Browsing by Subject "electronic warfare"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Electronic warfare asset allocation with human-swarm interaction
    (2018-05) Boler, William M.; Christopher, Lauren; King, Brian; Salama, Paul
    Finding the optimal placement of receiving assets among transmitting targets in a three-dimensional (3D) space is a complex and dynamic problem that is solved in this work. The placement of assets in R^6 to optimize the best coverage of transmitting targets requires the placement in 3D-spatiality, center frequency assignment, and antenna azimuth and elevation orientation, with respect to power coverage at the receiver without overloading the feed-horn, maintaining suficient power sensitivity levels, and maintaining terrain constraints. Further complexities result from the human-user having necessary and time-constrained knowledge to real-world conditions unknown to the problem space, such as enemy positions or special targets, resulting in the requirement of the user to interact with the solution convergence in some fashion. Particle Swarm Optimization (PSO) approaches this problem with accurate and rapid approximation to the electronic warfare asset allocation problem (EWAAP) with near-real-time solution convergence using a linear combination of weighted components for tness comparison and particles representative of asset con- gurations. Finally, optimizing the weights for the tness function requires the use of unsupervised machine learning techniques to reduce the complexity of assigning a tness function using a Meta-PSO. The result of this work implements a more realistic asset allocation problem with directional antenna and complex terrain constraints that is able to converge on a solution on average in 488.7167+-15.6580 ms and has a standard deviation of 15.3901 for asset positions across solutions.
  • Thumbnail Image
    Item
    Human Fitness Functions
    (IEEE, 2015-09) Christopher, Lauren; Reynolds, Joshua; Crespo, Jonah; Eberhart, Russ; Shaffer, Patrick; Department of Electrical and Computer Engineering, School of Engineering and Technology
    "Be careful what you measure" is a management adage that applies to Particle Swarm Optimization (PSO) and is especially important with Humans in the Swarm. PSO has been applied to the autonomous asset management problem in electronic warfare where the speed provides fast optimization of frequency allocations for receivers and jammers in highly complex and dynamic environments in our previous work. In this optimization problem, one key part of the fitness is adapted by the human: the 2D (and future 3D) battlefield environment. This paper explores the use of the human in the fitness function, adapting to the battlefield conditions as the PSO is acting. Two aspects of dynamic human influence will be discussed: Simple geometric zones and pheromone influenced zones.
  • Thumbnail Image
    Item
    Using computational swarm intelligence for real-time asset allocation
    (IEEE, 2015-05) Reynolds, Joshua; Christopher, Lauren; Eberhart, Russ; Shaffer, Patrick; Department of Electrical and Computer Engineering, Purdue School of Engineering and Technology
    Particle Swarm Optimization (PSO) is especially useful for rapid optimization of problems involving multiple objectives and constraints in dynamic environments. It regularly and substantially outperforms other algorithms in benchmark tests. This paper describes research leading to the application of PSO to the autonomous asset management problem in electronic warfare. The PSO speed provides fast optimization of frequency allocations for receivers and jammers in highly complex and dynamic environments. The key contribution is the simultaneous optimization of the frequency allocations, signal priority, signal strength, and the spatial locations of the assets. The fitness function takes into account the assets' locations in 2 and 3 dimensions maximizing their spatial distribution while maintaining allocations based on signal priority and power. The fast speed of the optimization enables rapid responses to changing conditions in these complex signal environments, which can have real-time battlefield impact. Initial results optimizing receiver frequencies and locations in 2 dimensions have been successful. Current run-times are between 300 (3 receivers, 30 transmitters) and 1000 (7 receivers, 30 transmitters) milliseconds on a single-threaded x86 based PC. Statistical and qualitative tests indicate the swarm has viable solutions, and finds the global optimum 99% of the time on a test case. The results of the research on the PSO parameters and fitness function for this problem is demonstrated.