TAILIEUCHUNG - A comparison of ARIMA and ANN techniques in predicting port productivity and berth effectiveness

This study explored the possibility of predicting port productivity and berth effectiveness of a seaport using ANN and ARIMA. A comparative analysis of a multi-layer perceptron (MLP) back propagation algorithm and ARIMA performance was carried out based on ships days at port, days at berth and tonnage: the model’s input parameters, while port productivity and berth effectiveness were the model outputs. | A comparison of ARIMA and ANN techniques in predicting port productivity and berth effectiveness International Journal of Data and Network Science 3 2019 13 22 Contents lists available at GrowingScience International Journal of Data and Network Science homepage ijds A comparison of ARIMA and ANN techniques in predicting port productivity and berth effec- tiveness Desmond Eseoghene Ighravwea and Christopher Osita Anyaecheb a Department of Mechanical and Biomedical Engineering Bells University of Technology Ota Nigeria b Department of Industrial and Production Engineering University of Ibadan Nigeria CHRONICLE ABSTRACT Article history Business process evaluation is a common norm in small-medium-large industries globally and Received October 2 2018 information obtained during such evaluation have been used in simulating the future performance Received in revised format Octo- of most industries using mathematical models such as Autoregressive Integrated Moving Average ber 20 2018 ARIMA and artificial neural network ANN . This study explored the possibility of predicting Accepted November 29 2018 Available online port productivity and berth effectiveness of a seaport using ANN and ARIMA. A comparative November 30 2018 analysis of a multi-layer perceptron MLP back propagation algorithm and ARIMA performance Keywords was carried out based on ships days at port days at berth and tonnage the model s input parame- ARIMA ters while port productivity and berth effectiveness were the model outputs. The MLP-ANN and Artificial neural network ARIMA 1 0 4- port productivity and 1 0 4-berth effectiveness results were compared based Back-propagation algorithm on their coefficient of correlation and mean square error. The coefficient of correlation for port Berth effectiveness productivity prediction using MLP-ANN was . This value outperformed that of ARIMA Port productivity for port productivity berth effectiveness coefficients of correlation of .

• Kĩ thuật Viễn thông
• Artificial neural network
• Back propagation algorithm
• Multi layer perceptron
• ANN and ARIMA
• Back propagation algorithm
• Journal of technology and science education
• Model detecting learning styles with artificial neural network
• Model detecting learning styles
• Singular Value Decomposition
• Latent Semantic Indexing
• International Journal of Computer Science & Communication Networks
• Design of intrusion detection system
• Artificial neural network and application of rough set
• Intrusions in a network
• Artificial neural network in textiles
• Biological nervous systems
• Process information
• Highly interconnected processing elements
• Building maintenance contractor
• Multi criteria decision making methods
• Artificial neural network model
• Spearman correlation coefficients
• Groundwater level
• Levenberg marquardt algorithm
• Groundwater level prediction
• Nuclear engineering and technology
• Radiation interaction position in plastic rod scintillators
• Fast and simple technique
• Position sensitive detector
• Artificial intelligence of particles in water management
• Data mining
• Swarms of particles in water management
• Prediction and planning in the management
• Numerical Model
• Storm surge
• Tropical cyclone
• Neural network models
• Electrical Energy Demand Forecasting
• Recurrent Neural Network
• Non linear factor
• Time series analysis
• Journal of Chemistry
• Heterogeneous Fenton
• Nanoporous clinoptilolite
• Neural network
• Artificial neural network (ANN)
• Multiple regression analysis
• Method development
• Artificial neural networks
• Mixture of ascorbic acid
• Solar irradiance forecasting
• Root mean square error
• Artificial neural networks via assessment
• Mean absolute error
• Bài giảng Máy học nâng cao
• Máy học nâng cao
• Bài giảng Máy học
• Backpropagation algorithm
• Elman neural network
• Recurrentneural network
• Groundwater level forecasting
• Simulation of groundwater level
• BMC Bioinformatics
• Gene regulatory networks
• Prediction of response
• Clinical trial
• Group Lasso
• Biological Neural Networks
• Artificial Neural
• Delta Rule
• The Backpropagation
• Hebbian Learning
• ANN representations
• Perceptron Training
• Multilayer networks
• Remarks on the Backpropagation algorithm
• Neural network application development
• data modeling tools
• Anrudimentary
• switches
• LCD screen
• non linear
• Vietnam Journal of Science and Technology
• Water quality classification
• Dong Nai river
• Excellently water quality
• High order sliding mode control
• Anti sway based compensation
• Pso algorithm for overhead crane
• Leaf length
• Leaf width
• Leaf area
• Developing estimation models
• New switching controller
• Soft computing high accuracy implementation
• Generates the duty ratios
• Risk management
• Risk assessment
• Failure mode
• Effect Analysis
• Construction project
• Modeling of laser direct structuring process
• Optimization of laser direct structuring process
• Artificial neural network and response surface methodology
• Response surface methodology
• The MID products
• Response surface and artificial neural network prediction model
• Optimization for surface roughness in machining
• Optimization for surface roughness
• Response surface model
• ANN prediction model sufficiently predict