Comparison of optimization algorithms for piecewise linear discriminant analysis: application to Fourier transform infrared remote sensing measurements

Shaffer, Ronald E.; Small, Gary W.

doi:10.1016/0003-2670(96)00204-8

Cited by 12 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PLDA method 5,6,[9][10][11][12][13][14]28 was then applied to the training patterns to compute the classifier. This is a mathematical technique used to form multiple linear boundaries or surfaces called discriminants within the data space.…”

Section: Resultsmentioning

confidence: 99%

“…With these data, classifiers can be developed that enable the analyst to identify the presence of target species within an image. Piecewise linear discriminant analysis [9][10][11][12][13][14] (PLDA) is used to generate classifiers based on training sets composed of simulated analyte-active data and randomly picked analyte-inactive measurements from background images. These classifiers are subsequently tested with field-collected imaging data with either ethanol or methanol as the target analyte.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simulated Radiance Profiles for Automating the Interpretation of Airborne Passive Multi-Spectral Infrared Images

Sulub

Small

2008

Appl Spectrosc

Self Cite

View full text Add to dashboard Cite

Methodology is developed for simulating the radiance profiles acquired from airborne passive multispectral infrared imaging measurements of ground sources of volatile organic compounds (VOCs). The simulation model allows the superposition of pure-component laboratory spectra of VOCs onto spectral backgrounds that simulate those acquired during field measurements conducted with a downward-looking infrared line scanner mounted on an aircraft flying at an altitude of 2000-3000 ft (approximately 600-900 m). Wavelength selectivity in the line scanner is accomplished through the use of a multichannel Hg:Cd:Te detector with up to 16 integrated optical filters. These filters allow the detection of absorption and emission signatures of VOCs superimposed on the upwelling infrared background radiance within the instrumental field of view (FOV). By combining simulated radiance profiles containing analyte signatures with field-collected background signatures, supervised pattern recognition methods can be employed to train automated classifiers for use in detecting the signatures of VOCs during field measurements. The targeted application for this methodology is the use of the imaging system to detect releases of VOCs during emergency response scenarios. In the work described here, the simulation model is combined with piecewise linear discriminant analysis to build automated classifiers for detecting ethanol and methanol. Field data collected during controlled releases of ethanol, as well as during a methanol release from an industrial facility, are used to evaluate the methodology.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Simulated Radiance Profiles for Automating the Interpretation of Airborne Passive Multi-Spectral Infrared Images

Sulub

Small

2008

Appl Spectrosc

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fifty interferogram s were collected for each of these three con gurations. This procedure was repeated at each step as the blackbody temperature was lowered to 45,40,35,30,29,28,27,26,25,24,23,22,21,20,15,10, and 5 8C. The data collection was then completed by raising the temperature to two nal settings of either 25.5/50, 18/32, 18/31, 24.5/25.5, or 18/50 8C.…”

Section: Methodsmentioning

confidence: 99%

Multiple Filtering Strategy for the Automated Detection of Ethanol by Passive Fourier Transform Infrared Spectrometry

et al. 2001

Self Cite

View full text Add to dashboard Cite

Digital filtering methods are evaluated for use in the automated detection of ethanol from passive Fourier transform infrared (FT-IR) data collected during laboratory and open-air remote sensing experiments. In applications in which analyte signals are overwhelmed by the overlapping signals of an interference, the use of multiple digital filters is observed to improve the sensitivity of the analyte detection. The detection strategy is based on the application of bandpass digital filters to short segments of the interferogram data collected by the FT-IR spectrometer. To implement the automated detection of a target analyte, the filtered interferogram segments are supplied as input to piecewise linear discriminant analysis. Through the use of a set of training data, discriminants are computed that can subsequently be applied to detect the presence of the analyte in an automated manner. This research focuses on the detection of ethanol vapor in the presence of an ammonia interference. A two-filter detection strategy based on the use of separate ethanol and ammonia filters is compared to an approach based on a single ethanol filter. Bandpass parameters of the digital filters and the interferogram segment location are optimized through the use of laboratory data in which ethanol and ammonia vapors are generated in a gas cell and viewed against various infrared background radiances. The filter and segment parameters obtained through this optimization are subsequently tested with field remote sensing data collected when the spectrometer is allowed to view ethanol and ammonia plumes generated from a heated stack. The two-filter strategy is found to outperform the single-filter approach with both the laboratory and field data in situations in which the ammonia interference dominates the ethanol signature.

show abstract

“…In the work described here, the patterns in the active data class are generated synthetically from the modulation of a single laboratory-collected spectrum. [44][45][46][47][48] These spectra are then overlaid with backgrounds collected from a broad range of locations around the nation, in order to simulate any theoretical scenario the ASPECT program may encounter from high to low intensity sources. This collection of synthetic active spectra is supplemented by a second set of inactive spectra drawn from a separate pool of backgrounds collected from multiple vetted locations.…”

Section: Referencesmentioning

confidence: 99%

“…Once computed, the classification model is applicable to other sets of data processed in the same fashion, assuming the target analyte remains the same. [44][45][46][47][48] The specifics of the implementation of PLDA for the thesis work will be described section 3.4.…”

Section: Introductionmentioning

confidence: 99%

Signal processing and pattern recognition methods for the remote, airborne detection of radioisotopes by gamma-ray spectroscopy

Dess¹

View full text Add to dashboard Cite

Comparison of optimization algorithms for piecewise linear discriminant analysis: application to Fourier transform infrared remote sensing measurements

Cited by 12 publications

References 38 publications

Simulated Radiance Profiles for Automating the Interpretation of Airborne Passive Multi-Spectral Infrared Images

Simulated Radiance Profiles for Automating the Interpretation of Airborne Passive Multi-Spectral Infrared Images

Multiple Filtering Strategy for the Automated Detection of Ethanol by Passive Fourier Transform Infrared Spectrometry

Signal processing and pattern recognition methods for the remote, airborne detection of radioisotopes by gamma-ray spectroscopy

Contact Info

Product

Resources

About