Deciding how to decide: Deciding how to decide: The added ...
Using BI for deciding and planning the best usage for governmental lands
-
Upload
cadysamer -
Category
Data & Analytics
-
view
26 -
download
0
Transcript of Using BI for deciding and planning the best usage for governmental lands
Using BI for deciding and planning the best usage for
governmental lands
Submitted ByBassant Nabil Mohamed Abass
AgendaA
gend
aMotivationObjectivesProblem StatementRelated WorksProposed Framework for land usages
BI Land Use Planning and Classification Model (BILUPC Model)
Case StudyConclusionFuture WorkPublication
-2-
3
عليكم ) ه الل نعمت اذكروا اس الن ها أي ياماء الس من يرزقكم ه الل غير خالق من هل
هو إال إله ال تؤفكون واألرض ى فأن )اآليه ) (3فاطر
1. Motivation
1. Quarrying2. Historical
Monuments3. Mining4. Oil Concession
areas5. Soil fertility6. Natural
protectorates
1. Raising the national development and the national income
2. Raising the number of investors in the country
3. Raising the number of human utilization to decrease unemployment -4-
2. Problem Statement• No existence for a model that can help decision maker
in planning and deciding the best usages in governmental lands, nothing exist to say how to utilize the governmental resources the best utilization.
-5-
3. Objective
Visualization Customization Security
Adapting GIS tools and
techniques in order to
present land usages
Dialogue system to support
Decision Making process
1.Privacy: Restrictions on data used like data on military lands or others
2.Security authentication:
to be authenticated by your password
Mak
ing
a U
I tha
t hel
ps in
Reporting
Reports Should be generated to help Decision Maker to take
the right decision at the right time in
the right format
-6-
• Providing a model that help decision makers to enhance usage of governmental lands by adapting Business Intelligence tools through the aid of the following 4 elements:
-7-
Background3 kinds of tools and techniques
are usedGIS tools
Data mining tools
Business Intelligent
tools
1. Layers2. Shape
files3. Attribut
es4. Maps
Shape FilesLayers
GIS tools
Data mining tools
Business Intelligent
tools
Background
Clustering Classification
Data warehouse from different repositories
(National land Database)
Integration between GIS tools + Data mining tools + Different data warehouses
-8-
4. Related Works
1 • Using GIS and outranking multi criteria analysis for land-use suitability assessment (England)
2 • An integrated GIS-based analysis system (IGAS) for supporting land-use management of lake areas in urban fringes ( China)
3 • Evaluation of soil erosion risk using Analytic Network Process and GIS: A case study from Spanish mountain olive plantations (Spain)
Related Works
Provides good
visualization for data
-9-
MCDA is applied to compare the set of identified
alternativesTo decide
and choose the best place for
building an airport
I = ∆ E +∆ L +∆ A+∆ R +∆ B+∆ H
1. Using GIS and outranking multi criteria analysis for land-use suitability assessment (England)
-10-
This model used to
select the best site
for certain purpose
only
I = D E + D L + D A + D R +DB +D HD E= Noise EmissionD L= Correction of distanceD R= Correction of reflectionD A= Correction of air absorptionD B= Correction for soil effectD H= Correction of obstacles
This model Used Multi-criteria decision analysis for choosing best alternatives through factors that helps in
building airports
1. Using GIS and outranking multi criteria analysis for land-use suitability assessment (England) cont…
-11-
2. An integrated GIS-based analysis system (IGAS) for supporting land-use management of lake areas in urban fringes ( China)
• The urban lake areas of China, are ideal locations for
recreational activities and the maintenance of ecological diversity.AHP: Analytical hierarchy process
Procedures of GIS-based land-use suitability assessment
• GDP = GDPI + GDPA + GDPSI1. Agricultural GDP:GDPA(t) = GDPA(t − dt) + GDPA GRA dt 2. Industrial GDP3. Service Industries
IGAS
MCDA
AHP
-12-
3. Evaluation of soil erosion risk using Analytic Network Process and GIS: A case study from Spanish mountain olive plantations
• The risk of soil erosion was evaluated in olive groves in Southern Spain,
• showing the potential of the ANP method (Analytic Network Process method) for modeling a complex physical process like
soil erosion.• showing usage of Multi-criteria
decision analysis.• Thus, soil erosion risk = 0.1986
+0.0428 + 0.0399 +0.027+0.0318 = 0.3401
shows the final weights of the soil erosion factors-13-
Proposed framework Vision (England Model)
I = D E + D L + D A + D R +DB +D H
-14-
Proposed Modelfor Land Use Planning and Classification Model
LUC= %F1∩%F2∩%F3∩%F4∩%Fn… = 100%LUC: stands for Land Use Classification
-15-
Models as:AgricultureIndustrialTouristic
National Land
Database
Dialogue Managemen
t (Agent
Negotiations)
DSS Support Decision
Maker for land use classification
Planning
To achieve the
proposed frame work,
dialogue should happen between
data warehouses
and models
-16-
5. Proposed Framework ( level 1)Data Capture:Data collected from different
Data ware houses of legal authorities ex: layer names,
areas, longitude, latitude
PreprocessingSelection Filtration elimination
To select proposed activities & area of interest
To use MCDA to select factors
To eliminate
unnecessary factors
Transformation:To transform text data into shape files &
layers
Data mining:Using 2 methods
cluster and classification to
analyze data & to detect intersection between factors
Interpretation evaluation:
To make user interface through
agent negotiations & Reports
Knowledge:For decision
maker to take decision
-17-
5. Proposed Framework ( level 2a) ( Filtration)Filtration (Preprocess phase)
Multi-criteria Decision analysis(MCDA)
SWOT Analysis
It comes out of Delphi studies
Benchmarking Method
identifying likely
competitive challenges
Delphi Method
is composed of integration between
Expert panels,Questionnaires,Send to experts,Send to experts with feedback.
Scanning
Analysis
Expert Survey
Results
-18-
5. Proposed Framework ( level 2b) ( Data mining)
Two methods used
Clustering
To integrate each similar factors in one cluster
Classification
To measure degree of importance to each factor in each cluster
-19-
5. Proposed Framework ( level 2b) ( Data mining) cont…
Clustering
Classification
Determine objectives
on the map +
determining
intersection between layers or degree of potentialiti
es
-20-
New vision for England model (old model)
Multi Criteria Decision Analysis is not the only phase that help in
Choosing alternative
s
Supporting Decision maker
in taking decisions
But it will be one of two phases implemented to support decision maker in planning
and deciding the best usage of the governmental lands
-21-
1. Implementing Multi criteria decision analysis in determining factors
Delphi Method
SWOT Analysis
Benchmarking
Method
1. Water2. Infrastructure3. Proximity to
Natural Protectorates
4. Soil5. Tourist Resorts or
monuments6. Island Marine7. Labor8. Hills and highlands9. Proximity to mines
and quarries10. Proximity to air
ports & ports11. Away from
contaminated areas
FactorsDELPHI RESULTED TO
DETERMININGwater
Infrastructure
Natural protectorates
Soil
Tourist resorts
Island Marine
-22-
2. Data Mining Phase (cluster + classification)
In order to determine the best utilization for governmental lands
Constituents of use(utilization)
Region Properties(Factors)
-23-
2. Data Mining Phase (CLUSTER + classification) cont…
Constituents of useRegion Properties
1. Water2. Infrastructure3. Proximity to
Natural Protectorates
4. Soil5. Tourist Resorts or
monuments6. Island Marine7. Labor8. Hills and highlands9. Proximity to mines
and quarries10. Proximity to air
ports & ports11. Away from
contaminated areas
If AgriculturalMake a cluster
that contains
• Through equation resulted from the new model 3 factors were achieved which are;
Water ∩ Soil ∩ Labor
LUC= %F1∩%F2∩%F3∩%F4∩%Fn… = 100%-24-
2. Data Mining Phase (CLUSTER + classification) cont…
Constituents of useRegion Properties
1.Water2.Infrastructure3.Proximity to Natural Protectorates
4.Soil5.Tourist Resorts or monuments
6.Island Marine7.Labor8.Hills and highlands9.Proximity to mines and quarries
10.Proximity to air ports & ports
11.Away from contaminated areas
Make a cluster
that contains
• Through equation resulted from the new model 4factors were achieved which are;
Tourist resort∩ Island marine ∩ proximity to air port ∩ Away from contaminations
LUC= %F1∩%F2∩%F3∩%F4∩%Fn… = 100%
Tourism
1ST STEP
-25-
2. Data Mining Phase (cluster + classification) cont…
Using Classification method in Data mining to classify each factor according to its degree of importance that leads to best utilization and best usage for governmental lands
2ND STEP
50%
1%2%
30%
1%1%
10%1%
2% 1% 1%
Water Infrastructure
Proximity to natural protectorates Soil
Tourist resort OR Monuments Islands Marine
Labor Hills and Highlands
Proximity to Mines and Quarries Proximity to air ports and ports
Away from Contaminated Areas
Agriculture
LUC= %F1∩%F2∩%F3∩%F4∩%Fn… = 100%-26-
Factors
Proximity to Mines & QuarriesProximity to Settlements-LaborTerrainIsland MarinesTourist Resorts or Moments
SoilsProximity to natural protectorates InfrastructureWater
Total Proximity to Transportation
Uses Agriculture(%)
5012
30
112
102
1
100
2. Data Mining Phase (cluster + classification) cont…
2. D
ata
Min
ing
Phas
e (c
lust
er +
cl
assi
ficat
ion)
con
t…
-27-
2. Data Mining Phase (cluster + classification) cont…
Using Classification method in Data mining to classify each factor according to its degree of importance that leads to best utilization and best usage for governmental lands
2ND STEPLUC= %F1∩%F2∩%F3∩%F4∩
%Fn… = 100%
The most important factors are:The greatest values
According to
equation
F2F1F3
Water 50%Soil 30%
Labor 10%Hills & High lands 1%
Island Marine 1%Proximity to mines 2%
Proximity to airports 1%Away from contaminated areas 1%
Infrastructure 1%Natural protectorates 2%
Monuments 1%
So, Small Percentages doesn’t affect
-28-
Case Study
Sinai
Working Environment:
1. Data Resources2. Data Maps
-30-
1. Topographic Data: Egyptian Survey Authority, Military Survey Authority
2. Climatic Data: Egyptian Climate Authority3. Soil Data: Research institute of ground water and
soil ( واالراضى الجوفيه المياة لبحوث القومى (المعهد4. Geologic and mining Data: Egyptian geological
survey5. Environmental data: Egyptian environmental affairs6. Agricultural Data: agricultural research institute7. Touristic Data: tourism development authority8. Industrial Data: industrial development authority
1. Data Resources:
-31-
2. Data Maps:Topographic Data: topographic maps drawn on a scale 1:250000 Military Survey
Soil Data: Meta-logic Map scale 1:1,000,000, issued by the Geological Survey of Egypt
Geologic and mining Data: hydrology map of scale 1:1000000-32-
Factors
Proximity to Mines & QuarriesProximity to Settlements-LaborTerrain (Hills and highlands)Island MarinesTourist Resorts or Moments
SoilsProximity to natural protectorates InfrastructureWater
Total Proximity to Transportation
Uses Agriculture(%)
60--
30
---
10-
-
100
Data Classification
-33-
Factors
Proximity to Mines & QuarriesProximity to Settlements-LaborTerrain (Hills and highlands)Island MarinesTourist Resorts or Moments
SoilsProximity to natural protectorates InfrastructureWater
Total Proximity to Transportation
Uses Agriculture(%)
60--
30
---
10-
-
100
Industry(%)
-30--
---
1060
-
100
Data Classification
-34-
Factors
Proximity to Mines & QuarriesProximity to Settlements-LaborTerrain (Hills and highlands)Island MarinesTourist Resorts or Moments
SoilsProximity to natural protectorates InfrastructureWater
Total Proximity to Transportation
Uses Agriculture(%)
60--
30
---
10-
-
100
Industry(%)
-30--
---
1060
-
100
Tourism(%)
----
50101010--
20
100
Data Classification
-35-
Factors
Proximity to Mines & QuarriesProximity to Settlements-LaborTerrain (Hills and highlands)Island MarinesTourist Resorts or Moments
SoilsProximity to natural protectorates InfrastructureWater
Total Proximity to Transportation
Uses Agriculture(%)
60--
30
---
10-
-
100
Industry(%)
-30--
---
1060
-
100
Tourism(%)
----
50101010--
20
100
Housing(%)
-40-
10
--
1010-
30
100
Data Classification
-36-
Agricultural
capability map
Data about layers (name, areas, longitude, latitude) Agricultural Capability
-37-
Soil fertilit
y degre
es
Data about layers (name, areas, longitude, latitude) Agricultural Capability (cont…)
-38-
Mining Capabilitie
s
Quarries Capabilities
Building Material
Capabilities
Data about layers (name, areas, longitude, latitude) Extractive industries Capability
-39-
Data about layers (name, areas, longitude, latitude) Tourism Capability
TourismCapability
Map
-40-
Soil Fertility- Land productivity
From 1- 5
-41-
Quarries
-42-
Building Material
s
-43-
Mining
-44-
Mining Capabilitie
s
Quarries Capabilities
Building Material
Capabilities
Extractive Industries
-45-
In Order to use this UI control you have to be authorized
Authentication security:
-46-
Detecting Overlap
• Now we have to convert all matrix values into zeros and ones for normalization as follows:
-47-
Using analysis tools to detect intersections between factors and layers
using HistogramDetecting Overlap cont…
-48-
Using Line plot diagram
Detecting Overlap cont…
-49-
• Tourism Potentialities• Mining quarrying
Potentialities
• Tourism Potentialities• Mining Potentialities• Solar energy potentialities
Overlapping Map
-50-
Overlapping MapMINING QUARRYING POTENTIALITIES
Tourism Potentialities
-51-
Overlapping Map MINING QUARRYING POTENTIALITIES
HAMMAM FARAON TOURISM POTENTIALITIES
SOLAR ENERGY
-52-
Report To Help
Decision Maker In
Taking Decisions
-53-
Performance Evaluation :
Features England model New Vision Using geo-database 1 1 Using dynamic model 1 1 Using model builder 0 1 Using spatial analysis 1 1 Using Multi-criteria decision analysis 1 1 Using clustering method 0 1 Using classification method 0 1 Using evaluation matrix 1 1 Social, economical, environmental goals 1 1 Showing best utilization for overlapping 0 1 Dynamic reports 0 1
Zeroes and ones in this table represents feature existence in the model
England Model
-54-
Performance Evaluation :
Features China model New Vision Using geo-database 1 1 Using dynamic model 0 1 Using model builder 0 1 Using spatial analysis 0 1 Using Multi-criteria decision analysis 1 1 Using clustering method 0 1 Using classification method 0 1 Applying Analytical hierarchy process 1 1 Using evaluation matrix 0 1 Economical goals 1 1 Social, environmental goals 0 1 Showing best utilization for overlapping 0 1 Dynamic reports 0 1
China Model
-55-
Zeroes and ones in this table represents feature existence in the model
Performance Evaluation :
Features Spain model New Vision Using geo-database 1 1 Using dynamic model 0 1 Using model builder 0 1 Using spatial analysis 0 1 Using Multi-criteria decision analysis 1 1 Using clustering method 0 1 Using classification method 0 1Analytical Network Process 1 0 Using evaluation matrix 0 1 Economical goals 1 1 Social, environmental goals 0 1Showing best utilization for overlapping 0 1Dynamic reports 0 1
Zeroes and ones in this table represents feature existence in the model
Spain Model
-56-
Conclusion:
-57-
1. Utilize Governmental resources with the best utilization
2. Applying automatic Reports about used areas and unused areas to help
the decision maker to decide and plan for the best usage of the
governmental land
3. Applying password to prevent governmental data from misusages
4. By using the Business Intelligent Land use Classification Planning
model, any piece of land could be classified according to its utilization,
by understanding its factors to collect the dataset elements, and then put
this data in the geo-database to reach the optimal utilization result by
applying the mathematical equation that runs through the dot net
application behind the arc-GIS tool.
Future Work: Land usages Future Challenges
Make an online application that help people to know their country resources in a transparent way. -58-
Thank You
-59-