SlideShare a Scribd company logo
Machine Learning techniques for the Task
Planning of the Ambulance Rescue Team
Francesco Cucari - fracu758
TDDD10 AI Programming - Individual Report
Link¨oping University
1 Introduction
The RoboCup Rescue project started after the earthquake that hit Kobe City
in the January of 1995 causing enormous number of victims and damage.
The aim behind this project is to propose solutions for overcoming these dis-
astrous scenarios with minimal loss. In order to achieve this goal, the RoboCup
Rescue simulation models an earthquake in an urban centre presented in the
form of a map. This simulation matches real world limits and problems as accu-
rately as possible. In fact, the simulated earthquake causes building to collapse,
roads to be blocked, fires ignitions and civilians to be trapped and buried inside
collapsed buildings.
In the simulator, there are three teams responsible for all rescuing purposes:
the ambulance team, fire-brigade and police forces. The main task of ambulance
team is to rescue civilians and carry them safely in the refuge; the aim of fire-
brigades is to extinguish buildings on fire and the task of police forces is to clear
roads.
1.1 Motivation
This project is mainly focused on the tasks of the ambulance team. Since
the score function of the simulator highly depends on the number of the alive
civilians and on the percentage of the health left for all civilians [1], in order
to get an high score, the highest priority is to save the maximum number of
civilians possible.
This implies the maximum utilization of the time ahead of each agent and
agents should be sure that no time will be wasted on targets that will die either
during or after rescuing. This problem arises for example when civilians are
prioritized according to the shortest distance from each agent.
1.2 Aim
The proposed solution is inspired by the GUC ArtSapience team’s approach
described in [6] and it is based on learning the Expected Time of Death (ETD) of
each civilian and thus having realistic estimations will lead to better performance
of the Ambulance team by prioritizing the agents tasks accordingly. Due to
difficulty in finding a realistic formula to estimate the ETD, a learning algorithm
1
can be used to learn the factors that are hard to be calculated using those
implicitly parameters [5]. The goal of this project is to reach better performance
introducing the ETD in the prioritization task compared to the results of the
shortest distances approach.
1.3 Research questions
Given the described domain, questions regarding this arise. The focus of the
resulting report as well as the project in general will revolve around these ques-
tions, and this project will aim for getting an answer to these questions:
1. Is it possible to introduce the ETD in the prioritization task?
(a) If so, does this lead to better performance compared to the results of
shortest distances approach?
2 Methods
This work can be divided in two main steps: Learning and Planning.
2.1 Learning
In each time step of simulation the state of any given civilian changes. These
values are collected and preprocessed in a dataset that is used for the learning
phase.
2.1.1 Data collection
Data are collected after many runs of multiple maps, where the agents log the
state of civilians at each step instead of rescuing them. Then, some further
changes to the simulator are done: maps were run without blockades, with the
fire-simulator enabled and with all static civilians. In order to collect more
data, maps were run with different scenarios where more fires were added in the
map. Tab.1 is an example of collected dataset that represent the history of each
civilian.
ID civilian Timestep HP Damage Buriedness
406067950 177 3000 1000 0
406067950 178 2000 1300 0
406067950 179 0 1800 0
1769673037 79 1000 100 60
1769673037 80 0 200 60
Table 1: An example of collected data before preprocessing
2.1.2 Preprocessing and Labelling
The collected data need some preprocessing. In fact, for a supervised learning
algorithm to be applied on a training dataset, each example of that set has to
have an output attribute, which is the output value of the classification. In the
2
proposed approach this attribute is the ETD of the civilian. The ID civilian and
time steps are used to label each example with the value of ETD. The resulting
dataset contains pairs of values for each attribute in the set and a value for the
time where this civilian will die. If civilian is not dead during the simulation,
this value is set to the maximum time step, that is 300. Tab.2 shows an extract
of the final dataset, that is used as input of the learning classifier.
HP Damage Buriedness ETD
3000 1000 0 179
2000 1300 0 179
0 1800 0 179
1000 100 60 80
0 200 60 80
Table 2: Final dataset after preprocessing and labelling
2.1.3 Classifier
Given the dataset, the goal is to learn the relation between the input pairs (HP,
Damage, Buriedness) and the output (ETD), following the approach developed
in [2]: this relation was obtained first by training the dataset and then using
the output learning model for future predictions. Thus, a classifier is needed to
achieve both goals: multiple linear regression.
Linear regression is an approach for predicting a quantitative response (nu-
meric value) using multiple feature (or ”predictor” or ”input variable”) [3]. It
takes the following form:
y = β0 + β1 ∗ x1 + β2 ∗ x2 + β3 ∗ x3 (1)
where β0 represent the intercept, each xi represents a different feature (hp,
damage and buriedness), and each feature has its own coefficient βi. Learning
these coefficients it’s possible to make prediction of the output value y, that is
the ETD of a civilian.
For model validation, 10-fold cross validation was used. As defined in [4],
cross-validation is a statistical method of evaluating and comparing learning
algorithms by dividing data into two segments: one used to learn or train a
model and the other used to validate the model. The division process can be
repeated k times, using different subsets of the data. So, the idea of cross
validation is to estimate how well the current dataset can predict an output
value for any given input instance.
Finally, the Weka1
tool is used for all learning purposes. Weka is a com-
prehensive suite of Java class libraries that implement many state-of-the-art
machine learning and data mining algorithms [7]. It is quite easy to use it since
the learning algorithms can be called directly from the Java code.
2.2 Planning
Rescue agents need to plan their decisions to reach their restricted goal that is
saving the maximum number of civilians possible. An ambulance agent notifies
1http://www.cs.waikato.ac.nz/ml/weka/
3
the parameters of found civilian to the ambulance centre. The ambulance centre
uses these parameters and the output learning model (3.1) to predict the ETD
and then to prioritize the agents tasks accordingly.
2.2.1 Exploring-Rescuing trade-off
The first decision of the centre takes in consideration the exploring-rescuing
trade-off. In fact, the ambulance centre should answer to the question: When
does the ambulance centre decide which civilian should be rescued? The first
option is to rescue when a victim is notified. This is not efficient because this
approach lead to a waste of time due to the fact that there could be a civilian
who need more help or with more HP and so on. The chosen approach is to
introduce a priority value based on ETD: if the priority value is greater than
a certain threshold then the ambulance centre orders for an agent to rescue a
civilian.
2.2.2 Task prioritization
The ambulance centre can prioritize the agents tasks according to:
• shortest distance, where closest targets have high priority;
• ETD, where targets with low ETD have high priority;
• shortest distance + ETD, where closest targets with low ETD have high
priority. This combined approach is inspired by A*: f(n) = g(n) + h(n)
where g(n) is the normalized shortest path’s cost and h(n) is the ETD of
the target.
3 Results
3.1 Learning
Using the Weka tool and applying the classifier, described in 2.1.3, on the ob-
tained training dataset, described in 2.1.2, the resulting model is the following:
Figure 1: Resulting output learning model
This model will be used by the ambulance center to predict the ETD and
prioritize the agent task accordingly using the parameters of each civilian no-
tified by the agents. Then, a summary of the model validation, described in
2.1.3, is shown in Fig.2.
4
Figure 2: Summary of the model validation
3.2 Planning
The number of rescued civilians was chosen to be the evaluation measurement
of proposed approaches since the score doesn’t depends only on civilians. Fig.3
shows the number of rescued civilians using the approaches described in 2.2.2.
Figure 3: Comparison of the number of rescued civilians using the three ap-
proaches
4 Discussion
The proposed approach, based on the introduction of the ETD in the prioriti-
zation task and in particular using the combined approach distance+ETD, lead
to better performance compared with the results of shortest-distance strategy.
It is worth noting that some statistical parameters of the output learning
model of this work are better than those described in [6]. In fact, the value of
correlation coefficient, that quantifies a statistical relationships between two or
more observed data values, is higher by 7%. Furthermore, the value of the root
relative squared error is lower by 5%.
Finally, with the proposed approach the number of rescued civilians is in-
creased by 7% compared with the shortest-distance strategy and by 15% com-
pared with only ETD-based strategy.
5
5 Conclusion
The introduction of a learning model in the task planning of the ambulance
rescue team helped to reach better results in the rescuing operation. This model
was the outcome of a training data set that was trained using linear regression
algorithm. Then, this model was used for prediction of ETD for task prioritizing
and planning. In particular, ETD was used for optimizing the search algorithm
that constructs paths for the agents to move from one location on the map to
another. This was done by replacing the traditional breadth first search by
a heuristic search, which includes the ETD as a heuristic for the evaluation
function of expanding nodes.
The proposed solution didn’t only help optimize the task planning of the
agents and achieve better results. It also helped to overcome the obstacles en-
forced by the inaccurate values retrieved from the simulator regarding civilians.
Having a training dataset allows to know and learn the relation between the
parameters of civilians.
In future work, the training dataset can be augmented with other param-
eters, for example the shortest distance of a civilian from the nearest agent.
Furthermore, the proposed approach combined with the division of the map in
clusters and the assignment of one or more agents to specific clusters could lead
to better results, increasing the number of rescue civilians and decreasing the
waste of time in rescuing operations.
References
[1] Cyrille Berger Developing a team, 2015.
[2] Fadwa Sakr, Slim Abdennadher, Harnessing Supervised Learning Techniques
for the Task Planning of Ambulance Rescue Agents, ICAART 2016, 2016
[3] James, Gareth, et al. An introduction to statistical learning. Vol. 6. New
York: springer, 2013.
[4] Refaeilzadeh, Payam, Lei Tang, and Huan Liu. Cross-validation. Encyclope-
dia of database systems. Springer US, 2009. 532-538.
[5] Sameh Metias, Mahmoud Walid and others, RoboCup 2015 Rescue Simula-
tion League Team Description GUC ArtSapience (Egypt), 2015
[6] Sameh Metias, Mohammed Waheed and others, RoboCup 2016 Rescue Sim-
ulation League Team Description GUC ArtSapience (Egypt), 2014
[7] Witten, Ian H and Frank, Eibe and Trigg, Leonard E and Hall, Mark A
and Holmes, Geoffrey and Cunningham, Sally Jo, Weka: Practical machine
learning tools and techniques with Java implementations, 1999
6

More Related Content

What's hot

Selection of optimal hyper-parameter values of support vector machine for sen...
Selection of optimal hyper-parameter values of support vector machine for sen...Selection of optimal hyper-parameter values of support vector machine for sen...
Selection of optimal hyper-parameter values of support vector machine for sen...
journalBEEI
 
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
IJERA Editor
 
Fuzzy clustering1
Fuzzy clustering1Fuzzy clustering1
Fuzzy clustering1
abc
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
IJITCA Journal
 
D111823
D111823D111823
One-Sample Face Recognition Using HMM Model of Fiducial Areas
One-Sample Face Recognition Using HMM Model of Fiducial AreasOne-Sample Face Recognition Using HMM Model of Fiducial Areas
One-Sample Face Recognition Using HMM Model of Fiducial Areas
CSCJournals
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Science
inventy
 
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET Journal
 
IRJET- Proposed System for Animal Recognition using Image Processing
IRJET-  	  Proposed System for Animal Recognition using Image ProcessingIRJET-  	  Proposed System for Animal Recognition using Image Processing
IRJET- Proposed System for Animal Recognition using Image Processing
IRJET Journal
 
Color Image Watermarking Application for ERTU Cloud
Color Image Watermarking Application for ERTU CloudColor Image Watermarking Application for ERTU Cloud
Color Image Watermarking Application for ERTU Cloud
CSCJournals
 
Methodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniquesMethodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniques
ijsc
 
Paper id 26201483
Paper id 26201483Paper id 26201483
Paper id 26201483
IJRAT
 
Multi Resolution features of Content Based Image Retrieval
Multi Resolution features of Content Based Image RetrievalMulti Resolution features of Content Based Image Retrieval
Multi Resolution features of Content Based Image Retrieval
IDES Editor
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
A Threshold Fuzzy Entropy Based Feature Selection: Comparative Study
A Threshold Fuzzy Entropy Based Feature Selection:  Comparative StudyA Threshold Fuzzy Entropy Based Feature Selection:  Comparative Study
A Threshold Fuzzy Entropy Based Feature Selection: Comparative Study
IJMER
 
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
IOSR Journals
 

What's hot (16)

Selection of optimal hyper-parameter values of support vector machine for sen...
Selection of optimal hyper-parameter values of support vector machine for sen...Selection of optimal hyper-parameter values of support vector machine for sen...
Selection of optimal hyper-parameter values of support vector machine for sen...
 
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
Comparision of Clustering Algorithms usingNeural Network Classifier for Satel...
 
Fuzzy clustering1
Fuzzy clustering1Fuzzy clustering1
Fuzzy clustering1
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
 
D111823
D111823D111823
D111823
 
One-Sample Face Recognition Using HMM Model of Fiducial Areas
One-Sample Face Recognition Using HMM Model of Fiducial AreasOne-Sample Face Recognition Using HMM Model of Fiducial Areas
One-Sample Face Recognition Using HMM Model of Fiducial Areas
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Science
 
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
 
IRJET- Proposed System for Animal Recognition using Image Processing
IRJET-  	  Proposed System for Animal Recognition using Image ProcessingIRJET-  	  Proposed System for Animal Recognition using Image Processing
IRJET- Proposed System for Animal Recognition using Image Processing
 
Color Image Watermarking Application for ERTU Cloud
Color Image Watermarking Application for ERTU CloudColor Image Watermarking Application for ERTU Cloud
Color Image Watermarking Application for ERTU Cloud
 
Methodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniquesMethodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniques
 
Paper id 26201483
Paper id 26201483Paper id 26201483
Paper id 26201483
 
Multi Resolution features of Content Based Image Retrieval
Multi Resolution features of Content Based Image RetrievalMulti Resolution features of Content Based Image Retrieval
Multi Resolution features of Content Based Image Retrieval
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
A Threshold Fuzzy Entropy Based Feature Selection: Comparative Study
A Threshold Fuzzy Entropy Based Feature Selection:  Comparative StudyA Threshold Fuzzy Entropy Based Feature Selection:  Comparative Study
A Threshold Fuzzy Entropy Based Feature Selection: Comparative Study
 
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
Automatic Determination Number of Cluster for NMKFC-Means Algorithms on Image...
 

Viewers also liked

DOE Forest Full Report_1110_1
DOE Forest Full Report_1110_1DOE Forest Full Report_1110_1
DOE Forest Full Report_1110_1Izabela Grobelna
 
DOE Polish Community Full Report_0
DOE Polish Community Full Report_0DOE Polish Community Full Report_0
DOE Polish Community Full Report_0Izabela Grobelna
 
DOE West Ridge Full Report_1
DOE West Ridge Full Report_1DOE West Ridge Full Report_1
DOE West Ridge Full Report_1Izabela Grobelna
 
We're Going Global - With or without you! by Melissa Powell, Founder & CEO, ...
We're Going Global - With or without you!  by Melissa Powell, Founder & CEO, ...We're Going Global - With or without you!  by Melissa Powell, Founder & CEO, ...
We're Going Global - With or without you! by Melissa Powell, Founder & CEO, ...
Melissa Powell
 
CAPABILITY STATEMENT OF META ARCH 2016
CAPABILITY STATEMENT OF META ARCH 2016CAPABILITY STATEMENT OF META ARCH 2016
CAPABILITY STATEMENT OF META ARCH 2016Gunjan Mangtani
 
Mood classification of songs based on lyrics
Mood classification of songs based on lyricsMood classification of songs based on lyrics
Mood classification of songs based on lyrics
Francesco Cucari
 
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
Francesco Cucari
 
Evolution of the Boathouse Summer 2016 Annual Display
Evolution of the Boathouse Summer 2016 Annual DisplayEvolution of the Boathouse Summer 2016 Annual Display
Evolution of the Boathouse Summer 2016 Annual DisplayPatrick Greenwald
 
How to succeed in the AU REU program taneja
How to succeed in the AU REU program   tanejaHow to succeed in the AU REU program   taneja
How to succeed in the AU REU program taneja
Shubbhi Taneja
 
Educating the STEM leaders of Tomorrow
Educating the STEM leaders of TomorrowEducating the STEM leaders of Tomorrow
Educating the STEM leaders of Tomorrow
Shubbhi Taneja
 
Software Design Patterns and Quality Assurance
Software Design Patterns and Quality AssuranceSoftware Design Patterns and Quality Assurance
Software Design Patterns and Quality Assurance
Shubbhi Taneja
 
Office_365_brochure_121216_TPAC_fields
Office_365_brochure_121216_TPAC_fieldsOffice_365_brochure_121216_TPAC_fields
Office_365_brochure_121216_TPAC_fieldsMartin G. Lee
 
Prueba de evaluación 2017
Prueba de evaluación 2017Prueba de evaluación 2017
Prueba de evaluación 2017
iesboliches2
 

Viewers also liked (17)

DOE Pilsen At A Glance_0
DOE Pilsen At A Glance_0DOE Pilsen At A Glance_0
DOE Pilsen At A Glance_0
 
DOE Austin Full Report
DOE Austin Full ReportDOE Austin Full Report
DOE Austin Full Report
 
DOE Forest Full Report_1110_1
DOE Forest Full Report_1110_1DOE Forest Full Report_1110_1
DOE Forest Full Report_1110_1
 
DOE Polish Community Full Report_0
DOE Polish Community Full Report_0DOE Polish Community Full Report_0
DOE Polish Community Full Report_0
 
DOE West Ridge Full Report_1
DOE West Ridge Full Report_1DOE West Ridge Full Report_1
DOE West Ridge Full Report_1
 
We're Going Global - With or without you! by Melissa Powell, Founder & CEO, ...
We're Going Global - With or without you!  by Melissa Powell, Founder & CEO, ...We're Going Global - With or without you!  by Melissa Powell, Founder & CEO, ...
We're Going Global - With or without you! by Melissa Powell, Founder & CEO, ...
 
CAPABILITY STATEMENT OF META ARCH 2016
CAPABILITY STATEMENT OF META ARCH 2016CAPABILITY STATEMENT OF META ARCH 2016
CAPABILITY STATEMENT OF META ARCH 2016
 
Mood classification of songs based on lyrics
Mood classification of songs based on lyricsMood classification of songs based on lyrics
Mood classification of songs based on lyrics
 
SWS-Full-Report
SWS-Full-ReportSWS-Full-Report
SWS-Full-Report
 
Navigator_Jessica
Navigator_JessicaNavigator_Jessica
Navigator_Jessica
 
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
Art Everywhere: progetto per workshop Google. Sviluppo di sistemi di pattern ...
 
Evolution of the Boathouse Summer 2016 Annual Display
Evolution of the Boathouse Summer 2016 Annual DisplayEvolution of the Boathouse Summer 2016 Annual Display
Evolution of the Boathouse Summer 2016 Annual Display
 
How to succeed in the AU REU program taneja
How to succeed in the AU REU program   tanejaHow to succeed in the AU REU program   taneja
How to succeed in the AU REU program taneja
 
Educating the STEM leaders of Tomorrow
Educating the STEM leaders of TomorrowEducating the STEM leaders of Tomorrow
Educating the STEM leaders of Tomorrow
 
Software Design Patterns and Quality Assurance
Software Design Patterns and Quality AssuranceSoftware Design Patterns and Quality Assurance
Software Design Patterns and Quality Assurance
 
Office_365_brochure_121216_TPAC_fields
Office_365_brochure_121216_TPAC_fieldsOffice_365_brochure_121216_TPAC_fields
Office_365_brochure_121216_TPAC_fields
 
Prueba de evaluación 2017
Prueba de evaluación 2017Prueba de evaluación 2017
Prueba de evaluación 2017
 

Similar to Machine Learning techniques for the Task Planning of the Ambulance Rescue Team

Long-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure RecoveryLong-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure Recovery
TELKOMNIKA JOURNAL
 
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMINGAMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
IRJET Journal
 
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large DataExtended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
AM Publications
 
Sequential estimation of_discrete_choice_models__copy_-4
Sequential estimation of_discrete_choice_models__copy_-4Sequential estimation of_discrete_choice_models__copy_-4
Sequential estimation of_discrete_choice_models__copy_-4
YoussefKitane
 
AMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLTAMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLT
IRJET Journal
 
Performance Comparision of Machine Learning Algorithms
Performance Comparision of Machine Learning AlgorithmsPerformance Comparision of Machine Learning Algorithms
Performance Comparision of Machine Learning Algorithms
Dinusha Dilanka
 
Advanced SOM & K Mean Method for Load Curve Clustering
Advanced SOM & K Mean Method for Load Curve Clustering Advanced SOM & K Mean Method for Load Curve Clustering
Advanced SOM & K Mean Method for Load Curve Clustering
IJECEIAES
 
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
Reza Nourjou, Ph.D.
 
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
gerogepatton
 
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
ijaia
 
07 18sep 7983 10108-1-ed an edge edit ari
07 18sep 7983 10108-1-ed an edge edit ari07 18sep 7983 10108-1-ed an edge edit ari
07 18sep 7983 10108-1-ed an edge edit ari
IAESIJEECS
 
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment ProblemIRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
IRJET Journal
 
A comparative study of three validities computation methods for multimodel ap...
A comparative study of three validities computation methods for multimodel ap...A comparative study of three validities computation methods for multimodel ap...
A comparative study of three validities computation methods for multimodel ap...
IJECEIAES
 
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
IJCSEIT Journal
 
Crowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line FilteringCrowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line Filtering
paperpublications3
 
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATIONMAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
VLSICS Design
 
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
IRJET Journal
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
IJITCA Journal
 
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERSFIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
csandit
 

Similar to Machine Learning techniques for the Task Planning of the Ambulance Rescue Team (20)

Long-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure RecoveryLong-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure Recovery
 
report
reportreport
report
 
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMINGAMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
AMBULANCE REDEPLOYMENT USING DYNAMIC DATA PROGRAMMING
 
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large DataExtended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
Extended Fuzzy C-Means with Random Sampling Techniques for Clustering Large Data
 
Sequential estimation of_discrete_choice_models__copy_-4
Sequential estimation of_discrete_choice_models__copy_-4Sequential estimation of_discrete_choice_models__copy_-4
Sequential estimation of_discrete_choice_models__copy_-4
 
AMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLTAMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLT
 
Performance Comparision of Machine Learning Algorithms
Performance Comparision of Machine Learning AlgorithmsPerformance Comparision of Machine Learning Algorithms
Performance Comparision of Machine Learning Algorithms
 
Advanced SOM & K Mean Method for Load Curve Clustering
Advanced SOM & K Mean Method for Load Curve Clustering Advanced SOM & K Mean Method for Load Curve Clustering
Advanced SOM & K Mean Method for Load Curve Clustering
 
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
Intelligent Algorithm for Assignment of Agents to Human Strategy in Centraliz...
 
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
 
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
A BI-OBJECTIVE MODEL FOR SVM WITH AN INTERACTIVE PROCEDURE TO IDENTIFY THE BE...
 
07 18sep 7983 10108-1-ed an edge edit ari
07 18sep 7983 10108-1-ed an edge edit ari07 18sep 7983 10108-1-ed an edge edit ari
07 18sep 7983 10108-1-ed an edge edit ari
 
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment ProblemIRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
IRJET- Comparison for Max-Flow Min-Cut Algorithms for Optimal Assignment Problem
 
A comparative study of three validities computation methods for multimodel ap...
A comparative study of three validities computation methods for multimodel ap...A comparative study of three validities computation methods for multimodel ap...
A comparative study of three validities computation methods for multimodel ap...
 
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
 
Crowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line FilteringCrowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line Filtering
 
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATIONMAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
 
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
The Evaluation of Topsis and Fuzzy-Topsis Method for Decision Making System i...
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
 
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERSFIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
FIDUCIAL POINTS DETECTION USING SVM LINEAR CLASSIFIERS
 

Recently uploaded

Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024
Globus
 
Enterprise Resource Planning System in Telangana
Enterprise Resource Planning System in TelanganaEnterprise Resource Planning System in Telangana
Enterprise Resource Planning System in Telangana
NYGGS Automation Suite
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
Georgi Kodinov
 
Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
Paco van Beckhoven
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
Google
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Globus
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Mind IT Systems
 
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus
 
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Globus
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
rickgrimesss22
 
SOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBrokerSOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
Matt Welsh
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
Globus
 
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdfDominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
AMB-Review
 
May Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdfMay Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdf
Adele Miller
 
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoamOpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
takuyayamamoto1800
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
Globus
 
First Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User EndpointsFirst Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User Endpoints
Globus
 
Understanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSageUnderstanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSage
Globus
 
top nidhi software solution freedownload
top nidhi software solution freedownloadtop nidhi software solution freedownload
top nidhi software solution freedownload
vrstrong314
 

Recently uploaded (20)

Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024
 
Enterprise Resource Planning System in Telangana
Enterprise Resource Planning System in TelanganaEnterprise Resource Planning System in Telangana
Enterprise Resource Planning System in Telangana
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
 
Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
 
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024
 
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
 
SOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBrokerSOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBroker
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
 
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdfDominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
 
May Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdfMay Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdf
 
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoamOpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
 
First Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User EndpointsFirst Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User Endpoints
 
Understanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSageUnderstanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSage
 
top nidhi software solution freedownload
top nidhi software solution freedownloadtop nidhi software solution freedownload
top nidhi software solution freedownload
 

Machine Learning techniques for the Task Planning of the Ambulance Rescue Team

  • 1. Machine Learning techniques for the Task Planning of the Ambulance Rescue Team Francesco Cucari - fracu758 TDDD10 AI Programming - Individual Report Link¨oping University 1 Introduction The RoboCup Rescue project started after the earthquake that hit Kobe City in the January of 1995 causing enormous number of victims and damage. The aim behind this project is to propose solutions for overcoming these dis- astrous scenarios with minimal loss. In order to achieve this goal, the RoboCup Rescue simulation models an earthquake in an urban centre presented in the form of a map. This simulation matches real world limits and problems as accu- rately as possible. In fact, the simulated earthquake causes building to collapse, roads to be blocked, fires ignitions and civilians to be trapped and buried inside collapsed buildings. In the simulator, there are three teams responsible for all rescuing purposes: the ambulance team, fire-brigade and police forces. The main task of ambulance team is to rescue civilians and carry them safely in the refuge; the aim of fire- brigades is to extinguish buildings on fire and the task of police forces is to clear roads. 1.1 Motivation This project is mainly focused on the tasks of the ambulance team. Since the score function of the simulator highly depends on the number of the alive civilians and on the percentage of the health left for all civilians [1], in order to get an high score, the highest priority is to save the maximum number of civilians possible. This implies the maximum utilization of the time ahead of each agent and agents should be sure that no time will be wasted on targets that will die either during or after rescuing. This problem arises for example when civilians are prioritized according to the shortest distance from each agent. 1.2 Aim The proposed solution is inspired by the GUC ArtSapience team’s approach described in [6] and it is based on learning the Expected Time of Death (ETD) of each civilian and thus having realistic estimations will lead to better performance of the Ambulance team by prioritizing the agents tasks accordingly. Due to difficulty in finding a realistic formula to estimate the ETD, a learning algorithm 1
  • 2. can be used to learn the factors that are hard to be calculated using those implicitly parameters [5]. The goal of this project is to reach better performance introducing the ETD in the prioritization task compared to the results of the shortest distances approach. 1.3 Research questions Given the described domain, questions regarding this arise. The focus of the resulting report as well as the project in general will revolve around these ques- tions, and this project will aim for getting an answer to these questions: 1. Is it possible to introduce the ETD in the prioritization task? (a) If so, does this lead to better performance compared to the results of shortest distances approach? 2 Methods This work can be divided in two main steps: Learning and Planning. 2.1 Learning In each time step of simulation the state of any given civilian changes. These values are collected and preprocessed in a dataset that is used for the learning phase. 2.1.1 Data collection Data are collected after many runs of multiple maps, where the agents log the state of civilians at each step instead of rescuing them. Then, some further changes to the simulator are done: maps were run without blockades, with the fire-simulator enabled and with all static civilians. In order to collect more data, maps were run with different scenarios where more fires were added in the map. Tab.1 is an example of collected dataset that represent the history of each civilian. ID civilian Timestep HP Damage Buriedness 406067950 177 3000 1000 0 406067950 178 2000 1300 0 406067950 179 0 1800 0 1769673037 79 1000 100 60 1769673037 80 0 200 60 Table 1: An example of collected data before preprocessing 2.1.2 Preprocessing and Labelling The collected data need some preprocessing. In fact, for a supervised learning algorithm to be applied on a training dataset, each example of that set has to have an output attribute, which is the output value of the classification. In the 2
  • 3. proposed approach this attribute is the ETD of the civilian. The ID civilian and time steps are used to label each example with the value of ETD. The resulting dataset contains pairs of values for each attribute in the set and a value for the time where this civilian will die. If civilian is not dead during the simulation, this value is set to the maximum time step, that is 300. Tab.2 shows an extract of the final dataset, that is used as input of the learning classifier. HP Damage Buriedness ETD 3000 1000 0 179 2000 1300 0 179 0 1800 0 179 1000 100 60 80 0 200 60 80 Table 2: Final dataset after preprocessing and labelling 2.1.3 Classifier Given the dataset, the goal is to learn the relation between the input pairs (HP, Damage, Buriedness) and the output (ETD), following the approach developed in [2]: this relation was obtained first by training the dataset and then using the output learning model for future predictions. Thus, a classifier is needed to achieve both goals: multiple linear regression. Linear regression is an approach for predicting a quantitative response (nu- meric value) using multiple feature (or ”predictor” or ”input variable”) [3]. It takes the following form: y = β0 + β1 ∗ x1 + β2 ∗ x2 + β3 ∗ x3 (1) where β0 represent the intercept, each xi represents a different feature (hp, damage and buriedness), and each feature has its own coefficient βi. Learning these coefficients it’s possible to make prediction of the output value y, that is the ETD of a civilian. For model validation, 10-fold cross validation was used. As defined in [4], cross-validation is a statistical method of evaluating and comparing learning algorithms by dividing data into two segments: one used to learn or train a model and the other used to validate the model. The division process can be repeated k times, using different subsets of the data. So, the idea of cross validation is to estimate how well the current dataset can predict an output value for any given input instance. Finally, the Weka1 tool is used for all learning purposes. Weka is a com- prehensive suite of Java class libraries that implement many state-of-the-art machine learning and data mining algorithms [7]. It is quite easy to use it since the learning algorithms can be called directly from the Java code. 2.2 Planning Rescue agents need to plan their decisions to reach their restricted goal that is saving the maximum number of civilians possible. An ambulance agent notifies 1http://www.cs.waikato.ac.nz/ml/weka/ 3
  • 4. the parameters of found civilian to the ambulance centre. The ambulance centre uses these parameters and the output learning model (3.1) to predict the ETD and then to prioritize the agents tasks accordingly. 2.2.1 Exploring-Rescuing trade-off The first decision of the centre takes in consideration the exploring-rescuing trade-off. In fact, the ambulance centre should answer to the question: When does the ambulance centre decide which civilian should be rescued? The first option is to rescue when a victim is notified. This is not efficient because this approach lead to a waste of time due to the fact that there could be a civilian who need more help or with more HP and so on. The chosen approach is to introduce a priority value based on ETD: if the priority value is greater than a certain threshold then the ambulance centre orders for an agent to rescue a civilian. 2.2.2 Task prioritization The ambulance centre can prioritize the agents tasks according to: • shortest distance, where closest targets have high priority; • ETD, where targets with low ETD have high priority; • shortest distance + ETD, where closest targets with low ETD have high priority. This combined approach is inspired by A*: f(n) = g(n) + h(n) where g(n) is the normalized shortest path’s cost and h(n) is the ETD of the target. 3 Results 3.1 Learning Using the Weka tool and applying the classifier, described in 2.1.3, on the ob- tained training dataset, described in 2.1.2, the resulting model is the following: Figure 1: Resulting output learning model This model will be used by the ambulance center to predict the ETD and prioritize the agent task accordingly using the parameters of each civilian no- tified by the agents. Then, a summary of the model validation, described in 2.1.3, is shown in Fig.2. 4
  • 5. Figure 2: Summary of the model validation 3.2 Planning The number of rescued civilians was chosen to be the evaluation measurement of proposed approaches since the score doesn’t depends only on civilians. Fig.3 shows the number of rescued civilians using the approaches described in 2.2.2. Figure 3: Comparison of the number of rescued civilians using the three ap- proaches 4 Discussion The proposed approach, based on the introduction of the ETD in the prioriti- zation task and in particular using the combined approach distance+ETD, lead to better performance compared with the results of shortest-distance strategy. It is worth noting that some statistical parameters of the output learning model of this work are better than those described in [6]. In fact, the value of correlation coefficient, that quantifies a statistical relationships between two or more observed data values, is higher by 7%. Furthermore, the value of the root relative squared error is lower by 5%. Finally, with the proposed approach the number of rescued civilians is in- creased by 7% compared with the shortest-distance strategy and by 15% com- pared with only ETD-based strategy. 5
  • 6. 5 Conclusion The introduction of a learning model in the task planning of the ambulance rescue team helped to reach better results in the rescuing operation. This model was the outcome of a training data set that was trained using linear regression algorithm. Then, this model was used for prediction of ETD for task prioritizing and planning. In particular, ETD was used for optimizing the search algorithm that constructs paths for the agents to move from one location on the map to another. This was done by replacing the traditional breadth first search by a heuristic search, which includes the ETD as a heuristic for the evaluation function of expanding nodes. The proposed solution didn’t only help optimize the task planning of the agents and achieve better results. It also helped to overcome the obstacles en- forced by the inaccurate values retrieved from the simulator regarding civilians. Having a training dataset allows to know and learn the relation between the parameters of civilians. In future work, the training dataset can be augmented with other param- eters, for example the shortest distance of a civilian from the nearest agent. Furthermore, the proposed approach combined with the division of the map in clusters and the assignment of one or more agents to specific clusters could lead to better results, increasing the number of rescue civilians and decreasing the waste of time in rescuing operations. References [1] Cyrille Berger Developing a team, 2015. [2] Fadwa Sakr, Slim Abdennadher, Harnessing Supervised Learning Techniques for the Task Planning of Ambulance Rescue Agents, ICAART 2016, 2016 [3] James, Gareth, et al. An introduction to statistical learning. Vol. 6. New York: springer, 2013. [4] Refaeilzadeh, Payam, Lei Tang, and Huan Liu. Cross-validation. Encyclope- dia of database systems. Springer US, 2009. 532-538. [5] Sameh Metias, Mahmoud Walid and others, RoboCup 2015 Rescue Simula- tion League Team Description GUC ArtSapience (Egypt), 2015 [6] Sameh Metias, Mohammed Waheed and others, RoboCup 2016 Rescue Sim- ulation League Team Description GUC ArtSapience (Egypt), 2014 [7] Witten, Ian H and Frank, Eibe and Trigg, Leonard E and Hall, Mark A and Holmes, Geoffrey and Cunningham, Sally Jo, Weka: Practical machine learning tools and techniques with Java implementations, 1999 6