SlideShare a Scribd company logo
1 of 17
Download to read offline
/ 17
SCIS 2020
2020.12.5
Visualizing the Importance of Floor-Plan Image Features


in Rent-Prediction Models


1
Ryosuke Hattori¹ Kazushi Okamoto¹ Atushi Shibata²


¹ Graduate School of Informatics and Engineering,The University of Electro Communications


² Graduate School of Industrial Technology,Advanced Institute of Industrial Technology
/ 17
SCIS 2020
2020.12.5
Features of properties


• almost properties with different attributes


• property attributes


• age, story, building structure, and so on


• effect on prices


Rent prediction model with images


• inside image, outside image, and street view image


• conversion an image to a vector by using feature extractor from
images


• improvement of the prediction accuracy
Introduction
2
Eman Ahmed, and Mohamed Moustafa, House price estimation from


visual and textual features, arXiv:1609.08399, 2016.


Stephen Law, Brooks Paige, and Chris Russell, Take a Look Around:


Using Street View and Satellite Images to Estimate House Prices, ACM


Transactions on Intelligent Systems and Technology, Vol. 10, No. 5, pp.


54:1–54:19, 2019.
[Eman+, 2016] [Stephen+, 2019]
/ 17
SCIS 2020
2020.12.5
Explanatory of Rent Prediction Model with Images
3
Real-estate agents


or room owners
Understand the importances


of the property attributes


by the regression coef
fi
cients
Can not understand the
importances of the image features


by the regression coef
fi
cients
ŷi = ↵1x1 + ↵2x2 + ↵3x3 + · · · + ↵nxn +
<latexit sha1_base64="vQx08F43bZHjET/G6F0shHJHj2A=">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</latexit>
<latexit sha1_base64="vQx08F43bZHjET/G6F0shHJHj2A=">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</latexit>
<latexit sha1_base64="Mhn41z7d/Q2n10aqYFv7sL5P/oA=">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</latexit>
rent image feature
story
age
ŷ
<latexit sha1_base64="xhpVBugrKGqsl/IOdSNq+waH9Pk=">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</latexit>
image feature
It is useful to understand which parts of the image are relevant


for a rent prediction
/ 17
SCIS 2020
2020.12.5
Floor-Plan Standards in Japan
4
kitchen and
other rooms
kitchen square
[0 m2,4.5 m2) [4.5 m2, 8.0 m2)
more than equal to 

8.0 m2
not
separated
Room 

(R)
separated
Kitchen

(K)
Dinning Kitchen 

(DK)
Living Dinning Kitchen
(LDK)
DK LDK
K
R
/ 17
SCIS 2020
2020.12.5
Floor-Plan Images
Floor-plan standard is the same, but
fl
oor layout is different


In japan, there is a custom to look at
fl
oor-plan images


when searching for a desired rental property [Kiyota+,2017]
5
Ex. Different
fl
oor-plan images in the same property and
fl
oor-plan standard
Y. Kiyota, T. Yamasaki, H. Suwa, C. Shimizu:
Real estate and AI, Journal of the Japanese
Society for Arti
fi
cial Intelligence, vol.32, no.4,
pp.529-535, 2017
/ 17
SCIS 2020
2020.12.5
Purpose


• to develop methods visualizing the importances of
fl
oor-plan
image features


Method


• build rent prediction models with
fl
oor-plan images


• regressor: Bayesian linear regression


• feature extractor


• Principal Component Analysis (PCA)


• Speed Up Robust Features (SURF) + Bag of Features (BoF)
6
Our Approach
/ 17
SCIS 2020
2020.12.5
✓(f) = ✓T
f
Prediction Model with Floor-Plan Image
7
ln
<latexit sha1_base64="cip2YhSnDwuYWh3CEG2B1EDrAqU=">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</latexit>
u
<latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit>
<latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit>
<latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit>
<latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit>
x = [u, ✓(v)]
<latexit sha1_base64="tbvrKtiF/xOXDGMbwaD2COlchy8=">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</latexit>
特
徴
量
属性
ベクトル
賃料
Image
Features
Property
Variables
Log
Rent
f
w
P(w|Y, X) = N(w|µ̂, ˆ
⌃)
Bayesian linear regression:


of posterior distribution:
ŷ
w
P(ŷ|x, w) = N(ŷ|wT
x, )
/ 17
SCIS 2020
2020.12.5
Feature Extraction of Floor-Plan Image by PCA
✓(f) = ✓T
f
f
µ̂f is coef
fi
cients for the
fl
oor-plan image
8
✓
✓ is a feature extractor
is a transformation matrix
✓µ̂f
Overlay: Visualized


feature importance
×
f
/ 17
SCIS 2020
2020.12.5
Feature Extraction of Floor-Plan Image by BoF
d1
d2
d3
K-means
Floor-plan image
9
Visualized


feature importance
SURF
v1
v2
v3
v4
v1 v2 v3 v4
v1 v2 v3 v4
v1 v2 v3 v4
✓(Di) =
1
|Di|
X
d2Di
✓(d)
v1 v2 v3 v4
w4
w3
w1 w2
w5
Coef
fi
cient of the Floor-Plan Image
(d1, d2, · · · , dj)
/ 17
SCIS 2020
2020.12.5
Experiment Environment
LIFULL HOME ’S dataset (as of September 2015)


• rental property data (70 variables, 5.33 million)


• 120 x 120 pixel image data (83 million
fi
les)


• used data


• Tokyo


• 100,000 properties


• 29 property variables


•
fl
oor-plan image
10
/ 17
SCIS 2020
2020.12.5 11
Dataset (1/2)
building structure (13 variables)
exclusive area num. of rooms
num. of ground
fl
oors
num. of
underground
fl
oors
fl
oor num.
age of building property type purpose of use building structure
orientation of
property
keeper days of occupancy
num. of vacant
properties
the others: one-hot vector
: continuous variables
/ 17
SCIS 2020
2020.12.5 12
Dataset (2/2)
location/access (15 variables)
city, ward, town city plan rail station 1 rail station 2 bus. times 1
bus. times 2
dist. to general
hospital
walking dist. to
station 1 

or bus stop
walking dist. to
station 2 

or bus stop
dist. to
convenience store
dist. to super
market
dist. to junior high
school
riding dist. to
station 1
riding dist. to
station 2
dist. to elementary
school
the others: one-hot vector
: categorical each 80m
grayscale
Floor-plan images
/ 17
SCIS 2020
2020.12.5
Outline of Experiment
13
Evaluation metric: Mean Absolute Percentage Error (MAPE)
Training data
(80%)
Test data
(20%)
K
R
DK
LDK
Using as training data to predict
test data
5-fold cross validation
• Prediction accuracy
• Visualizing the importance
of
fl
oor-plan image features
13
5,000
properties
determine dimension of image features
from [500,1000,2000]
ȳi = E[P(ŷi|x, w)]
MAPE =
100
N
N
X
i=1
yi ȳi
yi
/ 17
SCIS 2020
2020.12.5
Prediction Accuracy for Test Data
K R DK LDK
w/o FPI 

(Floor-Plan Image)
11.84 10.51 7.700 12.37
w/ FPI
PCA 

500
dimension
12.10 10.80 7.806 12.71
BoF 

2000
dimension
11.68 10.27 7.660 12.09
MAPE [%]
14
Lower MAPE means better prediction accuracy
/ 17
SCIS 2020
2020.12.5 15
Visualizing the Importance of Floor-Plan Image
Features in Floor-Plan Standard LDK
BoF
PCA
/ 17
SCIS 2020
2020.12.5 16
Visualizing the Importance of Floor-Plan Image
Features
PCA for
fl
oor-plan standard K
PCA for
fl
oor-plan standard DK BoF for
fl
oor-plan standard DK
BoF for
fl
oor-plan standard K
/ 17
SCIS 2020
2020.12.5
Purpose: to develop methods visualizing the importances of
fl
oor-plan image features


Method


• build rent prediction models with
fl
oor-plan images


• regressor: Bayesian linear regression


• feature extractor: PCA and BoF


Result


• BoF achieves a higher accuracy than PCA


• the wall and on orientation symbol are important
fl
oor-plan image features


• visualization by BoF is superior in visibility of which parts of a
fl
oor-plan image are
important


Future work: to trend analysis of importance of
fl
oor-plan image features
17
Conclusion
for each
fl
oor-plan standard

More Related Content

Similar to FloorPlanFeatures

Urbanetic2015_05pdf (1)
Urbanetic2015_05pdf (1)Urbanetic2015_05pdf (1)
Urbanetic2015_05pdf (1)Jose A. Alfano
 
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 16120111142420161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424Anshad cp
 
Presentation dr abeermoh_bahrain_gbforum2012kuwait
Presentation dr abeermoh_bahrain_gbforum2012kuwaitPresentation dr abeermoh_bahrain_gbforum2012kuwait
Presentation dr abeermoh_bahrain_gbforum2012kuwaitgreenbuilding
 
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기 도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기 Tae wook kang
 
Analysis and design of multistorey commercial building using Etabs
Analysis and design of multistorey commercial building using EtabsAnalysis and design of multistorey commercial building using Etabs
Analysis and design of multistorey commercial building using EtabsIRJET Journal
 
Estimation and Evaluation of G+3 Residential Building
Estimation and Evaluation of G+3 Residential BuildingEstimation and Evaluation of G+3 Residential Building
Estimation and Evaluation of G+3 Residential Buildingvivatechijri
 
Introduction to BIM
Introduction to BIM Introduction to BIM
Introduction to BIM YOGESH MAKKAR
 
Building Information Modelling in Sustainability Analysis
Building Information Modelling in Sustainability AnalysisBuilding Information Modelling in Sustainability Analysis
Building Information Modelling in Sustainability AnalysisIRJET Journal
 
Design and Development of BIM on GIS Interoperability Open Platform
Design and Development of BIM on GIS Interoperability Open PlatformDesign and Development of BIM on GIS Interoperability Open Platform
Design and Development of BIM on GIS Interoperability Open Platformslhead1
 
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...IRJET Journal
 
Research Sruti
Research SrutiResearch Sruti
Research Srutisrutin
 
GISenabledUrbanDesignAGSEPaper.pdf
GISenabledUrbanDesignAGSEPaper.pdfGISenabledUrbanDesignAGSEPaper.pdf
GISenabledUrbanDesignAGSEPaper.pdfSurenAdithyaaRA19112
 
Role of Building Information Modelling in Construction
Role of Building Information Modelling in ConstructionRole of Building Information Modelling in Construction
Role of Building Information Modelling in ConstructionAbhijeet Kulkarni
 
Ppt on design and modelling of residential society
Ppt on design and modelling of residential societyPpt on design and modelling of residential society
Ppt on design and modelling of residential societyGLAU, Mathura, UP, India
 
VenkataChary Maduri_CV_14.102016
VenkataChary Maduri_CV_14.102016VenkataChary Maduri_CV_14.102016
VenkataChary Maduri_CV_14.102016Venkatachary Maduri
 

Similar to FloorPlanFeatures (20)

Urbanetic2015_05pdf (1)
Urbanetic2015_05pdf (1)Urbanetic2015_05pdf (1)
Urbanetic2015_05pdf (1)
 
SATYA-new
SATYA-newSATYA-new
SATYA-new
 
What is BIM?
What is BIM?What is BIM?
What is BIM?
 
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 16120111142420161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424
20161111whatisbimwhatareitsbenefitstotheconstructionindustry 161201111424
 
Presentation dr abeermoh_bahrain_gbforum2012kuwait
Presentation dr abeermoh_bahrain_gbforum2012kuwaitPresentation dr abeermoh_bahrain_gbforum2012kuwait
Presentation dr abeermoh_bahrain_gbforum2012kuwait
 
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기 도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기
도시 인프라 공간정보 데이터 커넥션-통합 기술 표준화를 위한 ISO TC211 19166 개발 이야기
 
BIM Application in Hong Kong Housing Authority by Mr. Lawrence K.W. CHUNG
BIM Application in Hong Kong Housing Authority by Mr. Lawrence K.W. CHUNGBIM Application in Hong Kong Housing Authority by Mr. Lawrence K.W. CHUNG
BIM Application in Hong Kong Housing Authority by Mr. Lawrence K.W. CHUNG
 
Analysis and design of multistorey commercial building using Etabs
Analysis and design of multistorey commercial building using EtabsAnalysis and design of multistorey commercial building using Etabs
Analysis and design of multistorey commercial building using Etabs
 
Estimation and Evaluation of G+3 Residential Building
Estimation and Evaluation of G+3 Residential BuildingEstimation and Evaluation of G+3 Residential Building
Estimation and Evaluation of G+3 Residential Building
 
Introduction to BIM
Introduction to BIM Introduction to BIM
Introduction to BIM
 
Building Information Modelling in Sustainability Analysis
Building Information Modelling in Sustainability AnalysisBuilding Information Modelling in Sustainability Analysis
Building Information Modelling in Sustainability Analysis
 
Design and Development of BIM on GIS Interoperability Open Platform
Design and Development of BIM on GIS Interoperability Open PlatformDesign and Development of BIM on GIS Interoperability Open Platform
Design and Development of BIM on GIS Interoperability Open Platform
 
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...
IRJET-3D,4D and 5D Building Information Modeling for Commercial Building Proj...
 
Research Sruti
Research SrutiResearch Sruti
Research Sruti
 
Bim overview
Bim overviewBim overview
Bim overview
 
GISenabledUrbanDesignAGSEPaper.pdf
GISenabledUrbanDesignAGSEPaper.pdfGISenabledUrbanDesignAGSEPaper.pdf
GISenabledUrbanDesignAGSEPaper.pdf
 
Ijebea14 244
Ijebea14 244Ijebea14 244
Ijebea14 244
 
Role of Building Information Modelling in Construction
Role of Building Information Modelling in ConstructionRole of Building Information Modelling in Construction
Role of Building Information Modelling in Construction
 
Ppt on design and modelling of residential society
Ppt on design and modelling of residential societyPpt on design and modelling of residential society
Ppt on design and modelling of residential society
 
VenkataChary Maduri_CV_14.102016
VenkataChary Maduri_CV_14.102016VenkataChary Maduri_CV_14.102016
VenkataChary Maduri_CV_14.102016
 

More from Okamoto Laboratory, The University of Electro-Communications

More from Okamoto Laboratory, The University of Electro-Communications (18)

クラウドソーシングにおける協調的な共同作業に対する組織構成システム
クラウドソーシングにおける協調的な共同作業に対する組織構成システムクラウドソーシングにおける協調的な共同作業に対する組織構成システム
クラウドソーシングにおける協調的な共同作業に対する組織構成システム
 
リンク予測に基づく共同研究者推薦システムの試作
リンク予測に基づく共同研究者推薦システムの試作リンク予測に基づく共同研究者推薦システムの試作
リンク予測に基づく共同研究者推薦システムの試作
 
Directed Graph-based Researcher Recommendation by Random Walk with Restart an...
Directed Graph-based Researcher Recommendation by Random Walk with Restart an...Directed Graph-based Researcher Recommendation by Random Walk with Restart an...
Directed Graph-based Researcher Recommendation by Random Walk with Restart an...
 
間取り図を用いた賃料予測モデルに関する一検討
間取り図を用いた賃料予測モデルに関する一検討間取り図を用いた賃料予測モデルに関する一検討
間取り図を用いた賃料予測モデルに関する一検討
 
Development of a Collaborator Recommender System Based on Directed Graph Model
Development of a Collaborator Recommender System Based on Directed Graph ModelDevelopment of a Collaborator Recommender System Based on Directed Graph Model
Development of a Collaborator Recommender System Based on Directed Graph Model
 
分散表現を用いたリアルタイム学習型セッションベース推薦システム
分散表現を用いたリアルタイム学習型セッションベース推薦システム分散表現を用いたリアルタイム学習型セッションベース推薦システム
分散表現を用いたリアルタイム学習型セッションベース推薦システム
 
アイテム分散表現の階層化・集約演算に基づくセッションベース推薦システム
アイテム分散表現の階層化・集約演算に基づくセッションベース推薦システムアイテム分散表現の階層化・集約演算に基づくセッションベース推薦システム
アイテム分散表現の階層化・集約演算に基づくセッションベース推薦システム
 
発売日前のレビューとPU-Learningを用いた
スパムレビュー検出
発売日前のレビューとPU-Learningを用いた
スパムレビュー検出発売日前のレビューとPU-Learningを用いた
スパムレビュー検出
発売日前のレビューとPU-Learningを用いた
スパムレビュー検出
 
モデルベース協調フィルタリングにおける推薦の透明性に関する検討
モデルベース協調フィルタリングにおける推薦の透明性に関する検討モデルベース協調フィルタリングにおける推薦の透明性に関する検討
モデルベース協調フィルタリングにおける推薦の透明性に関する検討
 
重回帰分析による推薦の透明性を有したモデルベース協調フィルタリング
重回帰分析による推薦の透明性を有したモデルベース協調フィルタリング重回帰分析による推薦の透明性を有したモデルベース協調フィルタリング
重回帰分析による推薦の透明性を有したモデルベース協調フィルタリング
 
Word2Vecによる次元圧縮と重回帰分析型協調フィルタリングへの応用
Word2Vecによる次元圧縮と重回帰分析型協調フィルタリングへの応用Word2Vecによる次元圧縮と重回帰分析型協調フィルタリングへの応用
Word2Vecによる次元圧縮と重回帰分析型協調フィルタリングへの応用
 
数式からみるWord2Vec
数式からみるWord2Vec数式からみるWord2Vec
数式からみるWord2Vec
 
Rによるベイジアンネットワーク入門
Rによるベイジアンネットワーク入門Rによるベイジアンネットワーク入門
Rによるベイジアンネットワーク入門
 
単語の分散表現の 購買履歴への応用
単語の分散表現の 購買履歴への応用単語の分散表現の 購買履歴への応用
単語の分散表現の 購買履歴への応用
 
機関リポジトリから収集した学術論文のテキスト解析に関する一検討
機関リポジトリから収集した学術論文のテキスト解析に関する一検討機関リポジトリから収集した学術論文のテキスト解析に関する一検討
機関リポジトリから収集した学術論文のテキスト解析に関する一検討
 
Text Analysis of Academic Papers Archived in Institutional Repositories
Text Analysis of Academic Papers Archived in Institutional RepositoriesText Analysis of Academic Papers Archived in Institutional Repositories
Text Analysis of Academic Papers Archived in Institutional Repositories
 
Families of Triangular Norm Based Kernel Function and Its Application to Kern...
Families of Triangular Norm Based Kernel Function and Its Application to Kern...Families of Triangular Norm Based Kernel Function and Its Application to Kern...
Families of Triangular Norm Based Kernel Function and Its Application to Kern...
 
これから始めるディープラーニング
これから始めるディープラーニングこれから始めるディープラーニング
これから始めるディープラーニング
 

Recently uploaded

Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfBoston Institute of Analytics
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxBoston Institute of Analytics
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degreeyuu sss
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理e4aez8ss
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 

Recently uploaded (20)

Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 

FloorPlanFeatures

  • 1. / 17 SCIS 2020 2020.12.5 Visualizing the Importance of Floor-Plan Image Features in Rent-Prediction Models 1 Ryosuke Hattori¹ Kazushi Okamoto¹ Atushi Shibata² ¹ Graduate School of Informatics and Engineering,The University of Electro Communications ² Graduate School of Industrial Technology,Advanced Institute of Industrial Technology
  • 2. / 17 SCIS 2020 2020.12.5 Features of properties • almost properties with different attributes • property attributes • age, story, building structure, and so on • effect on prices Rent prediction model with images • inside image, outside image, and street view image • conversion an image to a vector by using feature extractor from images • improvement of the prediction accuracy Introduction 2 Eman Ahmed, and Mohamed Moustafa, House price estimation from visual and textual features, arXiv:1609.08399, 2016. Stephen Law, Brooks Paige, and Chris Russell, Take a Look Around: Using Street View and Satellite Images to Estimate House Prices, ACM Transactions on Intelligent Systems and Technology, Vol. 10, No. 5, pp. 54:1–54:19, 2019. [Eman+, 2016] [Stephen+, 2019]
  • 3. / 17 SCIS 2020 2020.12.5 Explanatory of Rent Prediction Model with Images 3 Real-estate agents or room owners Understand the importances of the property attributes by the regression coef fi cients Can not understand the importances of the image features by the regression coef fi cients ŷi = ↵1x1 + ↵2x2 + ↵3x3 + · · · + ↵nxn + <latexit sha1_base64="vQx08F43bZHjET/G6F0shHJHj2A=">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</latexit> <latexit sha1_base64="vQx08F43bZHjET/G6F0shHJHj2A=">AAADG3ichVFNSxxBFKwZYzSbGFdzCSSHJYtBEKR3FRQhIOYSSA5+ZFVYZenptNo4OzPMzC7ZLPkD+QMeJIcEJIT8DC8h5OrBnyAeDeSSQ2pmhxFdTB7MdPXrqlfvdTuBa6JYiFPLHrg1eHto+E7h7r2R+6PFsfH1yG+FSteU7/rhpiMj7RpP12ITu3ozCLVsOq7ecPafJ+cbbR1Gxvdex51Abzflrmd2jJIxU36xji3sQSJGCR00YLiW8IxZCRdBetZAFxW8x9scTZFznVHNGdUbGDM5YyZjHOENfHpHxFN9fC/ne3lFB5p82SiWxbRIo9QPKhkoI4tlv/iF4sRMoYUmi3gso2gnaR6hzrEErWNs004iJDLpuaZ1gdoWWZoMyew+/7vc1bOsx31SM0rVii4uv5DKEibEifgqLsR38U2ciT831uqmNZJeOlydnlYHjdEPD9d+/1fVTJ9w71L1z55j7GA+7dWw9yDNJFOonr797uBibWF1ovtUfBbn7P+TOBXHnMBr/1JHK3r1EAU+QOX6dfeD9ep0hXhltry4lD3FMB7hCSZ533NYxAssowZlPbaWrJfWK/ujfWz/sH/2qLaVaR7gStgnfwFUmKzq</latexit> <latexit sha1_base64="Mhn41z7d/Q2n10aqYFv7sL5P/oA=">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</latexit> rent image feature story age ŷ <latexit sha1_base64="xhpVBugrKGqsl/IOdSNq+waH9Pk=">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</latexit> image feature It is useful to understand which parts of the image are relevant for a rent prediction
  • 4. / 17 SCIS 2020 2020.12.5 Floor-Plan Standards in Japan 4 kitchen and other rooms kitchen square [0 m2,4.5 m2) [4.5 m2, 8.0 m2) more than equal to 
 8.0 m2 not separated Room 
 (R) separated Kitchen
 (K) Dinning Kitchen 
 (DK) Living Dinning Kitchen (LDK) DK LDK K R
  • 5. / 17 SCIS 2020 2020.12.5 Floor-Plan Images Floor-plan standard is the same, but fl oor layout is different In japan, there is a custom to look at fl oor-plan images 
 when searching for a desired rental property [Kiyota+,2017] 5 Ex. Different fl oor-plan images in the same property and fl oor-plan standard Y. Kiyota, T. Yamasaki, H. Suwa, C. Shimizu: Real estate and AI, Journal of the Japanese Society for Arti fi cial Intelligence, vol.32, no.4, pp.529-535, 2017
  • 6. / 17 SCIS 2020 2020.12.5 Purpose • to develop methods visualizing the importances of fl oor-plan image features Method • build rent prediction models with fl oor-plan images • regressor: Bayesian linear regression • feature extractor • Principal Component Analysis (PCA) • Speed Up Robust Features (SURF) + Bag of Features (BoF) 6 Our Approach
  • 7. / 17 SCIS 2020 2020.12.5 ✓(f) = ✓T f Prediction Model with Floor-Plan Image 7 ln <latexit sha1_base64="cip2YhSnDwuYWh3CEG2B1EDrAqU=">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</latexit> u <latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit> <latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit> <latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit> <latexit sha1_base64="x42OIFZO63bltL4H6gjza3ReZFg=">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</latexit> x = [u, ✓(v)] <latexit sha1_base64="tbvrKtiF/xOXDGMbwaD2COlchy8=">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</latexit> 特 徴 量 属性 ベクトル 賃料 Image Features Property Variables Log Rent f w P(w|Y, X) = N(w|µ̂, ˆ ⌃) Bayesian linear regression: of posterior distribution: ŷ w P(ŷ|x, w) = N(ŷ|wT x, )
  • 8. / 17 SCIS 2020 2020.12.5 Feature Extraction of Floor-Plan Image by PCA ✓(f) = ✓T f f µ̂f is coef fi cients for the fl oor-plan image 8 ✓ ✓ is a feature extractor is a transformation matrix ✓µ̂f Overlay: Visualized feature importance × f
  • 9. / 17 SCIS 2020 2020.12.5 Feature Extraction of Floor-Plan Image by BoF d1 d2 d3 K-means Floor-plan image 9 Visualized feature importance SURF v1 v2 v3 v4 v1 v2 v3 v4 v1 v2 v3 v4 v1 v2 v3 v4 ✓(Di) = 1 |Di| X d2Di ✓(d) v1 v2 v3 v4 w4 w3 w1 w2 w5 Coef fi cient of the Floor-Plan Image (d1, d2, · · · , dj)
  • 10. / 17 SCIS 2020 2020.12.5 Experiment Environment LIFULL HOME ’S dataset (as of September 2015) • rental property data (70 variables, 5.33 million) • 120 x 120 pixel image data (83 million fi les) • used data • Tokyo • 100,000 properties • 29 property variables • fl oor-plan image 10
  • 11. / 17 SCIS 2020 2020.12.5 11 Dataset (1/2) building structure (13 variables) exclusive area num. of rooms num. of ground fl oors num. of underground fl oors fl oor num. age of building property type purpose of use building structure orientation of property keeper days of occupancy num. of vacant properties the others: one-hot vector : continuous variables
  • 12. / 17 SCIS 2020 2020.12.5 12 Dataset (2/2) location/access (15 variables) city, ward, town city plan rail station 1 rail station 2 bus. times 1 bus. times 2 dist. to general hospital walking dist. to station 1 
 or bus stop walking dist. to station 2 
 or bus stop dist. to convenience store dist. to super market dist. to junior high school riding dist. to station 1 riding dist. to station 2 dist. to elementary school the others: one-hot vector : categorical each 80m grayscale Floor-plan images
  • 13. / 17 SCIS 2020 2020.12.5 Outline of Experiment 13 Evaluation metric: Mean Absolute Percentage Error (MAPE) Training data (80%) Test data (20%) K R DK LDK Using as training data to predict test data 5-fold cross validation • Prediction accuracy • Visualizing the importance of fl oor-plan image features 13 5,000 properties determine dimension of image features from [500,1000,2000] ȳi = E[P(ŷi|x, w)] MAPE = 100 N N X i=1 yi ȳi yi
  • 14. / 17 SCIS 2020 2020.12.5 Prediction Accuracy for Test Data K R DK LDK w/o FPI (Floor-Plan Image) 11.84 10.51 7.700 12.37 w/ FPI PCA 500 dimension 12.10 10.80 7.806 12.71 BoF 2000 dimension 11.68 10.27 7.660 12.09 MAPE [%] 14 Lower MAPE means better prediction accuracy
  • 15. / 17 SCIS 2020 2020.12.5 15 Visualizing the Importance of Floor-Plan Image Features in Floor-Plan Standard LDK BoF PCA
  • 16. / 17 SCIS 2020 2020.12.5 16 Visualizing the Importance of Floor-Plan Image Features PCA for fl oor-plan standard K PCA for fl oor-plan standard DK BoF for fl oor-plan standard DK BoF for fl oor-plan standard K
  • 17. / 17 SCIS 2020 2020.12.5 Purpose: to develop methods visualizing the importances of fl oor-plan image features Method • build rent prediction models with fl oor-plan images • regressor: Bayesian linear regression • feature extractor: PCA and BoF Result • BoF achieves a higher accuracy than PCA • the wall and on orientation symbol are important fl oor-plan image features • visualization by BoF is superior in visibility of which parts of a fl oor-plan image are important Future work: to trend analysis of importance of fl oor-plan image features 17 Conclusion for each fl oor-plan standard