Investigating the relationship between adverse events and infrastructure development in an active war theater using soft computing techniques
Graphical abstract
Introduction
Irregular warfare is defined by the U.S. Department of Defense (DoD) as “a violent struggle among state and non-state actors for legitimacy and influence over the relevant population(s).” Such warfare includes non-proportional force to convince and coerce where opposite forces are not large and effective in the region [1]. The success of irregular warfare operations depends heavily on the safety of civilian population, because the civilian population is the primary target of irregular warfare. Actors in warfare can work more effectively with a better understanding of this dynamic.
The U.S. military has made some adjustments to its force structure in response to the challenges of irregular warfare. Bhattacharjee [2] outlined the application of a program called human social culture behavior (HSCB) modeling to guide the U.S. military in achieving a better understanding of the different types of cultures encountered while operating in overseas countries [3]. The overarching aim of the HSCB modeling is to enable DoD and the U.S. Government to better organize and control the human terrain during nonconventional warfare and other missions [4]. In particular, models of human behavior could be used to predict the effects of actions intended to disrupt terrorist networks.
HSCB models are formed in order to understand the behavior and structure of organizational units at the macro level (economies, politics, socio-cultural regions) and at the micro level (terrorist networks, tribes, military units) [5]. These models are attracting much attention with regard to current and future operational requirements. HSCB models are complex systems and require computational modeling and simulation techniques to handle this complexity. Computational social scientists are currently researching how observations of human behavior might be used to develop scientifically based models of HSCB events [6]. To our best knowledge, there is currently no other study on the use of any computational methodology for representing the relationship between adverse events and infrastructure development investments in an active war theater.
Various challenges have been encountered while trying to address problems related to representing social sciences data. Numrich and Tolk [7] summarized these challenges: lack of common vocabulary, variations in modeling approaches, and data acquisition. Schmorrow et al. [8] emphasized the challenge of leveraging modeling and simulation (M&S) for HSCB. They cited the difficulty in understanding which M&S tools are actually useful and when and how best to use M&S tools within different complexity levels. All these challenges must be understood and researchers should meet specific modeling requirements before proceeding to apply various methodologies in the HSCB field.
There are modeling challenges with social data, particularly with regard to handling complexity, uncertainty, etc. Prediction is a particularly difficult task. Tools such as fuzzy inference systems (FIS), artificial neural networks (ANN), and adaptive neuro-fuzzy inference systems (ANFIS) are especially effective in handling the uncertainty and imprecision inherent in prediction modeling, and have demonstrated a high degree of accuracy in prediction applications. To demonstrate this, we’re going to use soft computing to analyze a certain characteristic we know aligns with stability and lack of violence (infrastructure and economic spending) and see if we can use it to do a really difficult but useful modeling task: predict adverse events.
In summary, this study extends the investigation into using the soft computing techniques ANN, FIS, and ANFIS for predictive modeling. In this study, we analyze real-world data, use ANN, FIS, and ANFIS to predict future behavior, and measure the accuracy of each methodology. Using data on activity in an active war theater (seven geographical regions in Afghanistan), we explore the relationship between the size and scope of infrastructure development within each region and the number of “adverse events” (people killed, wounded, or hijacked). We then use ANN, FIS and ANFIS to evaluate that relationship and predict the number of adverse events in the future.
Section snippets
The dataset
Two different kinds of Afghanistan datasets provided by the HSCB program management (2001–2010) were utilized in this research, including: (1) the adverse event dataset, which includes information regarding the date of event, incident type, number of people killed, wounded, and hijacked, province, city, district, description of the event, and simple event summary. (2) The infrastructure aid dataset, which includes information regarding the population density, province, city, district, project
ANN model development
ANNs are mathematical models of the human brain that mimic the functioning mechanism of biological neural networks [13]. Weighted-summation input and a nonlinear output activation function constitute a processing element (neuron), which is defined as a nonlinear mathematical model that sums the product of each input and its connection weight. The weight of an artificial neuron indicates how strong the related input is. There is a learning/training unit where the weights are updated. There is
Conclusion
This study developed three prediction models that allows: (i) investigation of the relationship between adverse events and infrastructure development in an active war theater using soft computing techniques, (ii) prediction of the occurrence of adverse events in different regions of Afghanistan, and (iii) assessment the potential impact of regional infrastructure development efforts on occurrence of adverse events.
ANN, FIS, and ANFIS were employed to relate population density and developmental
Acknowledgments
This study was supported in part by Grant no. 1052339, Complex Systems Engineering for Rapid Computational Socio-Cultural Network Analysis, from the Office of Naval Research. The authors acknowledge the helpful guidance of ONR program management, and the contributions of the technical team.
References (21)
- et al.
Forecasting with artificial neural networks: the state of the art
Int. J. Forecast.
(1998) - et al.
An effectiveness model for an indirect evaporative cooling (IEC) system: comparison of artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS) and fuzzy inference system (FIS) approach
Appl. Soft Comput.
(2011) Fuzzy sets
Inform. Control
(1965)- et al.
Applying fuzzy-set theory to performance evaluation
Socioecon. Plan. Sci.
(2000) - et al.
Predicting box-office success of motion pictures with neural networks
Expert Syst. Appl.
(2006) - et al.
Measuring effectiveness in irregular warfare
Parameters
(2007) Pentagon asks academics for help in understanding its enemies
Science
(2007)- et al.
Culture, conflict, and… climate?
Science
(2007) HSCB Modeling Program
(2009)Evolutionary Cognitive Neuroscience: Dual Use Discipline for Understanding & Managing Complexity and Altering Warfare
(2007)
Cited by (17)
Batch and data streaming classification models for detecting adverse events and understanding the influencing factors
2019, Engineering Applications of Artificial IntelligenceCitation Excerpt :Those in the North Western and North Eastern regions are the lowest. Thus, when the four variables are measured on the continuous scale the accurate prediction of the numbers of killed, wounded, hijacked, and events is an extremely challenging and difficult task regardless of the many techniques used as shown in the studies by Çakıt et al. (2014), Çakıt and Karwowski (2015a) and Çakıt and Karwowski (2015b, 2017a, b, 2018). The values of the mean absolute error and mean absolute percentage error for the four adverse events were several times larger than the mean values shown in Table 1.
Comparative analysis of machine learning algorithms for predicting standard time in a manufacturing environment
2023, Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAMAppropriate strategy selection for reliability-centered maintenance of one-shot systems using fuzzy model
2022, Journal of Quality in Maintenance Engineering