Derechos de autor 2020 Investigación e Innovación en Ingenierías
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Algoritmo greedy para predecir el índice de servicio de pavimento basado en agrupación y regresión lineal
Corresponding Author(s) : Francisco Javier Anacona-Campo
Investigación e Innovación en Ingenierías,
Vol. 8 Núm. 3 (2020): Numero especial - XV Jornadas iberoamericanas de Ingeniería de Software e Ingeniería del Conocimiento - JIISIC 2020
Resumen
Objetivo: Proponer un algoritmo CLR (Clusterwise Linear Regression) que realiza agrupamiento divisivo de muestras de segmentos de pavimentos utilizando modelos de regresión lineal y define automáticamente el número de agrupaciones con el fin de predecir el índice de capacidad de servicio del pavimento (pavement serviceability index, PSI). Metodología: Basado en el proceso de investigación iterativa propuesto por Pratt se desarrollaron dos ciclos de mejora del algoritmo propuesto. El primer ciclo permitió obtener una versión inicial, aplicarlo sobre los datasets de entrenamiento y prueba y observar las mejoras que se debían realizar. En el segundo ciclo se obtuvo la versión final a la que se le afinaron los parámetros y se comparó con el estado del arte usando varias métricas. Resultados: Se obtuvo un modelo compuesto por tres grupos de muestras de segmentos de pavimento con sus correspondientes modelos de regresión lineal multivariable (atributos mixtos) que permiten predecir el PSI de una muestra de pavimento. Conclusiones: El modelo se obtuvo con menor tiempo de cómputo (15,6 veces menos tiempo que el reportado por el estado del arte) y presenta mejores resultados en sencillez en comparación con los modelos lineales y no lineales reportados en la literatura, además, en calidad tiene resultados similares (incluso mejores en algunas métricas) al modelo lineal y es competitivo frente al modelo no lineal.
Palabras clave
Descargar cita
Endnote/Zotero/Mendeley (RIS)BibTeX
-
S. S. Jain, S. Aggarwal, and M. Parida, “HDM-4 pavement deterioration models for Indian national highway network,” J. Transp. Eng., vol. 131, no. 8, pp. 623–631, 2005, doi: 10.1061/(ASCE)0733-947X(2005)131:8(623).
M. Y. Shahin, M. M. Nunez, M. R. Broten, S. H. Carpenter, and A. Sameh, “New techniques for modeling pavement deterioration,” Transp. Res. Rec., no. 1123, pp. 40–46, 1987.
M. Rodríguez Moreno, G. Thenoux Zeballos, and A. González Vaccarezza, “Evaluación probabilística del agrietamiento de pavimentos asfálticos en carreteras de Chile,” Rev. la Constr., vol. 12, no. 2, pp. 152–165, 2013, doi: 10.4067/s0718-915x2013000200012.
H. Ceylan, M. B. Bayrak, and K. Gopalakrishnan, “Neural networks applications in pavement engineering: A recent survey,” Int. J. Pavement Res. Technol., vol. 7, no. 6, pp. 434–444, 2014, doi: 10.6135/ijprt.org.tw/2014.
R. Ramaswamy and M. Ben-Akiva, “Estimation of Highway Pavement Deterioration form In-Service Pavement Data,” Transp. Res. Rec., vol. 1272, pp. 96–106, 1990, [Online]. Available: https://trid.trb.org/view/351896.
S. Terzi, “Modeling the pavement present serviceability index of flexible highway pavements using data mining,” J. Appl. Sci., vol. 6, no. 1, pp. 193–197, 2006, doi: 10.3923/jas.2006.193.197.
N. Bandara and M. Gunaratne, “Current and future pavement maintenance prioritization based on rapid visual condition evaluation,” J. Transp. Eng., vol. 127, no. 2, pp. 116–123, 2001, doi: 10.1061/(ASCE)0733-947X(2001)127:2(116).
K. A. Abaza, “Deterministic performance prediction model for rehabilitation and management of flexible pavement,” Int. J. Pavement Eng., vol. 5, no. 2, pp. 111–121, 2004, doi: 10.1080/10298430412331286977.
H. Späth, “Algorithm 39 Clusterwise linear regression,” Computing, vol. 22, no. 4, pp. 367–373, 1979, doi: 10.1007/BF02265317.
K. Joki, A. M. Bagirov, N. Karmitsa, M. M. Mäkelä, and S. Taheri, “Clusterwise support vector linear regression,” Eur. J. Oper. Res., vol. 287, no. 1, pp. 19–35, 2020, doi: 10.1016/j.ejor.2020.04.032.
W. S. DeSarbo, R. L. Oliver, and A. Rangaswamy, “A simulated annealing methodology for clusterwise linear regression,” Psychometrika, vol. 54, no. 4, pp. 707–736, 1989, doi: 10.1007/BF02296405.
M. Khadka, A. Paz, and A. Singh, “Generalised clusterwise regression for simultaneous estimation of optimal pavement clusters and performance models,” Int. J. Pavement Eng., vol. 21, no. 9, pp. 1122–1134, 2020, doi: 10.1080/10298436.2018.1521970.
M. Khadka and A. Paz, “Comprehensive Clusterwise Linear Regression for Pavement Management Systems,” J. Transp. Eng. Part B Pavements, vol. 143, no. 4, p. 04017014, 2017, doi: 10.1061/jpeodx.0000009.
M. Khadka, A. Paz, C. Arteaga, and D. K. Hale, “Simultaneous Generation of Optimum Pavement Clusters and Associated Performance Models,” Math. Probl. Eng., vol. 2018, p. 2159865, 2018, doi: 10.1155/2018/2159865.
S. Gharehbaghi and M. Khatibinia, “Optimal seismic design of reinforced concrete structures under time-history earthquake loads using an intelligent hybrid algorithm,” Earthq. Eng. Eng. Vib., vol. 14, no. 1, pp. 97–109, 2015, doi: 10.1007/s11803-015-0009-2.
A. M. Bagirov, J. Ugon, and H. G. Mirzayeva, “An algorithm for clusterwise linear regression based on smoothing techniques,” Optim. Lett., vol. 9, no. 2, pp. 375–390, 2015, doi: 10.1007/s11590-014-0749-3.
A. M. Bagirov, A. Mahmood, and A. Barton, “Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach,” Atmos. Res., vol. 188, pp. 20–29, 2017, doi: 10.1016/j.atmosres.2017.01.003.
M. Rump, W. Esdar, and E. Wild, “Individual differences in the effects of academic motivation on higher education students’ intention to drop out,” Eur. J. High. Educ., vol. 7, no. 4, pp. 341–355, 2017, doi: 10.1080/21568235.2017.1357481.
Y. W. Park, Y. Jiang, D. Klabjan, and L. Williams, “Algorithms for generalized Clusterwise linear regression,” INFORMS J. Comput., vol. 29, no. 2, pp. 301–317, 2017, doi: 10.1287/ijoc.2016.0729.
A. M. Bagirov and J. Ugon, “Nonsmooth DC programming approach to clusterwise linear regression: optimality conditions and algorithms,” Optim. Methods Softw., vol. 33, no. 1, pp. 194–219, 2018, doi: 10.1080/10556788.2017.1371717.
R. A. M. Da Silva and F. de A. T. De Carvalho, “On combining fuzzy C-regression models and fuzzy c-means with automated weighting of the explanatory variables,” in IEEE International Conference on Fuzzy Systems, 2018, vol. 2018-July, pp. 1–8, doi: 10.1109/FUZZ-IEEE.2018.8491476.
I. Gitman, J. Chen, E. Lei, and A. Dubrawski, “Novel Prediction Techniques Based on Clusterwise Linear Regression,” arXiv Prepr. arXiv1804.10742, 2018, [Online]. Available: http://arxiv.org/abs/1804.10742.
S. Bougeard, V. Cariou, G. Saporta, and N. Niang, “Prediction for regularized clusterwise multiblock regression,” in Applied Stochastic Models in Business and Industry, 2018, vol. 34, no. 6, pp. 852–867, doi: 10.1002/asmb.2335.
N. Veeramisti, A. Paz, M. Khadka, and C. Arteaga, “A clusterwise regression approach for the estimation of crash frequencies,” J. Transp. Saf. Secur., pp. 1–31, 2019, doi: 10.1080/19439962.2019.1611681.
F. Torti, D. Perrotta, M. Riani, and A. Cerioli, “Assessing trimming methodologies for clustering linear regression data,” Adv. Data Anal. Classif., vol. 13, no. 1, pp. 227–257, 2019, doi: 10.1007/s11634-018-0331-4.
G. Galimberti, L. Nuzzi, and G. Soffritti, “Covariance matrix estimation of the maximum likelihood estimator in multivariate clusterwise linear regression,” Stat. Methods Appl., 2020, doi: 10.1007/s10260-020-00523-9.
G. P. Oliveira, M. D. Santos, and W. L. Roque, “Constrained clustering approaches to identify hydraulic flow units in petroleum reservoirs,” J. Pet. Sci. Eng., vol. 186, 2020, doi: 10.1016/j.petrol.2019.106732.
R. Di Mari, R. Rocci, and S. A. Gattone, “Scale-constrained approaches for maximum likelihood estimation and model selection of clusterwise linear regression models,” Stat. Methods Appl., vol. 29, no. 1, pp. 49–78, 2020, doi: 10.1007/s10260-019-00480-y.
K. S. Pratt, “Design Patterns for Research Methods: Iterative Field Research,” AAAI Spring Symp. Exp. Des. Real, no. 1994, pp. 1–7, 2009.
B. Kitchenham and P. Brereton, “A systematic review of systematic review process research in software engineering,” Information and Software Technology, vol. 55, no. 12. Elsevier B.V., pp. 2049–2075, 2013, doi: 10.1016/j.infsof.2013.07.010.
E. Frank, M. A. Hall, and I. H. Witten, “The WEKA workbench,” in Data Mining, Morgan Kaufmann, 2016, p. 128.
Referencias
M. Y. Shahin, M. M. Nunez, M. R. Broten, S. H. Carpenter, and A. Sameh, “New techniques for modeling pavement deterioration,” Transp. Res. Rec., no. 1123, pp. 40–46, 1987.
M. Rodríguez Moreno, G. Thenoux Zeballos, and A. González Vaccarezza, “Evaluación probabilística del agrietamiento de pavimentos asfálticos en carreteras de Chile,” Rev. la Constr., vol. 12, no. 2, pp. 152–165, 2013, doi: 10.4067/s0718-915x2013000200012.
H. Ceylan, M. B. Bayrak, and K. Gopalakrishnan, “Neural networks applications in pavement engineering: A recent survey,” Int. J. Pavement Res. Technol., vol. 7, no. 6, pp. 434–444, 2014, doi: 10.6135/ijprt.org.tw/2014.
R. Ramaswamy and M. Ben-Akiva, “Estimation of Highway Pavement Deterioration form In-Service Pavement Data,” Transp. Res. Rec., vol. 1272, pp. 96–106, 1990, [Online]. Available: https://trid.trb.org/view/351896.
S. Terzi, “Modeling the pavement present serviceability index of flexible highway pavements using data mining,” J. Appl. Sci., vol. 6, no. 1, pp. 193–197, 2006, doi: 10.3923/jas.2006.193.197.
N. Bandara and M. Gunaratne, “Current and future pavement maintenance prioritization based on rapid visual condition evaluation,” J. Transp. Eng., vol. 127, no. 2, pp. 116–123, 2001, doi: 10.1061/(ASCE)0733-947X(2001)127:2(116).
K. A. Abaza, “Deterministic performance prediction model for rehabilitation and management of flexible pavement,” Int. J. Pavement Eng., vol. 5, no. 2, pp. 111–121, 2004, doi: 10.1080/10298430412331286977.
H. Späth, “Algorithm 39 Clusterwise linear regression,” Computing, vol. 22, no. 4, pp. 367–373, 1979, doi: 10.1007/BF02265317.
K. Joki, A. M. Bagirov, N. Karmitsa, M. M. Mäkelä, and S. Taheri, “Clusterwise support vector linear regression,” Eur. J. Oper. Res., vol. 287, no. 1, pp. 19–35, 2020, doi: 10.1016/j.ejor.2020.04.032.
W. S. DeSarbo, R. L. Oliver, and A. Rangaswamy, “A simulated annealing methodology for clusterwise linear regression,” Psychometrika, vol. 54, no. 4, pp. 707–736, 1989, doi: 10.1007/BF02296405.
M. Khadka, A. Paz, and A. Singh, “Generalised clusterwise regression for simultaneous estimation of optimal pavement clusters and performance models,” Int. J. Pavement Eng., vol. 21, no. 9, pp. 1122–1134, 2020, doi: 10.1080/10298436.2018.1521970.
M. Khadka and A. Paz, “Comprehensive Clusterwise Linear Regression for Pavement Management Systems,” J. Transp. Eng. Part B Pavements, vol. 143, no. 4, p. 04017014, 2017, doi: 10.1061/jpeodx.0000009.
M. Khadka, A. Paz, C. Arteaga, and D. K. Hale, “Simultaneous Generation of Optimum Pavement Clusters and Associated Performance Models,” Math. Probl. Eng., vol. 2018, p. 2159865, 2018, doi: 10.1155/2018/2159865.
S. Gharehbaghi and M. Khatibinia, “Optimal seismic design of reinforced concrete structures under time-history earthquake loads using an intelligent hybrid algorithm,” Earthq. Eng. Eng. Vib., vol. 14, no. 1, pp. 97–109, 2015, doi: 10.1007/s11803-015-0009-2.
A. M. Bagirov, J. Ugon, and H. G. Mirzayeva, “An algorithm for clusterwise linear regression based on smoothing techniques,” Optim. Lett., vol. 9, no. 2, pp. 375–390, 2015, doi: 10.1007/s11590-014-0749-3.
A. M. Bagirov, A. Mahmood, and A. Barton, “Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach,” Atmos. Res., vol. 188, pp. 20–29, 2017, doi: 10.1016/j.atmosres.2017.01.003.
M. Rump, W. Esdar, and E. Wild, “Individual differences in the effects of academic motivation on higher education students’ intention to drop out,” Eur. J. High. Educ., vol. 7, no. 4, pp. 341–355, 2017, doi: 10.1080/21568235.2017.1357481.
Y. W. Park, Y. Jiang, D. Klabjan, and L. Williams, “Algorithms for generalized Clusterwise linear regression,” INFORMS J. Comput., vol. 29, no. 2, pp. 301–317, 2017, doi: 10.1287/ijoc.2016.0729.
A. M. Bagirov and J. Ugon, “Nonsmooth DC programming approach to clusterwise linear regression: optimality conditions and algorithms,” Optim. Methods Softw., vol. 33, no. 1, pp. 194–219, 2018, doi: 10.1080/10556788.2017.1371717.
R. A. M. Da Silva and F. de A. T. De Carvalho, “On combining fuzzy C-regression models and fuzzy c-means with automated weighting of the explanatory variables,” in IEEE International Conference on Fuzzy Systems, 2018, vol. 2018-July, pp. 1–8, doi: 10.1109/FUZZ-IEEE.2018.8491476.
I. Gitman, J. Chen, E. Lei, and A. Dubrawski, “Novel Prediction Techniques Based on Clusterwise Linear Regression,” arXiv Prepr. arXiv1804.10742, 2018, [Online]. Available: http://arxiv.org/abs/1804.10742.
S. Bougeard, V. Cariou, G. Saporta, and N. Niang, “Prediction for regularized clusterwise multiblock regression,” in Applied Stochastic Models in Business and Industry, 2018, vol. 34, no. 6, pp. 852–867, doi: 10.1002/asmb.2335.
N. Veeramisti, A. Paz, M. Khadka, and C. Arteaga, “A clusterwise regression approach for the estimation of crash frequencies,” J. Transp. Saf. Secur., pp. 1–31, 2019, doi: 10.1080/19439962.2019.1611681.
F. Torti, D. Perrotta, M. Riani, and A. Cerioli, “Assessing trimming methodologies for clustering linear regression data,” Adv. Data Anal. Classif., vol. 13, no. 1, pp. 227–257, 2019, doi: 10.1007/s11634-018-0331-4.
G. Galimberti, L. Nuzzi, and G. Soffritti, “Covariance matrix estimation of the maximum likelihood estimator in multivariate clusterwise linear regression,” Stat. Methods Appl., 2020, doi: 10.1007/s10260-020-00523-9.
G. P. Oliveira, M. D. Santos, and W. L. Roque, “Constrained clustering approaches to identify hydraulic flow units in petroleum reservoirs,” J. Pet. Sci. Eng., vol. 186, 2020, doi: 10.1016/j.petrol.2019.106732.
R. Di Mari, R. Rocci, and S. A. Gattone, “Scale-constrained approaches for maximum likelihood estimation and model selection of clusterwise linear regression models,” Stat. Methods Appl., vol. 29, no. 1, pp. 49–78, 2020, doi: 10.1007/s10260-019-00480-y.
K. S. Pratt, “Design Patterns for Research Methods: Iterative Field Research,” AAAI Spring Symp. Exp. Des. Real, no. 1994, pp. 1–7, 2009.
B. Kitchenham and P. Brereton, “A systematic review of systematic review process research in software engineering,” Information and Software Technology, vol. 55, no. 12. Elsevier B.V., pp. 2049–2075, 2013, doi: 10.1016/j.infsof.2013.07.010.
E. Frank, M. A. Hall, and I. H. Witten, “The WEKA workbench,” in Data Mining, Morgan Kaufmann, 2016, p. 128.