A Comparison of Traditional and Neural Networks Forecasting Techniques for Container Throughput at Bangkok Port

Gosasang, Veerachai; Chandraprakaikul, Watcharavee; Kiattisin, Supaporn

doi:10.1016/s2092-5212(11)80022-2

Cited by 100 publications

(70 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A typical example of such studies are works of [14,15,18,20,21]. The authors in study [15] have shown the importance of the relationships between the container volumes and different macroeconomic variables.…”

Section: Characteristics Of the Port Of Kopermentioning

confidence: 99%

Container Throughput Forecasting Using Dynamic Factor Analysis and ARIMAX Model

Intihar

Kramberger

Dragan

2017

PROMET

View full text Add to dashboard Cite

show abstract

Section: Characteristics Of the Port Of Kopermentioning

confidence: 99%

Container Throughput Forecasting Using Dynamic Factor Analysis and ARIMAX Model

Intihar

Kramberger

Dragan

2017

PROMET

View full text Add to dashboard Cite

show abstract

“…As Song (2013) indicated, the integration of the port and the city has become a major trend when constructing port cities in China [67]. Our intention here is to simply examine the relationship of port development and urban sprawl, while other studies have explored the development model of port and city combinations [68][69][70], and the methods relating the port cargo throughput with city GDP [71][72][73][74] in detail. The relationship implies the relatively close connection (R 2 is about 0.7) between the port development (represented by cargo throughput) and urban sprawl in the coastal zone.…”

Section: Relationship Between Port and Urban Sprawlmentioning

confidence: 99%

Spatiotemporal Characteristics of Urban Sprawl in Chinese Port Cities from 1979 to 2013

Zhang

Seen³

et al. 2016

Sustainability

View full text Add to dashboard Cite

China has been through a period of remarkable urban sprawl since the reform and opening-up policy in 1978, with the highest urbanization occurring in the coastal zones. Sustainable urban development requires a better understanding of the spatiotemporal characteristics of urbanization. This study systematically explored urban sprawl in Chinese coastal cities with a visual interpretation method from 1979 to 2013. The results show that urban built-up areas kept increasing at a faster pace during the study period (i.e., increased about 9-fold in 34 years), especially in the first decade of the 21st century. Spatially, urban sprawl intensity generally peaked in the urban fringe. Urban built-up areas expanded mostly at a cost to cultivated land and non-urban built-up land, and became more irregular and less compact through the study period. Land-use policies, economic development levels, port developments and locations are all closely related with urban sprawl in these port cities. The results also suggest that improving the utilization efficiency of urban land and coordinating the development of city and port are necessary and important for sustainable development in coastal cities.

show abstract

“…These techniques are appropriate when we can describe the general patterns or tendencies, without regard to the factors affecting the variable to be forecast [2]. Easy to develop and implement, times series models are preferred for their having been used in many applications such as: Economic Forecasting, Sales Forecasting, Budgetary Analysis, Stock Market Analysis, Process and Quality Control and Inventory Studies [3].…”

Section: Literature Reviewmentioning

confidence: 99%

Seasonal Time Series Forecasting Models based on Artificial Neural Network

Benkachcha¹,

Benhra²,

H³

2015

IJCA

View full text Add to dashboard Cite

Forecasting is the starting point for drawing good strategies facing the demand variability in the increasingly complex and competitive today's markets. This article discusses two methods of dealing with demand variability in seasonal time series using artificial neural networks (ANN). First a multilayer perceptron model for time series forecasting is proposed. Several learning rules used to adjust the ANN weights have been evaluated. Secondly a causal method based on artificial neural networks, using the components of decomposed time series as input variables, has been used. The results show that ANNs yield almost the same accuracy with or without decomposition of the original time series. General TermsFeedforward Neural Networks; Multilayer Perceptron; Levenberg-Marquardt backpropagation algorithm. Seasonal time series forecasting model and causal method.

show abstract

A Comparison of Traditional and Neural Networks Forecasting Techniques for Container Throughput at Bangkok Port

Cited by 100 publications

References 12 publications

Container Throughput Forecasting Using Dynamic Factor Analysis and ARIMAX Model

Container Throughput Forecasting Using Dynamic Factor Analysis and ARIMAX Model

Spatiotemporal Characteristics of Urban Sprawl in Chinese Port Cities from 1979 to 2013

Seasonal Time Series Forecasting Models based on Artificial Neural Network

Contact Info

Product

Resources

About