Machine Learning for Raman Spectroscopy-based Cyber-Marine Fish Biochemical Composition Analysis
Preprint
Abstract
The rapid and accurate detection of biochemical compositions in fish is a crucial real-world task that facilitates optimal utilization and extraction of high-value products in the seafood industry. Raman spectroscopy provides a promising solution for quickly and non-destructively analyzing the biochemical composition of fish by associating Raman spectra with biochemical reference data using machine learning regression models. This paper investigates different regression models to address this task and proposes a new design of Convolutional Neural Networks (CNNs) for jointly predicting water, protein, and lipids yield. To the best of our knowledge, we are the first to conduct a successful study employing CNNs to analyze the biochemical composition of fish based on a very small Raman spectroscopic dataset. Our approach combines a tailored CNN architecture with the comprehensive data preparation procedure, effectively mitigating the challenges posed by extreme data scarcity. The results demonstrate that our CNN can significantly outperform two state-of-the-art CNN models and multiple traditional machine learning models, paving the way for accurate and automated analysis of fish biochemical composition.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- RaT: Raman Transformer for highly accurate melanoma detection with critical features visualizationSpectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023
- Extensive evaluation of machine learning models and data preprocessings for Raman modeling in bioprocessingJournal of Raman Spectroscopy, 2022
- A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classification tasksChemometrics and Intelligent Laboratory Systems, 2022
- Machine learning prediction of lignin content in poplar with Raman spectroscopyBioresource Technology, 2022
- Multi-output 1-dimensional convolutional neural networks for simultaneous prediction of different traits of fruit based on near-infrared spectroscopyPostharvest Biology and Technology, 2022
- The employment of analytical techniques and chemometrics for authentication of fish oils: A reviewFood Control, 2021
- Deep learning for vibrational spectral analysis: Recent progress and a practical guideAnalytica Chimica Acta, 2019
- Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibrationChemometrics and Intelligent Laboratory Systems, 2018
- Chemical Composition of Fish and Fishery Products2015
- Applications of non-destructive spectroscopic techniques for fish quality and safety evaluation and inspectionTrends in Food Science & Technology, 2013