DOI : https://doi.org/10.18517/ijaseit.10.6.7189

Calibrating Trip Distribution Neural Network Models with Different Scenarios of Transfer Functions Used in Hidden and Output Layers

Gusri Yaldi (1), Imelda M. Nur (2), - Apwiddhal (3)
(1) Politeknik Negeri Padang, Limau Manis, Padang-Sumatera Barat, 25168, Indonesia
(2) Politeknik Negeri Padang, Limau Manis, Padang-Sumatera Barat, 25168, Indonesia
(3) Politeknik Negeri Padang, Limau Manis, Padang-Sumatera Barat, 25168, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
Yaldi, Gusri, et al. “Calibrating Trip Distribution Neural Network Models With Different Scenarios of Transfer Functions Used in Hidden and Output Layers”. International Journal on Advanced Science, Engineering and Information Technology, vol. 10, no. 6, Dec. 2020, pp. 2410-8, doi:10.18517/ijaseit.10.6.7189.
Citation Format :
The transfer function is used to process the summation outputs in the hidden and output nodes. It can generally be categorized as either a non-linear or linear function. Examples are Sigmoid and Purelin functions representing non-linear and linear transfer functions. It is often mentioned that there is no standard guideline in the transfer function selection, and the Sigmoid or Logsig is widely used. However, the transfer function and training algorithm have a procedural relationship in training Multilayer Feedforward Neural Network (MLFFNN), a famous Artificial Neural Network model structure. In the feedforward stage, this function transforms the linear summation output to either linear (Purelin) or non-linear form (Sigmoid). In the backpropagation stage, this function is used in calculating the magnitude of change in the connection weights involving its derivative. Nine scenarios of MLFFNN were developed based on different transfer functions used in both hidden and output layers. In order to make fair comparisons, each scenario has the same initial connection weight. The modelling is conducted at the calibration level only; however, it involves different levels of complexity. It was calibrated by using the Levenberg-Marquard training algorithm. The results suggest that some calibrations failed and negative estimations occurred once non-linear transfer functions were used in hidden and output layers. It was found that Purelin was superior to other transfer functions. However, it has a weakness which is its negative estimations.

S. T. Skias, Methods and procedures for the verification and validation of artificial neural networks. New York, NY: Springer Science+Business Media, 2006.

W. Chen, et al., "Using a Single Dendritic Neuron to Forecast Tourist Arrivals to Japan," IEICE Transactions on Information and Systems, vol. E100.D, pp. 190-202, 2017.

K. Kumar, et al., "Short term traffic flow prediction in heterogeneous condition using artificial neural network," Transport, vol. 30, pp. 397-405, 2015/10/02 2015.

R. Abdul Jabbar and H. Dia, "Predictive Intelligence: A Neural Network Learning System for Traffic Condition Prediction and Monitoring on Freeways," Journal of the Eastern Asia Society for Transportation Studies, vol. 13, pp. 1785-1800, 2019.

W. Guangxing and K. Jiwon, "A Large Scale Neural Network Model for Crash Prediction in Urban Road Networks " in Australasian Transport Research Forum, Auckland, New Zealand, 2017.

W. R. Black, "Spatial interaction modeling using artificial neural networks," Journal of Transport Geography, vol. 3, pp. 159-166, 1995.

M. Dougherty, "A review of neural networks applied to transport," Transportation Research Part C: Emerging Technologies, vol. 3, pp. 247-260, 1995.

H. Wang, et al., "Detecting Transportation Modes Using Deep Neural Network," IEICE Transactions on Information and Systems, vol. E100.D, pp. 1132-1135, 2017.

Y.-J. Byon, et al., "Real-Time Transportation Mode Identiï¬cation Using Artiï¬cial Neural Networks Enhanced with Mode Availability Layers: A Case Study in Dubai," Appled Sciences, vol. 7, 2017.

O. Lozhkina, et al., "Motor transport related harmful PM2.5 and PM10: from onroad measurements to the modelling of air pollution by neural network approach on street and urban level," Journal of Physics: Conference Series, vol. 772, p. 012031, 2016/11 2016.

G. Yaldi, "Improving the Neural Network Testing Performance for Trip Distribution Modelling by Transforming Normalized Data Non-linearly," International Journal on Advanced Science, Engineering and Information Technology, vol. 7, 2017.

G. Yaldi, "Analysing the Behaviour and Performance of Neural Network Trip Distribution Models toward Different Hidden Layer and Node Numbers," presented at the The 11th International Conference of Eastern Asia Society for Transportation Studies, Cebu, Philippines, 2015.

F. Moretti, et al., "Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling," Neurocomputing, vol. 167, pp. 3-7, 2015/11/01/ 2015.

D. Teodorovic and K. Vukadinovic, Traffic Control and Transport Planning: A Fuzzy Sets and Neural Networks Approach. Massachusetts, USA: Kluwer Academic Publisher, 1998.

M. Mozolin, et al., "Trip distribution forecasting with multilayer perceptron neural networks: A critical evaluation," Transportation Research Part B: Methodological, vol. 34, pp. 53-73, 2000.

A. Dantas, et al., "Neural network for travel demand forecast using GIS and remote sensing," in Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on, 2000, pp. 435-440 vol.4.

G. Yaldi, et al., "Improving Artificial Neural Network Performance in Calibrating Doubly-Constrained Work Trip Distribution by Using a Simple Data Normalization and Linear Activation Function," in Paper of The 32 Australasian Transportation Research Forum, Auckland, New Zealand. Available at www.patrec.org/atrf.aspx, 2009.

B. M. Wilamowski, et al., "An Algorithm for Fast Convergence in Training Neural Networks," IEEE, vol. 3, pp. 1778-1782, 2001.

G. Zhang, et al., "Forecasting with artificial neural networks:: The state of the art," International Journal of Forecasting, vol. 14, pp. 35-62, 1998.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).