Interpreting convolutional neural network for real-time volatile organic compounds detection and classification using optical emission spectroscopy of plasma

Wang, Ching‐Yu; Ko, T. S.; Hsu, Cheng–Che

doi:10.1016/j.aca.2021.338822

Cited by 30 publications

(16 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grad-CAM extracts the feature maps of the last convolutional layer of the model, calculates the average gradient in each feature, and multiplies the gradient multipliers with the corresponding feature maps to obtain the Grad-CAM heat map. 27…”

Section: Spectrum Data Analysis Methods and Indicatorsmentioning

confidence: 99%

Determination of soil source using laser induced breakdown spectroscopy combined with feature selection

Ding,

Shu,

et al. 2023

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

Section: Spectrum Data Analysis Methods and Indicatorsmentioning

confidence: 99%

Determination of soil source using laser induced breakdown spectroscopy combined with feature selection

Ding,

Shu,

et al. 2023

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

“…In [27] authors applied linear multivariate analysis to interpret development cognitive neuroscience spectroscopy data. Direct visualization of gradient-weighted class activation mapping of Convolutional Neural Network was developed in [75] to interpret detection of volatile organic compounds.…”

Section: Related Workmentioning

confidence: 99%

Explainable Predictive Modeling for Limited Spectral Data

Akulich¹,

Anahideh²,

Sheyyab³

et al. 2022

Preprint

View full text Add to dashboard Cite

Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction between matter and electromagnetic radiation, particularly holds a lot of information in a single sample. Since acquiring such high-dimensional data is a complex task, it is crucial to exploit the best analytical tools to extract necessary information. In this paper, we investigate the most commonly used feature selection techniques and introduce applying recent explainable AI techniques to interpret the prediction outcomes of high-dimensional and limited spectral data. Interpretation of the prediction outcome is beneficial for the domain experts as it ensures the transparency and faithfulness of the ML models to the domain knowledge. Due to the instrument resolution limitations, pinpointing important regions of the spectroscopy data creates a pathway to optimize the data collection process through the miniaturization of the spectrometer device. Reducing the device size and power and therefore cost is a requirement for the real-world deployment of such a sensor-to-prediction system as a whole. Furthermore, we consider a wide range of machine learning models that have been proven to be successful for the prediction of the Cetane Number of fuels. We specifically design three different scenarios to ensure that the evaluation of ML models is robust for the real-time practice of the developed methodologies and to uncover the hidden effect of noise sources on the final outcome. The evaluation is performed for both the full model and reduced models using different feature selection techniques on a real dataset. Finally, we propose a correctness metric for the feature selection techniques to assess the conformance of the selected subset

show abstract

“…Furthermore, an explainability technique based on Gradient-Weighted Class Activation Mapping (Grad-CAM) 26 was applied to identify class-discriminative Raman peaks associated with the observed responses. Applied to spectral data, Grad-CAM utilizes the gradients of the CNN classification score with respect to the last convolutional layer's output and the final output feature maps to calculate the relative classification importance of each wavenumber in a given input spectrum; 22,[27][28][29] the results are plotted as heatmaps superimposed on the input spectrum, highlighting the most critical Raman peaks to the CNN for correctly classifying the input. Our Grad-CAM maps displayed distinct patterns of discriminative Raman peaks for the different cell lines.…”

Section: Introductionmentioning

confidence: 99%

Stratification of tumour cell radiation response and metabolic signatures visualization with Raman spectroscopy and explainable convolutional neural network

Fuentes,

Milligan,

Wiebe

et al. 2024

Analyst

View full text Add to dashboard Cite

show abstract

Interpreting convolutional neural network for real-time volatile organic compounds detection and classification using optical emission spectroscopy of plasma

Cited by 30 publications

References 55 publications

Determination of soil source using laser induced breakdown spectroscopy combined with feature selection

Determination of soil source using laser induced breakdown spectroscopy combined with feature selection

Explainable Predictive Modeling for Limited Spectral Data

Stratification of tumour cell radiation response and metabolic signatures visualization with Raman spectroscopy and explainable convolutional neural network

Contact Info

Product

Resources

About