Traffic Prediction for Intelligent Transportation System using Machine Learning

杨利霞

Traffific Prediction for Intelligent Transportation

1 `; E, N/ c, x3 M* M5 R

System using Machine Learning

) I# E5 Z! X- `/ ^" p0 d

! Z7 D0 V2 f: G' J4 G/ A1 G
' L/ r1 T, t' \6 T5 n

+ [! w3 E+ f5 oThis paper aims to develop a tool for predicting
; g9 m2 |  |* O" R$ O! ^accurate and timely traffific flflow Information. Traffific Environment
) D+ z4 e; F+ t; Minvolves everything that can affect the traffific flflowing on the
& k7 B9 c6 K1 c0 Droad, whether it’s traffific signals, accidents, rallies, even repairing
of roads that can cause a jam. If we have prior information
2 n8 g; N1 ~- o( k  b/ b" Y( G4 vwhich is very near approximate about all the above and many
. ~7 a- m$ L3 D: Emore daily life situations which can affect traffific then, a driver
: T' g9 U0 P9 V& t; _6 j/ aor rider can make an informed decision. Also, it helps in the
future of autonomous vehicles. In the current decades, traffific data
/ z$ [+ o, j, c1 }have been generating exponentially, and we have moved towards
* d5 V/ K0 U  W/ M" ythe big data concepts for transportation. Available prediction
methods for traffific flflow use some traffific prediction models and
are still unsatisfactory to handle real-world applications. This fact
1 x5 l7 {. t) f9 C/ r, xinspired us to work on the traffific flflow forecast problem build on
8 F  {. l8 L3 d' g, q6 p. ]7 R0 mthe traffific data and models.It is cumbersome to forecast the traffific
flflow accurately because the data available for the transportation
2 ^3 v2 f7 E. D9 fsystem is insanely huge. In this work, we planned to use machine
6 x: }. t7 U% Qlearning, genetic, soft computing, and deep learning algorithms
to analyse the big-data for the transportation system with
much-reduced complexity. Also, Image Processing algorithms are
involved in traffific sign recognition, which eventually helps for the
. e. c3 R. n6 i0 f' {right training of autonomous vehicles.
4 m4 j* r# C( y/ F' i

9 v' B) B" _  Q( C$ i8 A