An innovative road traffic control prediction with multi-vehicle movement detection based on novel LSTM machine learning compared with BRNN

This study reports the vehicle images and detects their vehicle movement to predict the traffic flow using Novel LSTM Machine learning against BRNN. Long Short-Term Memory (LSTM) and Bidirectional Recurrent Neural Networks (BRNN) can be considered as two groups. For each algorithm consider N=5 sampl...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaswanth, A., Beenarani, B., Aishwarya, B.
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Image detection
Machine learning
Motion perception
Recurrent neural networks
Traffic control
Traffic flow
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study reports the vehicle images and detects their vehicle movement to predict the traffic flow using Novel LSTM Machine learning against BRNN. Long Short-Term Memory (LSTM) and Bidirectional Recurrent Neural Networks (BRNN) can be considered as two groups. For each algorithm consider N=5 samples from the dataset and perform each iteration on both the algorithms to predict vehicle images and their movement. The accuracy of the BRNN has a potential up to 51.60% and the Novel LSTM Machine Learning has an accuracy of 91.20% for image detection and the movement detection with significance value of 0.0001. Detection of vehicle images and their movement using Novel LSTM shows better accuracy than BRNN.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0178967