Random Forest, Artificial Neural Network, and Support Vector Machine Models for Honey Classification

  1. Martinez‐Castillo, Cecilia 11
  2. Astray, Gonzalo 1
  3. Mejuto, Juan Carlos 1
  4. Simal‐Gandara, Jesus 1
  1. 1 Universidade de Vigo
    info

    Universidade de Vigo

    Vigo, España

    ROR https://ror.org/05rdf8595

Revista:
eFood

ISSN: 2666-3066 2666-3066

Ano de publicación: 2019

Volume: 1

Número: 1

Páxinas: 69-76

Tipo: Artigo

DOI: 10.2991/EFOOD.K.191004.001 GOOGLE SCHOLAR lock_openAcceso aberto editor

Outras publicacións en: eFood

Objetivos de desarrollo sostenible

Resumo

Diferent separated protein fractions by the electrophoretic method in polyacrylamide gel were used to classify two diferent types of honeys, Galician honeys and commercial honeys produced and packaged outside of Galicia. Random forest, artiicial neural network, and support vector machine models were tested to diferentiate Galician honeys and other commercial honeys produced and packaged outside of Galicia. he results obtained for the best random forest model allowed us to determine the origin of honeys with an accuracy of 95.2%. he random forest model, and the other developed models, could be improved with the inclusion of new data from diferent commercial honeys.

Referencias bibliográficas

  • [1] Saurina J. Characterization of wines using compositional profiles and chemometrics. Trends Anal Chem 2010;29:234–45.
  • [2] Maione C, Barbosa F Jr, Barbosa RM. Predicting the botanical and geographical origin of honey with multivariate data analy-sis and machine learning techniques: a review. Comput Electron Agric 2019;157:436–46.
  • [3] Cuevas-Glory LF, Pino JA, Santiago LS, Sauri-Duch E. A review of volatile analytical methods for determining the botanical origin of honey. Food Chem 2007;103:1032–43.
  • [4] Siddiqui AJ, Musharraf SG, Iqbal Choudhary M, Rahman AU. Application of analytical methods in authentication and adulter-ation of honey. Food Chem 2017;217:687–98.
  • [5] Oroian M, Ropciuc S, Paduret S. Honey authentication using rheological and physicochemical properties. J Food Sci Technol 2018;55:4711–18.
  • [6] da Silva PM, Gauche C, Gonzaga LV, Costa ACO, Fett R. Honey: chemical composition, stability and authenticity. Food Chem 2016;196:309–23.
  • [7] Bertelli D, Lolli M, Papotti G, Bortolotti L, Serra G, Plessi M. Detection of honey adulteration by sugar syrups using one- dimensional and two-dimensional high-resolution nuclear mag-netic resonance. J Agric Food Chem 2010;58:8495–501.
  • [8] Gallego-Picó A, Garcinuño-Martínez RM, Fernández-Hernando P. Chapter 20 - Honey authenticity and traceability. Compr Anal Chem 2013;60:511–41.
  • [9] European Commission. Quality schemes explained. https://ec.europa.eu/info/food-farming-fisheries/food-safety-and-qual-ity/certification/quality-labels/quality-schemes-explained_en; 2019 (accessed on August 21, 2019).
  • [10] Cotte JF, Casabianca H, Chardon S, Lheritier J, Grenier-Loustalot MF. Application of carbohydrate analysis to verify honey authen-ticity. J Chromatogr A 2003;1021:145–55.
  • [11] Puscas A, Hosu A, Cimpoiu C. Application of a newly developed and validated high-performance thin-layer chromatographic method to control honey adulteration. J Chromatogr A 2013;1272:132–5.
  • [12] Guler A, Bakan A, Nisbet C, Yavuz O. Determination of import-ant biochemical properties of honey to discriminate pure and adulterated honey with sucrose (Saccharum officinarum L.) syrup. Food Chem 2007;105:1119–25.
  • [13] Azevedo MS, Valentim-Neto PA, Seraglio SKT, da Luz CFP, Arisi ACM, Costa ACO. Proteome comparison for discrimina-tion between honeydew and floral honeys from botanical species Mimosa scabrella Bentham by principal component analysis. J Sci Food Agric 2017;97:4515–9.
  • [14] Won SR, Li CY, Kim JW, Rhee HL. Immunological characteri-zation of honey major protein and its application. Food Chem 2009;113:1334–8.
  • [15] Lee DC, Lee SY, Cha SH, Choi YS, Rhee HI. Discrimination of native bee-honey and foreign bee-honey by SDS–PAGE. Korean J Food Sci 1998;30:1–5.
  • [16] Anklam E. A review of the analytical methods to determine the geo-graphical and botanical origin of honey. Food Chem 1998;63:549–62.
  • [17] Latorre MJ, Peña R, García S, Herrero C. Authentication of Galician (N.W. Spain) honeys by multivariate techniques based on metal content data. Analyst 2000;125:307–12.
  • [18] RapidMiner GmbH. RapidMiner Documentation. https://rapid-miner.com/; 2018 (accessed on August 21, 2019).
  • [19] Tian Y, Yan C, Zhang T, Tang H, Li H, Yu J, et al. Classification of wines according to their production regions with the contained trace elements using laser-induced breakdown spectroscopy. Spectrochim Acta B 2017;135:91–101.
  • [20] Breiman L. Random forests. Mach Learn 2001;45:5–32.
  • [21] Vigneau E, Courcoux P, Symoneaux R, Guérin L, Villière A. Random forests: a machine learning methodology to highlight the volatile organic compounds involved in olfactory perception. Food Quality and Preference 2018;68:135–45.
  • [22] Bauder RA, Khoshgoftaar TM. Medicare fraud detection using random forest with class imbalanced big data. In: Proceedings of the 2018 IEEE 19th International Conference on Information Reuse and Integration (IRI). Salt Lake City, UT, USA: IEEE; 2018. pp. 80–7.
  • [23] Herzallah W, Faris H, Adwan O. Feature engineering for detect-ing spammers on Twitter: modelling and analysis. J Inform Sci 2018;44:230–47.
  • [24] Osawa T, Kohyama K, Mitsuhashi H. Multiple factors drive regional agricultural abandonment. Sci Total Environ 2016;542:478–83.
  • [25] Vitale M, Proietti C, Cionni I, Fischer R, De Marco A. Random forests analysis: a useful tool for defining the relative importance of environmental conditions on crown defoliation. Water Air Soil Pollut 2014;225:1–17.
  • [26] Myronidis D, Ioannou K. Forecasting the urban expansion effects on the design storm hydrograph and sediment yield using artifi-cial neural networks. Water (Switzerland) 2019;11:31.
  • [27] Qaderi F, Babanezhad E. Prediction of the groundwater remedi-ation costs for drinking use based on quality of water resource, using artificial neural network. J Clean Prod 2017;161:840–9.
  • [28] Fazelpour F, Tarashkar N, Rosen MA. Short-term wind speed forecasting using artificial neural networks for Tehran, Iran. Int J Energy Environ Eng 2016;7:377–90.
  • [29] Sholahudin S, Han H. Simplified dynamic neural network model to predict heating load of a building using Taguchi method. Energy 2016;115:1672–78.
  • [30] Azizi A, Abbaspour-Gilandeh Y, Nooshyar M, Afkari-Sayah A. Identifying potato varieties using machine vision and artificial neural networks. Int J Food Prop 2016;19:618–35.
  • [31] Kalogirou SA. Artificial neural networks in renewable energy systems applications: a review. Renew Sustain Energy Rev 2001;5:373–401.
  • [32] Dong Q, Xing K, Zhang H. Artificial neural network for assess-ment of energy consumption and cost for cross laminated timber office building in severe cold regions. Sustainability (Switzerland) 2018;10:1–15.
  • [33] Astray G, Mejuto JC, Martínez-Martínez V, Nevares I, Alamo-Sanza M, Simal-Gandara J. Prediction models to control aging time in red wine. Molecules 2019;24:pii: E826.
  • [34] Gonzalez-Fernandez I, Iglesias-Otero MA, Esteki M, Moldes OA, Mejuto JC, Simal-Gandara J. A critical review on the use of artificial neural networks in olive oil production, characterization and authentication. Crit Rev Food Sci Nutr 2019;59:1913–26.
  • [35] Moldes ÓA, Morales J, Cid A, Astray G, Montoya IA, Mejuto JC. Electrical percolation of AOT-based microemulsions with n- alcohols. J Mol Liquids 2016;215:18–23.
  • [36] Jiang M, Ma C, Xia F, Zhang Y. Application of artificial neural networks to predict the hardness of Ni–TiN nanocoatings fabricated by pulse electrodeposition. Surf Coat Technol 2016;286:191–6.
  • [37] Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual Workshop on Computational Learning Theory (COLT). Pittsburgh, PA, USA: ACM; 1992. pp. 144–52.
  • [38] Srestasathiern P, Lawawirojwong S, Suwantong R. Support vector regression for rice age estimation using satellite imagery. In: Proceedings of the 2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). Chiang Mai, Thailand: IEEE; 2016. pp. 1–5.
  • [39] Ríos-Reina R, Elcoroaristizabal S, Ocaña-González JA, García-González DL, Amigo JM, Callejón RM. Characterization and authentication of Spanish PDO wine vinegars using multi-dimensional fluorescence and chemometrics. Food Chem 2017;230:108–16.
  • [40] Wang C, Li Z. Weed recognition using SVM model with fusion height and monocular image features. Trans Chinese Soc Agric Eng 2016;32:165–74.
  • [41] Qiao Z, Zhang Q, Dong Y, Yang JJ. Application of SVM based on genetic algorithm in classification of cataract fundus images. In: Proceedings of the 2017 IEEE International Conference on Imaging Systems and Techniques (IST). Beijing, China: IEEE; 2017. pp. 1–5.
  • [42] Chan K, Lee TW, Sample PA, Goldbaum MH, Weinreb RN, Sejnowski TJ. Comparison of machine learning and traditional classifiers in glaucoma diagnosis. IEEE Trans Biomed Eng 2002;49:963–74.
  • [43] Deng S, Yeh TH. Using least squares support vector machines for the airframe structures manufacturing cost estimation. Int J Prod Econ 2011;131:701–8.
  • [44] Shen W, Zhang Y, Ma X. Stock return forecast with LS-SVM and particle swarm optimization. In: Proceedings of the 2009 International Conference on Business Intelligence and Financial Engineering (BIFE). Beijing, China: IEEE; 2009. pp. 143–7.
  • [45] Akroyd P. Acrylamide gel slab electrophoresis in a simple glass cell for improved resolution and comparison of serum proteins. Anal Biochem 1967;19:399–410.
  • [46] Rodríguez-Otero JL, Paseiro Losada P, Simal-Lozano J, Cepeda Saez A. Intento de caracterización de las mieles de Galicia medi-ante las fracciones proteicas separadas por electroforesis de disco. Anal Bromatol 1990;XLII-1:83–98.
  • [47] Minaei S, Shafiee S, Polder G, Moghadam-Charkari N, van Ruth S, Barzegar M, et al. VIS/NIR imaging application for honey floral origin determination. Infrared Phys Technol 2017;86:218–25.
  • [48] Cajka T, Hajslova J, Pudil F, Riddellova K. Traceability of honey origin based on volatiles pattern processing by artificial neural networks. J Chromatogr A 2009;1216:1458–62.
  • [49] Anjos O, Iglesias C, Peres F, Martínez J, García Á, Taboada J. Neural networks applied to discriminate botanical origin of honeys. Food Chem 2015;175:128–36.
  • [50] Zhu X, Li S, Shan Y, Zhang Z, Li G, Su D, et al. Detection of adul-terants such as sweeteners materials in honey using near-infrared spectroscopy and chemometrics. J Food Eng 2010;101:92–7.
  • [51] Bisutti V, Merlanti R, Serva L, Lucatello L, Mirisola M, Balzan S, et al. Multivariate and machine learning approaches for honey botanical origin authentication using near infrared spectroscopy. J Near Infrared Spectrosc 2019;27:65–74.
  • [52] Gan Z, Yang Y, Li J, Wen X, Zhu M, Jiang Y, et al. Using sensor and spectral analysis to classify botanical origin and determine adulteration of raw honey. J Food Eng 2016;178:151–8.
  • [53] Batista BL, da Silva LRS, Rocha BA, Rodrigues JL, Berretta-Silva AA, Bonates TO, et al. Multi-element determination in Brazilian honey samples by inductively coupled plasma mass spectrometry and estimation of geographic origin with data mining techniques. Food Res Int 2012;49:209–15.
  • [54] Dai X, Shi H, Li Y, Ouyang Z, Huo Z. Artificial neural network models for estimating regional reference evapotranspiration based on climate factors. Hydrol Process 2009;23:442–50.
  • [55] da Costa NL, Llobodanin LAG, de Lima MD, Castro IA, Barbosa R. Geographical recognition of Syrah wines by combining feature selec-tion with extreme learning machine. Measurement 2018;120:92–9.
  • [56] Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing 2006;70:489–501.
  • [57] Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2011;2:27.
  • [58] Chang CC, Lin CJ. LIBSVM: a library for support vector machines. https://www.csie.ntu.edu.tw/~cjlin/libsvm/; 2018 (accessed on August 21, 2019).
  • [59] Hsu CW, Chang CC, Lin CJ. A practical guide to support vector classification. https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf; 2003. pp. 1–16.