Traffic Prediction for Intelligent Transportation System using Machine Learning

杨利霞

Traffific Prediction for Intelligent Transportation

$ b( K0 {2 m1 Q; \  L/ L% h

System using Machine Learning

( A: f; b1 k6 j, ~9 T



. c8 I+ n2 k+ N9 a3 c/ E) FThis paper aims to develop a tool for predicting
7 }" F9 a+ ^, ]" f3 t( Daccurate and timely traffific flflow Information. Traffific Environment
involves everything that can affect the traffific flflowing on the
7 D" h0 [: Z9 N; Troad, whether it’s traffific signals, accidents, rallies, even repairing
7 g' z) v; G6 s+ i: b" jof roads that can cause a jam. If we have prior information
which is very near approximate about all the above and many
more daily life situations which can affect traffific then, a driver
4 D* C: G7 Q+ e# }9 j4 w* D  `+ S. wor 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
the big data concepts for transportation. Available prediction
9 E4 p' Z2 O/ Mmethods for traffific flflow use some traffific prediction models and
are still unsatisfactory to handle real-world applications. This fact
* m6 A0 h* E! T" h# Ainspired us to work on the traffific flflow forecast problem build on
; u  s3 N) c2 b0 ?% U$ mthe traffific data and models.It is cumbersome to forecast the traffific
flflow accurately because the data available for the transportation
+ M4 B! K' _) f2 zsystem is insanely huge. In this work, we planned to use machine
' X/ ?7 w: T# H" Xlearning, genetic, soft computing, and deep learning algorithms
to analyse the big-data for the transportation system with
5 X  q' l5 [9 H3 p8 p0 Bmuch-reduced complexity. Also, Image Processing algorithms are
0 Z: }2 S& D! Linvolved in traffific sign recognition, which eventually helps for the
$ g* R3 h! ~$ N2 G) F: e' y0 O  \( Rright training of autonomous vehicles.

) N  |2 c  a* ^' L# h4 A& a8 i. y) Q
6 x1 T1 Z. H3 B, N2 S* @

. _5 ?4 f/ p4 ^$ D6 J+ X2 Q! H6 \2 q