Copyright and Licensing
Articles accepted for publication will be licensed under the Creative Commons BY-NC-SA. Authors must sign a non-exclusive distribution agreement after article acceptance.
Predictive model using neural networks and multitechnique validation in digital environments with scarce data for sustainable WEEE management
DOI:
https://doi.org/10.24215/16666038.26.e02Keywords:
Neural Networks, Predictive Modeling, Model Validation, E-Waste Management, Waste Forecasting.Abstract
The sustainable management of Waste Electrical and Electronic Equipment (WEEE) is a critical global challenge, particularly in contexts with limited data. This study proposes a predictive model based on artificial neural networks, developed from surveys and historical records in the city of Guayaquil, with the aim of estimating WEEE generation on annual and monthly scales. The model was structured in phases of data collection, preprocessing, training, and validation, integrating sociodemographic variables and categories of discarded devices. To ensure reliability, a multi-technique validation protocol was applied, including Hold-Out, Stratified K-Fold, and Bootstrap Sampling methods. Results showed strong performance, with a coefficient of determination (R²) of 0.9125 in initial tests, an average of 0.9097 in cross-validation, and up to 0.9789 with bootstrap, significantly outperforming traditional linear regression methods. These findings confirm the model’s ability to capture non-linear relationships and produce accurate forecasts in data-scarce environments. It is concluded that neural networks represent an effective tool to support strategic planning and decision-making in sustainable WEEE management, providing a replicable framework for other regions facing similar challenges.
Downloads
Download data is not yet available.
References
[1] G. M. Duman and E. Kongar, “ESG Modeling and Prediction Uncertainty of Electronic Waste,” Sustainability, vol. 15, no. 14, p. 11281, doi: 10.3390/su151411281.
[2] A. Vishwakarma, K. Kanaujia, and S. Hait, “Global scenario of E-waste generation: trends and future predictions,” in Global E-Waste Management Strategies and Future Implications, Elsevier, 2023, pp. 13–30. doi: 10.1016/B978-0-323-99919-9.00013-1.
[3] M. Algafri, M. Sayad, M. A. M. Abdel-Aal, and A. M. Attia, “A Comparative Study of Machine Learning Models for Accurate E-Waste Prediction,” Results in Engineering, vol. 26, p. 105388, Jun. 2025, doi: 10.1016/J.RINENG.2025.105388.
[4] A. Ramírez Restrepo and R. C. Baars, “A comprehensive systematic review in e-waste studies: themes beyond metrics,” International Journal of Environmental Science and Technology, vol. 22, no. 8, pp. 7459–7486, Apr. 2025, doi: 10.1007/s13762-025-06349-w.
[5] J. Facuy, A. Passini, E. Estevez, and C. Moran, “Modelo predictivo aplicando inteligencia ambiental orientado a la generación de residuos electrónicos con un enfoque de Ciudades inteligentes sostenible,” in 30° Congreso Argentino de Ciencias de la Computación, 2024. [Online]. Available: https://sedici.unlp.edu.ar/handle/10915/177331
[6] G. P. Oise and S. Konyeha, “Deep Learning System for E-Waste Management,” in The 3rd International Electronic Conference on Processes, Basel Switzerland: MDPI, Oct. 2024, p. 66. doi: 10.3390/engproc2024067066.
[7] S. Polymeni, E. Athanasakis, G. Spanos, K. Votis, and D. Tzovaras, “IoT-based prediction models in the environmental context: A systematic Litera-ture Review,” Internet of Things, vol. 20, p. 100612, doi: 10.1016/j.iot.2022.100612.
[8] M. K. Maurya, V. K. Singh, S. K. Shaw, and M. Kumar, “Fft-asvr: an adap-tive approach for accurate prediction of IoT data streams,” J Supercomput, vol. 80, no. 10, pp. 13976–13999, doi: 10.1007/s11227-024-05961-w.
[9] J. E. Z. Macias and S. Trilles, “Machine learning-based prediction model for battery levels in IoT devices using meteorological variables,” Internet of Things, vol. 25, p. 101109, doi: 10.1016/j.iot.2024.101109.
[10] N. D. Mu’azu and S. O. Olatunji, “K-nearest neighbor based computational intelligence and RSM predictive models for extraction of Cadmium from contaminated soil,” Ain Shams Engineering Journal, vol. 14, no. 4, p. 101944, doi: 10.1016/j.asej.2022.101944.
[11] S. Mao, Y. Kang, Y. Zhang, X. Xiao, and H. Zhu, “Fractional grey model based on non-singular exponential kernel and its application in the prediction of electronic waste precious metal content,” ISA Trans, vol. 107, pp. 12–26, doi: 10.1016/j.isatra.2020.07.023.
[12] M. Tran et al., “Python-based scikit-learn machine learning models for thermal and electrical performance prediction of high-capacity lithium-ion battery,” Int J Energy Res, vol. 46, no. 2, pp. 786–794, Feb. 2022, doi: 10.1002/er.7202.
[13] S. D. Walton and K. R. Murphy, “Superposed epoch analysis using time-normalization: A Python tool for statistical event analysis,” Frontiers in As-tronomy and Space Sciences, vol. 9, doi: 10.3389/fspas.2022.1000145.
[14] Y.-H. Jin, K.-H. Lee, and D.-W. Choi, “QueryNet: Querying neural networks for lightweight specialized models,” Inf Sci, vol. N Y), 589, pp. 186–198, doi: 10.1016/j.ins.2021.12.097.
[15] J. Cao, D. Zhao, C. Tian, T. Jin, and F. Song, “Adopting improved Adam optimizer to train dendritic neuron model for water quality prediction,” Math-ematical Biosciences and Engineering, vol. 20, no. 5, pp. 9489–9510, doi: 10.3934/mbe.2023417.
[16] X. Liang and J. Xu, “Biased ReLU neural networks,” Neurocomputing, vol. 423, pp. 71–79, doi: 10.1016/j.neucom.2020.09.050.
[17] A. Raj, G. Agarwal, P. Goyal, Y. Mittal, and S. K. Singh, “ParkSmart: Lever-aging Neural Networks for Predictive Parking in Smart Cities,” in 2024 Inter-national Conference on Integrated Circuits and Communication Systems (ICICACS), IEEE, Feb, pp. 1–5. doi: 10.1109/ICICACS60521.2024.10499086.
[18] M. G. V. Rueda, M. I. Reyes, F. G. F. García, and H. A. M. Casillas, “Redes neuronales aplicadas al control de riego usando instru-mentación y análisis de imágenes para un micro-invernadero aplicado al cul-tivo de Albahaca,” Research in Computing Science, vol. 147, no. 5, pp. 93–103, doi: 10.13053/rcs-147-5-7.
[19] R. Zemouri, N. Omri, F. Fnaiech, N. Zerhouni, and N. Fnaiech, “A new grow-ing pruning deep learning neural network algorithm (GP-DLNN,” Neural Comput Appl, vol. 32, no. 24, pp. 18143–18159, doi: 10.1007/s00521-019-04196-8.
[20] L. Khawaja et al., “Development of machine learning models for forecasting the strength of resilient modulus of subgrade soil: genetic and artificial neural network approaches,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-69316-4.
[21] J. P. Facuy Delgado, E. J. Yerovi Ricaurte, and W. O. Molina Oleas, “Estimación cuantitativa de residuos electrónicos con técnicas de aprendizaje estadístico: validación de un modelo XGBoost para Guayaquil,” Revista Ingenio global, vol. 4, no. 2, pp. 25–51, Jul. 2025, doi: 10.62943/rig.v4n2.2025.319.
[22] Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, and C. Zhang, “Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, New York, NY, USA: ACM, Aug. 2020, pp. 753–763. doi: 10.1145/3394486.3403118.
[23] A. Deng, “Graph Neural Network-Based Anomaly Detection in Multivariate Time Series,” 35th Aaai Conference on Artificial Intelligence Aaai 2021, vol. 5, pp. 4027–4035, 2021, doi: 10.1609/aaai.v35i5.16523.
[24] M. Kiran, P. V. Shanmugam, A. Mishra, A. Mehendale, and H. R. Nadheera Sherin, “A multivariate discrete grey model for estimating the waste from mobile phones, televisions, and personal computers in India,” J Clean Prod, vol. 293, p. 126185, Apr. 2021, doi: 10.1016/j.jclepro.2021.126185.
[25] I. M. Hidalgo-Cajo, S. Yasaca-Pucuna, B. G. Hidalgo-Cajo, D. P. Hidalgo-Cajo, and N. B. Latorre-Benalcázar, “Estudio comparativo de los algoritmos backpropagation (bp) y multiple linear regression (mlr) a través del análisis estadístico de datos aplicado a redes neuronales artificiales,” Revista Boletín Redipe, vol. 9, no. 3, pp. 144–152, doi: 10.36260/rbr.v9i3.939.
[26] S. Chen, “Review on Supervised and Unsupervised Learning Techniques for Electrical Power Systems: Algorithms and Applications,” IEEJ Transactions on Electrical and Electronic Engineering, vol. 16, no. 11, pp. 1487–1499, doi: 10.1002/tee.23452.
[27] P. K. Sarswat, R. S. Singh, and S. V. S. H. Pathapati, “Real time electronic-waste classification algorithms using the computer vision based on Convolu-tional Neural Network (CNN): Enhanced environmental incentives,” Resour Conserv Recycl, vol. 207, p. 107651, doi: 10.1016/j.resconrec.2024.107651.
[28] W. A. Bagwan, “Electronic waste (E-waste) generation and management scenario of India, and ARIMA forecasting of E-waste processing capacity of Maharashtra state till 2030,” Waste Management Bulletin, vol. 1, no. 4, pp. 41–51, doi: 10.1016/j.wmb.2023.08.002.
[29] J. C. Muyulema Allaica, I. D. R. Balón Ramos, I. E. Rodríguez Cortez, and F. X. Aguirre Flores, “Impacto de la Logística Inversa en la Sostenibilidad Ambiental: Una Propuesta de Marco sobre la Gestión de Residuos de Aparatos Electrónicos y Eléctricos,” Arandu UTIC, vol. 11, no. 2, pp. 2742–2767, Dec. 2024, doi: 10.69639/arandu.v11i2.462.
[30] J. Facuy, A. Passini, E. Estevez, and C. Moran, “WEEE Prediction Model Based on Neural Networks,” in 13th Conference on Cloud Computing, Big Data & Emerging Topics. [Online]. Available: https://sedici.unlp.edu.ar/handle/10915/182608
[31] R. Ulloa-Espíndola and Y. Pérez-Albert, “Validación de un modelo de predicción del crecimiento urbano en Quito (Ecuador) construido mediante pesos de evidencia y autómatas celulares,” EURE, vol. 48, no. 144, 2022, doi: 10.7764/EURE.48.144.06.
[32] F. Chen, S. Li, J. Han, F. Ren, and Z. Yang, “Review of Lightweight Deep Convolutional Neural Networks,” Archives of Computational Methods in Engineering, vol. 31, no. 4, pp. 1915–1937, May 2024, doi: 10.1007/s11831-023-10032-z.
[33] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput Sci, vol. 7, p. e623, Jul. 2021, doi: 10.7717/peerj-cs.623.
[34] L. A. Yates, Z. Aandahl, S. A. Richards, and B. W. Brook, “Cross validation for model selection: A review with examples from ecology,” Ecol Monogr, vol. 93, no. 1, Feb. 2023, doi: 10.1002/ecm.1557.
[35] E. Tavazzi et al., “Artificial intelligence and statistical methods for stratification and prediction of progression in amyotrophic lateral sclerosis: A systematic review,” Artif Intell Med, vol. 142, p. 102588, Aug. 2023, doi: 10.1016/j.artmed.2023.102588.
[36] G. Parady, D. Ory, and J. Walker, “The overreliance on statistical goodness-of-fit and under-reliance on model validation in discrete choice models: A review of validation practices in the transportation academic literature,” Journal of Choice Modelling, vol. 38, p. 100257, Mar. 2021, doi: 10.1016/j.jocm.2020.100257.
[37] A. Ali and C. Gravino, “An empirical comparison of validation methods for software prediction models,” Journal of Software: Evolution and Process, vol. 33, no. 8, Aug. 2021, doi: 10.1002/smr.2367.
[38] C. L. Ramspek, K. J. Jager, F. W. Dekker, C. Zoccali, and M. van Diepen, “External validation of prognostic models: what, why, how, when and where?,” Clin Kidney J, vol. 14, no. 1, pp. 49–58, Feb. 2021, doi: 10.1093/ckj/sfaa188.
Downloads
Published
2026-04-10
Issue
Section
Original Articles
License
Copyright (c) 2026 Dr. Jussen Facuy Delgado, Dr. Ariel Passini, Elsa, Dr. Cesar Moran
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
[1]
“Predictive model using neural networks and multitechnique validation in digital environments with scarce data for sustainable WEEE management”, JCS&T, vol. 26, no. 1, p. e02, Apr. 2026, doi: 10.24215/16666038.26.e02.
