(De La Salle University, Philippines)(2) Ronnie II Sabino Concepcion
(De La Salle University, Philippines)(3) Jonnel Dorado Alejandrino
(De La Salle University, Philippines)(4) Rogelio Ruzcko Tobias
(De La Salle University, Philippines)(5) Elmer Pamisa Dadios
(De La Salle University, Philippines)*corresponding author
AbstractClassification of lettuce life or growth stages is an effective tool for measuring the performance of an aquaponics system. It determines the balance in water nutrients, adequate temperature and lighting, other environmental factors, and the system’s productivity to sustain cultivars. This paper proposes a classification of lettuce life stages planted in an aquaponics system. The classification was done using the texture features of the leaves derived from machine vision algorithms. The attributes underwent three different feature selection processes, namely: Univariate Selection (US), Recursive Feature Elimination (RFE), and Feature Importance (FI) to determine the four most significant features from the original eight attributes. The features selected were used for training four estimators from Decision Trees Classifier (DTC), Gaussian Naïve Bayes (GNB), Stochastic Gradient Descent (SGD), and Linear Discriminant Analysis (LDA). The models trained using DTC and SGD were then optimized as they have hyperparameters for tuning. A comparative analysis among Machine Learning (ML) algorithms was conducted to identify the best-performing model with the given application. The best features were derived from US and FI as they have the same top four features using the DTC estimator optimized with the hyperparameters tuned to max depth having 5, criterion equated to ‘Gini', and splitter was set to 'Best'. The accuracy obtained from cross-validation evaluation resulted in 87.92%. Considering consistency with hold-out validation, LDA outperforms optimized DTC even with lower accuracy of 86.67%. This accuracy of LDA outperformed DTC due to its sufficient fit for generalizing the testing data on classifying lettuce growth stage.
KeywordsAquaponics Feature selection Growth stage classification Machine learning Machine vision
|
DOIhttps://doi.org/10.26555/ijain.v6i2.466 |
Article metricsAbstract views : 2319 | PDF views : 283 |
Cite |
Full Text Download
|
References
[1] S. A. A. Abusin and B. W. Mandikiana, “Towards sustainable food production systems in Qatar: Assessment of the viability of aquaponics,” Glob. Food Sec., no. December 2019, p. 100349, 2020, doi: 10.1016/j.gfs.2020.100349.
[2] A. T. Le, Y. Wang, L. Wang, V. C. Ta, and D. Li, “Numerical investigation on a low energy-consumption heating method for recirculating aquaponic systems,” Comput. Electron. Agric., vol. 169, no. December 2018, p. 105210, 2020, doi: 10.1016/j.compag.2019.105210.
[3] D. Karimanzira and T. Rauschenbach, “Enhancing aquaponics management with IoT-based Predictive Analytics for efficient information utilization,” Inf. Process. Agric., vol. 6, no. 3, pp. 375–385, 2019, doi: 10.1016/j.inpa.2018.12.003.
[4] R. Chen, H. Liu, S. Song, G. Sun, and R. Chen, “Effects of light quality on growth and quality of lettuces in hydroponic,” 2015 12th China Int. Forum Solid State Light. SSLCHINA 2015, pp. 154–156, 2015, doi: 10.1109/SSLCHINA.2015.7360712.
[5] S. Gertphol, P. Chulaka, and T. Changmai, “Predictive models for lettuce quality from internet of things-based hydroponic farm,” 2018 22nd Int. Comput. Sci. Eng. Conf. ICSEC 2018, pp. 1–5, 2019, doi: 10.1109/ICSEC.2018.8712676.
[6] Z. Tang, Y. Su, M. J. Er, F. Qi, L. Zhang, and J. Zhou, “A local binary pattern based texture descriptors for classification of tea leaves,” Neurocomputing, vol. 168, pp. 1011–1023, 2015, doi: 10.1016/j.neucom.2015.05.024.
[7] M. T. Sánchez, J. A. Entrenas, I. Torres, M. Vega, and D. Pérez-Marín, “Monitoring texture and other quality parameters in spinach plants using NIR spectroscopy,” Comput. Electron. Agric., vol. 155, no. June, pp. 446–452, 2018, doi: 10.1016/j.compag.2018.11.004.
[8] L. Fu et al., “Banana detection based on color and texture features in the natural environment,” Comput. Electron. Agric., vol. 167, no. July, p. 105057, 2019, doi: 10.1016/j.compag.2019.105057.
[9] L. Wang, B. Cheng, Z. Li, T. Liu, and J. Li, “Intelligent tobacco flue-curing method based on leaf texture feature analysis,” Optik (Stuttg)., vol. 150, pp. 117–130, 2017, doi: 10.1016/j.ijleo.2017.09.088.
[10] T. Pahikkala et al., “Classification of plant species from images of overlapping leaves,” Comput. Electron. Agric., vol. 118, pp. 186–192, 2015, doi: 10.1016/j.compag.2015.09.003.
[11] J. G. Thanikkal, A. Kumar Dubey, and M. T. Thomas, “Whether color, shape and texture of leaves are the key features for image processing based plant recognition? An analysis!,” 2017 Recent Dev. Control. Autom. Power Eng. RDCAPE 2017, vol. 3, pp. 404–409, 2018, doi: 10.1109/RDCAPE.2017.8358305.
[12] T. U. Rehman, M. S. Mahmud, Y. K. Chang, J. Jin, and J. Shin, “Current and future applications of statistical machine learning algorithms for agricultural machine vision systems,” Comput. Electron. Agric., vol. 156, no. December 2018, pp. 585–605, 2019, doi: 10.1016/j.compag.2018.12.006.
[13] D. Mondal, D. K. Kole, and K. Roy, “Gradation of yellow mosaic virus disease of okra and bitter gourd based on entropy based binning and Naive Bayes classifier after identification of leaves,” Comput. Electron. Agric., vol. 142, no. October, pp. 485–493, 2017, doi: 10.1016/j.compag.2017.11.024.
[14] M. Safa, K. E. Martin, B. KC, R. Khadka, and T. M. R. Maxwell, “Modelling nitrogen content of pasture herbage using thermal images and artificial neural networks,” Therm. Sci. Eng. Prog., vol. 11, no. December 2018, pp. 283–288, 2019, doi: 10.1016/j.tsep.2019.04.005.
[15] J. Webel, J. Gola, D. Britz, and F. Mücklich, “A new analysis approach based on Haralick texture features for the characterization of microstructure on the example of low-alloy steels,” Mater. Charact., vol. 144, no. May, pp. 584–596, 2018, doi: 10.1016/j.matchar.2018.08.009.
[16] Y. Park and J. M. Guldmann, “Measuring continuous landscape patterns with Gray-Level Co-Occurrence Matrix (GLCM) indices: An alternative to patch metrics?,” Ecol. Indic., vol. 109, no. October 2019, p. 105802, 2020, doi: 10.1016/j.ecolind.2019.105802.
[17] M. K. Uçar, “Classification Performance-Based Feature Selection Algorithm for Machine Learning: P-Score,” Irbm, vol. 1, pp. 1–11, 2020, doi: 10.1016/j.irbm.2020.01.006.
[18] T. Emura, S. Matsui, and H. Y. Chen, “compound.Cox: univariate feature selection and compound covariate for predicting survival,” Comput. Methods Programs Biomed., vol. 168, pp. 21–37, 2019, doi: 10.1016/j.cmpb.2018.10.020.
[19] S. Chatterjee, D. Dey, and S. Munshi, “Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification,” Comput. Methods Programs Biomed., vol. 178, pp. 201–218, 2019, doi: 10.1016/j.cmpb.2019.06.018.
[20] S. Belciug, “Logistic regression paradigm for training a single-hidden layer feedforward neural network. Application to gene expression datasets for cancer research,” J. Biomed. Inform., vol. 102, p. 103373, 2020, doi: 10.1016/j.jbi.2019.103373.
[21] J. Heaton, S. McElwee, J. Fraley, and J. Cannady, “Early stabilizing feature importance for TensorFlow deep neural networks,” Proc. Int. Jt. Conf. Neural Networks, vol. 2017-May, pp. 4618–4624, 2017, doi: 10.1109/IJCNN.2017.7966442.
[22] R. F. de Mello, C. Manapragada, and A. Bifet, “Measuring the Shattering coefficient of Decision Tree models,” Expert Syst. Appl., vol. 137, pp. 443–452, 2019, doi: 10.1016/j.eswa.2019.07.012.
[23] R. S. Concepcion et al., “Trophic state assessment using hybrid classification tree- artificial neural network,” vol. 6, no. 1, pp. 1–13, 2019, doi: 10.26555/ijain.v6i1.408.
[24] S. Chen, G. I. Webb, L. Liu, and X. Ma, “A novel selective naïve Bayes algorithm,” Knowledge-Based Syst., vol. 192, p. 105361, 2019, doi: 10.1016/j.knosys.2019.105361.
[25] Y. C. Zhang and L. Sakhanenko, “The naive Bayes classifier for functional data,” Stat. Probab. Lett., vol. 152, pp. 137–146, 2019, doi: 10.1016/j.spl.2019.04.017.
[26] P. Tsangaratos and I. Ilia, “Comparison of a logistic regression and Naïve Bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size,” Catena, vol. 145, pp. 164–179, 2016, doi: 10.1016/j.catena.2016.06.004.
[27] C. Chen, G. Zhang, J. Yang, J. C. Milton, and A. D. Alcántara, “An explanatory analysis of driver injury severity in rear-end crashes using a decision table/Naïve Bayes (DTNB) hybrid classifier,” Accid. Anal. Prev., vol. 90, pp. 95–107, 2016, doi: 10.1016/j.aap.2016.02.002.
[28] D. Petschke and T. E. M. Staab, “A supervised machine learning approach using naive Gaussian Bayes classification for shape-sensitive detector pulse discrimination in positron annihilation lifetime spectroscopy (PALS),” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 947, no. July, p. 162742, 2019, doi: 10.1016/j.nima.2019.162742.
[29] A. Ma and D. Needell, “Stochastic gradient descent for linear systems with missing data,” Numer. Math., vol. 12, no. 1, pp. 1–20, 2019, doi: 10.4208/nmtma.OA-2018-0066.
[30] A. Sharma, “Guided Stochastic Gradient Descent Algorithm for inconsistent datasets,” Appl. Soft Comput. J., vol. 73, pp. 1068–1080, 2018, doi: 10.1016/j.asoc.2018.09.038.
[31] K. S. Gyamfi, J. Brusey, A. Hunt, and E. Gaura, “Linear classifier design under heteroscedasticity in Linear Discriminant Analysis,” Expert Syst. Appl., vol. 79, pp. 44–52, 2017, doi: 10.1016/j.eswa.2017.02.039.
[32] W. T. de Sousa Junior, J. A. B. Montevechi, R. de C. Miranda, M. L. M. de Oliveira, and A. T. Campos, “Shop floor simulation optimization using machine learning to improve parallel metaheuristics,” Expert Syst. Appl., vol. 150, p. 113272, Jul. 2020, doi: 10.1016/j.eswa.2020.113272.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0