A Review on Traffic Forecast Based on Machine Learning Regression Models

  • Unique Paper ID: 169444
  • Volume: 11
  • Issue: 6
  • PageNo: 1029-1034
  • Abstract:
  • In the recent times, there has been a significant surge in the utilization of statistical and evolutionary algorithms in the development of intelligent traffic systems, particularly within the realm of Intelligent Transportation Systems (ITS). This involves the exploration of various methodologies to predict or estimate traffic volume in specific geographic areas under varying conditions. The objective is to effectively monitor and manage substantial traffic flows, a formidable challenge in urban and semi-urban areas globally. The forecasting task is intricate due to the inherently random and uncorrelated nature of the data. Establishing a clear functional relationship, such as through correlation or regression analysis, is rarely predefined. Consequently, conventional statistical algorithms are being investigated in a preliminary phase to adapt parameters according to the dynamic statistical properties of the input data. This paper provides a thorough examination of the necessity for evolutionary statistical algorithms in addressing traffic forecasting challenges, highlighting key points from existing literature. Additionally, it presents an extensive review of conventional statistical algorithms employed thus far. The paper concludes by elucidating performance metrics used to assess the efficacy of these algorithms. This comprehensive review aims to establish a foundational understanding for future research endeavors in this domain.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 6
  • PageNo: 1029-1034

A Review on Traffic Forecast Based on Machine Learning Regression Models

Related Articles