Traffic Prediction for Intelligent Transportation System using Machine Learning

杨利霞

Traffific Prediction for Intelligent Transportation

0 {7 x( T$ `* O3 C" u$ S7 ~

System using Machine Learning

; T* }5 q; Z0 ~# ^

4 ?' |- m6 w6 z* r+ L8 j/ c


This paper aims to develop a tool for predicting
* K1 I9 Q. D4 k# {accurate and timely traffific flflow Information. Traffific Environment
involves everything that can affect the traffific flflowing on the
8 a. O- |6 I5 T. R! v7 g, j! groad, whether it’s traffific signals, accidents, rallies, even repairing
8 j# h9 [. _9 }+ W. u/ Pof roads that can cause a jam. If we have prior information
) h: v1 v& T) m9 _which is very near approximate about all the above and many
  N" v/ H8 r# o+ U5 ~0 lmore daily life situations which can affect traffific then, a driver
or rider can make an informed decision. Also, it helps in the
0 [4 U0 H6 |( `. e6 Z2 F. ^: t; rfuture of autonomous vehicles. In the current decades, traffific data
have been generating exponentially, and we have moved towards
the big data concepts for transportation. Available prediction
methods for traffific flflow use some traffific prediction models and
( {) `5 W$ K& z  Kare still unsatisfactory to handle real-world applications. This fact
inspired us to work on the traffific flflow forecast problem build on
the traffific data and models.It is cumbersome to forecast the traffific
2 H5 w& A# P& i3 q" a) y" rflflow accurately because the data available for the transportation
, [1 A; X1 x! p! R2 `system is insanely huge. In this work, we planned to use machine
; C* Y% Y- I$ v6 L, }9 v# t+ ulearning, genetic, soft computing, and deep learning algorithms
: N$ l7 z: U0 w$ a. \( ~to analyse the big-data for the transportation system with
much-reduced complexity. Also, Image Processing algorithms are
, M0 j/ Q& \' Z( _7 Z  m- |! zinvolved in traffific sign recognition, which eventually helps for the
2 \3 }1 l* \4 T$ Iright training of autonomous vehicles.


$ s. f  |) J3 ?( P# Y* F