Abstract

Achieving high classification accuracy on trace chemical residues in active spectroscopic sensing is challenging due to the limited amount of training data available to the classifier. Such classifiers often rely on physics-based models for generating training data though these models are not always accurate when compared to measured data. To overcome this challenge, we developed a physics-guided neural network (PGNN) for predicting chemical reflectance for a set of parameterized inputs that is more accurate than the state-of-the-art physics-based signature model for chemical residues. After training the PGNN, we use it to generate a library of predicted spectra for training a classifier. We compare the classification accuracy when using this PGNN library versus a library generated by the physics-based model. Using the PGNN, the average classification accuracy increases from 0.623 to 0.813 on real chemical reflectance data, including data from chemicals not included in the PGNN training set.

© 2021 Optical Society of America

Full Article  |  PDF Article
More Like This
Neural network pattern recognition of thermal-signature spectra for chemical defense

Arthur H. Carrieri and Pascal I. Lim
Appl. Opt. 34(15) 2623-2635 (1995)

Using an artificial neural network to predict the residual stress induced by laser shock processing

Jiajun Wu, Xuejun Liu, Hongchao Qiao, Yongjie Zhao, Xianliang Hu, Yuqi Yang, and Jibin Zhao
Appl. Opt. 60(11) 3114-3121 (2021)

Pattern recognition in distributed fiber-optic acoustic sensor using an intensity and phase stacked convolutional neural network with data augmentation

Huan Wu, Bin Zhou, Kun Zhu, Chao Shang, Hwa-Yaw Tam, and Chao Lu
Opt. Express 29(3) 3269-3283 (2021)

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Data Availability

Data underlying the results presented in this paper are not publicly available at this time.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Figures (3)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Tables (3)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Equations (3)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription