• Home
  • Search
  • Physics-based feature engineering for simultaneous classification of bovine meat type and freshness by bioimpedance spectroscopy
  • https://doi.org/10.1016/j.measurement.2026.121041Copy DOI Icon

Physics-based feature engineering for simultaneous classification of bovine meat type and freshness by bioimpedance spectroscopy

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

• Identifying the type and freshness level of beef where beef is primarily sold in packaged form. • Impedance spectroscopy enables non-invasive meat assessment, existing methods often rely on raw data or complex feature sets, failing to explain the rationale behind their selection or justify their complexity. • A systematic, physics-based feature engineering methodology that can classify muscle type and freshness in bovine meat simultaneously using a single neural network. • Feature selection is primarily based on significant parameter variation measured over a 14-day period, enabling a classification accuracy of up to 91,5% using both neural networks and SVM models. • The evolution of these parameters aligns with biological fundamentals, confirming the relevance of the selected features and underlying physical principles In this paper, we propose a systematic, physics-based feature engineering methodology that can classify muscle type and freshness in bovine meat simultaneously using a single neural network. We identify a minimal, yet highly informative set of features extracted from bioimpedance spectra based on observed spectral behavior and underlying physical principles. Feature selection in this study is primarily based on significant parameter variation measured over a 14-day period, particularly between days 2 or 3 and day 14 for a binary classification of meat in the two classes safe-to-sell and not-safe-to-sell. This variation serves as a strong indicator of sensitivity and contributes to achieving a high classification rate. The key features selected include parameters from the modified Fricke model and characteristic points in the α and β frequency bands (Rex, Rin, C, Im1, Im2 and Im3). We validate the stability of these features and assess the model’s interpretability. Our analysis highlights the consistent relevance of these parameters, enabling a classification accuracy of up to 91,5% using both neural networks and SVM models. The evolution of these parameters aligns with biological fundamentals, confirming the relevance of the selected features.

Similar Papers
  • Research Article

Developed nonlinear model based on bootstrap aggregated neural networks for predicting global hourly scale horizontal irradiance

  • Jun 30, 2023
  • International Journal of Energetica
  • Abdennasser Dahmani +3
  • Conference Article
  • Citations2

Data mining in the diagnostics of oil extraction equipment

  • May 01, 2017
  • K F Tagirova +2
  • Research Article
  • Citations4

A Hybrid Prediction Model for Pumping Well System Efficiency Based on Stacking Integration Strategy

  • Jan 01, 2024
  • International Journal of Energy Research
  • Biao Ma +1
  • Research Article
  • Citations1

Regime-Switched Neural Networks: Flow Stress Modeling Strategy of 310s Stainless Steel During Hot Deformation

  • Jan 01, 2021
  • IEEE Access
  • Jeongho Cho +1
  • PDF
  • Research Article
  • Citations2

Recognition Method of Limb Motor Imagery EEG Signals Based on Integrated Back-propagation Neural Network.

  • Mar 31, 2015
  • The open biomedical engineering journal
  • Mingyang Li +3
  • Research Article
  • Citations2

Prediction of malignancy degree in brain glioma using selective neural networks ensemble

  • Jun 01, 2006
  • Journal of Shanghai University (English Edition)
  • Tian-Yu Liu +2
  • Book Chapter
  • Citations7

Pre-Processing And Feature Extraction

  • Nov 23, 1995
  • Christopher M Bishop
  • Research Article
  • Citations2

Classification of Heart Disease Using MFO Based Neural Network on MRI Images.

  • Sep 01, 2021
  • Current Medical Imaging Formerly Current Medical Imaging Reviews
  • Kalaivani K +2
  • Conference Article
  • Citations2

Engineering Design of Neural Network Architectures for Estimation of Inter-Well Connectivity and Production Performance

  • Jan 01, 2020
  • ECMOR XVII
  • J Yu +2
  • Research Article

GLEm-Net: Unified framework for data reduction with categorical and numerical features

  • Feb 01, 2026
  • Knowledge-Based Systems
  • Francesco De Santis +2
  • Conference Article
  • Citations12

Why are neural networks sometimes much more accurate than decision trees: an analysis on a bio-informatics problem

  • Nov 10, 2003
  • L.O Hall +3
  • Research Article
  • Citations52

Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

  • Jan 01, 2020
  • IEEE Access
  • Yibo Xu +2
  • Research Article
  • Citations109

Improved on-line process fault diagnosis through information fusion in multiple neural networks

  • Dec 20, 2005
  • Computers & Chemical Engineering
  • Jie Zhang
  • Research Article
  • Citations40

Neural network modelling of adsorption isotherms

  • Nov 04, 2010
  • Adsorption
  • Graham Morse +3
  • Research Article
  • Citations25

Dynamical analysis and vibration estimation of a flexible plate with enhanced active constrained layer damping treatment by combinatorial neural networks of surrogates

  • Jan 17, 2023
  • Aerospace Science and Technology
  • Weizhi Tao +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.