - 소스코드유사도측정도구의성능에관한비교연구 1. 서론 1) Revulytics, Top 20 Countries for Software Piracy and Licence Misuse (2017), March 21, 2017. www.revulytics.com/blog/top-20-countries-software
More informationElectronics and Telecommunications Trends 인공지능을이용한 3D 콘텐츠기술동향및향후전망 Recent Trends and Prospects of 3D Content Using Artificial Intelligence Technology
Electronics and Telecommunications Trends 인공지능을이용한 3D 콘텐츠기술동향및향후전망 Recent Trends and Prospects of 3D Content Using Artificial Intelligence Technology 이승욱 (S.W. Lee, tajinet@etri.re.kr) 황본우 (B.W. Hwang,
More information목 차 요약문 I Ⅰ. 연구개요 1 Ⅱ. 특허검색 DB 및시스템조사 5
2014 특허청정책연구결과보고서 발간등록번호 11-1430000-001369-01 ISBN 978-89-6199-792-8-13500 ᅦ 특허검색고도화를위한 검색시스템및검색기법연구 A Study on the Retrieval Systems and Techniques for Enhancing Patent Search 목 차 요약문 I Ⅰ. 연구개요 1 Ⅱ. 특허검색
More informationRNN & NLP Application
RNN & NLP Application 강원대학교 IT 대학 이창기 차례 RNN NLP application Recurrent Neural Network Recurrent property dynamical system over time Bidirectional RNN Exploit future context as well as past Long Short-Term
More information4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, (JBE Vol. 24, No. 3, May 2019
4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, 2019 5 (JBE Vol. 24, No. 3, May 2019) https://doi.org/10.5909/jbe.2019.24.3.387 ISSN 2287-9137
More information3월-기획특집1-4
Special Edition 2 60 REAL ESTATE FOCUS 2-1 2016 March Vol.94 61 Special Edition 2 62 REAL ESTATE FOCUS 2-1 2016 March Vol.94 63 Special Edition 2 64 REAL ESTATE FOCUS 2-1 2016 March Vol.94 65 Special Edition
More informationecorp-프로젝트제안서작성실무(양식3)
(BSC: Balanced ScoreCard) ( ) (Value Chain) (Firm Infrastructure) (Support Activities) (Human Resource Management) (Technology Development) (Primary Activities) (Procurement) (Inbound (Outbound (Marketing
More informationJournal of Educational Innovation Research 2018, Vol. 28, No. 3, pp DOI: NCS : * A Study on
Journal of Educational Innovation Research 2018, Vol. 28, No. 3, pp.157-176 DOI: http://dx.doi.org/10.21024/pnuedi.28.3.201809.157 NCS : * A Study on the NCS Learning Module Problem Analysis and Effective
More informationJournal of Educational Innovation Research 2017, Vol. 27, No. 4, pp DOI: A Study on the Opti
Journal of Educational Innovation Research 2017, Vol. 27, No. 4, pp.127-148 DOI: http://dx.doi.org/11024/pnuedi.27.4.201712.127 A Study on the Optimization of Appropriate Hearing-impaired Curriculum Purpose:
More informationMicrosoft Word - KSR2014A286
2014 년도한국철도학회추계학술대회논문집 KSR2014A286 위치검지센서를활용한열차위치검지시스템의기초결과 Preliminary Results of Train Positioning Detection System using Localization Sensors 김성진 *, 박성수 *, 이재호 *, 권민정 *, 김혜윤 ** Seong Jin Kim *, Sungsoo
More informationCh 1 머신러닝 개요.pptx
Chapter 1. < > :,, 2017. Slides Prepared by,, Biointelligence Laboratory School of Computer Science and Engineering Seoul National University 1.1 3 1.2... 7 1.3 10 1.4 16 1.5 35 2 1 1.1 n,, n n Artificial
More informationÆ÷Àå½Ã¼³94š
Cho, Mun Jin (E-mail: mjcho@ex.co.kr) ABSTRACT PURPOSES : The performance of tack coat, commonly used for layer interface bonding, is affected by application rate and curing time. In this study, bonding
More information성능 감성 감성요구곡선 평균사용자가만족하는수준 성능요구곡선 성능보다감성가치에대한니즈가증대 시간 - 1 -
- 1 - 성능 감성 감성요구곡선 평균사용자가만족하는수준 성능요구곡선 성능보다감성가치에대한니즈가증대 시간 - 1 - - 2 - - 3 - - 4 - - 5 - - 6 - - 7 - - 8 - - 9 - - 10 - - 11 - - 12 - 감각및자극 (Sensory & Information Stimuli) 개인 (a person) 감성 (Sensibility)
More informationBusiness Agility () Dynamic ebusiness, RTE (Real-Time Enterprise) IT Web Services c c WE-SDS (Web Services Enabled SDS) SDS SDS Service-riented Architecture Web Services ( ) ( ) ( ) / c IT / Service- Service-
More information임베디드-브로슈어2
www.givet.re.kr Gyeongbuk Research Institute of Vehicle Embedded Technology 2007. 7 2008. 7 2012. 3 SMART VEHICLE R&D Division Business Support Division Embedded Technology BUSINESS 1 센터 기반 구축사업 최적의 환경을
More informationMicrosoft PowerPoint - HS6000 Full HD Subtitle Generator Module Presentation
HS6000 Full HD Subtitle Generator Module High-performance Network DVR Solution Preliminary Product Overview (Without notice, following described technical spec. can be changed) AddPac Technology 2010,
More informationReinforcement Learning & AlphaGo
Gait recognition using a Discriminative Feature Learning Approach for Human identification 딥러닝기술및응용딥러닝을활용한개인연구주제발표 이장우 wkddn1108@kist.re.kr 2018.12.07 Overview 연구배경 관련연구 제안하는방법 Reference 2 I. 연구배경 Reinforcement
More information학습영역의 Taxonomy에 기초한 CD-ROM Title의 효과분석
,, Even the short history of the Web system, the techniques related to the Web system have b een developed rapidly. Yet, the quality of the Webbased application software has not improved. For this reason,
More information무선데이터_요금제의_가격차별화에_관한_연구v4.hwp
무선데이터 요금제의 가격차별화에 관한 연구 김태현, 이동명, 모정훈 연세대학교 정보산업공학과 서울시 서대문구 신촌동 연세대학교 제 3공학관 서울대학교 산업공학과 서울시 관악구 신림동 서울대학교 39동 Abstract 스마트폰의 도입으로 무선 데이타 트래픽 이 빠른 속도로 증가하고 있고 3G 무선 데 이타망의 용량으론 부족할 것으로 예측되 고 있다. 본 연구에서는
More information(JBE Vol. 22, No. 2, March 2017) (Regular Paper) 22 2, (JBE Vol. 22, No. 2, March 2017) ISSN
(JBE Vol. 22, No. 2, March 2017) (Regular Paper) 22 2, 2017 3 (JBE Vol. 22, No. 2, March 2017) https://doi.org/10.5909/jbe.2017.22.2.234 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a), a) Real-time
More information<32315FB9CEB0E6C8AF2DB1B3B7AE20BBF320C0DAB0A5B1CBB5B5C0C720C1BEC0FAC7D7B7C22E687770>
Journal of the Korea Academia-Industrial cooperation Society Vol. 17, No. 5 pp. 173-178, 2016 http://dx.doi.org/10.5762/kais.2016.17.5.173 ISSN 1975-4701 / eissn 2288-4688 교량상자갈궤도의종저항력측정을위한실험연구 민경환 1*,
More informationMicrosoft Word - KSR2012A103.doc
YWXY º º t rzyywxyhxwz ¼ ƒx p y v ³ Evaluation on Long-Term Behavior of Reinforced Railroad Subgrade with Bending Stiffness Wall Õá ã äõ ã äø ãã äø ãã Dae-Sang Kim *, Ung-Jin Kim *, Jong-Sik Park *, Seong-yong
More informationMicrosoft Word - KSR2015A065
년도한국철도학회추계학술대회논문집 KSRA 철도노반부설후성토부잔류침하발생에관한통계적분석 Statistical analysis of residual settlement on embankment after constructing railway roadbed 이세희 *, 조국환 Se-Hee Lee *, Kook-Hwan Cho Abstract The roadbed
More informationSNS 명예훼손의 형사책임
SNS 명예훼손의 형사책임 Criminal Liability for Defamation on the SNS 지 영 환 * (Ji, Young-Hwan) < 차 례 > Ⅰ. 서론 Ⅱ. SNS상 명예훼손 Ⅲ. SNS 명예훼손의 형사책임 Ⅳ. SNS 명예훼손행위의 정책적 예방과 입법적 검토 Ⅴ. 결론 주제어: 인터넷, SNS, 명예훼손, 형법, 정보통신망 이용촉진
More informationAV PDA Broadcastin g Centers Audio /PC Personal Mobile Interactive (, PDA,, DMB ),, ( 150km/h ) (PPV,, ) Personal Mobile Interactive Multimedia Broadcasting Services 6 MHz TV Channel Block A Block
More information10 이지훈KICS2015-03-068.hwp
논문 15-40-05-10 The Journal of Korean Institute of Communications and Information Sciences '15-05 Vol.40 No.05 http://dx.doi.org/10.7840/kics.2015.40.5.851 가로등 인프라를 활용한 안전한 스마트 방범 시스템 차 정 화, 이 주 용 *, 이
More informationDBPIA-NURIMEDIA
논문 10-35-03-03 한국통신학회논문지 '10-03 Vol. 35 No. 3 원활한 채널 변경을 지원하는 효율적인 IPTV 채널 관리 알고리즘 준회원 주 현 철*, 정회원 송 황 준* Effective IPTV Channel Control Algorithm Supporting Smooth Channel Zapping HyunChul Joo* Associate
More information<BCBCC1BEB4EB BFE4B6F72E706466>
세종대학교요람 Sejong University 2017 2017 Sejong University 4 SEJONG UNIVERSITY www.sejong.ac.kr 5 2017 Sejong University 8 SEJONG UNIVERSITY 10 SEJONG UNIVERSITY www.sejong.ac.kr 11 12 SEJONG UNIVERSITY www.sejong.ac.kr
More information<B1B9B3BBB1E2BEF7C0C720C7D8BFDCB0C5B7A128C0FBBBF6292E687770>
머리말 1 머리말 WTO의 출범과 정보통신기술의 발달, 금융 및 자본의 국제화 등으로 인하여 세계경제는 단일 시장으로의 통합이 가속되고 있습니다. 우리나라가 OECD에 가입한 이후 경제의 개방화 국제화가 가속되면서 우리 나라 기업들의 해외진출도 외국기업의 국내진출 못지않게 활발해지고 있습니다. 부존자원이 없고 내수시장이 규모가 한정되어 있는 우리나라의 현실을
More informationJournal of Educational Innovation Research 2018, Vol. 28, No. 4, pp DOI: A Study on Organizi
Journal of Educational Innovation Research 2018, Vol. 28, No. 4, pp.441-460 DOI: http://dx.doi.org/10.21024/pnuedi.28.4.201812.441 A Study on Organizing Software Education of Special Education Curriculum
More information03¼ºÅ°æ_2
102 103 R&D closed innovation strategy open innovation strategy spin-off Chesbrough technology marketing IBM Intel P&G IBM Dell Apple Nintendo Acer http //www ibm com/ibm/licensing MIT 1) 104 Bucher et
More information<4D F736F F F696E74202D F ABFACB1B8C8B85FBEF0BEEEC3B3B8AEBFCDB1E2B0E8B9F8BFAAC7F6C8B228C1F6C3A2C1F829>
Ebiz 연구회 2017 9 21 정의용 FrankJeong@systrangroupcom SYSTRAN History & Technology Natural Language Processing Machine Translation History MT Technique Neural Network Neural Machine Translation Data Landscape
More information001지식백서_4도
White Paper on Knowledge Service Industry Message Message Contents Contents Contents Contents Chapter 1 Part 1. Part 2. Part 3. Chapter
More information포스코 6월 표지 3차
6move Monthly Magazine of POSCO E&C June 009. Vol.73 MONTHLY MAGAZINE OF POSCO E&C POSCO ENGINEERING & CONSTRUCTION JUNE VOL.73 COVER MODEL Contents Photo Message Photo Message Special Theme People Talk
More informationMicrosoft Word - KSR2016A252
2016 년도한국철도학회추계학술대회논문집 KSR2016A252 Pagani Cone Test을이용한철도노반조사기법연구 A study on the ground investigation technique of railway using Pagani cone test 강성욱 *, 조국환 Sung-Wook Kang *, Kook-Hwan Cho Abstract Standard
More informationKR C Rev.8, 27. October 2017 본선부대및안전시설 한국철도시설공단
Rev.8, 27. October 2017 본선부대및안전시설 2017. 10. 27 한국철도시설공단 REVIEW CHART 1 2 1 2 3 4 5 6 7 8 9 10 11 12 13 Φ 14 1,500 1,580 1,000 1:2.5 자갈무덤 앞면벽이없을때 6,700 1 : 2 400 955 240 240 210 흙무덤표면에떼를입힘. 철선 4mm 690
More informationMicrosoft Word - KSR2016S168
2016 년도 한국철도학회 춘계학술대회 논문집 KSR2016S168 GPR 을 이용한 자갈궤도 파울링층 파악을 위한 실내실험적 접근 Evaluation of Applicability of GPR to Detect Fouled Layer in Ballast Using Laboratory Tests 신지훈 *, 최영태 **, 장승엽 *** Ji-hoon. Shin
More information포스코2월 표지-최종
Monthly Magazine of POSCO E&C February 009. Vol.69 MONTHLY MAGAZINE OF POSCO E&C POSCO ENGINEERING & CONSTRUCTION FEBRUARY VOL.69 COVER MODEL change Contents Photo Message Focus on 0 04 Special Theme People
More information3 Gas Champion : MBB : IBM BCS PO : 2 BBc : : /45
3 Gas Champion : MBB : IBM BCS PO : 2 BBc : : 20049 0/45 Define ~ Analyze Define VOB KBI R 250 O 2 2.2% CBR Gas Dome 1290 CTQ KCI VOC Measure Process Data USL Target LSL Mean Sample N StDev (Within) StDev
More informationJournal of Educational Innovation Research 2019, Vol. 29, No. 1, pp DOI: (LiD) - - * Way to
Journal of Educational Innovation Research 2019, Vol. 29, No. 1, pp.353-376 DOI: http://dx.doi.org/10.21024/pnuedi.29.1.201903.353 (LiD) -- * Way to Integrate Curriculum-Lesson-Evaluation using Learning-in-Depth
More information±è¼ºÃ¶ Ãâ·Â-1
Localization Algorithms Using Wireless Communication Systems For efficient Localization Based Services, development of accurate localization algorithm has to be preceded. In this paper, research trend
More information(JBE Vol. 24, No. 4, July 2019) (Special Paper) 24 4, (JBE Vol. 24, No. 4, July 2019) ISSN
(JBE Vol. 24, No. 4, July 2019) (Special Paper) 24 4, 2019 7 (JBE Vol. 24, No. 4, July 2019) https://doi.org/10.5909/jbe.2019.24.4.564 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a) Integral Regression
More information3 : 3D (Seunggi Kim et. al.: 3D Depth Estimation by a Single Camera) (Regular Paper) 24 2, (JBE Vol. 24, No. 2, March 2019)
3 : 3D (Regular Paper) 24 2, 2019 3 (JBE Vol. 24, No. 2, March 2019) https://doi.org/10.5909/jbe.2019.24.2.281 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 3D a), a), a), a) 3D Depth Estimation by a
More informationMicrosoft Word - KSR2012A090.doc
2012 년도한국철도학회추계학술대회논문집 KSR2012A090 3D 이동하중을고려한선로하부비개착구조물주변거동특성연구 The Behavior Characteristic of Transition Zone Existence around Substructure using 3Dimension Moving load 권혁일, 염태중 *, 조국환 ** HukIl Kwon,
More information< BCADC3A2C1F82DB9ABC0CE20C7D7B0F8B1E2B8A620C0CCBFEBC7D120B9D0C1FDBFB5BFAA2E485750>
Journal of the Korea Academia-Industrial cooperation Society Vol. 19, No. 3 pp. 693-698, 2018 https://doi.org/10.5762/kais.2018.19.3.693 ISSN 1975-4701 / eissn 2288-4688 무인항공기를이용한밀집영역자동차탐지 서창진상명대학교정보보안공학과
More informationPowerPoint 프레젠테이션
ㆍ Natural Language Understanding 관련기술 ㆍ Semantic Parsing Conversational AI Natural Language Understanding / Machine Learning ㆍEntity Extraction and Resolution - Machine Learning 관련기술연구개발경험보유자ㆍStatistical
More information팸
2014 Vol.08 Special Feature Special Interview Contents 4 I 5 8 I 9 BRAND NEWS www.ikfa.or.kr 10 I 11 SPECIAL INTERVIEW 12 I 13 14 I 15 16 I 17 18 I 19 20 I 21 22 I 23 24 I 25 26 I 27 28 I 29 30 I 31
More information02이승민선생_오라클.PDF
Oracle Internet Procurement Agenda 1 2 3 4 5 Introduction Oracle Solution Overview Oracle Internet Procurement Value Proposition Reference Conclusion e-procurement, E- Commerce Internet Automated Transactions
More information04김호걸(39~50)ok
Journal of Environmental Impact Assessment, Vol. 22, No. 1(2013) pp.39~50 Prediction of Landslides Occurrence Probability under Climate Change using MaxEnt Model Kim, Hogul* Lee, Dong-Kun** Mo, Yongwon*
More information14.531~539(08-037).fm
G Journal of the Korea Concrete Institute Vol. 20, No. 4, pp. 531~539, August, 2008 š x y w m š gj p { sƒ z 1) * 1) w w Evaluation of Flexural Strength for Normal and High Strength Concrete with Hooked
More information(JBE Vol. 21, No. 5, September 2016) (Regular Paper) 21 5, (JBE Vol. 21, No. 5, September 2016) ISS
(JBE Vol. 21, No. 5, September 2016) (Regular Paper) 21 5, 2016 9 (JBE Vol. 21, No. 5, September 2016) http://dx.doi.org/10.5909/jbe.2016.21.5.782 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), b),
More information지능정보연구제 16 권제 1 호 2010 년 3 월 (pp.71~92),.,.,., Support Vector Machines,,., KOSPI200.,. * 지능정보연구제 16 권제 1 호 2010 년 3 월
지능정보연구제 16 권제 1 호 2010 년 3 월 (pp.71~92),.,.,., Support Vector Machines,,., 2004 5 2009 12 KOSPI200.,. * 2009. 지능정보연구제 16 권제 1 호 2010 년 3 월 김선웅 안현철 社 1), 28 1, 2009, 4. 1. 지능정보연구제 16 권제 1 호 2010 년 3 월 Support
More informationSoftware Requirrment Analysis를 위한 정보 검색 기술의 응용
EPG 정보 검색을 위한 예제 기반 자연어 대화 시스템 김석환 * 이청재 정상근 이근배 포항공과대학교 컴퓨터공학과 지능소프트웨어연구실 {megaup, lcj80, hugman, gblee}@postech.ac.kr An Example-Based Natural Language System for EPG Information Access Seokhwan Kim
More information1217 WebTrafMon II
(1/28) (2/28) (10 Mbps ) Video, Audio. (3/28) 10 ~ 15 ( : telnet, ftp ),, (4/28) UDP/TCP (5/28) centralized environment packet header information analysis network traffic data, capture presentation network
More information07_À±ÀåÇõ¿Ü_0317
170 171 1) 2)3) 4)5) 6) 7) 172 8) 9) 10) 11)12)13) 14)15) 16) 17)18) 19) 173 174 20)21) 22) 23) 24) 175 25) 26) 27) 28) 29) 30) 31) 32)33) 34) 176 35) 36) 177 37)38) 39) 40)41) 178 42) 179 180 181 R(Appm,CPm)
More information# KM
PARTS BOOK 1-NEEDLE, STRAIGHT LOCK-STITCH MACHINE WITH VERTICAL EDGE TRIMMER 1-NEEDLE, NEEDLE FEED LOCK-STITCH MACHINE WITH VERTICAL EDGE TRIMMER MODEL KM-506 SERIES KM-506-7S 1-NEEDLE, STRAIGHT LOCK-STITCH
More information1. 서 론
두 장의 영상을 이용한 저조도 환경에서의 실용적 계산 사진 기법과 Mosaic 에의 응용 Practical Computational Photography with A Pair of Images under Low Illumination and Its Application to Mosaic 안택현 O, 홍기상 포항공과대학교 정보통신학과 O, 포항공과대학교 전자전기공학과
More informationMicrosoft Word - KSR2013A221.doc
2013 년도한국철도학회추계학술대회논문집 KSR2013A221 경부고속 1,2 단계 KTX 주행진동특성비교 Comparison of KTX traveling vibration characteristics on Gyeong-bu high speed railway 김주원 *, 정형일 *, 김대식 *, 소진섭 *, 정연일 *, 김상영 * Ju-Won Kim *,
More information