1
|
Fan Y, Dong R, Luo Y, Tan Y, Hong H, Ji Z, Shi C. Deep learning models with optimized fluorescence spectroscopy to advance freshness of rainbow trout predicting under nonisothermal storage conditions. Food Chem 2024; 454:139774. [PMID: 38810453 DOI: 10.1016/j.foodchem.2024.139774] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2024] [Revised: 05/06/2024] [Accepted: 05/19/2024] [Indexed: 05/31/2024]
Abstract
This study established long short-term memory (LSTM), convolution neural network long short-term memory (CNN_LSTM), and radial basis function neural network (RBFNN) based on optimized excitation-emission matrix (EEM) from fish eye fluid to predict freshness changes of rainbow trout under nonisothermal storage conditions. The method of residual analysis, core consistency diagnostics, and split-half analysis of parallel factor analysis was used to optimize EEM data, and two characteristic components were extracted. LSTM, CNN_LSTM, and RBFNN models based on characteristic components of EEM used to predict the freshness indices. The results demonstrated the relative errors of RBFNN models with an R2 above 0.96 and relative errors less than 10% for K-value, total viable counts, and volatile base nitrogen, which were better than those of LSTM and CNN_LSTM models. This study presents a novel approach for predicting the freshness of rainbow trout under nonisothermal storage conditions.
Collapse
Affiliation(s)
- Yanwei Fan
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China
| | - Ruize Dong
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Beijing Laboratory for Food Quality and Safety, College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China
| | - Yongkang Luo
- Beijing Laboratory for Food Quality and Safety, College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| | - Yuqing Tan
- Beijing Laboratory for Food Quality and Safety, College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| | - Hui Hong
- Beijing Laboratory for Food Quality and Safety, College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| | - Zengtao Ji
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; Key Laboratory of Cold Chain Logistics Technology for Agro-product, Ministry of Agriculture and Rural Affairs, Beijing 100097, China
| | - Ce Shi
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; Key Laboratory of Cold Chain Logistics Technology for Agro-product, Ministry of Agriculture and Rural Affairs, Beijing 100097, China.
| |
Collapse
|
2
|
Baptista RC, Oliveira RBA, Câmara AA, Lang É, Dos Santos JLP, Pavani M, Guerreiro TM, Catharino RR, Filho EGA, Rodrigues S, de Brito ES, Alvarenga VO, Bicca GB, Sant'Ana AS. Chilled Pacu (Piaractus mesopotamicus) fillets: Modeling Pseudomonas spp. and psychrotrophic bacteria growth and monitoring spoilage indicators by 1H NMR and GC-MS during storage. Int J Food Microbiol 2024; 415:110645. [PMID: 38430687 DOI: 10.1016/j.ijfoodmicro.2024.110645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 02/13/2024] [Accepted: 02/25/2024] [Indexed: 03/05/2024]
Abstract
This study aimed to assess the growth of Pseudomonas spp. and psychrotrophic bacteria in chilled Pacu (Piaractus mesopotamicus), a native South American fish, stored under chilling conditions (0 to 10 °C) through the use of predictive models under isothermal and non-isothermal conditions. Growth kinetic parameters, maximum growth rate (μmax, 1/h), lag time (tLag, h), and (Nmax, Log10 CFU/g) were estimated using the Baranyi and Roberts microbial growth model. Both kinetic parameters, growth rate and lag time, were significantly influenced by temperature (P < 0.05). The square root secondary model was used to describe the bacteria growth as a function of temperature. Secondary models, √μ = 0.016 (T + 10.13) and √μ =0.017 (T + 9.91) presented a linear correlation with R2 values >0.97 and were further validated under non-isothermal conditions. The model's performance was considered acceptable to predict the growth of Pseudomonas spp. and psychrotrophic bacteria in refrigerated Pacu fillets with bias and accuracy factors between 1.24 and 1.49 (fail-safe) and 1.45-1.49, respectively. Fish biomarkers and spoilage indicators were assessed during storage at 0, 4, and 10 °C. Volatile organic compounds, VOCs (1-hexanol, nonanal, octenol, and indicators 2-ethyl-1-hexanol) showed different behavior with storage time (P > 0.05). 1H NMR analysis confirmed increased enzymatic and microbial activity in Pacu fillets stored at 10 °C compared to 0 °C. The developed and validated models obtained in this study can be used as a tool for decision-making on the shelf-life and quality of refrigerated Pacu fillets stored under dynamic conditions from 0 to 10 °C.
Collapse
Affiliation(s)
- Rafaela C Baptista
- Department of Food Science and Nutrition, University of Campinas, Campinas, SP, Brazil
| | - Rodrigo B A Oliveira
- Department of Food Technology, Faculty of Veterinary, Fluminense Federal University, Niterói, RJ, Brazil
| | - Antonio A Câmara
- Department of Food Science and Nutrition, University of Campinas, Campinas, SP, Brazil
| | - Émilie Lang
- Department of Food Science and Nutrition, University of Campinas, Campinas, SP, Brazil
| | | | - Matheus Pavani
- Innovare Laboratory, Faculty of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil
| | - Tatiane M Guerreiro
- Innovare Laboratory, Faculty of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil
| | - Rodrigo R Catharino
- Innovare Laboratory, Faculty of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil
| | - Elenilson G A Filho
- Department of Food Engineering, Federal University of Ceará, Fortaleza, CE, Brazil
| | - Sueli Rodrigues
- Department of Food Engineering, Federal University of Ceará, Fortaleza, CE, Brazil
| | | | - Verônica O Alvarenga
- Department of Food, Faculty of Pharmacy, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil
| | | | - Anderson S Sant'Ana
- Department of Food Science and Nutrition, University of Campinas, Campinas, SP, Brazil.
| |
Collapse
|
3
|
Abamba Omwange K, Saito Y, Firmanda Al Riza D, Zichen H, Kuramoto M, Shiraga K, Ogawa Y, Kondo N, Suzuki T. Japanese dace (Tribolodon hakonensis) fish freshness estimation using front-face fluorescence spectroscopy coupled with chemometric analysis. SPECTROCHIMICA ACTA. PART A, MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2022; 276:121209. [PMID: 35397451 DOI: 10.1016/j.saa.2022.121209] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Revised: 03/13/2022] [Accepted: 03/26/2022] [Indexed: 06/14/2023]
Abstract
Although fish and its related products are good sources of protein and unsaturated fatty acids, like omega-3 in the human diet, their shelf-life is limited by biochemical and microbial changes. In this study, a front-face fluorescence spectroscopy technique was used to acquire Excitation-emission matrices (EEM) to monitor Japanese dace (Tribolodon hakonensis) fish freshness degradation during storage. EEM of Japanese dace fish parts (intact eyeball and surface-containing scales), excitation from 220 to 585 nm and emissions from 250 to 600 nm, were measured at different times during storage. To simplify the acquired complex spectra datasets from each fish part, the variables were reduced to those that were only significant/important (those with higher positive or negative correlation) for K value prediction, and as an index of freshness. Partial least square regression (PLSR) results demonstrated that combining the fluorescence EEM of the eyeball and surface-containing scales the best monitoring of fish freshness; excitation at 280 and 350 nm for both the eyeball and surface-containing scales, with 2.84 and 0.96 as RMSE and R2, respectively. These findings demonstrate that multiple excitation fluorescence approaches can be convenient for the freshness evaluation of fish.
Collapse
Affiliation(s)
- Ken Abamba Omwange
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan
| | - Yoshito Saito
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan
| | - Dimas Firmanda Al Riza
- Department of Agricultural Engineering, Faculty of Agricultural Technology, University of Brawijaya, Jl. Veteran, Malang, 65145, Indonesia
| | - Huang Zichen
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan
| | - Makoto Kuramoto
- Advanced Research Support Center, Ehime University, 2-5 Bunkyo-cho, Matsuyama, Ehime, 790-8577, Japan
| | - Keiichiro Shiraga
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan; PRESTO, Japan Science and Technology Agency, Hon-cho, Kawaguchi, Saitama 332-0012, Japan
| | - Yuichi Ogawa
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan
| | - Naoshi Kondo
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan
| | - Tetsuhito Suzuki
- Laboratory of Biosensing Engineering, Graduate School of Agriculture, Kyoto University, Kitashirakawa-Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan.
| |
Collapse
|
4
|
The investigation of storage situation of fish muscle via the analysis of its exudate by MALDI-TOF MS. Food Chem 2022; 373:131450. [PMID: 34717091 DOI: 10.1016/j.foodchem.2021.131450] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2021] [Revised: 10/16/2021] [Accepted: 10/18/2021] [Indexed: 11/20/2022]
Abstract
The potential of MALDI-TOF MS was investigated in terms of its capability to determine the change of exudates of fish muscle with different freeze-thaw cycles (0, 1 and 2), and frozen storage periods. The exudates were collected from dead chilled marine fish species, large yellow croacker (Larimichthys crocea, LC) and freshly slaughtered freshwater fish species, Japanese seabass (Lateolabrax japonicus) to be studied as models. 109 proteins, in which, 32 are extracellular proteins, and 15 are intracellular proteins, were identified by analyzing exudate of LC using MALDI-TOF MS and HPLC-MS/MS. The results show that the present method may be able to determine the change of fish muscle foods in a more sensitive mode than K value indicated quality control. The feasibility of verifying the storage situation of fish sample was performed by analyzing fish samples obtained from the local market. It is promising to estimate the storage situation of fishery products or other animal muscle foods by analyzing their muscle exudates based on the presently developed strategy.
Collapse
|
5
|
Shi X, Zhang J, Shi C, Tan Y, Hong H, Luo Y. Nondestructive prediction of freshness for bighead carp (Hypophthalmichthys nobilis) head by Excitation-Emission Matrix (EEM) analysis based on fish eye fluid: Comparison of BPNNs and RBFNNs. Food Chem 2022; 382:132341. [PMID: 35144187 DOI: 10.1016/j.foodchem.2022.132341] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2021] [Revised: 01/16/2022] [Accepted: 02/01/2022] [Indexed: 11/04/2022]
Abstract
This study established back-propagation neural networks (BPNNs) and radial basis function neural networks (RBFNNs) models for evaluating the freshness of bighead carp head storage at different temperatures via the characteristic components of Excitation-Emission Matrix (EEM). Two characteristic components of EEM data of fish eye fluid were extracted by parallel factor analysis (PARAFAC) and were the most efficient components to stimulate fluorophores responsible for fish freshness detection during variable temperatures. EEM-RBFNNs and EEM-BPNNs models based on characteristic components of EEM used to predict the fish freshness. The results demonstrated the relative errors of EEM-BPNNs models for hiobarbituric acid reactive substances (TBARS) and total viable bacteria count (TAC) prediction were less than 10% which were better than those of EEM-RBFNNs models. It indicated that EEM-BPNNs model of bighead carp eye fluid by PARAFAC has a high potential for predicting fish freshness under variable storage conditions.
Collapse
Affiliation(s)
- Xin Shi
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China; National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing 100097, China
| | - Jiaran Zhang
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing 100097, China
| | - Ce Shi
- Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing 100097, China.
| | - Yuqing Tan
- College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| | - Hui Hong
- College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| | - Yongkang Luo
- College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China
| |
Collapse
|
6
|
Evaluating Japanese dace (Tribolodon hakonensis) fish freshness during storage using multispectral images from visible and UV excited fluorescence. Lebensm Wiss Technol 2021. [DOI: 10.1016/j.lwt.2021.112207] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
7
|
Fish freshness monitoring using UV-fluorescence imaging on Japanese dace (Tribolodon hakonensis) fisheye. J FOOD ENG 2020. [DOI: 10.1016/j.jfoodeng.2020.110111] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
8
|
Emerging Techniques for Differentiation of Fresh and Frozen-Thawed Seafoods: Highlighting the Potential of Spectroscopic Techniques. Molecules 2020; 25:molecules25194472. [PMID: 33003382 PMCID: PMC7582365 DOI: 10.3390/molecules25194472] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2020] [Accepted: 09/27/2020] [Indexed: 01/12/2023] Open
Abstract
Fish and other seafood products have a limited shelf life due to favorable conditions for microbial growth and enzymatic alterations. Various preservation and/or processing methods have been developed for shelf-life extension and for maintaining the quality of such highly perishable products. Freezing and frozen storage are among the most commonly applied techniques for this purpose. However, frozen–thawed fish or meat are less preferred by consumers; thus, labeling thawed products as fresh is considered a fraudulent practice. To detect this kind of fraud, several techniques and approaches (e.g., enzymatic, histological) have been commonly employed. While these methods have proven successful, they are not without limitations. In recent years, different emerging methods have been investigated to be used in place of other traditional detection methods of thawed products. In this context, spectroscopic techniques have received considerable attention due to their potential as being rapid and non-destructive analytical tools. This review paper aims to summarize studies that investigated the potential of emerging techniques, particularly those based on spectroscopy in combination with chemometric tools, to detect frozen–thawed muscle foods.
Collapse
|
9
|
Hassoun A, Sahar A, Lakhal L, Aït-Kaddour A. Fluorescence spectroscopy as a rapid and non-destructive method for monitoring quality and authenticity of fish and meat products: Impact of different preservation conditions. Lebensm Wiss Technol 2019. [DOI: 10.1016/j.lwt.2019.01.021] [Citation(s) in RCA: 49] [Impact Index Per Article: 9.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
|