kiyo5_1-masuzawa.indd

Similar documents
28 TCG SURF Card recognition using SURF in TCG play video

Studies of Foot Form for Footwear Design (Part 9) : Characteristics of the Foot Form of Young and Elder Women Based on their Sizes of Ball Joint Girth

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

日本内科学会雑誌第102巻第4号

Web Web Web Web Web, i

第62巻 第1号 平成24年4月/石こうを用いた木材ペレット

原稿.indd

IPSJ SIG Technical Report Vol.2016-CE-137 No /12/ e β /α α β β / α A judgment method of difficulty of task for a learner using simple

23 A Comparison of Flick and Ring Document Scrolling in Touch-based Mobile Phones

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

4.1 % 7.5 %

GPGPU

17 Proposal of an Algorithm of Image Extraction and Research on Improvement of a Man-machine Interface of Food Intake Measuring System

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

大学における原価計算教育の現状と課題


2017 (413812)

<836F F312E706466>

Sobel Canny i

[1] 2 キトラ古墳天文図に関する従来の研究とその問題点 mm 3 9 mm cm 40.3 cm 60.6 cm 40.5 cm [2] 9 mm [3,4,5] [5] 1998

塗装深み感の要因解析

SURF,,., 55%,.,., SURF(Speeded Up Robust Features), 4 (,,, ), SURF.,, 84%, 96%, 28%, 32%.,,,. SURF, i

Table 1. Reluctance equalization design. Fig. 2. Voltage vector of LSynRM. Fig. 4. Analytical model. Table 2. Specifications of analytical models. Fig

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

soturon.dvi

1 [1, 2, 3, 4, 5, 8, 9, 10, 12, 15] The Boston Public Schools system, BPS (Deferred Acceptance system, DA) (Top Trading Cycles system, TTC) cf. [13] [

06’ÓŠ¹/ŒØŒì

揃 Lag [hour] Lag [day] 35

日本内科学会雑誌第98巻第4号

日本内科学会雑誌第97巻第7号

Vol. 48 No. 4 Apr LAN TCP/IP LAN TCP/IP 1 PC TCP/IP 1 PC User-mode Linux 12 Development of a System to Visualize Computer Network Behavior for L

3_23.dvi

2 ( ) i

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.


IIC Proposal of Range Extension Control System by Drive and Regeneration Distribution Based on Efficiency Characteristic of Motors for Electric

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

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

Fig. 3 Flow diagram of image processing. Black rectangle in the photo indicates the processing area (128 x 32 pixels).

Fig. 1. Relation between magnetron anode current and anode-cathod voltage. Fig. 2. Inverter circuit for driving a magnetron. 448 T. IEE Japan, Vol. 11

IPSJ SIG Technical Report An Evaluation Method for the Degree of Strain of an Action Scene Mao Kuroda, 1 Takeshi Takai 1 and Takashi Matsuyama 1

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

04長谷川英伸_様.indd

Table 1. Assumed performance of a water electrol ysis plant. Fig. 1. Structure of a proposed power generation system utilizing waste heat from factori

Public Pension and Immigration The Effects of Immigration on Welfare Inequality The immigration of unskilled workers has been analyzed by a considerab

DPA,, ShareLog 3) 4) 2.2 Strino Strino STRain-based user Interface with tacticle of elastic Natural ObjectsStrino 1 Strino ) PC Log-Log (2007 6)

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

paper.dvi

ÿþ

IT i

Fig. 1. Horizontal displacement of the second and third order triangulation points accompanied with the Tottori Earthquake of (after SATO, 1973)

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

untitled

<303288C991BD946797C797592E696E6464>


パナソニック技報

05_藤田先生_責

九州大学学術情報リポジトリ Kyushu University Institutional Repository 看護師の勤務体制による睡眠実態についての調査 岩下, 智香九州大学医学部保健学科看護学専攻 出版情報 : 九州大学医学部保健学

Estimation of Photovoltaic Module Temperature Rise Motonobu Yukawa, Member, Masahisa Asaoka, Non-member (Mitsubishi Electric Corp.) Keigi Takahara, Me


IPSJ SIG Technical Report Vol.2009-BIO-17 No /5/26 DNA 1 1 DNA DNA DNA DNA Correcting read errors on DNA sequences determined by Pyrosequencing

1: A/B/C/D Fig. 1 Modeling Based on Difference in Agitation Method artisoc[7] A D 2017 Information Processing

浜松医科大学紀要

_加登田先生_責.indd



Vol. 42 No. SIG 8(TOD 10) July HTML 100 Development of Authoring and Delivery System for Synchronized Contents and Experiment on High Spe

産業構造におけるスポーツ産業の範囲に関する研究Ⅰ

394-04

1..FEM FEM 3. 4.

Tsuken Technical Information 1

Core Ethics Vol. a

untitled

IPSJ SIG Technical Report Pitman-Yor 1 1 Pitman-Yor n-gram A proposal of the melody generation method using hierarchical pitman-yor language model Aki

Fig. 1. Schematic drawing of testing system. 71 ( 1 )

johnny-paper2nd.dvi

.,,, [12].,, [13].,,.,, meal[10]., [11], SNS.,., [14].,,.,,.,,,.,,., Cami-log, , [15], A/D (Powerlab ; ), F- (F-150M, ), ( PC ).,, Chart5(ADIns

Fig. 2 Signal plane divided into cell of DWT Fig. 1 Schematic diagram for the monitoring system

評論・社会科学 116号(P)Y☆/1.郭

JOURNAL OF THE JAPANESE ASSOCIATION FOR PETROLEUM TECHNOLOGY VOL. 66, NO. 6 (Nov., 2001) (Received August 10, 2001; accepted November 9, 2001) Alterna


24 Depth scaling of binocular stereopsis by observer s own movements

II A LexisNexis JP 80, /03/

58 10

01-加藤 実-5.02

Abstract This paper concerns with a method of dynamic image cognition. Our image cognition method has two distinguished features. One is that the imag

™…

474 Nippon Shokuhin Kagaku Kogaku Kaishi Vol. /-, No.3,.1..2* (,**0) 24 Measurement of Deterioration of Frying Oil Using Electrical Properties Yoshio

2007-Kanai-paper.dvi

2 1 ( ) 2 ( ) i

On the Wireless Beam of Short Electric Waves. (VII) (A New Electric Wave Projector.) By S. UDA, Member (Tohoku Imperial University.) Abstract. A new e

alternating current component and two transient components. Both transient components are direct currents at starting of the motor and are sinusoidal

技術研究報告第26号

bosai-2002.dvi

IPSJ SIG Technical Report Secret Tap Secret Tap Secret Flick 1 An Examination of Icon-based User Authentication Method Using Flick Input for

06_学術.indd

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

Takens / / 1989/1/1 2009/9/ /1/1 2009/9/ /1/1 2009/9/30,,, i

Y X X Y1 X 2644 Y1 Y2 Y1 Y3 Y1 Y1 Y1 Y2 Y3 Y2 Y3 Y1 Y1 Y2 Y3 Y1 Y2 Y3 Y1 X Lexis X Y X X2 X3 X2 Y2 Y1 Y1

NO

Transcription:

.pp. A Study on Wind Forecast using Self-Organizing Map FUJIMATSU Seiichiro, SUMI Yasuaki, UETA Takuya, KOBAYASHI Asuka, TSUKUTANI Takao, FUKUI Yutaka SOM SOM Elman SOM SOM Elman SOM Abstract : Now a small wind generator with the power assistance is developed. In order to aim at the power assistance with good efficiency or more, we have studied wind forecast based on the weather observation data in the narrow region using Self- Organizing map SOM. In this paper, we have examined about the wind forecast to aim at the forecast rate improvement by using both Bi-directional SOM and Elman-type feedback SOM. In our experiment, we have forecasted and evaluated by changing the weather observation data and the learning data. As a result, there is very little difference in both bi-directional SOM and Elman-type feedback SOM. However, It has been understood that the forecast rate improves though it is a little, by using the difference value of the wind velocity for the learning data. Moreover, it has been understood that the forecast rate improves greatly by narrowing the average time width of weather observation data. Keywordswind generator, wind condition, forecast, Self-Organizing Map

N.N. : Neural networkgp : Genetic Programming - SOM : Self-Organizing Map SOM SOM SOM Elman SOM - SOM SOM SOM SOMElman SOM SOM SOM T. SOM T. i t mt i xt xt n mt i n h ci t αt t =,,... SOM - SOM n xt mt i n Fig. - Composition chart of Fundamental SOM SOM SOM SOM xt x m i i c

h ci tαt h ci t t αt SOM SOM - SOM SOM SOM SOM X Y X,Y SOM ij * X W ij Dij SOM ij * ε W ij X Y Y V ij Bij ij ij * R ε T Fig. - Composition chart of Bi-directional SOM

Elman SOM Elman SOM - SOM x y h z L MM M N Elman Elman SOM Elman SOM Elman SOM Elman SOM j y j w j k z k w k t x h Fig. - Composition chart of Elman-type Feedback SOM j * β γ Elman SOM γ γ SOM Elman SOM SOM SOM SOM n SOM SOM Elman SOM

SOM SOM SOM SOM SOM X Y X Y - X Y - RMSE : Root Mean Square Error RMSE - RMSE RMSE.... Fig. - Input data

a RMSE armse in spring Fig. - RMSE each season b RMSE brmse in autumn a RMSE:.// amin RMSE in spring:.// b RMSE:.// bmax RMSE in spring:.// Fig. - Wind forecast value in spring a RMSE:.// b RMSE:.// amin RMSE in autumn:.// bmax RMSE in autumn:.// Fig. - Wind forecast value in autumn

-a RMSE RMSE RMSE... -b RMSE RMSE RMSE.... - RMSE - RMSE m/s m/s - SOM SOM RMSE SOM RMSE - SOM SOM SOM Fig. - Difference value distribution of wind velocity Fig. - Comparison between Bidirectional SOM and Fundamental SOM SOM SOM SOM SOM SOM

. Fig. - Forecast every one hour RMSE : Root Mean Square Error RMSE ME : Mean Error ME ME ME Fig. - Forecast every ten minutes - - - - - - Fig. - Forecast every five minutes

SOM RMSE - ME ME Elman SOM Elman SOM SOM SOM Elman SOM Elman SOM SOM Fig. - Comparison of ME - RMSE SOM xk xk xk Fig. - Comparison of RMSE RMSE Elman SOM. β. γ.

- Fig. - Forecast // SOM SOM Elman SOM ME:.RMSE:. SOM ME.RMSE.. SOM SOM RMSE.... SOM SOM SOM SOM ME RMSE Elman SOM Elman β γ Vol., No., pp.-, Jul.,. Vol., No., pp.-,. / pp.-, Nov.,. / pp.-, Oct.,. -,Jun.,. T.. Feature Map Vol. J-D-II, No., pp.-, Apr.,. D-IIVol.J- D-IINo. pp.-,. Seiichiro FUJIMATSU, Yasuaki SUMI, Takuya UETA, Takao TSUKUTANI, Yutaka FUKUI,The study of the wind synopsis prediction system by using

Self-Organization Map,ITC-CSCC Proceedings, Vol., pp.-, Jul.,. SOM G, Nov.,. SOM pp.-, Apr.,.