Detection of moisture content in salted sea cucumbers by hyperspectral and low field nuclear magnetic resonance based on deep learning network framework

Zeng, Fanyi; Shao, Weidong; Kang, Jiaming; Yang, Jianhong; Zhang, Xu; Liu, Yang

doi:10.1016/j.foodres.2022.111174

Cited by 8 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each sample was placed on a stepper motor displacement stage for scanning, and the entire acquisition system was performed in a dark box. Generally, the presence of a dark current or uneven distribution of light intensity and other influencing factors would result in a noise effect on HSI (Zeng et al., 2022). Thus, the original spectral image acquired should be corrected for black and white, and the corrected image is obtained according to the following equation.…”

Section: Methodsmentioning

confidence: 99%

“…It enables one to quickly and accurately analyze and interpret the spectral characteristics of objects and generate visualization results (Ma et al., 2019; Wang et al., 2020). Numerous studies have indicated that the technology for detecting chemical composition by using HSI is relatively mature (Dong et al., 2023; Zeng et al., 2022; Zhang et al., 2021). HSI is widely used for quality evaluation in meats including pork fat and protein (Zuo et al., 2023), beef alanine (Dong, Bi et al., 2022), and lamb palmitic acid and oleic acid (Wang et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of comprehensive PAH index in roasted Tan lamb by two‐dimensional correlation spectroscopy combined with hyperspectral imaging

Chen,

Wang

2024

Journal of Food Science

View full text Add to dashboard Cite

Thermally processed meat may contain harmful compounds, including polycyclic aromatic hydrocarbons (PAHs). This study constructed, for the first time, the comprehensive PAH index (CPI) concentration (phenanthrene [26.47%], acenaphthene [21.83%], pyrene [18.64%], fluoranthene [17.11%], fluorene [8.49%], and anthracene [7.46%]). A visible near‐infrared (Vis–NIR) hyperspectral image (HSI) system was employed to detect CPI in 150 roasted Tan lamb samples. Furthermore, two‐dimensional correlation spectra were used to identify spectral features and reveal the order of chemical bond changes under the characteristic peaks at 579–737–631–449 nm. The results indicated that competitive adaptive reweighted sampling–multiple linear regression quantitative prediction model worked the best with calibration set coefficient of determination of 0.9161, calibration set coefficient of root mean square error of 2.3426 µg/kg, R‐squared prediction of 0.8469, and root mean square error of prediction of 2.4119 µg/kg. Finally, PAH content distributions were visualized using the best prediction model. This study aimed to propose a feasible method for CPI in roasted Tan lamb detection based on Vis–NIR HSI coupled with multivariate analysis methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessment of comprehensive PAH index in roasted Tan lamb by two‐dimensional correlation spectroscopy combined with hyperspectral imaging

Chen,

Wang

2024

Journal of Food Science

View full text Add to dashboard Cite

show abstract

“…As a result, these models have become more robust, economical and accessible. 16 Recently a new technology based on computer vision science has been prevailing in different domains of science, and even is successful in quality evaluation of agricultural produce. 17 The computer vision (CV) science using image classification based on a 2D-CNN algorithm has been used in a limited way in the determination of food authentication based on geographical origin, botanical origin, process parameter control etc.…”

Section: Introductionmentioning

confidence: 99%

AI and CV based 2D-CNN algorithm: botanical authentication of Indian honey

Brar,

Aggarwal,

Nanda

et al. 2024

Sustainable Food Technol.

View full text Add to dashboard Cite

show abstract

“…Furthermore, Zhou et al (2023) predicted lead content in oilseed rape leaves by combining fluorescence HSI with DL techniques (Zhou et al, 2023). In another study, Zeng et al (2022) merged HSI and low-field nuclear magnetic resonance with DL to rapidly and nondestructively detect moisture content in salted sea cucumbers (Zeng et al, 2022). Additionally, Soni et al (2021) quantified Clostridium sporogenes spores in food using HSI and compared the performance of 1DCNN and random forest models.…”

Section: Introductionmentioning

confidence: 99%

Non-destructive prediction of isoflavone and starch by hyperspectral imaging and deep learning in Puerariae Thomsonii Radix

Hu,

Wang,

Wei

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Accurate assessment of isoflavone and starch content in Puerariae Thomsonii Radix (PTR) is crucial for ensuring its quality. However, conventional measurement methods often suffer from time-consuming and labor-intensive procedures. In this study, we propose an innovative and efficient approach that harnesses hyperspectral imaging (HSI) technology and deep learning (DL) to predict the content of isoflavones (puerarin, puerarin apioside, daidzin, daidzein) and starch in PTR. Specifically, we develop a one-dimensional convolutional neural network (1DCNN) model and compare its predictive performance with traditional methods, including partial least squares regression (PLSR), support vector regression (SVR), and CatBoost. To optimize the prediction process, we employ various spectral preprocessing techniques and wavelength selection algorithms. Experimental results unequivocally demonstrate the superior performance of the DL model, achieving exceptional performance with mean coefficient of determination (R2) values surpassing 0.9 for all components. This research underscores the potential of integrating HSI technology with DL methods, thereby establishing the feasibility of HSI as an efficient and non-destructive tool for predicting the content of isoflavones and starch in PTR. Moreover, this methodology holds great promise for enhancing efficiency in quality control within the food industry.

show abstract

Detection of moisture content in salted sea cucumbers by hyperspectral and low field nuclear magnetic resonance based on deep learning network framework

Cited by 8 publications

References 32 publications

Assessment of comprehensive PAH index in roasted Tan lamb by two‐dimensional correlation spectroscopy combined with hyperspectral imaging

Assessment of comprehensive PAH index in roasted Tan lamb by two‐dimensional correlation spectroscopy combined with hyperspectral imaging

AI and CV based 2D-CNN algorithm: botanical authentication of Indian honey

Non-destructive prediction of isoflavone and starch by hyperspectral imaging and deep learning in Puerariae Thomsonii Radix

Contact Info

Product

Resources

About