investigating the relationship between adverse events and infrastructure development in an active

382 Pages·2013·16.17 MB·English

INVESTIGATING THE RELATIONSHIP BETWEEN ADVERSE EVENTS AND
INFRASTRUCTURE DEVELOPMENT IN AN ACTIVE WAR THEATER USING
SOFT COMPUTING TECHNIQUES

by

ERMAN ÇAKIT
B.S. Industrial Engineering, University of Gaziantep, Turkey, 2006
M.S. Industrial Engineering, Çukurova University, Turkey, 2008

A dissertation submitted in partial fulfillment of the requirements
for the degree of Doctor of Philosophy
in the Department of Industrial Engineering and Management Systems
in the College of Engineering and Computer Science
at the University of Central Florida
Orlando, Florida

Summer Term
2013

Major Professor: Waldemar Karwowski
© 2013 Erman Çakıt

ii
ABSTRACT

The military recently recognized the importance of taking sociocultural factors into
consideration. Therefore, Human Social Culture Behavior (HSCB) modeling has been getting
much attention in current and future operational requirements to successfully understand the
effects of social and cultural factors on human behavior. There are different kinds of modeling
approaches to the data that are being used in this field and so far none of them has been widely
accepted. HSCB modeling needs the capability to represent complex, ill-defined, and imprecise
concepts, and soft computing modeling can deal with these concepts.
There is currently no study on the use of any computational methodology for representing
the relationship between adverse events and infrastructure development investments in an active
war theater. This study investigates the relationship between adverse events and infrastructure
development projects in an active war theater using soft computing techniques including fuzzy
inference systems (FIS), artificial neural networks (ANNs), and adaptive neuro-fuzzy inference
systems (ANFIS) that directly benefits from their accuracy in prediction applications. Fourteen
developmental and economic improvement project types were selected based on allocated budget
values and a number of projects at different time periods, urban and rural population density, and
total adverse event numbers at previous month selected as independent variables. A total of four
outputs reflecting the adverse events in terms of the number of people killed, wounded, hijacked,
and total number of adverse events has been estimated. For each model, the data was grouped for
training and testing as follows: years between 2004 and 2009 (for training purpose) and year
2010 (for testing). Ninety-six different models were developed and investigated for Afghanistan
iii
and the country was divided into seven regions for analysis purposes. Performance of each
model was investigated and compared to all other models with the calculated mean absolute error
(MAE) values and the prediction accuracy within ±1 error range (difference between actual and
predicted value). Furthermore, sensitivity analysis was performed to determine the effects of
input values on dependent variables and to rank the top ten input parameters in order of
importance.
According to the the results obtained, it was concluded that the ANNs, FIS, and ANFIS
are useful modeling techniques for predicting the number of adverse events based on historical
development or economic projects’ data. When the model accuracy was calculated based on the
MAE for each of the models, the ANN had better predictive accuracy than FIS and ANFIS
models in general as demonstrated by experimental results. The percentages of prediction
accuracy with values found within ±1 error range around 90%. The sensitivity analysis results
show that the importance of economic development projects varies based on the regions,
population density, and occurrence of adverse events in Afghanistan. For the purpose of
allocating resources and development of regions, the results can be summarized by examining
the relationship between adverse events and infrastructure development in an active war theater;
emphasis was on predicting the occurrence of events and assessing the potential impact of
regional infrastructure development efforts on reducing number of such events.

iv
Throughout my work, two special people have always been there during those years of hard
times. This dissertation is dedicated to my parents, Ayşe and Şükrü Çakıt, for their endless love,
support and encouragement.

v
ACKNOWLEDGMENTS

I would like to express my deepest gratitude to my advisor Dr. Waldemar Karwowski.
This dissertation would not have been finished without his guidance and persistent support. My
decision to become an academician was sparked after I met with him. It is my sincere hope that I
affect students in my professional life as profoundly as he has affected me.
I would like to thank my committee members, Dr. Thompson, Dr. Lee, and Dr.
Mikusinski for being in committee and for their time and invaluable feedback.
I would like to thank Dr. Ahram for his support. During the research meetings, I
appreciate his invaluable and motivational comments to help me progress in research.
I would like to thank Republic of Turkey Ministry of National Education for their
financial support and encouragement during my graduate study.
Finally, I would like to thank Office of Naval Research Human Social Cultural
Behavioral Program. This dissertation was supported in part by Grant No. 1052339, Complex
Systems Engineering for Rapid Computational Socio-Cultural Network Analysis, from the
Office of Naval Research.

vi
TABLE OF CONTENTS
LIST OF FIGURES ....................................................................................................................... xi
LIST OF TABLES ..................................................................................................................... xxvi
LIST OF ABBREVIATIONS ................................................................................................... xxxv
CHAPTER I: INTRODUCTION .................................................................................................... 1
1.1 From War to Nation-Building in Afghanistan ...................................................................... 1
1.2 Human Social Culture Behavior (HSCB) Modeling ............................................................. 5
1.3 Problem Statement ................................................................................................................ 7
1.4 Research Gap......................................................................................................................... 8
1.5 Research Objectives .............................................................................................................. 8
1.6 Research Questions ............................................................................................................... 8
1.7 Study Design ......................................................................................................................... 9
CHAPTER II: LITERATURE REVIEW ..................................................................................... 11
2.1 Challenges and General Modeling Approaches .................................................................. 11
2.2 Spatial Statistics .................................................................................................................. 12
2.3 Soft Computing Techniques and Applications.................................................................... 15
2.3.1 Fuzzy Clustering ........................................................................................................... 16
2.4 Application of Crime Pattern Detection Techniques .......................................................... 17
vii
2.5 Agent-Based Approaches .................................................................................................... 18
2.6 Linguistic Pattern Analysis ................................................................................................. 20
CHAPTER III: METHODOLOGY .............................................................................................. 21
3.1 Soft-Computing Techniques ............................................................................................... 21
3.1.1 Artificial Neural Networks ........................................................................................... 23
3.1.1.1 The Architecture of ANNs ..................................................................................... 25
3.1.1.2 Network Training Algorithm ................................................................................. 29
3.1.1.3 Transfer (Activation) functions.............................................................................. 30
3.1.1.4 Data Normalization ................................................................................................ 32
3.1.2 Fuzzy Sets ..................................................................................................................... 35
3.1.2.1 Membership Functions........................................................................................... 36
3.1.2.2 Fuzzy Systems ....................................................................................................... 37
3.1.2.3 Data Clustering ...................................................................................................... 40
3.1.3 Adaptive Neuro-Fuzzy Inference Systems (ANFIS) .................................................... 44
3.1.3.1 ANFIS Input Selection ........................................................................................... 47
3.2 The dataset........................................................................................................................... 49
3.3 Performance Metrics ........................................................................................................... 54
CHAPTER IV: RESULTS ............................................................................................................ 55
4.1 ANN Model Development .................................................................................................. 58
viii
4.1.1 Prediction of number of people killed .......................................................................... 59
4.1.2 Prediction of number of people wounded..................................................................... 63
4.1.3 Prediction of number of people hijacked ...................................................................... 67
4.1.4 Prediction of total number of adverse events ............................................................... 71
4.2 FIS Model Development ..................................................................................................... 75
4.2.1 Prediction of number of people killed .......................................................................... 77
4.2.2 Prediction of number of people wounded..................................................................... 81
4.2.3 Prediction of number of people hijacked ...................................................................... 85
4.2.4 Prediction of total number of adverse events ............................................................... 89
4.3 ANFIS Model Development ............................................................................................... 94
4.3.1 Prediction of number of people killed .......................................................................... 97
4.3.2 Prediction of number of people wounded................................................................... 100
4.3.3 Prediction of number of people hijacked .................................................................... 104
4.3.4 Prediction of total number of adverse events ............................................................. 108
4.4 Performance Comparison of Models................................................................................. 112
4.5 Sensitivity Analysis ........................................................................................................... 126
CHAPTER V: CONCLUSION................................................................................................... 148
5.1. Study Contributions.......................................................................................................... 148
5.2. Summary of Study ............................................................................................................ 148
ix
5.3 Study Limitations and Future Work .................................................................................. 149
5.3.1 Data Limitations ......................................................................................................... 149
5.3.2 ANN Model Limitations ............................................................................................. 150
5.3.3 FIS Model Limitations................................................................................................ 150
5.3.4 ANFIS Model Limitations .......................................................................................... 151
APPENDIX A: SNAPSHOT OF PARTIAL DATASET ........................................................... 152
APPENDIX B: CORRELATION RESULTS ............................................................................ 162
APPENDIX C: MATLAB CODE FOR EACH METHODOLOGY ......................................... 171
APPENDIX D: MAP REPRESENTATION OF MONTHLY PREDICTED AND OBSERVED
VALUES FOR ENTIRE AFGHANISTAN ............................................................................... 177
APPENDIX E: MONTHLY MAE AND PERCENTAGE VALUES ........................................ 225
APPENDIX F: SENSITIVITY ANALYSIS RESULTS FOR ALL RANKED INPUT VALUES
..................................................................................................................................................... 242
APPENDIX G: SENSITIVITY ANALYSIS GRAPHS FOR THE TOP TWO RANKED
VALUES ..................................................................................................................................... 309
REFERENCES ........................................................................................................................... 337

x