Authors :
Preeti Rekha Sahu
Volume/Issue :
Volume 8 - 2023, Issue 9 - September
Google Scholar :
https://tinyurl.com/2csnxmhx
Scribd :
https://tinyurl.com/mv4vaz8k
DOI :
https://doi.org/10.5281/zenodo.10066506
Abstract :
Congested roads is a fundamental urban areas' issue which is primarily contributed from unexpected vehicular
population growth and inefficient traffic operation and control in some mechanisms. The field of intelligent
transportation systems (ITS) has developed quickly inrecent years. A cost-effective method for managing and planning
smart public transportation.ITS enhances traffic safety, and mobility reduces the externalities that arise through all
the transportation-related activities. (ITS) applications require the minimum human intervention and are utilized for
advance route planning and traffic control systems. ITS applications areefficient in large scale traffic data collection
both in time and space and several studies uselarge scale traffic data for developing efficient traffic operation programs
for a city. Large scale data collection programs have several potential applications in solving transportation related
problems by developing robust traffic flow prediction models. In recent times, researchersapply novel tools such as
Machine Learning (ML) and Deep Learning (DL) to predict real-timetraffic. Real-time traffic prediction models are helpful
for improved traffic control and efficienttraffic management system. Statistical models, ML and DL models are used for
traffic signaldesign, que length analysis, and delay minimization for traffic stream in an urban network. Inessence, these
models help in minimizing travel time for users and thus reduces travel cost.This paper's goal is to present a thorough
grasp of the use of ML and DL approaches to improve traffic flow prediction models with recommendations for ITS
application in smart cities. The findings from this research may be applied by smart city managers for developing
efficienttraffic management programs in the cities in India and elsewhere.
Keywords :
ITS, Machine Learning, Deep Learning, Traffic flow Control and Prediction.
Congested roads is a fundamental urban areas' issue which is primarily contributed from unexpected vehicular
population growth and inefficient traffic operation and control in some mechanisms. The field of intelligent
transportation systems (ITS) has developed quickly inrecent years. A cost-effective method for managing and planning
smart public transportation.ITS enhances traffic safety, and mobility reduces the externalities that arise through all
the transportation-related activities. (ITS) applications require the minimum human intervention and are utilized for
advance route planning and traffic control systems. ITS applications areefficient in large scale traffic data collection
both in time and space and several studies uselarge scale traffic data for developing efficient traffic operation programs
for a city. Large scale data collection programs have several potential applications in solving transportation related
problems by developing robust traffic flow prediction models. In recent times, researchersapply novel tools such as
Machine Learning (ML) and Deep Learning (DL) to predict real-timetraffic. Real-time traffic prediction models are helpful
for improved traffic control and efficienttraffic management system. Statistical models, ML and DL models are used for
traffic signaldesign, que length analysis, and delay minimization for traffic stream in an urban network. Inessence, these
models help in minimizing travel time for users and thus reduces travel cost.This paper's goal is to present a thorough
grasp of the use of ML and DL approaches to improve traffic flow prediction models with recommendations for ITS
application in smart cities. The findings from this research may be applied by smart city managers for developing
efficienttraffic management programs in the cities in India and elsewhere.
Keywords :
ITS, Machine Learning, Deep Learning, Traffic flow Control and Prediction.
