Traffic Image Analysis Based on Stacked Denoising Autoencoder Neural Network
Abstract views: 74
,
PDF downloads: 69
Abstract
This study aims to explore major neural network models - Stacked Denoising Autoencoder (SDAE), Deep Belief Network (DBN), Backpropagation - that have recently garnered attention and propose the most suitable and reliable artificial neural network model for real-time road traffic information collection. In this study, to enhance the reliability of experimental results, numerous experiments were conducted under identical conditions (such as parameter values and network configuration) by setting different initial values for the weight vector. The results of the experiments were statistically validated to draw conclusions. The research results showed that the SDAE model exhibited the most superior performance, while the accuracy of the DBN was somewhat lower compared to the SDAE model. On the other hand, the Backpropagation model demonstrated a relatively low predictive accuracy compared to both models, particularly showing a significant influence of the initial values
References
D. Kim, “Acquiring Real-Time Traffic Information Using Deep Learning Neural Networks,” Asia-Pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol. 5, no. 1, pp. 435-444, 2016. DOI: 10.35873/ajmahs.2016.6.5.042
H. Cui, G. Y., N. Liu, M. Xu, and H. Song, "Convolutional neural network for recognizing highway traffic congestion," Journal of Intelligent Transportation Systems, vol. 24, no. 3, pp. 279-289, 2020. DOI: 10.1080/15472450.2020.1742121
H. Nguyen, "Deep Neural Network-based Detection of Road," International Journal of Advanced Computer Science and Applications, vol. 14, no. 9, pp.307-314, 2023.
D. Kim, "Standard and Advanced Backpropagation Models for Image Processing Application in Traffic Engineering," Journal of Intelligent Transportation Systems, vol. 7, no.3-4, pp.199-211, 2002. DOI: 10.1080/714040816
D. Kim, "Pre-processing of inputs to a neural network model for better performance in traffic scene analysis," Civil Engineering and Environmental Systems, vol. 27, no.1, pp. 23-31, 2010. DOI: 10.1080/10286600802252719
Y. Gao et al., "A novel image-based convolutional neural network approach for traffic congestion estimation," Expert Systems with Applications, vol. 180, 2021, 115037. DOI: 10.1016/j.eswa.2021.115037
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," In D.E. Rumelhart, J.L. McClelland and the PDP Research Group, eds. Parallel distributed processing, Cambridge, MA: MIT Press, 1986.
G. E. Hinton, R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, 2006.
P. Vincent et al., "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion," Journal of Machine Learning Research, vol. 11, no. 110, pp. 3371-3408, 2010.
L. Wang, Z. Zhang, and J. Chen, “Short-Term Electricity Price Forecasting with Stacked Denoising Autoencoders,” IEEE Transactions on Power Systems, vol. 32, no. 4, pp. 2673-2681, 2016. DOI: 10.1109/TPWRS.2016.2628873
O.M. Saad et al., “Automatic Arrival Time Detection for Earthquakes Based on Stacked Denoising Autoencoder,” IEEE Geoscience and Remote Sensing Letters, vol. 15, no. 11, pp. 1687-1691, 2018. DOI: 10.1109/LGRS.2018.2861218
W. Lin et al., “A Deep Neural Collaborative Filtering based Service Recommendation Method with Multi-Source Data for Smart Cloud-Edge Collaboration Applications,” Tsinghua Science and Technology, 2023. DOI: 10.26599/TST.2023.9010050
P. Singh, A. Sharma, S. Maiya, “Automated atrial fibrillation classification based on denoising stacked autoencoder and optimized deep network,” Expert Systems with Applications, vol. 233, 120975, 2023. DOI: 10.1016/j.eswa.2023.120975
Y. Bengio et al., "Greedy layer-wise training of deep networks," International conference on neural information processing systems, MIT Press, pp. 153-160, 2006.
L. Gondara, "Medical image denoising using convolutional denoising autoencoders," 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), 2016. DOI: 10.1109/ICDMW.2016.0041
R. B. Palm, "Prediction as a candidate for learning deep hierarchical models of data," MSC thesis, Technical University of Denmark, 2012.
G. E. Hinton, S. Osindero, Y. W. The, "A fast learning algorithm for deep belief nets," Neural Comput, vol. 18, no. 7, pp. 1527-1554, 2006.
A. Mohamed, G. Dahl, G. Hinton, "Acoustic modeling using deep belief networks," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
D. Kim, "Normalization of Input Vectors in Deep Belief Networks (DBNs) for Automatic Incident Detection," Asia-Pacific Journal of Convergent Research Interchange, vol. 4, no. 4, pp. 61-70, 2018. DOI: 10.14257/apjcri.2018.12.07
D. Kim, "Improving prediction performance of neural networks in pattern classification," Int. J. Comput. Math., Vol. 82, no. 4, pp. 391-399, 2005. DOI: 10.1080/0020716042000301806
D. Kim, "Normalization methods for input and output vectors in backpropagation neural networks," Int. J. Comput. Math., vol. 71, no. 2, pp. 161-171, 1999. DOI: 10.1080/00207169908804800
D. Kim, "Prediction performance of support vector machines on input vector normalization methods," Int. J. Comput. Math., vol. 81, no. 5, pp. 547-554, 2004. DOI: 10.1080/00207160410001684325
D. Kim, "Nonlinear Normalization Model to Improve the Performance of Neural Networks," Asia-Pacific Journal of Convergent Research Interchange, vol. 6, no. 11, pp. 183-192, 2020. DOI: 10.47116/apjcri.2020.11.16
R. Bevans, "One-way ANOVA | When and How to Use It (With Examples) (scribbr.com)," June 22, 2023. https://www.scribbr.com/statistics/one-way-anova/
Copyright (c) 2023 Daehyon Kim
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- 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.
- 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.
- 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).
