skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

Abstract

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splitting of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this papermore » is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.« less

Authors:
 [1];  [1];  [1];  [1];  [1]
  1. Montana State Univ., Bozeman, MT (United States)
Publication Date:
Research Org.:
Montana State Univ., Bozeman, MT (United States)
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1409671
Grant/Contract Number:
FC26-05NT42587
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Additional Journal Information:
Journal Volume: 10; Journal Issue: 9; Journal ID: ISSN 1939-1404
Publisher:
IEEE
Country of Publication:
United States
Language:
English
Subject:
58 GEOSCIENCES; histograms; vegetation mapping; training; hyperspectral imaging; data models; sensors; agriculture; biophysics; clustering methods; remote sensing

Citation Formats

McCann, Cooper, Repasky, Kevin S., Morin, Mikindra, Lawrence, Rick L., and Powell, Scott. Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data. United States: N. p., 2017. Web. doi:10.1109/JSTARS.2017.2701360.
McCann, Cooper, Repasky, Kevin S., Morin, Mikindra, Lawrence, Rick L., & Powell, Scott. Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data. United States. doi:10.1109/JSTARS.2017.2701360.
McCann, Cooper, Repasky, Kevin S., Morin, Mikindra, Lawrence, Rick L., and Powell, Scott. Tue . "Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data". United States. doi:10.1109/JSTARS.2017.2701360. https://www.osti.gov/servlets/purl/1409671.
@article{osti_1409671,
title = {Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data},
author = {McCann, Cooper and Repasky, Kevin S. and Morin, Mikindra and Lawrence, Rick L. and Powell, Scott},
abstractNote = {Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splitting of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.},
doi = {10.1109/JSTARS.2017.2701360},
journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
number = 9,
volume = 10,
place = {United States},
year = {Tue May 23 00:00:00 EDT 2017},
month = {Tue May 23 00:00:00 EDT 2017}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:
  • Purpose: To evaluate the severity of genitourinary (GU) toxicity in high-dose-rate (HDR) brachytherapy combined with hypofractionated external beam radiotherapy (EBRT) for prostate cancer and to explore factors that might affect the severity of GU toxicity. Methods and Materials: A total of 100 Japanese men with prostate cancer underwent {sup 192}Ir HDR brachytherapy combined with hypofractionated EBRT. Mean (SD) dose to 90% of the planning target volume was 6.3 (0.7) Gy per fraction of HDR. After 5 fractions of HDR treatment, EBRT with 10 fractions of 3 Gy was administrated. The urethral volume receiving 1-15 Gy per fraction in HDR brachytherapymore » (V1-V15) and the dose to at least 5-100% of urethral volume in HDR brachytherapy (D5-D100) were compared between patients with Grade 3 toxicity and those with Grade 0-2 toxicity. Prostate volume, patient age, and International Prostate Symptom Score were also compared between the two groups. Results: Of the 100 patients, 6 displayed Grade 3 acute GU toxicity, and 12 displayed Grade 3 late GU toxicity. Regarding acute GU toxicity, values of V1, V2, V3, and V4 were significantly higher in patients with Grade 3 toxicity than in those with Grade 0-2 toxicity. Regarding late GU toxicity, values of D70, D80, V12, and V13 were significantly higher in patients with Grade 3 toxicity than in those with Grade 0-2 toxicity. Conclusions: The severity of GU toxicity in HDR brachytherapy combined with hypofractionated EBRT for prostate cancer was relatively high. The volume of prostatic urethra was associated with grade of acute GU toxicity, and urethral dose was associated with grade of late GU toxicity.« less
  • Using the k-means cluster analysis algorithm, we carry out an unsupervised classification of all galaxy spectra in the seventh and final Sloan Digital Sky Survey data release (SDSS/DR7). Except for the shift to rest-frame wavelengths and the normalization to the g-band flux, no manipulation is applied to the original spectra. The algorithm guarantees that galaxies with similar spectra belong to the same class. We find that 99% of the galaxies can be assigned to only 17 major classes, with 11 additional minor classes including the remaining 1%. The classification is not unique since many galaxies appear in between classes; however,more » our rendering of the algorithm overcomes this weakness with a tool to identify borderline galaxies. Each class is characterized by a template spectrum, which is the average of all the spectra of the galaxies in the class. These low-noise template spectra vary smoothly and continuously along a sequence labeled from 0 to 27, from the reddest class to the bluest class. Our Automatic Spectroscopic K-means-based (ASK) classification separates galaxies in colors, with classes characteristic of the red sequence, the blue cloud, as well as the green valley. When red sequence galaxies and green valley galaxies present emission lines, they are characteristic of active galactic nucleus activity. Blue galaxy classes have emission lines corresponding to star formation regions. We find the expected correlation between spectroscopic class and Hubble type, but this relationship exhibits a high intrinsic scatter. Several potential uses of the ASK classification are identified and sketched, including fast determination of physical properties by interpolation, classes as templates in redshift determinations, and target selection in follow-up works (we find classes of Seyfert galaxies, green valley galaxies, as well as a significant number of outliers). The ASK classification is publicly accessible through various Web sites.« less
  • Cited by 2
  • A novel series of ionic liquids have been synthesized with a new methodology. The essence of this methodology is to form the cations of ionic liquids through the complexation reactions of neutral organic ligands with metal ions, followed by the subsequent metathesis reactions of the resulting salts with anion donors. We chose N-lithiotrifluoromethanesulfonimide (Li{sup +} Tf{sub 2}N{sup -}) as a candidate for anion donors because Tf{sub 2}N{sup -} anions have high thermal stabilities and weakly coordinating properties, which are crucial to the generation of less viscous and more hydrophobic ionic liquids. The transition-metal ions chosen in our investigation are Ag{supmore » +} and Zn{sup 2+}. The uses of these ionic liquids as the new electrolytes for electrodeposition have been demonstrated.« less
  • The possible contribution by natural hydrocarbon emissions to the total ozone budget recorded in the tidewater region of southeastern Virginia during the height of the summer period was examined. Natural sources investigated were limited to the primary HC emitters and most prevalent natural vegetation, the forests. Three forest types and their areal coverage were determine for Region VI of the Virgina State Air Pollution Control Board using remotely sensed data from Landsat, a NASA experimental earth resources satellite. Emission factors appropriate to the specific types (coniferous 0.24 x 10/sup 13/, mixed 0.63 x 10/sup 13/, deciduous 1.92 x 10/sup 13/more » ..mu..g/h), derived from contemporary procedures, were applied to produce an overall regional emission rate of 2.79 x 10/sup 13/ ..mu..g/h for natural non-methane hydrocarbons (NMHC). This rate was used with estimates of the anthropogenic NO/sub x/ and NMHC loading, as input into a photochemical box model. Additional HC loading on the order of that estimated to be produced by the natural forest communities was required in order to reach certain measured summer peak ozone levels as the computer simulation was unable to account for these measured episodic levels on the basis of the anthropogenic inventory alone.« less