Journal
MICROCHEMICAL JOURNAL
Volume 157, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.microc.2020.105020
Keywords
Frozen pork; Total volatile basic nitrogen; Random frog partial least squares; Near-infrared spectroscopy; Chemometrics
Categories
Funding
- National Key Research and Development Program of China [2017YFC1600801]
- Natural Science Foundation of Jiangsu Province [BK20190100]
- Project of Faculty of Agricultural Equipment of Jiangsu University
Ask authors/readers for more resources
Quality of frozen pork is gained attractive attention around the world for its significance in international trade and national strategic reserves. This work proposed to explore the feasibility of predicting total volatile basic nitrogen (TVB-N) content in frozen pork samples without thawing using a developed portable near-infrared (NIR) spectroscopy. Various preprocessing techniques and variable selection algorithms have been applied to build the prediction model. Based on the final result achieved better performance was noted by using 2nd derivate as a preprocessing technique and efficient spectra variable selection algorithms. Variable selection algorithm random frog partial least squares (RF-PLS) showed the best prediction model of TVB-N content in frozen pork samples; with 0.9669 of coefficient of determination for the independent samples in prediction set. This study demonstrated that the fast, non-destructive, non-invasive, and accurate approach portable NIR spectroscopy could be successfully utilized for monitoring the quality of frozen pork coupled variable selection algorithms.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available