Development of Crime Scene Intelligence Using a Hand-Held Raman Spectrometer and Transfer Learning

Abstract

The classification of ignitable liquids, such as gasoline, is critical crime scene intelligence to assist arson investigations. Rapid field gasoline classification is challenging because the current forensic testing standard requires gas chromatography–mass spectrometry analysis of evidence in an accredited laboratory. In this work, we reported a new intelligent analytical platform for field identification and classification of gasoline evidence. A hand-held Raman spectrometer was utilized to collect Raman spectra of reference gasoline samples with various octane numbers. The Raman spectrum pattern was converted into image presentations by continuous wavelet transformation (CWT) to facilitate artificial intelligence development using the transfer learning technique. GoogLeNet, a pretrained convolutional neural network (CNN), was adapted to train the classification model. Six different classification models were also developed from the same data set using conventional machine learning algorithms to evaluate the performance of our new approach. The experimental results indicated that the pretrained CNN model developed by our new data workflow outperformed other models in several performance benchmarks, such as accuracy, precision, recall, F1, Cohen’s Kappa, and Matthews correlation coefficient. When the transfer learning model was challenged with the data collected from weathered gasoline samples, the classifier could still offer 73 and 53% accuracy for 50 and 25% weathered gasoline samples, respectively. In conclusion, wavelet transforms combined with transfer learning successfully processed and classified complex Raman spectral data without feature engineering. We envision that this nondestructive, automated, and accurate platform will accelerate crime scene intelligence development based on evidence’s chemical signatures detected by hand-held Raman spectrometers.

Deeply-recursive convolutional neural network for Raman spectra identification

“… 12 Huang et al also used a transfer learning method based on a GoogLeNet model for the field identification and classification of gasoline evidence. 13 Ho et al applied CNN-based deep learning approaches to accurately identify 30 common bacterial pathogens. 14 Deng et al proposed a method that can learn multi-scale features using the automatic combination of multi-receptive fields of convolutional layers.…”

A novel polynomial reconstruction algorithm‐based 1D convolutional neural network used for transfer learning in Raman spectroscopy application

“…[ 12 ] Huang's group applied continuous wavelet transformation to convert Raman spectra into images and then introduced GoogLeNet to discriminate the converted images through transfer learning. [ 29 ] However, in both of above works, the number of calibration data in training set was no less than twice that in test set. In this study, it is found that the 1D‐CNN performed better than KNN when using only 75% calibration data for retraining, which is a fresh contribution of this study.…”

Raman spectrum matching with contrastive representation learning

“…Identification of unknown substances is critical in many fields such as food product quality control, 1 pharmaceutical drug characterization, 2 forensic investigation, 3 and bacterial detection. 4 Raman spectroscopy is often used in these applications 2–4 as a low-cost, non-invasive technique. Raman spectroscopy provides a chemical fingerprint by using scattered light to probe the vibrational modes of a sample.…”