Classification method based on Siamese‐like neural network for inter‐species blood Raman spectra similarity measure

Abstract

Analysis of blood species is an extremely important part in customs inspection, forensic investigation, wildlife protection and other fields. In this study, a classification method based on Siamese-like neural network (SNN) for interspecies blood (22 species) was proposed to measure Raman Spectra similarity. The average accuracy was above 99.20% in the test set of spectra (known species) that did not appear in the training set. This model could detect species not represented in the dataset underlying the model. After adding new species to the training set, we can update the training based on the original model without retraining the model from scratch. For species with lower accuracy, SNN model can be trained intensively in the form of enriched training data for that species. A single model can achieve both multiple-classification and binary classification functions. Moreover, SNN showed higher accuracy rates when trained with smaller datasets compared to other methods.

Siamese Networks for Clinically Relevant Bacteria Classification Based on Raman Spectroscopy

“…Additionally, retraining is needed when the reference database or the training set are modified, which induces impractical computational costs., i.e., the addition of a new class or the availability of more training data [ 34 , 40 , 41 ]. To address these limitations, a Siamese network has been proposed, which converts the classification problem into a similarity problem and solves the issue of limited available data for training CNNs [ 42 , 43 , 44 , 45 , 46 , 47 ], where, in many practical cases, only a few spectra are available per substance or class.…”