Traffic Prediction for Intelligent Transportation System using Machine Learning

杨利霞

Traffific Prediction for Intelligent Transportation

System using Machine Learning

! l* ?* m) A4 ]. f  S

7 p" }: n* ]9 w* r2 U3 ~* V" J
- ^+ }9 i, G+ w( A+ c
This paper aims to develop a tool for predicting
( n" h( R  a5 z5 C- l4 Naccurate and timely traffific flflow Information. Traffific Environment
1 }% X/ ^  N1 O4 J# o  Uinvolves everything that can affect the traffific flflowing on the
" w2 E0 }3 C2 [road, whether it’s traffific signals, accidents, rallies, even repairing
of roads that can cause a jam. If we have prior information
% i2 f( W' l0 n4 A3 Mwhich is very near approximate about all the above and many
more daily life situations which can affect traffific then, a driver
or rider can make an informed decision. Also, it helps in the
# J+ I3 }: g% }3 R* J' M  Ofuture of autonomous vehicles. In the current decades, traffific data
have been generating exponentially, and we have moved towards
4 n, B; }  K# m' X( R& }5 H" k8 y, Ithe big data concepts for transportation. Available prediction
methods for traffific flflow use some traffific prediction models and
& `" _( \0 Q8 o, e: c& M% Ware still unsatisfactory to handle real-world applications. This fact
* w: y" H1 {' K7 q% \inspired us to work on the traffific flflow forecast problem build on
the traffific data and models.It is cumbersome to forecast the traffific
& o3 O) A  X# c; ]5 ^& Sflflow accurately because the data available for the transportation
& u5 h6 a# x) q, [; O& ?% Wsystem is insanely huge. In this work, we planned to use machine
8 P% f% S, @1 Z- H8 i& k% llearning, genetic, soft computing, and deep learning algorithms
* o0 {3 w" P5 V* d$ hto analyse the big-data for the transportation system with
much-reduced complexity. Also, Image Processing algorithms are
/ ]9 x7 M& T  o: c' Qinvolved in traffific sign recognition, which eventually helps for the
0 H5 L) U/ X, y, w, Hright training of autonomous vehicles.

/ a8 f  H" O% D* B3 R


  ?) R/ }) Y& |1 G% R