Library-Based Raman Spectral Identification Using Multi-Input Hybrid ResNet.

Raman spectroscopy is widely used for its exceptional identification capabilities in various fields. Traditional methods for target identification using Raman spectroscopy rely on signal correlation with moving windows, requiring data preprocessing that can significantly impact identification performance. In recent years, deep-learning approaches have been proposed to leverage data augmentation techniques, such as baseline and additive noise addition, in order to overcome data scarcity. However, these deep-learning methods are limited to the spectra encountered during training and struggle to handle unseen spectra. To address these limitations, we propose a multi-input hybrid deep-learning model trained with simulated spectral data. By employing simulated spectra, our method tackles the challenges of data scarcity and the handling of unseen spectra encountered in traditional and deep-learning methods. Experimental results demonstrate that our proposed method achieves outstanding identification performance and effectively handles spectra obtained from different Raman spectroscopy systems.

Baseline correction using a deep-learning model combining ResNet and UNet.

Most spectral data, such as those obtained via infrared, Raman, and mass spectroscopy, have baseline drifts due to fluorescence or other reasons, which have an adverse impact on subsequent analyses. Therefore, several researchers have proposed the use of various baseline-correction methods to address the aforementioned issue. However, most baseline-correction methods require manual adjustment of the parameters to achieve desirable performance. In this study, we propose a baseline-correction method based on a deep-learning model that combines ResNet and UNet. The method uses a deep-learning model trained with simulated spectral data to perform baseline corrections and eliminates the need for manual parameter adjustments. Based on the results of the qualitative and quantitative analyses of the simulated spectral data and actual Raman spectra, the proposed method is easier to apply and has better performance compared to the existing methods. As the proposed method can be applied to Raman spectra and other spectra, it is expected to be widely used.

Adaptive Hit-Quality Index for Raman Spectrum Identification.

The recognition capability of the identification system using Raman spectroscopy is increasing with the demands in the field. Among the various approaches that determine the identity of a target, signal correlation using a moving window is one of the most effective and intuitive methods. In this paper, we report a new correlation method that is robust to spectral intensity variations. Using the peak distribution of a given spectrum, this method adaptively determines meaningful spectral regions for the identification target. Three commercial Raman spectrometer and a 14 033 library were included in the study, which was used for a library-based chemical discrimination test and mixed material analysis experiments. According to the identification experimental results, the proposed method correctly identified all of the spectra and maintained a mean correlation score above 0.95 while maintaining the correlation score of nontarget materials as low as possible.

Raman spectrum identification based on the correlation score using the weighted segmental hit quality index.

In this paper, we consider a novel method for identification of Raman spectra recorded on different instruments with different wavelengths. Since the conventional hit quality index (HQI) is vulnerable to intensity variation, it needs intensity calibration or standardization for each spectrometer, which causes additional time consuming work. To simplify this process and enhance the identification performance, we propose a new scoring method which is defined as the weighted sum of the HQIs from segmented spectra by windowing. To show the effectiveness of the proposed method, the experiments were carried out with 10 kinds of chemicals with their spectra recorded on 3 different instruments with different laser wavelengths. According to the identification results with 14 033 chemicals, the proposed method identified all test chemicals without error, which indicates that the proposed method could be used as a promising alternative to the existing methods.

Baseline correction using asymmetrically reweighted penalized least squares smoothing.

Baseline correction methods based on penalized least squares are successfully applied to various spectral analyses. The methods change the weights iteratively by estimating a baseline. If a signal is below a previously fitted baseline, large weight is given. On the other hand, no weight or small weight is given when a signal is above a fitted baseline as it could be assumed to be a part of the peak. As noise is distributed above the baseline as well as below the baseline, however, it is desirable to give the same or similar weights in either case. For the purpose, we propose a new weighting scheme based on the generalized logistic function. The proposed method estimates the noise level iteratively and adjusts the weights correspondingly. According to the experimental results with simulated spectra and measured Raman spectra, the proposed method outperforms the existing methods for baseline correction and peak height estimation.

Ultrasensitive trace analysis for 2,4,6-trinitrotoluene using nano-dumbbell surface-enhanced Raman scattering hot spots.

We report an ultra-sensitive surface-enhanced Raman scattering (SERS)-based detection system for 2,4,6-trinitrotoluene (TNT) using nano-dumbbell structures formed by the electrostatic interaction between positively and negatively charged gold nanoparticles. First, Meisenheimer complexes were produced between TNT and l-cysteine on gold substrates, and 4-mercaptopyridine (4-MPY) labeled gold nanoparticles (positively charged) were allowed to interact with the Meisenheimer complexes through the electrostatic interaction between the negatively charged aromatic ring of the complex molecules and the positively charged nanoparticles. Then, negatively charged gold nanoparticles were added in order to form nano-dumbbells. As a result, many hot junctions were generated by the dumbbell structures, and the SERS signals were greatly enhanced. Our experimental results demonstrate that the SERS-based assay system using nano-dumbbells provides an ultra-sensitive approach for the detection of TNT explosives. It also shows strong potential for broad application in detecting various explosive materials used for military purposes.