Skip to main content
SpringerLink
Log in

Artificial intelligence predictability of moisture, fats and fatty acids composition of fish using low frequency Nuclear Magnetic Resonance (LF-NMR) relaxation

  • ORIGINAL ARTICLE
  • Published:
Journal of Food Science and Technology Aims and scope Submit manuscript

Abstract

Moisture, fats and fatty acids of 14 pelagic and demersal fishes were measured by conventional chemical analysis to relate these with the proton relaxation using Low Frequency Nuclear Magnetic Resonance (LF-NMR). Artificial intelligence was used to assess the predictability of composition using six relaxation parameters of LF-NMR. Multiple linear regression showed significant prediction for moisture (W) (P < 0.00001), total fat (F) (P < 0.0001), ω-6 fatty acid (O6) (P < 0.001), saturated fats (SF), fatty acids (FA), mono-unsaturated fatty acids (MU) and ω-3 fatty acid (O3) (P < 0.01). However, the highest regression coefficient was observed for water (R2: 0.490) and the lowest was observed for SF (R2: 0.224). The low regression coefficients indicated strong non-linear relationships exited between LF-NMR parameters and composition. However, decision tree showed higher regression coefficients for all compositions considered in this study (R2:0.780–0.694). In addition, it provided simple decision rules for the prediction of composition. General Regression Neural Network provided the highest prediction capability (R2:0.847–1.000 for training and 0.506–0.924 for validation).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Availability of data and materials

All data are available in the manuscript.

Code availability

Not applicable.

References

  • Al-Habsi NA, Al-Hadhrami S, Al-Kasbi H, Rahman MS (2017) Molecular mobility of fish flesh measured by low-field nuclear magnetic resonance (LF-NMR) relaxation: effects of freeze–thaw cycles. Fish Sci 83(5):845–851

    Article  Google Scholar 

  • AOAC (2000) Official methods of analysis of the association of official analytical chemists, 17th edn. Association of Official Analytical Chemists Inc., Virginia

    Google Scholar 

  • Bennett-Lenane H, Griffin BT, O’Shea JP (2022) Machine learning methods for prediction of food effects on bioavailability: a comparison of support vector machines and artificial neural networks. Eur J Pharmac Sci 168:1–13

    Article  Google Scholar 

  • Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H (1997) Basic concepts of artificial neural networks (ANN) modeling in the application to pharmaceutical development. Pharmac Dev Technol 2(2):95–109

    Article  CAS  Google Scholar 

  • Brar D S, Aggarwal A K, Nanda V, Saxena S, Gautam S (2024) AI and CV based 2D-CNN algorithm: botanical authentication of Indian honey. Sustainable Food Technology (in press)

  • Chaijan M, Panpipat W (2009) Post harvest discoloration of dark-fleshed fish muscle: a review. Walailak J Sci Technol 6(2):149–166

    Google Scholar 

  • Duflot M, Sanchez-Alonso I, Duflos G, Careche M (2019) LF1H NMR T2 relaxation rate as affected by water addition, NaCl and pH in fresh, frozen and cooked minced hake. Food Chem 277:229–237

    Article  CAS  PubMed  Google Scholar 

  • Erikson U, Standal I, Aursand IG, Veliyulin E, Aursand M (2012) Use of NMR in fish processing optimization: a review of recent progress. Magn Reson Chem 50:471–480

    Article  CAS  PubMed  Google Scholar 

  • Esmaeily R, Razavi MA, Razavi SH (2024) A step forward in food science, technology and industry using artificial intelligence. Trends Food Sci Technol 143:1–17

    Article  Google Scholar 

  • Folch J, Lees M, Stanley GS (1957) A simple method for the isolation and purification of total lipides from animal tissues. J Biol Chem 226(1):497–509

    Article  CAS  PubMed  Google Scholar 

  • Gu H, Huang X, Sun Y, Chen Q, Wei Z, Lv R (2021) Intelligent evaluation of total polar compounds (TPC) content of frying oil based on fluorescence spectroscopy and low-field NMR. Food Chem 342:1–8

    Article  Google Scholar 

  • Gudjonsdottir M, Romotowska PE, Karlsdottir MG, Arason S (2019) Low field nuclear magnetic resonance and multivariate analysis for prediction of physicochemical characteristics of Atlantic mackerel as affected by season of catch, freezing method, and frozen storage duration. Food Res Int 116:471–482

    Article  CAS  PubMed  Google Scholar 

  • Hearty AP, Gibney MJ (2008) Analysis of meal patterns with the use of supervised data mining techniques-artificial neural networks and decision trees. Am J Clin Nutr 88:1632–1642

    Article  CAS  PubMed  Google Scholar 

  • Hickey H, MacMillan B, Newling B, Ramesh M, Van Eijck P, Balcom B (2006) Magnetic resonance relaxation measurements to determine oil and water content in fried foods. Food Res Int 39:612–618

    Article  CAS  Google Scholar 

  • Hou X, Wang G, Wang X, Ge X, Fan Y, Nie S (2020) Convolutional neural network based approach for classification of edible oils using low-field nuclear magnetic resonance. J Food Compos Anal 92:1–8

    Article  CAS  Google Scholar 

  • Jimenez-Carvelo AM, Gonzalez-Casado A, Bagur-Gonzalez G, Cuadros-Rodriguez L (2019) Alternative data mining/machine learning methods for the analytical evaluation of food quality and authenticity—a review. Food Res Int 122:25–39

    Article  PubMed  Google Scholar 

  • Jørgensen BM, Jensen KN (2008) Water distribution and mobility in fish products in relation to quality. In: Webb GA (ed) Modern magnetic resonance. Springer, Dordrecht

    Google Scholar 

  • Li Y, Obadi M, Shi J, Sun J, Chen Z, Xu B (2020) Determination of moisture, total lipid, and bound lipid contents in oats using low-field nuclear magnetic resonance. J Food Compos Anal 87:103401

    Article  CAS  Google Scholar 

  • MacMillan B, Hickey H, Newling B, Ramesh M, Balcom B (2008) Magnetic resonance measurements of French fries to determine spatially resolved oil and water content. Food Res Int 41:676–681

    Article  Google Scholar 

  • Mariette F (2009) Investigations of food colloids by NMR and MRI. Curr Opin Colloid Interface Sci 14(3):203–211

    Article  CAS  Google Scholar 

  • Medus LD, Saban M, Frances-Víllora JV, Bataller-Mompean M, Rosado-Munoz A (2021) Hyperspectral image classification using CNN: application to industrial food packaging. Food Control 125:1–12

    Article  Google Scholar 

  • Nakashima Y (2019) Non-destructive quantification of lipid and water in fresh tuna meat by a single-sided nuclear magnetic resonance scanner. J Aquat Food Product Technol 28(2):241–252

    Article  CAS  Google Scholar 

  • Nakitto M, Ssali RT, Johanningsmeier SD, Moyo M, de Kock H, Berget I, Okello JJ, Mayanja S, Tinyiro SE, Mendes T, Benard Y, Chelengat D, Osaru F, Bugaud C (2023) Decision tree scoring system to guide selection for consumer preference in sweetpotato breeding trials. J Sci Food Agric. https://doi.org/10.1002/jsfa.12883

    Article  PubMed  Google Scholar 

  • Nielsen D, Hyldig G, Nielsen J, Nielsen HH (2005) Lipid content in herring (Clupea harengus L.)—influence of biological factors and comparison of different methods of analyses: solvent extraction, Fatmeter, NIR and NMR. LWT Food Sci Technol 38:537–548

    Article  CAS  Google Scholar 

  • Petrov OV, Hay J, Mastikhin IV, Balcom BJ (2008) Fat and moisture content determination with unilateral NMR. Food Res Int 41:758–764

    Article  CAS  Google Scholar 

  • Povlsen VT, Rinnan A, van den Berg F, Andersen HJ, Thybo AK (2003) Direct decomposition of NMR relaxation profiles and prediction of sensory attributes of potato samples. Food Sci Technol 36:423–432

    CAS  Google Scholar 

  • Rahman MS, Suresh S, Al-Habsi N (2021) Proton relaxation in freeze-dried broccoli as measured by low-frequency nuclear magnetic resonance (LF-NMR) and its relationship with the thermal glass transition. J Therm Anal Calorim 143:3147–3159

    Article  CAS  Google Scholar 

  • Sánchez-Zapata E, Amensour M, Oliver R, Navarro C, Fernández-López J, Sendra E, Pérez-Alvarez JA (2011) Quality characteristics of dark muscle from yellowfin tuna Thunnus albacares to its potential application in the food industry. Food Nutr Sci 2(01):22

    Google Scholar 

  • Sherrod P H (2015) NLREG: nonlinear regression analysis program, version, 6.6, 9207 Brushboro Drive, Brentwood, TN 37027, US

  • Sherrod PH (2018) DTREG: predictive modeling program, advanced version, 9207 Brushboro Drive, Brentwood, TN 37027, US

  • Shindo K, Tsuchiya T, Matsumoto J, J. (1986) Histological study on white and dark muscles of various fishes. Bull Jpn Ocietyo f Sci Sheries 52(8):1377–1399

    Article  Google Scholar 

  • Sorland GH, Larsen PM, Lundby F, Rudi A, Guijeneuf T (2004) Determination of total fat and moisture in meat using low field NMR. Meat Sci 66:543–550

    Article  PubMed  Google Scholar 

  • Sun Y, Zhang M, Fan D (2019) Effect of ultrasonic on deterioration of oil in microwave vacuum frying and prediction of frying oil quality based on low field nuclear magnetic resonance (LF-NMR). Ultrasonics-Sonochemistry 51:77–89

    Article  CAS  PubMed  Google Scholar 

  • Todt H, Guthausen G, Burk W, Schmalbein D, Kamlowski A (2006) Water/moisture and fat analysis by time-domain NMR. Food Chem 96:436–440

    Article  CAS  Google Scholar 

  • van Asselt ED, Noordam MY, Pikkemaat MG, Dorgelo FO (2018) Risk-based monitoring of chemical substances in food: Prioritization by decision trees. Food Control 93:112–120

    Article  Google Scholar 

  • Varra MO, Husakova L, Patocka J, Ghidini S, Zanardi E (2021) Classification of transformed anchovy products based on the use of element patterns and decision trees to assess traceability and country of origin labelling. Food Chem 360:1–11

    Article  Google Scholar 

  • Vasiljevic T, Toebes A, Huppertz T (2021) Moisture sorption by dairy powders studied by low-field NMR. Int Dairy J 119:1–5

    Article  Google Scholar 

  • Wang C, Su G, Wang X, Nie S (2019) Rapid assessment of deep frying oil quality as well as water and fat contents in French fries by low-field nuclear magnetic resonance. J Agric Food Chem 67:2361–2368

    Article  CAS  PubMed  Google Scholar 

  • WEKA. 2019. Waikato environment for knowledge analysis. Version 3.9.4, The University of Waikato, Hamilton, New Zealand

  • Xu C, Li Y, Yu H (2014) Effect of far-infrared drying on the water state and glass transition temperature in carrots. J Food Eng 136:42–47

    Article  CAS  Google Scholar 

  • Zamora R, Hidalgo FJ (2008) Determination of fatty acid composition and oxidation in fish oils by high resolution nuclear magnetic resonance spectroscopy. In: Webb GA (ed) Modern magnetic resonance. Springer, Dordrecht

    Google Scholar 

  • Zellerbach K, Ruiz C (2019) Machine learning to predict overeating from macronutrient composition. In: 2019 IEEE International conference on bioinformatics and biomedicine (BIBM) pp. 1268–1270

Download references

Acknowledgements

Authors would like to acknowledge the support of the Sultan Qaboos University towards the utilization of LF-NMR in predicting fish compositions and assessing fresh, frozen and dried fish quality. Moreover, the authors would like to thank Prof Michel Claereboudt for his advises in statistical analysis.

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of Food Science and Nutrition, College of Agricultural and Marine Sciences, Sultan Qaboos University, P. O. Box 34-123, Seeb, Oman

    Nasser Al-Habsi, Ruqaya Al-Julandani, Afrah Al-Hadhrami, Zaher Al-Attabi & Mohammad Shafiur Rahman

  2. Central Laboratory, College of Agricultural and Marine Sciences, Sultan Qaboos University, P. O. Box 34-123, Seeb, Oman

    Houda Al-Ruqaishi & Jamal Al-Sabahi

Authors
  1. Nasser Al-Habsi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruqaya Al-Julandani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Afrah Al-Hadhrami
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Houda Al-Ruqaishi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jamal Al-Sabahi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zaher Al-Attabi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Mohammad Shafiur Rahman
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The authors confirm contribution to the paper as follows: study conception and design: Nasser Al-Habsi, Ruqaya Al-Julandani, Afrah Al-Hadhrami; data collection: Nasser Al-Habsi, Ruqaya Al-Julandani, Afrah Al-Hadhrami, Jamal Al-Sabahi and Houda Al-Ruqaishi; analysis and interpretation of results: Nasser Al-Habsi, Houda Al-Ruqaishi, Jamal Al-Sabahi, Mohammad Shafiur Rahman and Zaher Al Attabi; draft manuscript preparation: Nasser Al-Habsi, Ruqaya Al-Julandani and Mohammad Shafiur Rahman. All authors reviewed the results and approved the final version of the manuscript.

Corresponding author

Correspondence to Nasser Al-Habsi.

Ethics declarations

Conflict of interest

The authors declare that they have no competing interests.

Consent to participate

All authors of the manuscript are aware from submission of this manuscript.

Consent for publication

All authors of the manuscript are aware from submission of this manuscript. This manuscript has not been published or presented elsewhere in part or in entirety.

Ethics approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 18 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Al-Habsi, N., Al-Julandani, R., Al-Hadhrami, A. et al. Artificial intelligence predictability of moisture, fats and fatty acids composition of fish using low frequency Nuclear Magnetic Resonance (LF-NMR) relaxation. J Food Sci Technol (2024). https://doi.org/10.1007/s13197-024-05977-3

Download citation

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13197-024-05977-3

Keywords

Search

Navigation