Samuel H. Huddleston

A Statistical Threat Assessment

Criminal gangs, insurgent groups, and terror networks demonstrate observable preferences in selecting the sites where they commit their crimes. Accordingly, police departments, military organizations, and intelligence agencies seek to learn these preferences and identify locations with a high probability of experiencing the particular event of interest in the near future. Often, such agencies are keen not just to predict the spatial pattern of future events but even more importantly to conduct threat assessments of particular criminal gangs or insurgent groups. These threat assessments include identifying where each of the various groups presents the greatest threat to the community, what the most likely targets are for each criminal group, what makes one location more likely to experience an attack than another, and how to most efficiently allocate resources to address the specific threats to the community. Previous research has demonstrated that applying multivariate prediction models to relate features in an area to the occurrence of crimes offers an improvement in predictive performance over traditional methods of hot-spot analysis. This paper introduces the application of multilevel modeling to these multivariate spatial choice models, demonstrating that it is possible to significantly improve the predictive performance of the spatial choice models for individual groups and leverage that information to provide improved threat assessments of the criminal elements in a given geographic area.

A comparison of evaluation methods for police patrol district designs

Police patrol district design presents a multi-objective optimization problem with two goals: minimizing workload variation between patrol districts and minimizing the response time for officers responding to calls for service. We evaluate three different methods for scoring district designs: a closed form probability based approach, a discrete-event simulation based on hypercube models for spatial queuing systems, and an agent-based simulation model. We find that all methods provide similar evaluations when service demand is low enough that cross-boundary support is infrequent. However, when the demand for service routinely exceeds the supply available within districts, only the agent-based simulation model accurately represents the resulting complexities and significantly changes the evaluation scores to reflect the behavior of the system.

Shaping senior leader officer talent: using a multi-dimensional model of talent to analyze the effect of personnel management decisions and attrition on the flow of Army Officer talent throughout the officer career model

Army Officer requirements for operational talent decline precipitously with increasing rank. While 80 percent of Junior Officers serve in operational billets, only 20 percent of Senior Leaders serve in operational billets. Yet despite this operational talent requirement inversion, Army development efforts tend to focus disproportionately on building operational talent. Moreover, career progression through the rank of General Officer tends to excessively favor officers who have spent most of their career in operational billets. By opening additional opportunities for officers who serve outside of operational billets to reach senior leader ranks, and by exposing more officers to opportunities that develop non-operational talents, the Army can mitigate against talent gaps at senior ranks. This analysis employs discrete event simulation to quantify the extent to which attrition, promotion, and the dynamically changing need for two types of talent (operational and non-operational) impact the distribution of talent available across the Armys officer ranks.

Changing knives into spoons

Politicians and the media paint contrasting pictures of the situation in Iraq from a growing insurgency and pending civil war to a blooming democracy in the Middle East. However, in all of the discussions, the question of how to employ forces to fight the insurgency is often avoided and rarely answered. This project will attempt to develop a hybrid agent-based simulation to examine resource allocation strategies. The study will examine insurgent behavior and responses to distance based outpost manning and a more incident driven strategy. Initial results show that a tradeoff between the strategies offers the best benefits in both the short and long term for a collection of counter-insurgency metrics.

Using discrete event simulation to evaluate time series forecasting methods for security applications

This paper documents the use of a discrete event simulation model to compare the effectiveness of forecasting systems available to support routine forecasts of criminal events in security applications. Military and police units regularly use forecasts of criminal events to divide limited resources, assign and redeploy special details, and conduct unit performance assessment. We use the simulation model to test the performance of available forecasting methods under a variety of conditions, including the presence of trends, seasonality, and shocks. We find that, in most situations, a simple forecasting method that fuses the outputs of crime hot-spot maps with the outputs of univariate time series methods both significantly reduces modeling workload and provides significant performance improvement over the three currently used methods: naive forecasts, Holt-Winters smoothing, and ARIMA models.

Statistical models for target detection in infrared imagery

This paper illustrates a statistical model-based approach to the problem of target detection in a cluttered scene from long-wave infrared images, accommodating both unknown range to the target, unknown target location in the image, and unknown gain control settings on the imaging device. The philosophical perspective adopted emphasizes an iterative process of model creation and refinement and subsequent evaluation. The overarching theme is on the clear statement of all assumptions regarding the relationships between ground truth and corresponding imagery, the assurance that each admits quantifiable refutation, and the opportunity costs associated with their adoption for a particular problem.

Shaping senior leader officer talent: how personnel management decisions and attrition impact the flow of army officer talent throughout the officer career model

Army Officers play a critical role in our nations security strategy. Throughout a career of service, officers develop talents through a unique and rare set of experiences, education, and formal training. The demand by corporations for these talents, coupled with a distinct feature of the Officer Career Model, limited lateral entry, create significant retention challenges for the U.S. Army. Understanding how personnel policies, resources, and organizational decisions affect the flow of officer talent through the Officer Career Model is a first step in addressing these retention challenges. This analysis employs discrete event simulation to quantify the probable impacts of attrition on the distribution of talent available for service across the Armys officer ranks.

Geographic profiling of criminal groups for military cordon and search

In the course of counter-insurgency campaigns, military forces expend considerable resources and time conducting cordon and search operations in an effort to interdict and suppress criminal groups. However, these operations have a low success rate, with most operations yielding little intelligence or marginal tactical gains while simultaneously angering the local populace. This paper demonstrates methods for improving the success rate of cordon and search operations by leveraging Criminal Site Selection (CSS) models for geographic profiling. This new modeling approach provides statistically significant performance improvements over the current best method for geographic profiling and provides geographic profiles that are often accurate enough to facilitate tactical success, with the modeled criminal groups anchor point falling within the search profile for military unit cordon and search operations.

Methodology for analyzing the compromise of a deployed tactical network

As the Department of Defense transitions to a ubiquitous computing environment, our military operations become increasingly vulnerable to compromise via cyber attacks at echelons as low as the Brigade Combat Team (BCT). There is a need to design a system to facilitate the analysis of a nation states ability to compromise the confidentiality, availability, and integrity of a deployed tactical network. Research demonstrated that, on these networks, compromises due to security protocols violated by humans are much more common than compromises due to technological vulnerabilities. Therefore, this analysis focuses on developing a simulation modeling approach to analyze the effectiveness of security protocols “within the fortress” and to track the damage done by various forms of cyber attacks that have successfully breached the network perimeter. Our network model uses agent-based simulation in order to model the flow of information at the packet level with dictated behavior specific to the agents modeled: individual network packets, computer systems, routers, servers, and files. The advantage to using an agent-based, rather than a discrete-event, simulation model in this situation is that agent-based models focus on the relationship between entities from the bottom-up, such as at the network packet level, rather than the entire system from the top-down. The developed simulation model allows us to simulate various network attacks, observe their interaction with network security protocols, assess the resulting damage in terms of the networks availability, and quantify the damage in terms of sensitive information lost.