VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds
Conventional black box machine learning (ML) algorithms for gas-phase species identification from THz frequency region absorption spectra have been reported in the literature. While the robust classification performance of such ML models is promising, the black box nature of these ML tools limits th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/17/8447 |
| _version_ | 1797496482511716352 |
|---|---|
| author | M. Arshad Zahangir Chowdhury Timothy E. Rice Matthew A. Oehlschlaeger |
| author_facet | M. Arshad Zahangir Chowdhury Timothy E. Rice Matthew A. Oehlschlaeger |
| author_sort | M. Arshad Zahangir Chowdhury |
| collection | DOAJ |
| description | Conventional black box machine learning (ML) algorithms for gas-phase species identification from THz frequency region absorption spectra have been reported in the literature. While the robust classification performance of such ML models is promising, the black box nature of these ML tools limits their interpretability and acceptance in application. Here, a one-dimensional convolutional neural network (CNN), VOC-Net, is developed and demonstrated for the classification of absorption spectra for volatile organic compounds (VOCs) in the THz frequency range, specifically from 220 to 330 GHz where prior experimental data is available. VOC-Net is trained and validated against simulated spectra, and also demonstrated and tested against experimental spectra. The performance of VOC-Net is examined by the consideration of confusion matrices and receiver-operator-characteristic (ROC) curves. The model is shown to be 99+% accurate for the classification of simulated spectra and 97% accurate for the classification of noisy experimental spectra. The model’s internal logic is examined using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, which provides a visual and interpretable explanation of the model’s decision making process with respect to the important distinguishing spectral features. |
| first_indexed | 2024-03-10T03:04:17Z |
| format | Article |
| id | doaj.art-01d4efc03a764f3eb914655da05b5f86 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:04:17Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-01d4efc03a764f3eb914655da05b5f862023-11-23T12:39:55ZengMDPI AGApplied Sciences2076-34172022-08-011217844710.3390/app12178447VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic CompoundsM. Arshad Zahangir Chowdhury0Timothy E. Rice1Matthew A. Oehlschlaeger2Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, 110 8th Street, Troy, NY 12180, USADepartment of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, 110 8th Street, Troy, NY 12180, USADepartment of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, 110 8th Street, Troy, NY 12180, USAConventional black box machine learning (ML) algorithms for gas-phase species identification from THz frequency region absorption spectra have been reported in the literature. While the robust classification performance of such ML models is promising, the black box nature of these ML tools limits their interpretability and acceptance in application. Here, a one-dimensional convolutional neural network (CNN), VOC-Net, is developed and demonstrated for the classification of absorption spectra for volatile organic compounds (VOCs) in the THz frequency range, specifically from 220 to 330 GHz where prior experimental data is available. VOC-Net is trained and validated against simulated spectra, and also demonstrated and tested against experimental spectra. The performance of VOC-Net is examined by the consideration of confusion matrices and receiver-operator-characteristic (ROC) curves. The model is shown to be 99+% accurate for the classification of simulated spectra and 97% accurate for the classification of noisy experimental spectra. The model’s internal logic is examined using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, which provides a visual and interpretable explanation of the model’s decision making process with respect to the important distinguishing spectral features.https://www.mdpi.com/2076-3417/12/17/8447VOCDNNCNNclassificationTHzspectroscopy |
| spellingShingle | M. Arshad Zahangir Chowdhury Timothy E. Rice Matthew A. Oehlschlaeger VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds Applied Sciences VOC DNN CNN classification THz spectroscopy |
| title | VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds |
| title_full | VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds |
| title_fullStr | VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds |
| title_full_unstemmed | VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds |
| title_short | VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds |
| title_sort | voc net a deep learning model for the automated classification of rotational thz spectra of volatile organic compounds |
| topic | VOC DNN CNN classification THz spectroscopy |
| url | https://www.mdpi.com/2076-3417/12/17/8447 |
| work_keys_str_mv | AT marshadzahangirchowdhury vocnetadeeplearningmodelfortheautomatedclassificationofrotationalthzspectraofvolatileorganiccompounds AT timothyerice vocnetadeeplearningmodelfortheautomatedclassificationofrotationalthzspectraofvolatileorganiccompounds AT matthewaoehlschlaeger vocnetadeeplearningmodelfortheautomatedclassificationofrotationalthzspectraofvolatileorganiccompounds |