Container flow forecasting through neural networks based on metaheuristics
Abstract
In this paper we propose a fuzzy neural network prediction approach based on metaheuristics for container flow forecasting. The approach uses fuzzy if–then rules for selection between two different heuristics for developing neural network architecture, simulated annealing and genetic algorithm, respectively. These non-parametric models are compared with traditional parametric ARIMA technique. Time series composed from monthly container traffic observations for Port of Barcelona are used for model developing and testing. Models are compared based on the most important criteria for performance evaluation and for each of the data sets (total container traffic, loaded, unloaded, transit and empty) the appropriate model is selected.
Keywords:
Neural networks / Simulated annealing / Genetic algorithm / ARIMA / Container / ForecastingSource:
Operational research, 2019, 21, 965-997Publisher:
- Springer
Funding / projects:
- Development of new information and communication technologies, based on advanced mathematical methods, with applications in medicine, telecommunications, power systems, protection of national heritage and education (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-44006)
- Critical infrastructure management for sustainable development in postal, telecommunication and railway sector of Republic of Serbia (RS-MESTD-Technological Development (TD or TR)-36022)
Collections
Institution/Community
Poljoprivredni fakultetTY - JOUR AU - Milenković, Miloš AU - Milosavljević, Nataša S. AU - Bojović, Nebojša AU - Susana, Vall PY - 2019 UR - http://aspace.agrif.bg.ac.rs/handle/123456789/6829 AB - In this paper we propose a fuzzy neural network prediction approach based on metaheuristics for container flow forecasting. The approach uses fuzzy if–then rules for selection between two different heuristics for developing neural network architecture, simulated annealing and genetic algorithm, respectively. These non-parametric models are compared with traditional parametric ARIMA technique. Time series composed from monthly container traffic observations for Port of Barcelona are used for model developing and testing. Models are compared based on the most important criteria for performance evaluation and for each of the data sets (total container traffic, loaded, unloaded, transit and empty) the appropriate model is selected. PB - Springer T2 - Operational research T1 - Container flow forecasting through neural networks based on metaheuristics EP - 997 SP - 965 VL - 21 DO - 10.1007/s12351-019-00477-1 ER -
@article{ author = "Milenković, Miloš and Milosavljević, Nataša S. and Bojović, Nebojša and Susana, Vall", year = "2019", abstract = "In this paper we propose a fuzzy neural network prediction approach based on metaheuristics for container flow forecasting. The approach uses fuzzy if–then rules for selection between two different heuristics for developing neural network architecture, simulated annealing and genetic algorithm, respectively. These non-parametric models are compared with traditional parametric ARIMA technique. Time series composed from monthly container traffic observations for Port of Barcelona are used for model developing and testing. Models are compared based on the most important criteria for performance evaluation and for each of the data sets (total container traffic, loaded, unloaded, transit and empty) the appropriate model is selected.", publisher = "Springer", journal = "Operational research", title = "Container flow forecasting through neural networks based on metaheuristics", pages = "997-965", volume = "21", doi = "10.1007/s12351-019-00477-1" }
Milenković, M., Milosavljević, N. S., Bojović, N.,& Susana, V.. (2019). Container flow forecasting through neural networks based on metaheuristics. in Operational research Springer., 21, 965-997. https://doi.org/10.1007/s12351-019-00477-1
Milenković M, Milosavljević NS, Bojović N, Susana V. Container flow forecasting through neural networks based on metaheuristics. in Operational research. 2019;21:965-997. doi:10.1007/s12351-019-00477-1 .
Milenković, Miloš, Milosavljević, Nataša S., Bojović, Nebojša, Susana, Vall, "Container flow forecasting through neural networks based on metaheuristics" in Operational research, 21 (2019):965-997, https://doi.org/10.1007/s12351-019-00477-1 . .