Traffic Prediction for Intelligent Transportation System using Machine Learning

杨利霞

Traffific Prediction for Intelligent Transportation

System using Machine Learning

+ Q5 r/ ]" R( S

9 d$ R0 i& X$ W8 {+ Z/ T' e
: n7 ?% f- K: i, `* k2 s2 R+ a% `/ V
This paper aims to develop a tool for predicting
accurate and timely traffific flflow Information. Traffific Environment
involves everything that can affect the traffific flflowing on the
0 u8 j7 |( K3 K' U* [8 W, Xroad, whether it’s traffific signals, accidents, rallies, even repairing
4 Y+ j3 d4 G# f  K  [$ Zof roads that can cause a jam. If we have prior information
6 a2 \5 d7 y" H* R+ P( C# Bwhich is very near approximate about all the above and many
; Y, r! f( D% |( u% B* Y# _more daily life situations which can affect traffific then, a driver
4 G; M9 X0 k& V0 Nor rider can make an informed decision. Also, it helps in the
future of autonomous vehicles. In the current decades, traffific data
have been generating exponentially, and we have moved towards
( }  c) ]1 i/ [the big data concepts for transportation. Available prediction
methods for traffific flflow use some traffific prediction models and
' j# q3 Q) P0 f; nare 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
( l" s- ~5 R) ^1 J& U5 Gflflow accurately because the data available for the transportation
system is insanely huge. In this work, we planned to use machine
, d; I( z4 X. Y0 S! {# J- Olearning, genetic, soft computing, and deep learning algorithms
to analyse the big-data for the transportation system with
9 _7 V" I' _$ Y6 }" G* J1 b, e5 }much-reduced complexity. Also, Image Processing algorithms are
5 v" O8 u" P6 J% _involved in traffific sign recognition, which eventually helps for the
9 U/ s: t1 h2 g, b+ Eright training of autonomous vehicles.


& s; p2 W/ K# k6 k8 s