Application of Machine Learning in Food Flavor Analysis
Abstract
Flavor plays a crucial role in the sensory perception of food and is a key determinant for consumer preference and choice. Therefore, flavor analysis methods are of paramount importance. Traditional methods for flavor analysis have limitations such as time-consuming and unable to handle large sample data. The emergence of machine learning is poised to address these problems. Machine learning possesses the capability to analyze and process vast amounts of data, identify complex patterns in high-dimensional variable spaces, autonomously learn useful information from known data, and automatically generate and optimize algorithms for prediction based on new data. The emergence of machine learning provides a new method for understanding the complex flavor characteristics of food. This article provides a comprehensive review of the advantages and disadvantages of traditional and novel machine learning methods as well as their various application scenarios in conjunction with analytical instruments such as electronic tongue, electronic nose, and gas chromatography-mass spectrometry (GC-MS). Additionally, it reviews the application of machine learning in food flavor analysis. Through research, it has been found that different scenarios of food flavor analysis require different machine learning methods. Machine learning holds significant potential for enhancing food quality, safety and consumer satisfaction. The combination of multiple machine learning models and analytical techniques will play a crucial role in food flavor analysis.
Keywords
References
PU D D, SHAN Y M, WANG J, et al. Recent trends in aroma release and perception during food oral processing: a review[J]. Critical Reviews in Food Science and Nutrition, 2022. DOI:10.1080/10408398.2022.2132209.
JI H Z, PU D D, YAN W J, et al. Recent advances and application of machine learning in food flavor prediction and regulation[J]. Trends in Food Science & Technology, 2023, 138: 738-751. DOI:10.1016/j.tifs.2023.07.012.
CAYOT N. Sensory quality of traditional foods[J]. Food Chemistry, 2007, 102(2): 445-453. DOI:10.1016/j.foodchem.2006.01.012.
REGUEIRO J, NEGREIRA N, SIMAL-GÁNDARA J. Challenges in relating concentrations of aromas and tastes with flavor features of foods[J]. Critical Reviews in Food Science and Nutrition, 2017, 57(10): 2112-2127. DOI:10.1080/10408398.2015.1048775.
LAWLESS H T, HEYMANN H. Sensory evaluation of food: principles and practices[M]. Berlin: Springer, 2010: 1-2.
WAYMARK C, HILL A E. The influence of yeast strain on whisky new make spirit aroma[J]. Fermentation, 2021, 7(4): 311. DOI:10.3390/fermentation7040311.
FENG T, SUN J Q, SONG S Q, et al. Geographical differentiation of Molixiang table grapes grown in China based on volatile compounds analysis by HS-GC-IMS coupled with PCA and sensory evaluation of the grapes[J]. Food Chemistry: X, 2022, 15: 100423. DOI:10.1016/j.fochx.2022.100423.
WANG R J, ZHANG Y Y, LU H, et al. Comparative aroma profile analysis and development of a sensory aroma lexicon of seven different varieties of Flammulina velutipes[J]. Frontiers in Nutrition, 2022, 9: 827825. DOI:10.3389/fnut.2022.827825.
FENG T, SUN J Q, WANG K, et al. Variation in volatile compounds of raw pu-erh tea upon steeping process by gas chromatography-ion mobility spectrometry and characterization of the aroma-active compounds in tea infusion using gas chromatography-olfactometry-mass spectrometry[J]. Journal of Agricultural and Food Chemistry, 2022, 70(42): 13741-13753. DOI:10.1021/acs.jafc.2c04342.
BOUYSSET C, BELLOIR C, ANTONCZAK S, et al. Novel scaffold of natural compound eliciting sweet taste revealed by machine learning[J]. Food Chemistry, 2020, 324: 126864. DOI:10.1016/j.foodchem.2020.126864.
VIEJO C G, TORRICO D D, DUNSHEA F R, et al. Development of artificial neural network models to assess beer acceptability based on sensory properties using a robotic pourer: a comparative model approach to achieve an artificial intelligence system[J]. Beverages, 2019, 5(2): 33. DOI:10.3390/beverages5020033.
BI K X, QIU T, HUANG Y Z. A deep learning method for yogurt preferences prediction using sensory attributes[J]. Processes, 2020, 8(5): 518. DOI:10.3390/pr8050518.
MILLER C, HAMILTON L, LAHNE J. Sensory descriptor analysis of whisky lexicons through the use of deep learning[J]. Foods, 2021, 10(7): 1633. DOI:10.3390/foods10071633.
FERNIE A R, ALSEEKH S. Metabolomic selection-based machine learning improves fruit taste prediction[J]. Proceedings of the National Academy of Sciences, 2022, 119(9): e2201078119. DOI:10.1073/pnas.2201078119.
BO W C, QIN D Y, ZHENG X, et al. Prediction of bitterant and sweetener using structure-taste relationship models based on an artificial neural network[J]. Food Research International, 2022, 153: 110974. DOI:10.1016/j.foodres.2022.110974.
CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297. DOI:10.1007/BF00994018.
YANG Z W, MIAO N, ZHANG X, et al. Employment of an electronic tongue combined with deep learning and transfer learning for discriminating the storage time of Pu-erh tea[J]. Food Control, 2021, 121: 107608. DOI:10.1016/j.foodcont.2020.107608.
WANG H M, WANG X D, LIU D Y, et al. Evaluation of beef flavor attribute based on sensor array in tandem with support vector machines[J]. Journal of Food Measurement and Characterization, 2019, 13(4): 2663-2671. DOI:10.1007/s11694-019-00187-4.
AMARAPPA S, SATHYANARAYANA D S V. Data classification using support vector machine (SVM), a simplified approach[J]. International Journal of Electronics and Computer Science Engineering, 2014, 3: 435-445.
COVER T, HART P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21-27. DOI:10.1109/TIT.1967.1053964.
LI K, ONODA K, KUMAZAKI T. Modeling taste score of rice by data mining from physicochemical parameters[J]. AIP Conference Proceedings, 2017, 1807: 020027. DOI:10.1063/1.4974809.
SAVILLE R, KAZUOKA T, SHIMOGUCHI N N, et al. Recognition of Japanese sake quality using machine learning based analysis of physicochemical properties[J]. Journal of the American Society of Brewing Chemists, 2022, 80(2): 146-154. DOI:10.1080/03610470.2021.1939973.
MYLES A J, FEUDALE R N, LIU Y, et al. An introduction to decision tree modeling[J]. Journal of Chemometrics, 2004, 18(6): 275-285. DOI:10.1002/cem.873.
TUWANI R, WADHWA S, BAGLER G. BitterSweet: building machine learning models for predicting the bitter and sweet taste of small molecules[J]. Scientific Reports, 2019, 9(1): 7155. DOI:10.1038/s41598-019-43664-y.
SABILLA I A, FATICHAH C. The tomatoes and chilies type classifications by using machine learning methods[J]. Journal of Development Research, 2020, 4(1): 1-6. DOI:10.28926/jdr.v4i1.93.
HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501. DOI:10.1016/j.neucom.2005.12.126.
FENG L, ZHANG M, BHANDARI B, et al. A novel method using MOS electronic nose and ELM for predicting postharvest quality of cherry tomato fruit treated with high pressure argon[J]. Computers and Electronics in Agriculture, 2018, 154: 411-419. DOI:10.1016/j.compag.2018.09.032.
QIU S S, GAO L P, WANG J. Classification and regression of ELM, LVQ and SVM for E-nose data of strawberry juice[J]. Journal of Food Engineering, 2015, 144: 77-85. DOI:10.1016/j.jfoodeng.2014.07.015.
QIU S S, WANG J, TANG C, et al. Comparison of ELM, RF, and SVM on E-nose and E-tongue to trace the quality status of mandarin (Citrus unshiu Marc.)[J]. Journal of Food Engineering, 2015, 166: 193-203. DOI:10.1016/j.jfoodeng.2015.06.007.
SINAGA K P, YANG M S. Unsupervised K-means clustering algorithm[J]. IEEE Access, 2020, 8: 80716-80727. DOI:10.1109/ACCESS.2020.2988796.
LING M Q, XIE H, HUA Y B, et al. Flavor profile evolution of bottle aged rosé and white wines sealed with different closures[J]. Molecules, 2019, 24(5): 836. DOI:10.3390/molecules24050836.
MURTAGH F, CONTRERAS P. Algorithms for hierarchical clustering: an overview[J]. WIREs Data Mining and Knowledge Discovery, 2012, 2(1): 86-97. DOI:10.1002/widm.53.
SERRANO-MEGÍAS M, LÓPEZ-NICOLÁS J M. Application of agglomerative hierarchical clustering to identify consumer tomato preferences: influence of physicochemical and sensory characteristics on consumer response[J]. Journal of the Science of Food and Agriculture, 2006, 86(4): 493-499. DOI:10.1002/jsfa.2392.
HUANG M G, LI Y L, ZHAN P, et al. Correlation of volatile compounds and sensory attributes of Chinese traditional sweet fermented flour pastes using hierarchical cluster analysis and partial least squares-discriminant analysis[J]. Journal of Chemistry, 2017, 2017: 3213492. DOI:10.1155/2017/3213492.
PEARSON K. LIII. On lines and planes of closest fit to systems of points in space[J]. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 1901, 2(11): 559-572. DOI:10.1080/14786440109462720.
WOLD S, ESBENSEN K, GELADI P. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1/2/3): 37-52. DOI:10.1016/0169-7439(87)80084-9.
LI M Q, YANG R W, ZHANG H, et al. Development of a flavor fingerprint by HS-GC-IMS with PCA for volatile compounds of Tricholoma matsutake Singer[J]. Food Chemistry, 2019, 290: 32-39. DOI:10.1016/j.foodchem.2019.03.124.
LENG P, HU H W, CUI A H, et al. HS-GC-IMS with PCA to analyze volatile flavor compounds of honey peach packaged with different preservation methods during storage[J]. LWT-Food Science and Technology, 2021, 149: 111963. DOI:10.1016/j.lwt.2021.111963.
ABIODUN O I, JANTAN A, OMOLARA A E, et al. State-of-the-art in artificial neural network applications: a survey[J]. Heliyon, 2018, 4(11): e00938. DOI:10.1016/j.heliyon.2018.e00938.
HUANG Y B. Advances in artificial neural networks: methodological development and application[J]. Algorithms, 2009, 2(3): 973-1007. DOI:10.3390/algor2030973.
CUI J W, WANG Y H et al. Prediction of flavor of Maillard reaction product of beef tallow residue based on artificial neural network[J]. Food Chemistry: X, 2022, 15: 100447. DOI:10.1016/j.fochx.2022.100447.
HUANG X, WANG H K, LUO W J, et al. Prediction of loquat soluble solids and titratable acid content using fruit mineral elements by artificial neural network and multiple linear regression[J]. Scientia Horticulturae, 2021, 278: 109873. DOI:10.1016/j.scienta.2020.109873.
SINGH R R B, RUHIL A P, JAIN D K, et al. Prediction of sensory quality of UHT milk: a comparison of kinetic and neural network approaches[J]. Journal of Food Engineering, 2009, 92(2): 146-151. DOI:10.1016/j.jfoodeng.2008.10.032.
GU J X, WANG Z H, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern recognition, 2018, 77: 354-377. DOI:10.1016/j.patcog.2017.10.013.
LI J, CHEN M L, MAO Q Z, et al. Deep learning based flavor evaluation of rice wine[J]. AIP Conference Proceedings, 2020, 2208: 020034. DOI:10.1063/5.0000289.
CHANG Y T, HSUEH M C, HUNG S P, et al. Prediction of specialty coffee flavors based on near-infrared spectra using machine-and deeplearning methods[J]. Journal of the Science of Food and Agriculture, 2021, 101(11): 4705-4714. DOI:10.1002/jsfa.11116.
QI L L, DU J L, SUN Y, et al. Umami-MRNN: deep learning-based prediction of umami peptide using RNN and MLP[J]. Food Chemistry, 2023, 405: 134935. DOI:10.1016/j.foodchem.2022.134935.
SHERSTINSKY A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306. DOI:10.1016/j.physd.2019.132306.
TAKEOKA G R, BUTTERY R G, LING L C, et al. Odor thresholds of various unsaturated branched esters[J]. LWT-Food Science and Technology, 1998, 31(5): 443-448. DOI:10.1006/fstl.1998.0382.
QUEIROZ L P, NOGUEIRA I B R. Generating flavor molecules using scientific machine learning[J]. ACS Omega, 2023, 8(12): 10875-10887. DOI:10.1021/acsomega.2c07176.
BOCCORH R K, PATERSON A. An artificial neural network model for predicting flavour intensity in blackcurrant concentrates[J]. Food Quality and Preference, 2002, 13(2): 117-128. DOI:10.1016/s0950-3293(01)00072-6.
MEN H, SHI Y, FU S L, et al. Mining feature of data fusion in the classification of beer flavor information using E-tongue and E-nose[J]. Sensors, 2017, 17(7): 1656. DOI:10.3390/s17071656.
VIEJO C G, TONGSON E J, FUENTES S. Integrating a low-cost electronic nose and machine learning modelling to assess coffee aroma profile and intensity[J]. Sensors, 2021, 21(6): 2016. DOI:10.3390/s21062016.
BI K X, ZHANG D, QIU T, et al. GC-MS fingerprints profiling using machine learning models for food flavor prediction[J]. Processes, 2019, 8(1): 23. DOI:10.3390/pr8010023.
CHEN C, HUSNY J, RABE S. Predicting fishiness off-flavour and identifying compounds of lipid oxidation in dairy powders by SPME-GC/MS and machine learning[J]. International Dairy Journal, 2018, 77: 19-28. DOI:10.1016/j.idairyj.2017.09.009.
TIAN H X, LIU H, HE Y J, et al. Combined application of electronic nose analysis and back-propagation neural network and random forest models for assessing yogurt flavor acceptability[J]. Journal of Food Measurement and Characterization, 2020, 14(1): 573-583. DOI:10.1007/s11694-019-00335-w.
WU D L, LUO D H, WONG K Y, et al. POP-CNN: predicting odor pleasantness with convolutional neural network[J]. IEEE Sensors Journal, 2019, 19(23): 11337-11345. DOI:10.1109/JSEN.2019.2933692.
BRENDEL R, SCHWOLOW S, ROHN S, et al. Gas-phase volatilomic approaches for quality control of brewing hops based on simultaneous GC-MS-IMS and machine learning[J]. Analytical and Bioanalytical Chemistry, 2020, 412(26): 7085-7097. DOI:10.1007/s00216-020-02842-y.
LIU M, HAN X M, TU K, et al. Application of electronic nose in Chinese spirits quality control and flavour assessment[J]. Food Control, 2012, 26(2): 564-570. DOI:10.1016/j.foodcont.2012.02.024.
VIEJO C G, FUENTES S, TORRICO D D, et al. Assessment of beer quality based on a robotic pourer, computer vision, and machine learning algorithms using commercial beers[J]. Journal of Food Science, 2018, 83(5): 1381-1388. DOI:10.1111/1750-3841.14114.
TEYE E, HUANG X Y, HAN F K, et al. Discrimination of cocoa beans according to geographical origin by electronic tongue and multivariate algorithms[J]. Food Analytical Methods, 2014, 7(2): 360-365. DOI:10.1007/s12161-013-9634-4.
TIAN X J, WANG J, MA Z R, et al. Combination of an E-nose and an E-tongue for adulteration detection of minced mutton mixed with pork[J]. Journal of Food Quality, 2019, 2019: 4342509. DOI:10.1155/2019/4342509.
BOUGRINI M, TAHRI K, SAIDI T, et al. Classification of honey according to geographical and botanical origins and detection of its adulteration using voltammetric electronic tongue[J]. Food Analytical Methods, 2016, 9(8): 2161-2173. DOI:10.1007/s12161-015-0393-2.
ORDUKAYA E, KARLIK B. Quality control of olive oils using machine learning and electronic nose[J]. Journal of Food Quality, 2017, 2017: 1-7. DOI:10.1155/2017/9272404.
AYARI F, MIRZAEE-GHALEH E, RABBANI H, et al. Detection of the adulteration in pure cow ghee by electronic nose method(case study: sunflower oil and cow body fat)[J]. International Journal of Food Properties, 2018, 21(1): 1670-1679. DOI:10.1080/10942912.2018.1505755.
KOYAMA K, TANAKA M, CHO B H, et al. Predicting sensory evaluation of spinach freshness using machine learning model and digital images[J]. PLoS ONE, 2021, 16(3): e0248769. DOI:10.1371/journal.pone.0248769.
YANG H H, WANG Y T, ZHAO J Y, et al. A machine learning method for juice human sensory hedonic prediction using electronic sensory features[J]. Current Research in Food Science, 2023, 7: 100576. DOI:10.1016/j.crfs.2023.100576.
ZHOU F, JIANG Y C, QIAN Y, et al. Product consumptions meet reviews: inferring consumer preferences by an explainable machine learning approach[J]. Decision Support Systems, 2024, 177: 114088. DOI:10.1016/j.dss.2023.114088.
MORO S, CORTEZ P, RITA P. A data-driven approach to predict the success of bank telemarketing[J]. Decision Support Systems, 2014, 62: 22-31. DOI:10.1016/j.dss.2014.03.001.
VIEJO C G, TORRICO D D, DUNSHEA F R, et al. Emerging technologies based on artificial intelligence to assess the quality and consumer preference of beverages[J]. Beverages, 2019, 5(4): 62. DOI:10.3390/beverages5040062.
HAMILTON L M, LAHNE J. Fast and automated sensory analysis: using natural language processing for descriptive lexicon development[J]. Food Quality and Preference, 2020, 83: 103926. DOI:10.1016/j.foodqual.2020.103926.
AL-RIFAIE M M, GONCALVES A, CAVAZZA M. Evolutionary optimisation of beer organoleptic properties: a simulation framework[J]. Foods, 2022, 11(3): 351. DOI:10.3390/foods11030351.
京公网安备11010802044758号