Abstract

Artificial neural network systems were built for detecting amino acids, sugars, and other solid organic matter by pattern recognition of their polarized light scattering signatures in the form of a Mueller matrix. Backward-error propagation and adaptive gradient descent methods perform network training. The product of the training is a weight matrix that, when applied as a filter, discerns the presence of the analytes on the basis of their cued susceptive Mueller matrix difference elements. This filter function can be implemented as a software or a hardware module to a future differential absorption Mueller matrix spectrometer.

© 1999 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. A. H. Carrieri, P. I. Lim, “Neural network pattern recognition of thermal-signature spectra for chemical defense,” Appl. Opt. 34, 2623–2635 (1995).
    [CrossRef] [PubMed]
  2. S. M. Haugland, E. Z. Bahar, A. H. Carrieri, “Identification of contaminant coatings over rough surfaces using polarized infrared scattering,” Appl. Opt. 19, 3847–3852 (1992).
    [CrossRef]
  3. A. H. Carrieri, J. R. Bottiger, D. J. Owens, E. S. Roese, “Differential absorption Mueller matrix spectroscopy and the infrared detection of crystalline organics,” Appl. Opt. 37, 6550–6557 (1998).
    [CrossRef]
  4. P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
    [CrossRef]
  5. D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
    [CrossRef]
  6. NeuralWorks Predict: Complete Solution for Neural Data Modeling (Technical Publications Group, NeuralWare, Inc., Pittsburgh, Pa., 1995).
  7. INNTS Neural Network Training Solutions, Development Solutions Manual and User’s Guide (Intel Corporation, Santa Clara, Calif., 1992).

1998 (1)

1996 (1)

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

1995 (1)

1992 (1)

S. M. Haugland, E. Z. Bahar, A. H. Carrieri, “Identification of contaminant coatings over rough surfaces using polarized infrared scattering,” Appl. Opt. 19, 3847–3852 (1992).
[CrossRef]

Bahar, E. Z.

S. M. Haugland, E. Z. Bahar, A. H. Carrieri, “Identification of contaminant coatings over rough surfaces using polarized infrared scattering,” Appl. Opt. 19, 3847–3852 (1992).
[CrossRef]

Bottiger, J. R.

Buydens, L.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Cammann, K.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Carrieri, A. H.

Feldhoff, R.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Hashem, S.

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Haugland, S. M.

S. M. Haugland, E. Z. Bahar, A. H. Carrieri, “Identification of contaminant coatings over rough surfaces using polarized infrared scattering,” Appl. Opt. 19, 3847–3852 (1992).
[CrossRef]

Huth-Fehre, T.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Kangas, L. J.

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Kantimm, T.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Keller, P. E.

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Kouzes, R. T.

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Lim, P. I.

Linden, L. H.

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Owens, D. J.

Roese, E. S.

van den Broek, W.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Wienke, D.

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Appl. Opt. (3)

Chemom. Intell. Lab. Syst. (1)

D. Wienke, W. van den Broek, L. Buydens, T. Huth-Fehre, R. Feldhoff, T. Kantimm, K. Cammann, “Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP),” Chemom. Intell. Lab. Syst. 32, 165–176 (1996).
[CrossRef]

Other (3)

NeuralWorks Predict: Complete Solution for Neural Data Modeling (Technical Publications Group, NeuralWare, Inc., Pittsburgh, Pa., 1995).

INNTS Neural Network Training Solutions, Development Solutions Manual and User’s Guide (Intel Corporation, Santa Clara, Calif., 1992).

P. E. Keller, L. J. Kangas, L. H. Linden, S. Hashem, R. T. Kouzes, “Electronic noses and their applications,” in Proceedings of the IEEE Technical Applications Conference at Northcon ’95: Neural Network Application Studies Workshop (IEEE Press, Piscataway, N.J., 1995), pp. 116–119.
[CrossRef]

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (2)

Fig. 1
Fig. 1

Scaled and distributed differential Mueller matrix elements most susceptive to two stereoisomers of tartaric acid in backscattering on and off its molecular vibration resonance band plotted in Mueller matrix space. For graphical brevity, only the three most significant differential elements of levorotary tartaric acid (five were measured) are plotted.

Fig. 2
Fig. 2

Flowchart of the DIAMMS data processing hardware unit. Characteristics of sensor preprocessing; including acquisition of scattergrams, data processing; including Mueller matrix element conversions, neural network pattern recognition, and data postprocessing; including decision-making and transmission of reports, are shown.

Tables (3)

Tables Icon

Table 1 Mueller Matrix Detection of Isomers of Tartaric Acid by Neural Network Pattern Recognitiona

Tables Icon

Table 2 Neural Network Transform Functions Built from a Database of 16 Biosimulants in the Format of Table 1, a

Tables Icon

Table 3 Neural Network Model Performancea

Equations (2)

Equations on this page are rendered with MathJax. Learn more.

Δ M ¯ ij λ o ,   λ r ,   α = 90.00 ° 1 + SD × DIST ,
Δ M ¯ ij λ o ,   λ r ,   α = [ Δ M ij λ o ,   λ r ,   α - Δ M ¯ ij λ o ,   λ r ,   α ] / 4 × SD ,

Metrics