• Manjula

Traffic flow forecasting is of great importance for traffic safety, energy conservation and protection of the environment. Nonetheless, making reliable assumptions about traffic volumes is a difficult problem in the face of many external uncertainties. Many previous types of research only explore the usefulness of a single factor in their prediction and do multi-factor research rarely. As for the prediction of traffic flow, many past types of research focus primarily on the temporal distribution of traffic flow at a single point on the road, ignoring the correlation between spaces. As regards global forecasting, the mechanical view of traffic as images was logically far-fetched. Given the effects of several exogenous variables and the interaction between monitor locations, we are proposing a hybrid model to simultaneously predict traffic flow in multiple positions by combining the layer-wise structure with the Markov transition matrix (MTM). Specifically, we use the layer wise structure to capture traffic flow's periodicity,pattern, and nonlinearity characteristics and then generate the MTM that captures the dynamics expressed in the data and generates the corresponding distributions.

Markov transition matrix (MTM), traffic, Xiamen

"Road Traffic Speed Prediction using Multi-Source Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 10, page no.571-577, October-2020, Available :http://www.jetir.org/papers/JETIR2010068.pdf

"Road Traffic Speed Prediction using Multi-Source Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 10, page no. pp571-577, October-2020, Available at : http://www.jetir.org/papers/JETIR2010068.pdf