USMA Digital Commons (United States Military Academy, West Point)
Not a member yet
1355 research outputs found
Sort by
A Class of Spatially Correlated Self-Exciting Statistical Models
No full textThe statistical modeling of multivariate count data observed on a space–time lattice has generally focused on using a hierarchical modeling approach where space–time correlation structure is placed on a continuous, latent, process. The count distribution is then assumed to be conditionally independent given the latent process. However, in many real-world applications, especially in the modeling of criminal or terrorism data, the conditional independence between the count distributions is inappropriate. In this manuscript we propose a class of models that capture spatial variation and also account for the possibility of data model dependence. The resulting model allows both data model dependence, or self-excitation, as well as spatial dependence in a latent structure. We demonstrate how second-order properties can be used to characterize the spatio-temporal process and how misspecification of error may inflate self-excitation in a model. Finally, we give an algorithm for efficient Bayesian inference for the model demonstrating its use in capturing the spatio-temporal structure of burglaries in Chicago from 2010–2015
Maximizing object detection using sUAS
Get PDFThis paper examines optimal look-angles for a camera which is mounted on a small unmanned aerial system (sUAS), that provides for maximized object detection on the ground. Using a generic convolutional neural network (CNN), this research identifies the best angle for detecting a ground target from an aerial perspective. The study involves altering camera angles on an sUAS that is flown along a fixed trajectory and then determining the angle which provides the highest detection rate of predefined objects, which are emplaced at known locations on the ground. The experiment is conducted in simulation and validated on a physical quadcopter. The results of this paper directly influence the U.S. Army’s research efforts on training neural networks and developing object detection algorithms
Using Virtual Battlespace Classroom Gaming Simulations in the Classroom: Searching for IEDs in Class
No full textExperiential learning is a cyclical, transformative process that involves four components. The learner has concrete experiences, reflects on those experiences, forms new abstractions, and then draws conclusions that can be tested in new situations. The process is continual, and each successive experience can be used to propel new abstractions, in particular when there is previous experience with course content. Advanced General Psychology for Leaders is a core course taken in cadets’ first year of education; it is an advanced course specifically designed for students who have completed prior coursework in psychology, at either the high school or college level. The military has one of the longest histories of using simulations to facilitate learning. The unique missions designed for this exercise are high fidelity, low-threat, and low-cost experiences that expose them to militarily-relevant scenarios where they can see the psychology concepts and theories they learn about in action. Cadets complete three missions in small teams at the simulation center
A Sensitivity Analysis of Poisoning and Evasion Attacks in Network Intrusion Detection System Machine Learning Models
No full textAs the demand for data has increased, we have witnessed a surge in the use of machine learning to help aid industry and government in making sense of massive amounts of data and, subsequently, making predictions and decisions. For the military, this surge has manifested itself in the Internet of Battlefield Things. The pervasive nature of data on today\u27s battlefield will allow machine learning models to increase soldier lethality and survivability. However, machine learning models are predicated upon the assumptions that the data upon which these machine learning models are being trained is truthful and the machine learning models are not compromised. These assumptions surrounding the quality of data and models cannot be the status-quo going forward as attackers establish novel methods to exploit machine learning models for their benefit. These novel attack methods can be described as adversarial machine learning (AML). These attacks allow an attacker to unsuspectingly alter a machine learning model before and after model training in order to degrade a model\u27s ability to detect malicious activity. In this paper, we show how AML, by poisoning data sets and evading well trained models, affect machine learning models\u27 ability to function as Network Intrusion Detection Systems (NIDS). Finally, we highlight why evasion attacks are especially effective in this setting and discuss some of the causes for this degradation of model effectiveness
Mechanistic data-driven prediction of as-built mechanical properties in metal additive manufacturing
No full textMetal additive manufacturing provides remarkable flexibility in geometry and component design, but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties, significantly complicating the materials design process. To this end, we develop a mechanistic data-driven framework integrating wavelet transforms and convolutional neural networks to predict location-dependent mechanical properties over fabricated parts based on process-induced temperature sequences, i.e., thermal histories. The framework enables multiresolution analysis and importance analysis to reveal dominant mechanistic features underlying the additive manufacturing process, such as critical temperature ranges and fundamental thermal frequencies. We systematically compare the developed approach with other machine learning methods. The results demonstrate that the developed approach achieves reasonably good predictive capability using a small amount of noisy experimental data. It provides a concrete foundation for a revolutionary methodology that predicts spatial and temporal evolution of mechanical properties leveraging domain-specific knowledge and cutting-edge machine and deep learning technologies
Silent Tuning: Matching a transmitter to an antenna without emitting a signal
No full textThis work describes a practical alternative for antenna matching by leveraging the relatively recent availability of small, portable vector network analyzers. Unlike traditional antenna analyzers which only measure SWR, these instruments provide an accurate measurement of complex impedance and easily cover the high frequency (HF) range. The antenna described here combines a network analyzer sweep of the antenna impedance with a pre-measured mathematical model of the tuner itself in an optimization process to predicatively tune the antenna. Except for the signal needed by the network analyzer (which is typically less than 1 mW) the tuning process is accomplished with no emission from the antenna before actually communicating (which might, itself, be a frequency hopping scheme). A working system is described for Near Vertical Incident Skywave (NVIS) communications which achieves an standing wave ratio (SWR) of less than 1.2:1 over the frequency range of 1.8 to 8 MHz
The Behavioral Intervention with Technology for E-Weight Loss Study (BITES): Incorporating Energy Balance Models and the Bite Counter into an Online Behavioral Weight Loss Program.
No full textThis study evaluated feasibility and acceptability of adding energy balance modeling displayed on weight graphs combined with a wrist-worn bite counting sensor against a traditional online behavioral weight loss program. Adults with a BMI of 27-45 kg/
Army Officer Corps Science, Technology, Engineering and Mathematics (STEM) Foundation Gaps Place Countering Weapons of Mass Destruction (CWMD) Operations at Risk – Part 1
Get PDFThis is the first of three articles from the authors describing the risk to Joint Operations incurred by an Army that is vulnerable to the STEM challenges faced in a great power competition involving CWMD operations. In this article, we describe the problem. In articles two and three of the series, we will elaborate on the problem utilizing the Joint Publication 3-0 as our guide and recommend solutions to address this gap
A Dual U-Net Algorithm for Automating Feature Extraction from Satellite Imagery
No full textQuick identification of building and roads is critical for execution of tactical US military operations in an urban environment. To this end, a gridded, referenced, satellite images of an objective, often referred to as a gridded reference graphic or GRG, has become a standard product developed during intelligence preparation of the environment. At present, operational units identify key infrastructure by hand through the work of individual intelligence officers. Recent advances in Convolutional Neural Networks, however, allows for this process to be streamlined through the use of object detection algorithms. In this paper, we describe an object detection algorithm designed to quickly identify and label both buildings and road intersections present in an image. Our work leverages both the U-Net architecture as well the SpaceNet data corpus to produce an algorithm that accurately identifies a large breadth of buildings and different types of roads. In addition to predicting buildings and roads, our model numerically labels each building by means of a contour finding algorithm. Most importantly, the dual U-Net model is capable of predicting buildings and roads on a diverse set of test images and using these predictions to produce clean GRGs