AFIT neural network research

A brief summary of research done at the Air Force Institute of Technology (AFIT) in the area of neural networks is provided. It has been shown that backpropagation, used for feedforward artificial neural networks, is just a degenerate version of an extended Kalman filter, and that networks can do about as well as the optimum statistical classification technique. A method of finding the importance of features for use by a neural network classifier has been determined. Techniques for using neural networks for image segmentation have been developed. In optical pattern recognition, techniques that allow the processing of real FLIR (forward-looking infrared) images with existing binary spatial light modulators have been devised. An optical direction of arrival detector applicable to laser illumination direction determination has been designed and tested; the design is similar to a fly's eye. Coated mirrors for the optical confocal Fabry-Perot interferometer have been designed, specified, fabricated, and installed. Significant progress has been made in the use of neural networks for processing multiple-feature sets for speech recognition     

A wavelet multiresolution analysis for spatio-temporal signals

The wavelet filters of the conventional 3D multiresolution analysis possess homogeneous spatial and temporal frequency characteristics which limits one's ability to match filter frequency characteristics to signal frequency behavior. Also, the conventional 3D multiresolution analysis employs an oct-tree decomposition structure which restricts the analysis of signal details to identical resolutions in space and time. This paper presents a 3D wavelet multiresolution analysis constructed from nonhomogeneous spatial and temporal filters, and an orthogonal sub-band coding scheme that decouples the spatial and temporal decomposition processes     

The finite element analysis of shells of revolution with a branching meridian

We present an algorithm for calculating the shells of revolution with the branching meridian using the triangular finite elements, the rigidity matrices of which are formed based on the vector method of displacement interpolation [1]. The correct kinematic and static conditions of shell conjugation on the line of their coupling have been developed. The shell structure consisting of a cylinder and adjacent shells is calculated under various conditions of support.     

Spiral evolution applied to legacy avionics systems

The US Department of Defense (DoD), through the Office of the Secretary of Defense (OSD), has determined that evolutionary acquisition is their strategy of choice for future software-intensive systems, and that the spiral development model (SDM) is the preferred method/process for software-intensive development life cycles. Electronic Systems Command (ESC) at Hanscom AFB, Massachusetts, has written a draft handbook on the use of Spiral Development for all future Command and Control (C2) systems, including reference to the DoD 5000 series and Air Force Program Directive 63-1, Acquisition System, which deploys this OSD mandate for future C2 systems. Barry Boehm's continued work on SDM which he conceived in the 1980s, is heavily biased toward development of new systems that are software-intensive, as noted in a workshop he gave at the Software Engineering Institute (SEI) in 2000.     

Automotive-grade MEMS sensors used for general aviation

The attitude heading reference system (AHRS) provides data for primary flight instruments, head-up displays, autopilots, and moving map navigation systems. Advances in solid-state MEMS rate sensors, coupled with Kalman filter algorithms designed to mitigate high drift rates, provide the basis for low-cost, high-performance AHRS for general aviation. This paper describes the performance of a low cost, miniaturized AHRS using automotive-grade MEMS sensors. The performance of the system is detailed. The implications for certification of this class of system and fault tolerance are discussed.     

Optimal number of phased array faces and signal processors for horizon surveillance

The problem of the optimal number of phased array faces for performing 360/spl deg/ horizon surveillance is considered. Assuming the detection performance is the same in all beam positions and the total number of T/R modules is constant, it is shown that the optimal number of array faces is three. This is true whether the arrays are operating simultaneously or sequentially. A parametric analysis is performed between the number of array faces operating simultaneously and the associated cost of simultaneous operation in terms of the size of the array.     

SETI education programs in Australia

This paper discusses and evaluates two innovative SETI education programs conducted at the University of Western Sydney, viz: the SETI Pathways Program and the Life in the Universe Curriculum Project.     

Distributed decision fusion using empirical estimation

The problem of optimal data fusion in multiple detection systems is studied in the case where training examples are available, but no a priori information is available about the probability distributions of errors committed by the individual detectors. Earlier solutions to this problem require some knowledge of the error distributions of the detectors, for example, either in a parametric form or in a closed analytical form. Here we show that, given a sufficiently large training sample, an optimal fusion rule can be implemented with an arbitrary level of confidence. We first consider the classical cases of Bayesian rule and Neyman-Pearson test for a system of independent detectors. Then we show a general result that any test function with a suitable Lipschitz property can be implemented with arbitrary precision, based on a training sample whose size is a function of the Lipschitz constant, number of parameters, and empirical measures. The general case subsumes the cases of nonindependent and correlated detectors.     

An experiment with an S-band radar using pulse compression andrange sidelobe suppression for meteorological measurements

A major technology barrier to the application of pulse compression for the meteorological functions required by a next generation ATC radar is range/time sidelobes which mask and corrupt observations of weak phenomena occurring near areas of strong extended meteorological scatterers. Techniques for suppressing range sidelobes are well known but without prior knowledge of the scattering medium's velocity distribution their performance degrades rapidly in the presence of Doppler. Recent investigations have presented a “doppler tolerant” range sidelobe suppression technique. The thrust of the work described herein is the extension of previous simulations to actual transmitted dispersed/coded waveforms using the S-band surveillance radar located at Rome Laboratory Surveillance Facility. The objectives of the experiment are: 1) to extend the verification of the simulation of the Doppler tolerant technique; and 2) to demonstrate that the radar transmitter, waveform generator, and receiver imperfections do not significantly degrade resolution, performance or reliability of meteorological spectral moment estimates