2026-04-16T21:03:45Zhttps://repositorio.cuc.edu.co/server/oai/request

oai:repositorio.cuc.edu.co:11323/103102024-09-17T16:04:12Zcom_11323_3col_11323_2032

Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) Derechos de autor 2021 INGE CUC https://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess http://purl.org/coar/access_right/c_abf2 Mantilla Ramírez, Naren Arley Ruiz Jimenez, Luisa Fernanda Ortega Boada, Homero Sepúlveda Sepúlveda, Alexander 2023-07-10T16:42:54Z 2023-07-10T16:42:54Z 2021 N. Mantilla Ramírez, L. Ruiz Jiménez, H. Ortega Boada & A. Sepúlveda Sepúlveda, “Identificación de especies de maderas locales mediante el uso de nariz electrónica y aprendizaje automático: un experimento preliminar”, INGECUC, vol. 17. no. 1, pp. 188–205. DOI: http://doi.org/10.17981/ingecuc.17.1.2021.15 0122-6517 https://hdl.handle.net/11323/10310 10.17981/ingecuc.17.1.2021.15 2382-4700 Corporación Universidad de la Costa REDICUC - Repositorio CUC https://repositorio.cuc.edu.co/ Introducción— La deforestación y extracción desordenada de madera ponen en peligro algunas especies maderables vulnerables. Estas especies prohibidas podrían detectarse durante su proceso de transporte si las entidades de vigilancia y control tuvieran los instrumentos de seguimiento adecuados. Si bien en trabajos anteriores se reportan métodos para identificar especies de madera, estos no son aplicables a sitios alejados de las principales ciudades. Objetivo— En el presente trabajo se propone utilizar narices electrónicas (arreglos de sensores químicos) para identificar especies maderables, a partir de los compuestos volátiles que estas emanan. Metodología— La medición de aromas se realiza mediante el uso de una matriz de 16 sensores químicos, cuyas curvas son la entrada a un procedimiento de estimación de características. Luego, se realiza un análisis de componentes principales, para finalmente aplicar una estrategia de clasificación basada en máquinas de vectores de soporte. En contraste a trabajos previos, en el presente trabajo las condiciones de recolección de muestras son más cercanas a las encontradas en entornos reales para los cuales este trabajo busca resolver el problema. Además, el número de muestras es mayor y más variado. Sin embargo, el número de muestras recolectadas para cada especie no está balanceado; por lo tanto, se aplica una técnica de aumento de datos para compensar el desequilibrio en las clases. Resultados— Al realizar los experimentos se encuentra un desempeño de aproximadamente 80%. Conclusiones— A pesar de los resultados prometedores, se deben realizar mayores esfuerzos para obtener un mejor desempeño. Introduction— Deforestation and disordered timber extraction endanger some vulnerable timber species. These prohibited species could be detected during their transportation process if surveillance and control entities had adequate monitoring instruments. Although methods for identifying wood species are reported in previous works, they are not applicable to sites far from the main cities. Objective— In present work it is proposed to use electronic noses (chemical sensor arrays) in order to quickly identify wood species, from the volatile compounds their timbers emanate. Methodology— The measurement of aromas is done by using an array of 16 chemical sensors, whose curves are the input to a feature estimation procedure. Then, principal component analysis is performed, to finally apply a classification strategy based on support vector machines. In contrast to previous works, in present work the samples collection conditions are closer to those found on real environments for which this work seeks to solve the problem. In addition, the number of samples is larger and more varied. However, the number of samples collected for each species is not balanced; thus, a data augmentation technique is applied to compensate the class imbalance. Results— When carrying out the experiments, a performance of approximately 80% is found. Conclusions— Although the promising results, greater efforts must be carried out in order to obtain a better performance 13 páginas application/pdf eng Corporación Universidad de la Costa Colombia Identificación de especies de maderas locales mediante el uso de nariz electrónica y aprendizaje automático: un experimento preliminar Identification of local wood species by using electronic nose and machine learning: a preliminary experiment Artículo de revista http://purl.org/coar/resource_type/c_6501 Text info:eu-repo/semantics/article http://purl.org/redcol/resource_type/ART info:eu-repo/semantics/publishedVersion http://purl.org/coar/version/c_970fb48d4fbd8a85 INGE CUC [1] E. A. Wheeler & P. Baas, “Wood identification-a review,” IAWA J, vol. 19, no. 3, pp. 241–264, 1998. Available: https://brill.com/view/journals/iawa/19/3/article-p241_2.xml?language=en [2] F. Hanssen, N. Wischnewski, U. Moreth & E. A. Magel, “Molecular identification of Fitzroya cupressoides, Sequoia sempervirens, and Thuja plicata wood using taxon-specific rDNA-ITS primers,” IAWA J, vol. 32, no. 2, pp. 273–283, 2011. https://doi.org/10.1163/22941932-90000057 [3] M. Yu, K. Liu, L. Zhou, L. Zhao & S. Liu, “Testing three proposed DNA barcodes for the wood identification of Dalbergia odorifera T. Chen and Dalbergia tonkinensis Prain,” Holzforschung, vol. 70, no. 2, pp. 127–136, 2016. https://doi.org/10.1515/hf-2014-0234 [4] E. C. Cabral, R. C. Simas, V. G. Santos, C. L. Queiroga, V. S. da Cunha, G. F. de Sá, R. J. Daroda & M. N. Eberlin, “Wood typification by Venturi easy ambient sonic spray ionization mass spectrometry: The case of the endangered Mahogany tree,” J. Mass Spectrom, vol. 47, no. 1, pp. 1–6, 2012. https://doi. org/10.1002/jms.2016 [5] R. Rana, G. Müller, A. Naumann & A. Polle, “FTIR spectroscopy in combination with principal component analysis or cluster analysis as a tool to distinguish beech (Fagus sylvatica L.) trees grown at different sites,” Holzforschung, vol. 62, no. 5, pp. 530–538, 2008. https://doi.org/10.1515/HF.2008.104 [6] A. Dickson, B. Nanayakkara, D. Sellier, D. Meason, L. Donaldson & R. Brownlie, “Fluorescence imaging of cambial zones to study wood formation in Pinus radiata D. Don,” Trees - Struct Funct, vol. 31, no. 2, pp. 479–490, 2017. https://doi.org/10.1007/s00468-016-1469-3 [7] J. M. Kalaw & F. B. Sevilla, “Discrimination of wood species based on a carbon nanotube/polymer composite chemiresistor array,” Holzforschung, vol. 72, no. 3, pp. 215–223, 2018. https://doi.org/10.1515/ hf-2017-0097 [8] R. Fedele, I. E. Galbally, N. Porter, and I. A. Weeks, “Biogenic VOC emissions from fresh leaf mulch and wood chips of Grevillea robusta (Australian Silky Oak),” Atmos Environ, vol. 41, no. 38, pp. 8736– 8746. Dec. 2007. https://doi.org/10.1016/j.atmosenv.2007.07.037 [9] K. Müller, S. Haferkorna, W. Grabmer, A. Wisthaler, A. Hansel, J. Kreuzwieser, C. Cojocariu, H. Rennenberg & H. Herrmanna, “Biogenic carbonyl compounds within and above a coniferous forest in Germany,” Atmos Environ, vol. 40, No. 1, pp. 81–91, 2006. https://doi.org/10.1016/j.atmosenv.2005.10.070 [10] H. J. I. Rinne, A. B. Guenther, J. P. Greenberg & P. C. Harley, “Isoprene and monoterpene fluxes measured above Amazonian rainforest and their dependence on light and temperature,” Atmos Environ, vol. 36, no. 14, pp. 2421–2426, May. 2002. https://doi.org/10.1016/S1352-2310(01)00523-4 [11] A. D. Wilson, D. G. Lester & C. S. Oberle, “Application of conductive polymer analysis for wood and woody plant identifications,” For Ecol Manage, vol. 209, no. 3, pp. 207–224, May. 2005. https://doi. org/10.1016/j.foreco.2005.01.030 [12] H. Shi, M. Zhang & B. Adhikari, “Advances of electronic nose and its application in fresh foods: A review,” Crit Rev Food Sci Nutr, vol. 58, no. 16, pp. 1–11, 2017. https://doi.org/10.1080/10408398.2017.1 327419 [13] L. Capelli, S. Sironi & R. Del Rosso, “Electronic Noses for Environmental Monitoring Applications,” Sensors, vol. 14, no. 11, pp. 19979–20007, 2014. https://doi.org/10.3390/s141119979 [14] L. Guo, Z. Yang & X. Dou, “Artificial Olfactory System for Trace Identification of Explosive Vapors Realized by Optoelectronic Schottky Sensing,” Adv Mater, vol. 29, no. 5, pp. 1–8, 2017. https://doi. org/10.1002/adma.201604528 [15] J. P. Santos & J. Lozano, “Real time detection of beer defects with a hand held electronic nose ,” presented at 10th Spanish Conference on Electron Devices, CDE, MD, ES, pp. 1–4, 11-13 Feb. 20015. https://doi.org/10.1109/CDE.2015.7087492 [16] J. R. Cordeiro, R. W. C. Li, É. S. Takahashi, G. P. Rehder, G. Ceccantini & J. Gruber, “Wood identification by a portable low-cost polymer-based electronic nose,” RSC Adv, vol. 6, no. 111, pp. 109945– 109949, 2016. https://doi.org/10.1039/c6ra22246c [17] A. D. Wilson, “Application of a Conductive Polymer Electronic-Nose Device to Identify Aged Woody Samples,” 3 IARIA, Xpert Publishing, RO, IT, pp. 77–82, 2012. Available: https://www.fs.usda.gov/ treesearch/pubs/45153 [18] F. X. Garneau, B. Riedl, S. Hobbs, A. Pichette & H. Gagnon, “The use of sensor array technology for rapid differentiation of the sapwood and heartwood of Eastern Canadian spruce, fir and pine,” Holz als Roh- und Werkst, vol. 62, no. 6, pp. 470–473, 2003. https://doi.org/10.1007/s00107-004-0508-8 [19] L. F. Ruiz, “Detección de los insectos de la subfamilia Triatominae basado en narices electrónicas,” tesis maestría, UIS, BGA, CO, 2018. [20] Figaro Engineering Inc, “Operating principle,” figaro Engineering, 2018. Available: https://www.figarosensor.com/technicalinfo/principle/mos-type.html [21] Jia Yan, X. Guo, S. Duan, P. Jia, L. Wang, C Peng & S. Zhang, “Electronic Nose Feature Extraction Methods: A Review,” Sensors, vol. 15, no. 11, pp. 27804 –27831, Nov. 2015. https://doi.org/10.3390/ s151127804 [22] I. Rodriguez-Lujan, J. Fonollosa, A. Vergara, M. Homer & R. Huerta, “On the calibration of sensor arrays for pattern recognition using the minimal number of experiments,” Chemom Intell Lab Syst, vol. 130, pp. 123–134, Jan. 2014. https://doi.org/10.1016/j.chemolab.2013.10.012 [23] L. Carmel, S. Levy, D. Lancet & D. Harel, “A feature extraction method for chemical sensors in electronic noses,” Sens Actuators B:Chem, vol. 93, no. 1-3, pp. 67–76, Aug. 2003. https://doi.org/10.1016/ S0925-4005(03)00247-8 [24] J. Van Hulse, T. M. Khoshgoftaar & A. Napolitano, “Experimental perspectives on learning from imbalanced data,” presented at Proceedings of the 24th international conference on Machine learnin, ICML, NY, USA., pp. 935–942, Jun. 20, 2007. https://doi.org/10.1145/1273496.1273614 [25] D. A. Cieslak, N. V Chawla & A. Striegel, “Combating imbalance in network intrusion datasets,” IEEE International Conference on Granular Computing, GRC, ATL, USA, pp. 732–737, 2006. https://doi. org/10.1109/GRC.2006.1635905 [26] R. Blagus & L. Lusa, “Class prediction for high-dimensional class-imbalanced data,” BMC Bioinf, vol. 11, no. 1, pp. 1–17, 2010. https://doi.org/10.1186/1471-2105-11-523 [27] N. V Chawla, K. W. Bowyer, L. O. Hall & W. P. Kegelmeyer, “SMOTE: synthetic minority over-sampling technique,” J Artif Intell Res, vol. 16, pp. 321–357, 2002. https://doi.org/10.1613/jair.953 [28] M. A. Akbar, A. Ait Si Ali, A. Amira, F. Bensaali, M. Benammar, M. Hassan & A. Bermak, “An Empirical Study for PCA and LDA-Based Feature Reduction for Gas Identification,” IEEE Sens J, vol. 16, no. 14, pp. 5734–5746, 2016. https://doi.org/10.1109/JSEN.2016.2565721 [29] I. Goodfellow, Y. Bengio & A. Courville, Deep Learning, CBG: MIT Press, 2016. [30] J. Friedman, T. Hastie & R. Tibshirani, The elements of statistical learning, NY, USA: Springer, 2001. [31] G. James, D. Witten, T. Hastie & R. Tibshirani, An introduction to statistical learning. NY, USA: Springer, 2013. 200 188 1 17 Identificación de madera Nariz electrónica Matriz de sensores químicos Aplicaciones de aprendizaje automático Clasificación de Vectores de Soporte (SVM) Aumento de datos Wood identification Electronic Nose (E-Nose) Chemical sensor arrays Machine learning applications Support Vector Classification (SVM) Data augmentation Publicationopen.access