SBIR-STTR Award

Metrological differences between tactical sensors result in a wide range of accuracy, completeness, and correctness of features used for object classification. Thus, it is typical practice for Subject Matter Experts (SMEs) to develop the required reference libraries so that they are tailored to each tactical sensor type and, in some cases, sensing environments. The process of developing this tailored library is often called coloring the reference library. The SMEs objective is to optimize the classification performance (w.r.t. some metric(s)) using a feature-based classifier. The proposed Hierarchical Emitter Library Optimization (HELO) technology mimics the coloring process in order to generate an Emitter Library that optimizes the classifier performance while avoiding the need for a labor-intensive manual process that requires SME knowledge. HELO employs a general Hierarchical Evolutionary Programming (H-EP) based upon the Genetic Programming (GP) optimization paradigm to achieve this optimization. This approach provides a computationally scalable process that rigorously quantifies the performance of the classification algorithms without knowledge of its algorithms. Using the performance assessment of the classifier, a large set of potential emitter libraries (population) is iteratively refined (evolved) until an optimal (or sufficiently good) emitter library is generated. The solution is hierarchical because the evolution of the population is achieved jointly in two stages: (1) evolution of the coloring functions to generate a parameter library for a particular parameter type and (2) evolution of the set of parameters used by the classifier.

Benefit:
This H-EP approach is beneficial because it generically applies to the optimization of any feature-based classifier that relies on a reference library for feature correlation. This is accomplished by employing a fitness function that assesses the performance of the classifier against candidate reference libraries without knowledge of the classifier algorithm(s). This black box approach means that the H-EP approach can be quickly adapted to a wide range of classification problem domains. In addition, the H-EP avoids the need to have SME operators develop the reference libraries and allows for repeatable/comparable optimization results across users with varying levels of expertise.

Keywords:
metrology, metrology, Genetic Programming, Electronic Order of Battle, Operational Shipboard Electromagnetic Environment, Electronic warfare libraries, Electronic Intelligence (ELINT), Electronic Warfare, Situational Awareness

The proposed Hierarchical Evolutionary Programming (H-EP) technology focuses on improving threat classification and electronic warfare battle management using the Genetic Programming (GP) optimization paradigm. The applications of the technology include: (1) on-shore emitter reference library optimization for classification performance, (2) forward deployed near real-time emitter reference library optimization for rapid adaptability, and (3) coordination of spectrum use and electronic attack tactics across multiple platforms. Leveraging the Hierarchical Emitter Library Optimization (HELO) prototype from Phase I, the Phase II program seeks to mature this technology, demonstrate its operational utility as a forward deployed capability, and illustrate improved effectiveness in both offensive and defensive electronic warfare operations. Using Lakotas Genetic Programming framework, each of these optimization problems can be solved by defining appropriate hierarchical hypotheses, fitness functions, and evolution operators. Once implemented, Lakotas GP analysis and test framework provides a formal methodology for selecting the most appropriate GP implementation and runtime parameters to solve the optimization problem within the desired time and with the desired accuracy.

Benefit:
This Phase I prototyped H-EP approach is beneficial because it generically applies to the optimization of any feature-based classifier that relies on a reference library for feature correlation. This is accomplished by employing a fitness function that assesses the performance of the classifier against candidate reference libraries without knowledge of the classifier algorithm(s). This black box approach means that the H-EP approach can be quickly adapted to a wide range of classification problem domains. In addition, the H-EP avoids the need to have SME operators develop the reference libraries and allows for repeatable/comparable optimization results across users with varying levels of expertise. The Phase II benefits extend beyond on-shore emitter library optimization to include near real-time emitter library optimization onboard tactical platforms using current environmental/weather information as well as intelligence reports. This forward deployment of the technology enables emitter classification optimization: (1) tailored to forecasted weather conditions and (2) adapting to threats via intelligence reports in theatre. Both of these capabilities allow for more rapid adaptation to the threat environment in a matter of hours rather than months, which improves survivability as well as electronic warfare operational success. Under the Phase II Option, the benefits of the evolutionary programming framework extend to: (1) different sensor suites with varying capabilities and performance, (2) spectrum management for effective joint operations, and (3) electronic attack tactic selection for defensive and offensive postures. The benefits of the proposed work under the Phase II Option include the ability to improve emitter classification and electronic attack tactics in a multi-platform joint environment with varying electronic warfare capabilities, resources, and performance characteristics. By applying optimization techniques to this problem space, joint operations can increase effectiveness for mission such as Integrated Air Defense (IAD) suppression and battle group force protection.

Keywords:
Operational Shipboard Electromagnetic Environment, Electronic Attack, BATTLE MANAGEMENT, Genetic Programming, Electronic Warfare, Situational Awareness, Electronic Intelligence (ELINT), Electronic Order of Battle