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     

TerraSAR-X active radar ground calibrator system

In April 2006, the TerraSAR-X satellite was launched. This paper describes the development of a novel and highly integrated, digitally-controlled active SAR system calibrator (DARC). It consists of both an active transponder path for absolute radiometric calibration and a calibrated receiver chain for antenna pattern evaluation of the satellite antenna. A total of 16 active transponder and receiver systems and 17 receiver-only systems will be fabricated for a calibration campaign in 2006.     

Microdosimetric measurements of heavy ion tracks.

The biological effectiveness of radiations depends on the spatial pattern of ionizations and excitations produced by the charged particle tracks involved. Ionizations produced by both the primary ion and by energetic delta rays may contribute to the production of biologically relevant damage and to the concentration of damage which may effect the probability of repair. Although average energy concentration (dose) can be calculated using homogeneous track models, the energy is actually concentrated in small volumes containing segments of the ion and delta ray tracks. These local concentrations are studied experimentally using low pressure proportional counters, and theoretically, using Monte Carlo methods. Small volumes near an ion track may be traversed by a delta ray. If they are, the energy deposited will be similar to that produced by a single electron track in a low-energy x-ray irradiation. The probability of a delta ray interaction occurring decreases with the square of the radial distance from the track. The average energy deposited is the product of this probability and the energy deposited in an interaction. Average energy deposited calculated from measured interaction probability is in good agreement with the results of homogeneous track models.     

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     

Monte Carlo transport model comparison with 1A GeV accelerated iron experiment: heavy-ion shielding evaluation of NASA space flight-crew foodstuff.

Deep-space manned flight as a reality depends on a viable solution to the radiation problem. Both acute and chronic radiation health threats are known to exist, with solar particle events as an example of the former and galactic cosmic rays (GCR) of the latter. In this experiment Iron ions of 1A GeV are used to simulate GCR and to determine the secondary radiation field created as the GCR-like particles interact with a thick target. A NASA prepared food pantry locker was subjected to the iron beam and the secondary fluence recorded. A modified version of the Monte Carlo heavy ion transport code developed by Zeitlin at LBNL is compared with experimental fluence. The foodstuff is modeled as mixed nuts as defined by the 71st edition of the Chemical Rubber Company (CRC) Handbook of Physics and Chemistry. The results indicate a good agreement between the experimental data and the model. The agreement between model and experiment is determined using a linear fit to ordered pairs of data. The intercept is forced to zero. The slope fit is 0.825 and the R2 value is 0.429 over the resolved fluence region. The removal of an outlier, Z=14, gives values of 0.888 and 0.705 for slope and R2 respectively.     

Field formation around negatively biased solar arrays in the LEO-plasma

Heavy emission caused by impacting plasma ions results in a fast discharging effect of the initially large surface potentials on the dielectric solar cells. This eventually counteracts the energization process of the plasma ions to the cover glasses and leaves no significant electric fields. Thus, with an existing thermal plasma, electrons are again able to reach dielectric surfaces. Strong localized electric fields of the order of several 10 kV/cm form near the interconnector-cover glass interface.     

A bioreactor system for the nitrogen loop in a Controlled Ecological Life Support System.

As space missions become longer in duration, the need to recycle waste into useful compounds rises dramatically. This problem can be addressed by the development of Controlled Ecological Life Support Systems (CELSS) (i.e., Engineered Closed/Controlled Eco-Systems (ECCES)), consisting of human and plant modules. One of the waste streams leaving the human module is urine. In addition to the reclamation of water from urine, recovery of the nitrogen is important because it is an essential nutrient for the plant module. A 3-step biological process for the recycling of nitrogenous waste (urea) is proposed. A packed-bed bioreactor system for this purpose was modeled, and the issues of reaction step segregation, reactor type and volume, support particle size, and pressure drop were addressed. Based on minimization of volume, a bioreactor system consisting of a plug flow immobilized urease reactor, a completely mixed flow immobilized cell reactor to convert ammonia to nitrite, and a plug flow immobilized cell reactor to produce nitrate from nitrite is recommended. It is apparent that this 3-step bioprocess meets the requirements for space applications.     

Dose equivalent, absorbed dose and charge spectrum investigation in low Earth orbit.

Particle intensity, dose equivalent and absorbed dose have been measured on board the space shuttle Endeavour during STS-108 in December 2001 by Dublin Institute for Advanced Studies (DIAS). The dose estimates are based on very accurate measurements of recoils produced in CR-39 by cosmic ray primary and secondary protons and heavier nuclei and by secondary neutrons. The corresponding LET spectra were used to determine dose equivalent and absorbed dose values. Estimates of the total flux of Z > or = 2 nuclei have been undertaken and a preliminary charge spectrum was measured. Some comparisons are made with preliminary data obtained on STS-105 (ISS Expedition) and other missions using CR-39 detectors.     

New instrumentation for optical measuring of oxygen in gas or dissolved in liquids.

The optical oxygen sensor is a novel device for the determination of oxygen in gases or dissolved in liquids. It is based on the measurement principle of fluorescence quenching, which is completely different from that of polarographic oxygen sensors (today the most widespread devices of oxygen detection). The new instrument offers features and advantages, which render it not only a realistic alternative, but, for specific applications, make it superior to existing electrochemical methods. The system is based on low-cost semiconductor devices (light-emitting diodes, photodiodes, low-cost analogue and digital components) and new LED-compatible oxygen-sensitive membranes. The flow cell of the instrument may be thermostatted and the sensor can be calibrated by a simple two-point calibration procedure. The optical oxygen sensor is particularly suitable for measuring dissolved oxygen in respirometry, since no oxygen is consumed by the device and the signal is independent of sample flowrate or stirring speed. Typical fields of application are monitoring of oxygen in ground and drinking water, in process control in bioreactors and in breath gas and blood gas analysis.