SOM SOM(Self-Organizing Maps) SOM SOM SOM SOM SOM SOM i



Similar documents
SNS ( ) SNS(Social Networking Service) SNS SNS i

,,,,., C Java,,.,,.,., ,,.,, i

58 10

IT,, i

19 Systematization of Problem Solving Strategy in High School Mathematics for Improving Metacognitive Ability

Web Web Web Web Web, i

IT i

29 jjencode JavaScript

子どもの自尊感情の変容と教師との関係性

大学における原価計算教育の現状と課題

kut-paper-template.dvi

Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Social Networking

paper.dvi

7,, i

udc-2.dvi

kiyo5_1-masuzawa.indd

2 ( ) i

Web Web Web Web i

卒業論文2.dvi

Sobel Canny i

06’ÓŠ¹/ŒØŒì

28 TCG SURF Card recognition using SURF in TCG play video

, IT.,.,..,.. i

WebRTC P2P Web Proxy P2P Web Proxy WebRTC WebRTC Web, HTTP, WebRTC, P2P i

28 Horizontal angle correction using straight line detection in an equirectangular image

23 The Study of support narrowing down goods on electronic commerce sites

1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,

25 Removal of the fricative sounds that occur in the electronic stethoscope

28 Docker Design and Implementation of Program Evaluation System Using Docker Virtualized Environment

DTN DTN DTN DTN i

26 Development of Learning Support System for Fixation of Basketball Shoot Form

soturon.dvi

4.1 % 7.5 %


16_.....E...._.I.v2006

i


Wide Scanner TWAIN Source ユーザーズガイド

paper.dvi

2 The Bulletin of Meiji University of Integrative Medicine 3, Yamashita 10 11

21 e-learning Development of Real-time Learner Detection System for e-learning

07_伊藤由香_様.indd

2017 (413812)

Web Basic Web SAS-2 Web SAS-2 i

Q-Learning Support-Vector-Machine NIKKEI NET Infoseek MSN i

Web Web Web Web 1 1,,,,,, Web, Web - i -

20 Method for Recognizing Expression Considering Fuzzy Based on Optical Flow

第5部門_05_垣本 徹.indd

P2P Web Proxy P2P Web Proxy P2P P2P Web Proxy P2P Web Proxy Web P2P WebProxy i

Wi-Fi Wi-Fi Wi-Fi Wi-Fi SAS SAS-2 Wi-Fi i

) 2) , , ) 1 2 Q1 / Q2 Q Q4 /// Q5 Q6 3,4 Q7 5, Q8 HP Q9 Q10 13 Q11

Appropriate Disaster Preparedness Education in Classrooms According to Students Grade, from Kindergarten through High School Contrivance of an Educati

評論・社会科学 84号(よこ)(P)/3.金子

n 2 n (Dynamic Programming : DP) (Genetic Algorithm : GA) 2 i

<8ED089EF8B D312D30914F95742E696E6464>

,,.,.,,.,.,.,.,,.,..,,,, i

07_高平小百合.indd

29 Short-time prediction of time series data for binary option trade

Web Web ID Web 16 Web Web i

..,,,, , ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i

(1) i NGO ii (2) 112


Core Ethics Vol. a

Bull. of Nippon Sport Sci. Univ. 47 (2) ) 1) 1) 1) 2) 1) 1) 2) The study of university and technical school freshmen in judo

<836F F312E706466>

1 4 4 [3] SNS 5 SNS , ,000 [2] c 2013 Information Processing Society of Japan

22 Google Trends Estimation of Stock Dealing Timing using Google Trends

220 28;29) 30 35) 26;27) % 8.0% 9 36) 8) 14) 37) O O 13 2 E S % % 2 6 1fl 2fl 3fl 3 4

A B C B C ICT ICT ITC ICT

’ÓŠ¹/‰´„û

B_01田中.indd

untitled

Input image Initialize variables Loop for period of oscillation Update height map Make shade image Change property of image Output image Change time L

2 122

23 Study on Generation of Sudoku Problems with Fewer Clues

13 RoboCup The Interface System for Learning By Observation Applied to RoboCup Agents Ruck Thawonmas

Web Stamps 96 KJ Stamps Web Vol 8, No 1, 2004

人文学部研究年報12号.indb

24_ChenGuang_final.indd

24 Region-Based Image Retrieval using Fuzzy Clustering

161 J 1 J 1997 FC 1998 J J J J J2 J1 J2 J1 J2 J1 J J1 J1 J J 2011 FIFA 2012 J 40 56

1 1 tf-idf tf-idf i

1 Web Web 1,,,, Web, Web : - i -

特-3.indd


Core Ethics Vol.

評論・社会科学 98号(P)☆/1.鰺坂


e-learning e e e e e-learning 2 Web e-leaning e 4 GP 4 e-learning e-learning e-learning e LMS LMS Internet Navigware

API SCORM e-learning SCORM Sharable Content Object Reference ModelSCORM e-learning e-learning SCORM SCORM SCO LMS SCORM SCORM HTML XML JavaScript SCO


ODA NGO NGO JICA JICA NGO JICA JBIC SCP

08医療情報学22_1_水流final.PDF

GPGPU

, (GPS: Global Positioning Systemg),.,, (LBS: Local Based Services).. GPS,.,. RFID LAN,.,.,.,,,.,..,.,.,,, i

p _08森.qxd

kut-paper-template2.dvi



Sport and the Media: The Close Relationship between Sport and Broadcasting SUDO, Haruo1) Abstract This report tries to demonstrate the relationship be

Transcription:

20 SOM Development of Syllabus Vsualization System using Spherical Self-Organizing Maps 1090366 2009 3 5

SOM SOM(Self-Organizing Maps) SOM SOM SOM SOM SOM SOM i

Abstract Development of Syllabus Vsualization System using Spherical Self-Organizing Maps Hiroshi HAMADA In recent years, syllabi have been introduced into most of universities. Syllabus is a booklet that shows course outline, and it is used for making students study plan. Syllabus has information to show relations between subjects. It is important that students understand the information of syllabus for the purpose of making systematic study plan. However, syllabi have problem what is that syllabi are difficult to understand the subjects relations. To solve the problem, syllabus visualization was proposed to easy to understand the subjects relations. A study of syllabus visualization using Self-Organizing Maps(SOM) was proposed as a past study. SOM makes node on a map learning data, and data is classified by their similarity. In the past study, the result of SOM was visualized by 2D map. However, the method of the past study has a problem that the result of visualizing become distorted at edge of map. In this paper, to solve the problem in the past study, we proposed syllabus visualizing system using spherical SOM. Moreover, to evaluate the validity of the system, we send out questionnaires to teachers and students. As a result, we confirmed that the system is easier to understand the subjects relations than the past study. key words Syllabus, Syllabus Visualization, SOM, Spherical SOM ii

1 1 2 2 2.1................................. 2 2.2.............................. 2 2.3................................ 4 2.3.1 SOM................... 4 2.3.2 SOM............. 5 3 7 3.1 SOM............................ 7 3.2 SOM.................................. 10 3.3................................. 11 3.4.............................. 12 3.5............................. 14 3.6............................ 14 4 15 4.1................................ 15 4.2................................ 15 4.3 SOM.............................. 15 4.4............................ 16 4.5............... 18 4.6................................... 19 4.7........................... 19 iii

5 23 5.1................................... 23 5.2................................... 26 5.3................................ 28 6 30 31 32 iv

2.1............ 3 2.2........................ 5 3.1 SOM................................. 8 3.2...................... 10 3.3.................................... 12 3.4 1.............................. 12 3.5 2.............................. 12 4.1.................................... 16 4.2.................. 17 4.3.................... 18 4.4............................. 20 4.5......................... 21 4.6................................ 21 4.7............................... 22 5.1 1 2.......................... 24 5.2....................... 24 5.3......................... 24 5.4 3......................... 25 5.5 3........................ 25 5.6 4............................. 25 v

3.1.............................. 13 4.1............................. 17 5.1................... 26 5.2 1 2............................ 26 5.3 3............................... 27 5.4 4............................... 27 vi

1 Web [1] SOM(Self-Organizing Maps) SOM SOM SOM SOM SOM 1

2 2.1 2.2 2

2.2 2.1 2.1 3

2.3 8 8 8 8 2.3 2.3.1 SOM [1] SOM Self-Organizing Maps [2] SOM 2.2 2.2 4

2.3 2.2 2.3.2 SOM SOM SOM 5

2.3 SOM SOM SOM 6

3 SOM SOM [1] 3.1 SOM SOM Teuvo Kohonen [2] SOM SOM 2 N in = ( m 1 m 2 m L ) m 11 m 12 m 1N m 21 m 22 m 2N N out =...... m M1 m M2 m MN m k n w k = (w k1, w k2,, w kn ) 7

3.1 SOM 3.1 SOM 3.1 SOM SOM λ R M N λ 1000 R 2 1 M N 1. N in N out 2. m m x 3. 8

3.1 SOM v m ij w ij 2 dist(v, v ) = v v 2 = n (v i v i) 2 (3.1) dist(x, w ij ) m ij 4. m m xy x w xy (3.2) 0 t λ 1 v (t) v t w (t+1) xy = (1 T ) w (t) xy + T x (3.2) i=1 (3.2) T α(t) h(m, m xy ) (3.3) T = α(t) h(m, m xy ) (3.3) α(t) α(t) = 1 t λ (3.4) w (t) xy v α(t) 0 1 (3.2) x h(m, m xy ) ( dist(m, m h(m, m ) ( ) ) m m 2 ) = exp = exp ( ) 2 α(t) R σ 2 (3.5) h(m, m xy ) m xy m 1 0 σ 0 < σ < R 9

3.2 SOM 0 (3.2) m R (3.5) 3.2 h(m, m ) 1 3.2 5. t λ 2 6. 3.2 SOM SOM SOM H.Ritter [7] 10

3.3 2.3.2 SOM 3.3 SOM SOM 1 1. 2. 3. 4. 5. 2 3.3 3.4 3.5 3 3 3 642 11

3.4 3.3 3.4 1 3.5 2 20 3.4 [1] 3.1 [4] 5 12

3.4 3.1,,,,,,,,,,, ( ), ( ), ( ), ( ), ( ), ( ), ( ), ( ),,,,,, ( ), ( ), ( ), ( ),, ( ), ( ), ( ), ( ),,,, ( ), ( ), ( ), ( ),,,, 13

3.5 3.5 [6] 3.6 1 14

4 4.1 SOM Java SOM Java3D[5] 4.2 SOM 4.1 4.1 4.3 SOM SOM 3.3 SOM 15

4.4 4.1 4.4 [6] 4.1 4.2 4.2 16

4.4 4.1 4.3 4.2 17

4.5 4.3 4.5 SOM SOM SOM 18

4.6 6 4.6 4.4 4.5 4.7 2 4.6 3 XY Z 3 (x,y,z) λ λ = tan 1 y x 3 φ φ = tan 1 z x 2 + y 2 19

4.7 4.4 20

4.7 4.5 4.6 21

4.7 4.7 φ λ R x = cos φ(rλ) y = Rλ 1 x = λ y = φ 4.7 1 22

5 5.1 3 3 5.1 4.6 23

5.1 評価方法 図 5.1 図 5.2 問 1 問 2 のウィンドウ 論理回路理論 に注目した画面 24 図 5.3 画像処理 に注目した画面

5.1 5.4 3 5.5 3 5.6 4 25

5.2 5.1 1 5.1 1 2 2 5.2 5.3 1 2 3 5.4 5.5 3 3 4 5.1 5.6 1 2 4 1 2 3 4 5 1 2 3 4 5 1 2 1 1 2 2 4 5.2 7 5 12 5.2 5.3 5.4 5.2 1 2 1 2 3 4 5 1 0(0) 0(0) 0(0) 10(4) 2(1) 2 0(0) 0(0) 2(1) 4(2) 6(2) 26

5.2 5.3 3 1( 5.4) 2( 5.5) 6(3) 6(2) 5.4 4 1( 5.1 ) 2( 5.6 ) 8(3) 4(2) 3 2 5.6 5.3 27

5.3 5.3 1 1 3 2 3 4 1 3 28

5.3 2 4 Web Web 29

6 SOM SOM SOM SOM 3 SOM 30

2 1 4 3 3 31

[1] 19 2007 [2] Teuvo Kohonen 2005 [3] SOM NC2004-23 pp.67 72 2004 [4],http://www.ieice.org/jpn/index.html. [5] Java3D,http://java.sun.com/javase/technologies/desktop/java3d/index.jsp. [6] 19 2007. [7] H.Ritter,Self-Organizing Maps on non-euclidean Spaces,in Kohonen Maps,ed.E.Oja and S.Kaski,pp.95-110,Elsever,New York,1999. 32