Methodological Evaluation of a Fuzzy Inference System for Vehicular Traffic Using Parallel Computing: A Simulated Study on Avenida Cero

Authors

  • Johann Leonardo Latorre Jaimes Universidad de Pamplona, Villa del Rosario, Colombia https://orcid.org/0009-0001-6362-7164
  • Jose Gerardo Chacón Rangel Universidad de Pamplona, Villa del Rosario, Colombia
  • Juan Carlos Escalante Universidad de Pamplona, Villa del Rosario, Colombia
  • Daniel Alexis Celis Ferrer Universidad de Pamplona, Villa del Rosario, Colombia.

DOI:

https://doi.org/10.61799/2216-0388.2076

Keywords:

fuzzy logic, vehicular traffic, methodological evaluation, synthetic data, machine learning, neural networks, hybrid model, parallel computing.

Abstract

Vehicular traffic in border cities like Cúcuta poses a significant urban challenge due to its impact on mobility, travel times, and the environment. This study develops and methodologically evaluates a fuzzy inference system for estimating traffic levels in simulated scenarios associated with Avenida Cero. It employs a Mamdani Fuzzy Inference System (FIS) with parallel execution leveraging Python's multiprocessing capabilities. The tool utilizes time, weather, and day of the week as inputs, outputting a traffic score ranging from 0 to 10, which is then categorized as low, medium, or high. Rules were established based on clear traffic engineering principles and local knowledge. Final result adjustments were performed solely using training data within a simulation. Due to the absence of verified hourly traffic count records for Avenida Cero, numerical validation was conducted using 2,400 reproducible simulated data points. This dataset was split into 80% for training and 20% for testing. On the test sample, the FIS yielded an MAE of 0.953, an RMSE of 1.183, and an R² of 0.511. A Random Forest model achieved an MAE of 0.386, an RMSE of 0.484, and an R² of 0.918; an MLP network produced an MAE of 0.416, an RMSE of 0.521, and an R² of 0.905; and a hybrid FIS-Random Forest design resulted in an MAE of 0.400, an RMSE of 0.497, and an R² of 0.913. The comparison demonstrates that data-driven models outperform the FIS in predictive accuracy within the synthetic environment. At the same time, the fuzzy system retains its advantages regarding interpretability and rule traceability. Parallel processing reduced evaluation time compared to the sequential version, achieving a maximum speedup of 2.92x in the recorded tests. These findings constitute a methodological validation based exclusively on simulated data and do not constitute empirical validation of system performance on Avenida Cero. Incorporating actual flow measurements is the next crucial step in assessing the method's generalizability and operational utility.

Downloads

Download data is not yet available.

References

[1] L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, pp. 338–353, 1965.

[2] L. Li, W.-H. Lin, and H. Liu, "Type-2 fuzzy logic approach for short-term traffic forecasting," Transportation Research Part C: Emerging Technologies, vol. 14, no. 4, pp. 303–317, 2006.

[3] X. Jiang, R. Sengupta, J. Demmel, and S. Williams, "Large scale multi-GPU based parallel traffic simulation for accelerated traffic assignment and propagation," arXiv preprint arXiv:2406.08496, 2024.

[4] J. A. Bernal-Sánchez and J. Riascos-Ochoa, "Traffic Forecasting in Bogota, Colombia, with Attention Temporal Graph Convolutional Networks (A3T-GCN)," CEUR Workshop Proceedings, vol. 3795, pp. 210–221, 2024.

[5] Y. Liu, X.-K. Wang, W.-H. Hou, H. Liu, and J.-Q. Wang, "A novel hybrid model combining a fuzzy inference system and a deep learning method for short-term traffic flow prediction," Knowledge-Based Systems, vol. 255, art. 109760, 2022, doi: 10.1016/j.knosys.2022.109760.

[6] Alcaldía de Cúcuta, "Resumen Ejecutivo – Plan de Movilidad Sostenible y Segura (PMSS)," Documento oficial, 2023.

[7] Python Software Foundation, "multiprocessing — Process-based parallelism," Python 3.x Documentation, 2024.

[8] G. M. Amdahl, "Validity of the single processor approach to achieving large scale computing capabilities," in AFIPS Conference Proceedings, vol. 30, pp. 483–485, 1967.

[9] Congreso de la República de Colombia, "Ley 1581 de 2012 – Protección de datos personales," Diario Oficial, 2012.

[10] H. J. Zimmermann, Fuzzy Set Theory and Its Applications, 4th ed. Springer, 2010.

[11] K. M. Passino and S. Yurkovich, Fuzzy Control. Addison-Wesley, 1997.

[12] M. Sugeno, "Industrial applications of fuzzy control," Elsevier Science Publishing, 1985.

[13] K. Tanaka, Fuzzy Control Systems Design and Analysis. Wiley-Interscience, 2001.

[14] D. P. Filev and R. R. Yager, "Fuzzy modeling and control of uncertain systems," IEEE Transactions on Systems, Man, and Cybernetics, pp. 604–615, 1994.

[15] J. M. Mendel, Uncertain Rule-Based Fuzzy Logic Systems. Springer, 2017.

[16] D. A. Bader, Designing Parallel Algorithms. CRC Press, 2018.

[17] J. Dongarra et al., "Trends in high-performance computing: A historical overview," Computing in Science & Engineering, vol. 22, no. 6, pp. 18–29, 2020.

[18] Nvidia Corporation, "CUDA C Programming Guide," Nvidia Developer Documentation, 2023.

[19] T. Mattson, B. Sanders, and B. Massingill, Patterns for Parallel Programming. Addison-Wesley, 2004.

[20] M. Treiber and A. Kesting, Traffic Flow Dynamics: Data, Models and Simulation. Springer, 2013.

[21] J. Barceló (Ed.), Fundamentals of Traffic Simulation. Springer, 2010.

[22] S. Hoogendoorn and P. Bovy, "Traffic flow theory and modelling," Transportation Research Part C, vol. 13, pp. 1–28, 2013.

[23] C. F. Daganzo, Fundamentals of Transportation and Traffic Operations. Pergamon, 1997.

[24] ONU-Hábitat, Cities and Mobility Report, 2022.

[25] A. Ortúzar and L. Willumsen, Modelling Transport, 4th ed. Wiley, 2011.

[26] L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, no. 3, pp. 338–353, 1965.

[27] H. J. Zimmermann, Fuzzy Set Theory and Its Applications, 4th ed. Springer, 2001.

[28] J. M. Mendel, "Fuzzy logic systems for engineering: a tutorial," IEEE Trans. Industrial Electronics, vol. 40, no. 2, pp. 211–221, 1993.

[29] O. Cordon, F. Herrera, L. Magdalena, and P. Villar, A Genetic Learning Process for Fuzzy Rule-Based System Modeling. Springer, 2001.

[30] K. S. Cardozo Rueda, "Aplicación de redes neuronales artificiales para el pronóstico de precios de café," RCTA, vol. 1, no. 39, pp. 113–117, Feb. 2022. doi: 10.24054/rcta.v1i39.1403

[31] J. E. Meneses Flórez, F. A. Garavito, and E. Meneses, "Identificación de fallas en sistemas de bombeo mecánico de petróleo utilizando neurofuzzy," RCTA, vol. 1, no. 37, pp. 10–22, Feb. 2021. doi: 10.24054/rcta.v1i37.973

[32] R. Jiménez Moreno, J. E. Martínez Baquero, and O. Agudelo Varela, "Control difuso para pinza robótica blanda orientada a objetos no rígidos," RCTA, vol. 2, no. 42, pp. 1–7, Oct. 2023. doi: 10.24054/rcta.v2i42.2647

[33] D. Arenas Seleey, C. E. Prieto Triana, and D. C. Chacón López, "Ingeniería de requerimientos e inteligencia artificial: una revisión de la literatura," RCTA, vol. 1, no. 39, pp. 100–106, Feb. 2022. doi: 10.24054/rcta.v1i39.1395

[34] Y. González Castro, O. Manzano Durán, and C. A. Vera Romero, "Tendencias de la formación docente en competencias investigativas desde la analítica de datos," RCTA, vol. 2, no. 44, pp. 74–82, Jul. 2024. doi: 10.24054/rcta.v2i44.3009

[35] J. Gómez Gómez, C. A. Parra Urueta, and J. J. Guzmán Pineda, "Sistema de trazabilidad de cacao soportado en Internet de las cosas," RCTA, vol. 1, no. 45, pp. 204–215, Jan. 2025. doi: 10.24054/rcta.v1i45.3283

[36] J.-D. Wang and C. O. N. Susanto, "Traffic Flow Prediction with Heterogenous Data Using a Hybrid CNN-LSTM Model," Computers, Materials & Continua, vol. 76, no. 3, pp. 3097–3112, 2023, doi: 10.32604/cmc.2023.040914.

[37] N. Cini and Z. Aydin, "A Deep Ensemble Approach for Long-Term Traffic Flow Prediction," Arabian Journal for Science and Engineering, vol. 49, pp. 12377–12392, 2024, doi: 10.1007/s13369-023-08672-1.

[38] L. Jin et al., "Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach," Data Science for Transportation, vol. 6, art. 17, 2024, doi: 10.1007/s42421-024-00102-4.

[39] X. Yin et al., "Short-term urban traffic forecasting in smart cities: a dynamic diffusion spatial-temporal graph convolutional network," Complex & Intelligent Systems, vol. 11, art. 158, 2025, doi: 10.1007/s40747-024-01769-6.

[40] Alcaldía de San José de Cúcuta, "Alcaldía de Cúcuta adopta medidas para mejorar la movilidad en la Avenida Cero y la Diagonal Santander," 18 mayo 2023.

Published

2026-09-01

Issue

Section

Artículo Originales

How to Cite

[1]
Latorre Jaimes, J.L. et al. 2026. Methodological Evaluation of a Fuzzy Inference System for Vehicular Traffic Using Parallel Computing: A Simulated Study on Avenida Cero. Mundo FESC Journal. 16, 36 (Sep. 2026). DOI:https://doi.org/10.61799/2216-0388.2076.

Most read articles by the same author(s)