Rapid quantitative analysis of adulterated rice with partial least squares regression using hyperspectral imaging system

Guo, Lianbo; Yu, Yunxin; Yu, Hanyue; Tang, Yun; Li, Jun; Du, Yu; Chu, Yanwu; Ma, Shixiang; Ma, Yuyang; Zeng, Xiaoyan

doi:10.1002/jsfa.9824

Cited by 28 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first derivative transforms can eliminate the influence of the constant spectral baseline offset. However, it is necessary to refine the raw spectra because the derivative is sensitive to noise . The effects of dispersion were removed, and the confounding effects of the baseline shift were reduced using SNV+ first derivative.…”

Section: Methodsmentioning

confidence: 99%

Detection and identification of fungal growth on freeze‐dried Agaricus bisporus using spectra and olfactory sensors

Wang

Pei

et al. 2020

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUND Fungal contamination in food products leads to mustiness, biochemical changes, and undesirable odors, which result in lower food quality and lower market value. To develop a rapid method for detecting fungi, hyperspectral imaging (HSI) was applied to identify five fungi inoculated on plates (Aspergillus niger, Aspergillus flavus, Penicillium chrysogenum, Aspergillus fumigatus, and Aspergillus ochraceus). Near‐infrared (NIR) spectroscopy, mid‐infrared (MIR) spectroscopy, and an electronic nose (E‐nose) were applied to detect and identify freeze‐dried Agaricus bisporus infected with the five fungi. RESULTS Partial least squares regression (PLSR) models were used to distinguish the HSI spectra of the five fungi on the plates. The A. ochraceus group had the highest calibration performance: coefficient of calibration (Rc2) = 0.786, root mean‐square error of calibration (RMSEC) = 0.125 log CFU g−1. The A. flavus group had the highest prediction performance: coefficient of prediction (Rp2) = 0.821, root mean‐square error of prediction (RMSEP) = 0.083 log CFU g−1. The ratio of performance deviation (RPD) values of all of the models was higher than 2.0 for the NIR, MIR, and E‐nose results for freeze‐dried A. bisporus infected with different fungi. The fungal species and degree of infection can be distinguished by principal component analysis (PCA) and partial least squares discriminant analysis (PLS‐DA) using NIR, MIR, and E‐nose, as the discrimination accuracy was more than 90%. The NIR methods had a higher recognition rate than the MIR and E‐nose methods. CONCLUSION Principal component analysis (PCA) and PLSR models based on full spectra of HSI can achieve good discrimination results for these five fungi on plates. Moreover, NIR, MIR, and the E‐nose were proven to be effective in monitoring fungal contamination on freeze‐dried A. bisporus. However, NIR could be a more accurate method. © 2020 Society of Chemical Industry

show abstract

Section: Methodsmentioning

confidence: 99%

Detection and identification of fungal growth on freeze‐dried Agaricus bisporus using spectra and olfactory sensors

Wang

Pei

et al. 2020

J Sci Food Agric

View full text Add to dashboard Cite

show abstract

“…Hyperspectral imaging (HSI) which employs spectroscopy and vision analysis synergistically to mine information from both the spectral and spatial domain of specimens satisfies the need as a vital tool for nondestructive food quality monitoring (Guo et al., 2019). The ability to extract meaningful information from the entire surface of a sample and present maps of attributes loci makes HSI the most suitable tool for studying PSPs in the current case than NIR.…”

Section: Introductionmentioning

confidence: 99%

Quantitative analysis and visualization of moisture and anthocyanins content in purple sweet potato by Vis–NIR hyperspectral imaging

Tian

Aheto

Bai

et al. 2020

J. Food Process. Preserv.

View full text Add to dashboard Cite

Total anthocyanin (TA) and moisture content (MC) are critical indexes of processed purple sweet potatoes (PSPs). The current study examined the feasibility of hyperspectral imaging to investigate how MC and TA contents of PSPs change during processing under two different drying methods namely convective hot‐air drying (CHD) and microwave drying (MD). Models based on spectral data and the integration of spectral and one or three gray‐level co‐occurrence matrix features were established with partial least square regression. The best prediction outcome based on Spectra + HOMOGENEITY + CONTRAST + ENTROPY combinations were (Rp2 = 0.862, 0.847; RMSEP = 0.079, 0.303), respectively, for MC and TA for the CHD samples. Similarly, for the MD samples, the best prediction outcomes were (Rp2 = 0.867, 0.859; RMSEP = 0.088, 0.241), respectively, for MC and TA. Image algorithms were also developed to generate distribution of MC and TA in some representative samples. Practical applications Anthocyanins have been reported as having the potential to lower blood pressure, improve eyesight, reduce cancer cell multiplication, impede tumor formation, and prevent diabetes. Studies have, however, shown that cooking modes including boiling, baking, and steaming decreased the contents of anthocyanins. This study assessed the impact of convective hot‐air and microwave drying (MD) process of purple sweet potato (PSP) on total anthocyanin (TA) content as a function of moisture loss. Hyperspectral Imaging (HSI) was useful in estimating not only the contents of TA and moisture, but also in generating a visual map of their distribution pattern in the processed PSPs. The TA content of PSPs processed by MD was higher than that by convective hot‐air drying, but the distribution uniformity of TA in microwave dried PSPs was worse than that in convective hot‐air dried samples. Finally, to guarantee consistency in drying processes of food products, the HSI could be used to obtain visual images of their chemical parameters.

show abstract

“…As the HSI technology does not require sample preparation and scans a large number of samples simultaneously, it is capable of meeting the demand for non‐destructive and rapid detection in mass production and processing. The HSI technology has been implemented successfully to assess grain and seed quality, such as contaminant detection in wheat, quantitative analysis of adulterated rice, viability measurement of corn and soybean seeds, and estimation of fusarium‐damaged kernels in hard wheat . As far as we know, the use of HSI to identify heat damage, especially in combination with waveband selection methods, has not been studied.…”

Section: Introductionmentioning

confidence: 99%

Identification of heat damage in imported soybeans based on hyperspectral imaging technology

Liu

Wang

et al. 2020

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUND: Imported soybeans are prone to heat damage due to high storage temperatures or poor ventilation during transportation. Heat damage directly degrades the quality of the produce and greatly reduces the edible value of soybeans. Rapid and nondestructive techniques for assessing the quality of imported soybeans are in demand. Hyperspectral imaging (HSI) technology was used to distinguish sound soybeans from heat-damaged soybeans.RESULTS: For testing the effectiveness of preprocessing methods in enhancing model performance, five different preprocessing methods were implemented to original spectra. To solve problems related to accuracy, efficiency, and model interpretability caused by high-dimensional HSI data, three waveband selection algorithmsdependency measure (DM-NRS), mutual information (MI-NRS) and variable precision (VP-NRS)based on neighborhood rough set (NRS) theory were proposed to identify the waveband subsets with optimal distinguishing ability. The effectiveness of preprocessing methods and waveband selection algorithms was validated by establishing two kinds of models: extreme learning machine (ELM) and random forest (RF) models. In addition to the classification accuracy, the robustness of the waveband selection algorithms was studied. The results demonstrated that the Savitzky-Golay (SG) smoothing preprocessing method combined with the MI-NRS waveband selection algorithm and the ELM classifier achieved the best classification and robustness results. Classification accuracy reached 99.98% when using only two optimal wavebands, and reached 100% when using more than four optimal wavebands. CONCLUSION: The results prove that the HSI technology is an accurate, effective, and nondestructive technique for classifying sound and heat-damaged soybeans. PRELIMINARIESThe NRS theory Rough set theory 27 is a mathematical method to research imprecise or incomplete information. The classical rough set model only www.soci.org Y Liu et al.wileyonlinelibrary.com/jsfa

show abstract

Rapid quantitative analysis of adulterated rice with partial least squares regression using hyperspectral imaging system

Cited by 28 publications

References 26 publications

Detection and identification of fungal growth on freeze‐dried Agaricus bisporus using spectra and olfactory sensors

Detection and identification of fungal growth on freeze‐dried Agaricus bisporus using spectra and olfactory sensors

Quantitative analysis and visualization of moisture and anthocyanins content in purple sweet potato by Vis–NIR hyperspectral imaging

Identification of heat damage in imported soybeans based on hyperspectral imaging technology

Contact Info

Product

Resources

About