Comparison of Different Approaches of Machine Learning Methods with Conventional Approaches on Container Throughput Forecasting DOI Creative Commons
Shuojiang Xu,

Shidong Zou,

Junpeng Huang

et al.

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(19), P. 9730 - 9730

Published: Sept. 27, 2022

Container transportation is an important mode of international trade logistics in the world today, and its changes will seriously affect development market. For example, COVID-19 pandemic has added a huge drag to global container logistics. Therefore, accurate forecasting throughput can make significant contribution stakeholders who want develop more operational strategies reduce costs. However, current research on port mainly focuses proposing innovative methods single time series, but lacks comparison performance different basic models same series series. This study uses nine forecast historical world’s top 20 ports compares results within between methods. The main findings this are as follows. First, GRU method that produce (0.54–2.27 MAPE 7.62–112.48 RMSE) with higher probability (85% for 75% when constructing models. Secondly, NM be used rapid simple estimation computing equipment services not available. Thirdly, average accuracy machine learning than traditional methods, individual may best conventional

Language: Английский

A pattern of collaborative logistics during multiple crises DOI Creative Commons

Bayu Fajar Nugroho,

La Ode Nazaruddin, Ahmad Syamil

et al.

International Journal of Disaster Risk Reduction, Journal Year: 2024, Volume and Issue: 108, P. 104499 - 104499

Published: April 25, 2024

The prolonged COVID-19 pandemic and the Russia-Ukraine War (multiple crises or catastrophes) affected logistics sector in world, especially developing countries. Collaborative is a strategy to mitigate negative impacts of multiple crises. Thus, this study aims uncover impact on collaboration countries case Indonesia disclose patterns among companies country. Data were collected through questionnaire survey 183 professionals working from June November 2023. Of respondents, 148 observations used statistical analysis using Partial-Least Square–Structural Equation Model (PLS-SEM) with Rstudio. This had following findings: First, early days (2020-2021) promoted domestic international collaborations. Second, latter (2022-2023) promote less intensive at levels due termination some restrictions contain spread relative resiliency sector. Third, drove collaborate intensively levels. Fourth, companies' responses demonstrate fluctuating pattern, depending severity crisis. it suggested that maintaining gain resilience unintended events negatively affect supply chain. has an academic contribution chain field, emphasising during

Language: Английский

Citations

1

Description of the Characteristics of Different Multiple Criteria Decision-Making (MCDM) Techniques for the Selection of Passive Energy Consumption Optimisation Strategies in Buildings DOI
Amirhossein Balali, Akilu Yunusa‐Kaltungo

Lecture notes in energy, Journal Year: 2024, Volume and Issue: unknown, P. 199 - 271

Published: Jan. 1, 2024

Language: Английский

Citations

1

Strategic approaches to crisis management: Global challenges in the Turkish container shipping sector due to the COVID-19 DOI
Arda Toygar, Umut Yıldırım

Case Studies on Transport Policy, Journal Year: 2024, Volume and Issue: 18, P. 101283 - 101283

Published: Aug. 31, 2024

Language: Английский

Citations

1

Progress towards the Sustainable Development Goal 14 (Life below water) in the context of Brazil: A Multicriteria approach DOI Creative Commons
Vinicius Moretti, Natália Ramos Corraini, Everton Luiz de Melo

et al.

Sustainable Futures, Journal Year: 2024, Volume and Issue: unknown, P. 100410 - 100410

Published: Dec. 1, 2024

Language: Английский

Citations

1

Comparison of Different Approaches of Machine Learning Methods with Conventional Approaches on Container Throughput Forecasting DOI Creative Commons
Shuojiang Xu,

Shidong Zou,

Junpeng Huang

et al.

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(19), P. 9730 - 9730

Published: Sept. 27, 2022

Container transportation is an important mode of international trade logistics in the world today, and its changes will seriously affect development market. For example, COVID-19 pandemic has added a huge drag to global container logistics. Therefore, accurate forecasting throughput can make significant contribution stakeholders who want develop more operational strategies reduce costs. However, current research on port mainly focuses proposing innovative methods single time series, but lacks comparison performance different basic models same series series. This study uses nine forecast historical world’s top 20 ports compares results within between methods. The main findings this are as follows. First, GRU method that produce (0.54–2.27 MAPE 7.62–112.48 RMSE) with higher probability (85% for 75% when constructing models. Secondly, NM be used rapid simple estimation computing equipment services not available. Thirdly, average accuracy machine learning than traditional methods, individual may best conventional

Language: Английский

Citations

6