Shortwave infrared hyperspectral imaging system coupled with multivariable method for TVB-N measurement in pork

Authors: BAEK, INSUCK - Orise Fellow; LEE, HOONSOO - Chungbuk National University; CHO, BYOUNG-KWAN - Chungnam National University; MO, CHANGYEUN - Kangwon National University; Chan, Diane; Kim, Moon

Submitted to: Food Control
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/24/2020
Publication Date: 12/29/2020
Citation: Baek, I., Lee, H., Cho, B., Mo, C., Chan, D.E., Kim, M.S. 2020. Shortwave infrared hyperspectral imaging system coupled with multivariable method for TVB-N measurement in pork. Food Control. 124, 107854. https://doi.org/10.1016/j.foodcont.2020.107854.
DOI: https://doi.org/10.1016/j.foodcont.2020.107854

Interpretive Summary: Monitoring meat freshness is important to ensuring food safety for meat products during processing and distribution. Traditional sensory evaluation of meat based on tactile examination and visual and olfactory observations is subjective and slow. Although conventional microbiological and technological methods can be more accurate, these time-consuming and sample-destructive procedures are also unsuitable for high-volume food monitoring. Because total volatile basic nitrogen (TVB-N) content can be used as a reference indicator for pork freshness, this study investigated the use of a hyperspectral short-wave infrared imaging with multiple modeling techniques to nondestructively predict TVB-N content in fresh pork samples that were held in refrigerated storage from one to twenty-one days. The results of the prediction models showed high correlation between predicted and measured TVB-N levels, demonstrating that the methods may be feasible for rapid and nondestructive evaluation of pork freshness in automated, high-volume meat processing operations.

Technical Abstract: Monitoring and maintaining the freshness of meat is important to ensuring a supply of meat that is safe for consumption. The purpose of this study is to present a short-wave infrared (SWIR) hyperspectral imaging system in combination with partial least-squares regression (PLSR) model and feature selection methods that were used for the prediction of the total volatile basic nitrogen (TVB-N) content in fresh pork samples stored between 1 and 21 days in refrigeration. The SWIR hyperspectral reflectance images were acquired for pork samples removed from refrigerated storage after 1, 4, 8, 11, 15, and 21 days. The hyperspectral SWIR images and actual TVB-N contents were used for constructing the PLSR model. PLSR models were optimized by using feature selection strategies such as random frog (RF) and variable importance in projection (VIP) score. The predictions from the optimal RF-PLSR model value with maximum normalization preprocessing exhibited correlation coefficient values for R_c^2 and R_p^2 of 0.94 and 0.90, respectively. Moreover, this research showed that visualization of TVB-N levels applied to the optimal model based on selected wavebands provide an intuitive way to interpret the spatial information of the sample. This study revealed that the multivariate models developed here for rapid and nondestructive evaluation of pork freshness may be feasible for use in online inspection systems as an effective substitute for traditional methods to evaluate pork freshness.