1
|
Bu Y, Hu J, Chen C, Bai S, Chen Z, Hu T, Zhang G, Liu N, Cai C, Li Y, Xuan Q, Wang Y, Su Z, Xiang Y, Gong Y. ResNet incorporating the fusion data of RGB & hyperspectral images improves classification accuracy of vegetable soybean freshness. Sci Rep 2024; 14:2568. [PMID: 38297076 PMCID: PMC11224382 DOI: 10.1038/s41598-024-51668-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Accepted: 01/08/2024] [Indexed: 02/02/2024] Open
Abstract
The freshness of vegetable soybean (VS) is an important indicator for quality evaluation. Currently, deep learning-based image recognition technology provides a fast, efficient, and low-cost method for analyzing the freshness of food. The RGB (red, green, and blue) image recognition technology is widely used in the study of food appearance evaluation. In addition, the hyperspectral image has outstanding performance in predicting the nutrient content of samples. However, there are few reports on the research of classification models based on the fusion data of these two sources of images. We collected RGB and hyperspectral images at four different storage times of VS. The ENVI software was adopted to extract the hyperspectral information, and the RGB images were reconstructed based on the downsampling technology. Then, the one-dimensional hyperspectral data was transformed into a two-dimensional space, which allows it to be overlaid and concatenated with the RGB image data in the channel direction, thereby generating fused data. Compared with four commonly used machine learning models, the deep learning model ResNet18 has higher classification accuracy and computational efficiency. Based on the above results, a novel classification model named ResNet-R &H, which is based on the residual networks (ResNet) structure and incorporates the fusion data of RGB and hyperspectral images, was proposed. The ResNet-R &H can achieve a testing accuracy of 97.6%, which demonstrates a significant enhancement of 4.0% and 7.2% compared to the distinct utilization of hyperspectral data and RGB data, respectively. Overall, this research is significant in providing a unique, efficient, and more accurate classification approach in evaluating the freshness of vegetable soybean. The method proposed in this study can provide a theoretical reference for classifying the freshness of fruits and vegetables to improve classification accuracy and reduce human error and variability.
Collapse
Affiliation(s)
- Yuanpeng Bu
- Institute of Vegetables, Key Laboratory of Vegetable Legumes Germplasm Enhancement and Southern China of the Ministry of Agriculture and Rural Affairs, Zhejiang Academy of Agricultural Sciences, Hangzhou, China
| | - Jinxuan Hu
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Cheng Chen
- Zhejiang Yuncheng Information technology Co Ltd., Hangzhou, China
| | - Songhang Bai
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Zuohui Chen
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Tianyu Hu
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Guwen Zhang
- Institute of Vegetables, Key Laboratory of Vegetable Legumes Germplasm Enhancement and Southern China of the Ministry of Agriculture and Rural Affairs, Zhejiang Academy of Agricultural Sciences, Hangzhou, China
| | - Na Liu
- Institute of Vegetables, Key Laboratory of Vegetable Legumes Germplasm Enhancement and Southern China of the Ministry of Agriculture and Rural Affairs, Zhejiang Academy of Agricultural Sciences, Hangzhou, China
| | - Chang Cai
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Yuhao Li
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Qi Xuan
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Ye Wang
- Faculty of Engineering, Lishui University, Lishui, China
| | - Zhongjing Su
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China
| | - Yun Xiang
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou, China.
| | - Yaming Gong
- Institute of Vegetables, Key Laboratory of Vegetable Legumes Germplasm Enhancement and Southern China of the Ministry of Agriculture and Rural Affairs, Zhejiang Academy of Agricultural Sciences, Hangzhou, China.
| |
Collapse
|
2
|
Liao X, Wang S, Li Y, Michael Olajide T, Zhai X, Qian J, Miao S, Huang J. Effects of "nine steaming nine sun-drying" on proximate composition, protein structure and volatile compounds of black soybeans. Food Res Int 2022; 155:111070. [PMID: 35400448 DOI: 10.1016/j.foodres.2022.111070] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Revised: 02/22/2022] [Accepted: 02/24/2022] [Indexed: 11/04/2022]
Abstract
Nine steaming nine sun-drying is a traditional processing technology for food or medicinal materials. The dynamic changes of the proximate composition, protein structure and volatile compounds during nine-time steaming and sun-drying of black soybeans (BS) were studied. The proximate composition results showed that the content of protein, carbohydrate and fat of BS decreased after processing, whereas the relative content of amino acids remained basically unchanged. Protein structure was evaluated using Fourier transform infrared spectroscopy (FT-IR), Ultraviolet absorption spectroscopy (UV) and Fluorescence spectroscopy. FT-IR result revealed that the relative contents of β-sheet and β-turn of the secondary structure of black soybean protein isolate (BSPI) decreased but the relative contents of α-helix and random coil increased after steaming and sun-drying. The results of UV and fluorescence spectroscopy confirmed changes in the protein conformation. In addition, SPME-GCMS analysis demonstrated that hydrocarbons, alcohols and aldehydes were the main volatile compounds. The relative contents of 1-octen-3-ol and hexanal, which are the main sources of beany flavor decreased significantly compared with raw BS. Principal component analysis (PCA) results showed that the volatile compounds of nine steamed and nine sun-dried BS could be well distinguished during the process. These findings may therefore provide a scientific basis for the application of nine-time steamed and sun-dried BS in food industry and contribute to the understanding of process-induced chemical transformations in this ancient processing technique.
Collapse
Affiliation(s)
- Xianyan Liao
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China
| | - Shanshan Wang
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China
| | - Yingqiu Li
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China
| | | | - Xiaolin Zhai
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China
| | - Jiana Qian
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China
| | - Song Miao
- Teagasc Food Research Centre Moorepark, Co. Cork, Ireland.
| | - Junyi Huang
- Food Nutrition and Chronic Disease Intervention Laboratory, School of Life Sciences, Shanghai University, Shanghai 200444, China.
| |
Collapse
|
3
|
Guo L, Huang L, Cheng X, Gao Y, Zhang X, Yuan X, Xue C, Chen X. Volatile Flavor Profile and Sensory Properties of Vegetable Soybean. Molecules 2022; 27:939. [PMID: 35164204 PMCID: PMC8839288 DOI: 10.3390/molecules27030939] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2021] [Revised: 01/26/2022] [Accepted: 01/26/2022] [Indexed: 11/25/2022] Open
Abstract
The volatile flavor profiles and sensory properties of different vegetable soybean varieties popularized and cultivated in China for 20, 10, and 2 years (TW292, X3, and SX6, respectively) were investigated. Nutrient composition analysis revealed that TW292 had a high soluble protein and soluble sugar content but low fat content. The total free amino acid content (15.43 mg/g) and umami free amino acid content (6.08 mg/g) of SX6 were significantly higher (p < 0.05) than those of the other varieties. An electronic tongue effectively differentiated between the umami and sweetness characteristics of the vegetable soybeans. Differences in sensory evaluation results were mainly reflected in texture and taste. A total of 41 volatile compounds were identified through HS-SPME-GC-MS, and the main flavor compounds were 1-octen-3-ol, hexanal, (Z)-2-heptenal, 2-octene, nonanal, (Z)-2-decenal, and 3,5-octadien-2-one. However, the volatile composition of different vegetable soybean varieties exhibited large variability in type and relative contents. Considerable differences in nutritional, organoleptic, and aroma characteristics were found among different varieties. The results of this study will provide a good basis for the assessment and application of the major vegetable soybean varieties grown in China.
Collapse
Affiliation(s)
- Luping Guo
- Department of Food Science and Engineering, School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China;
| | - Lu Huang
- Institute of Industrial Crops, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China; (L.H.); (X.Z.); (X.Y.); (X.C.)
| | - Xi Cheng
- Department of Food Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023, China;
| | - Yuan Gao
- Department of Horticulture, Nanjing Agricultural University, Nanjing 210095, China;
| | - Xiaoyan Zhang
- Institute of Industrial Crops, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China; (L.H.); (X.Z.); (X.Y.); (X.C.)
| | - Xingxing Yuan
- Institute of Industrial Crops, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China; (L.H.); (X.Z.); (X.Y.); (X.C.)
| | - Chenchen Xue
- Institute of Industrial Crops, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China; (L.H.); (X.Z.); (X.Y.); (X.C.)
| | - Xin Chen
- Institute of Industrial Crops, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China; (L.H.); (X.Z.); (X.Y.); (X.C.)
| |
Collapse
|
4
|
An NN, Sun WH, Li BZ, Wang Y, Shang N, Lv WQ, Li D, Wang LJ. Effect of different drying techniques on drying kinetics, nutritional components, antioxidant capacity, physical properties and microstructure of edamame. Food Chem 2021; 373:131412. [PMID: 34731799 DOI: 10.1016/j.foodchem.2021.131412] [Citation(s) in RCA: 28] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2021] [Revised: 09/08/2021] [Accepted: 10/13/2021] [Indexed: 02/03/2023]
Abstract
The present study aimed to investigate the effect of hot air drying (HD), microwave rolling-bed drying (MRD), hot air microwave rolling-bed drying (HMRD), pulse-spouted microwave vacuum drying (PSMVD) and freeze-drying (FD) on the drying characteristics, quality properties and microstructure of edamame. Six models were fitted the drying curves, and quality attributes were analyzed. Results indicated that Page model was the most suited model for edamame drying. Compared with HD, MRD and HMRD improved the quality of edamame and decreased the drying time by 45.59% and 36.03% respectively. The FD and PSMVD possessed higher rehydration ability, nutrient retention and antioxidant capacity compared with other methods. Moreover, PSMVD products showed a crunchy texture, the less color change and the shortest drying time (70 min). Microscopy images demonstrated a distinct porous structure in PSMVD, which facilitated the moisture transfer. Overall, PSMVD is a promising dehydration method for obtaining high value-added edamame products.
Collapse
Affiliation(s)
- Nan-Nan An
- College of Engineering, Beijing Advanced Innovation Center for Food Nutrition and Human Health, National Energy R & D Center for Non-food Biomass, China Agricultural University, P. O. Box 50, 17 Qinghua Donglu, Beijing 100083, China
| | - Wei-Hong Sun
- School of Agricultural Engineering, Jiangsu University, Zhenjiang, Jiangsu, China
| | - Bing-Zheng Li
- Guangxi Bioscience and Technology Research Center, Guangxi Academy of Sciences, Nanning, Guangxi, China
| | - Yong Wang
- School of Chemical Engineering, UNSW, Sydney, NSW 2052, Australia
| | - Nan Shang
- College of Engineering, Beijing Advanced Innovation Center for Food Nutrition and Human Health, National Energy R & D Center for Non-food Biomass, China Agricultural University, P. O. Box 50, 17 Qinghua Donglu, Beijing 100083, China
| | - Wei-Qiao Lv
- College of Engineering, Beijing Advanced Innovation Center for Food Nutrition and Human Health, National Energy R & D Center for Non-food Biomass, China Agricultural University, P. O. Box 50, 17 Qinghua Donglu, Beijing 100083, China
| | - Dong Li
- College of Engineering, Beijing Advanced Innovation Center for Food Nutrition and Human Health, National Energy R & D Center for Non-food Biomass, China Agricultural University, P. O. Box 50, 17 Qinghua Donglu, Beijing 100083, China.
| | - Li-Jun Wang
- College of Food Science and Nutritional Engineering, Beijing Key Laboratory of Functional Food from Plant Resources, China Agricultural University, Beijing, China.
| |
Collapse
|