Rapid beef quality detection using spectra pre‐processing methods in electrical impedance spectroscopy and machine learning

Abstract

SummaryThe fraudulent practice of beef adulteration is a growing concern, as it violates consumer rights. Electrical impedance spectroscopy (EIS) combined with machine learning has emerged as a widely used approach to identify low‐quality meat. Unlike traditional biochemical methods that require expensive instruments, complex sample preparation, and chemical reagents, EIS is a cost‐effective alternative. However, EIS data are susceptible to temperature fluctuations, requiring a waiting period under consistent temperature conditions for data stabilisation before measurements. This process becomes impractical when dealing with a large number of samples. To overcome this limitation, standardisation, normalisation, and smoothing methods were introduced in the meat quality detection based on EIS data. A recognition model for detecting carrageenan adulteration in beef was established. Under an inconsistent temperature condition, by applying the spectra pre‐processing methods to the prediction dataset, the model accuracy reached 84%, whereas the accuracy of the unprocessed prediction dataset dropped to 54%. This study demonstrates that acquiring EIS data under consistent temperature conditions is unnecessary if proper spectra pre‐processing methods are applied. By eliminating the waiting time for data stabilisation, this practical approach enhances the efficiency and accuracy of meat quality detection.

Real‐time quantitative detection of hydrocolloid adulteration in meat based on Swin Transformer and smartphone

“…The experimental setup involved using an inductance, capacitance, and resistance (LCR) meter (TH2816A, Tonghui, Changzhou, China), a custom 3D printed test platform with a square base and a sample holder with probe holes, as well as a cooling incubator (LRH-150, Bluepard, Shanghai, China), as described in the literature by Qiu et al (2024). Two copper probes were inserted into the beef samples to a depth of 1 cm, spaced 1.5 cm apart.…”

“…Due to carrageenan being the most widely used hydrocolloid in meat products (Bartlová et al, 2021), this study selected carrageenan as the experimental subject to explore the feasibility of smartphone-based computer vision for quantitatively detecting hydrocolloid adulteration. Previous studies on meat quality assessment often categorized meat into high quality and low quality (Qiu et al, 2024;Yulianti et al, 2016), or further subdivided it into categories such as premium, average, and poor (Díaz et al, 2005;Monroy et al, 2010). However, in order to achieve quantitative analysis, a multi-classification approach is needed that can distinguish subtle differences.…”

“…To enhance the practicality of the experiment, this study further classified images of beef with carrageenan adulteration and beef with composite hydrocolloids adulteration. The combination of electrochemical impedance spectroscopy (EIS) and machine learning has been widely used for meat quality assessment due to its non-destructive testing, rapid analysis, and lower cost (Afonso et al, 2020;Damez et al, 2008;Qiu et al, 2024). In order to evaluate the performance and validate the effectiveness of the computer vision model, the EIS experiment was also conducted and compared in this study.…”