Traffic Image Analysis Based on Stacked Denoising Autoencoder Neural Network

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 collecti...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of Innovation Information Technology and Application Ročník 5; číslo 2; s. 183 - 192
Hlavný autor: Kim, Daehyon
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Pusat Penelitian dan Pengabdian Masyarakat (P3M), Politeknik Negeri Cilacap 29.12.2023
Predmet:
autoencoding
backpropagation
deep belief network
neural network
stacked denoising
ISSN:2716-0858, 2715-9248
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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
ISSN:2716-0858
2715-9248
DOI:10.35970/jinita.v5i2.2133