Traffific Prediction for Intelligent Transportation 6 A3 ^3 n2 O5 _2 w
System using Machine Learning , \! t$ {: Z* L$ a o; c
' W; W; O# j1 U# U/ _
3 E. D4 |3 e( R1 d. |
9 {8 n z$ O: p4 R7 Y }9 Z* \: L+ |
! D2 J3 ~& a( l0 XThis paper aims to develop a tool for predicting
( E9 c" I8 p0 Jaccurate and timely traffific flflow Information. Traffific Environment1 b0 h0 A* T& j* M
involves everything that can affect the traffific flflowing on the) V3 S0 R3 G6 I) A; D9 T d8 N
road, whether it’s traffific signals, accidents, rallies, even repairing6 B7 \; \' E# t; z, v; U. {( `
of roads that can cause a jam. If we have prior information6 R% E/ ]4 w1 q1 L v
which is very near approximate about all the above and many
7 r+ n; G* q3 o2 s( x# imore daily life situations which can affect traffific then, a driver
0 q* D& m# \' _2 ^ A- cor rider can make an informed decision. Also, it helps in the# }2 a% r4 K( O# S4 j: c5 ]6 m
future of autonomous vehicles. In the current decades, traffific data
2 {3 p. U- [% C) K( l5 m: ]" u: Zhave been generating exponentially, and we have moved towards4 q' U4 i+ k- c, Q
the big data concepts for transportation. Available prediction, ?9 A0 C8 i5 d* q+ d
methods for traffific flflow use some traffific prediction models and
# k# ~- [; @* O0 q j% M6 pare still unsatisfactory to handle real-world applications. This fact, ?! o. Q! G7 M0 n
inspired us to work on the traffific flflow forecast problem build on
& ^8 Y7 P/ ?( N2 M$ o3 [4 {/ Wthe traffific data and models.It is cumbersome to forecast the traffific
( i4 [/ |+ u, V$ M7 Mflflow accurately because the data available for the transportation+ G4 @% y3 O$ m7 S3 G8 f( s
system is insanely huge. In this work, we planned to use machine
* F! H' I4 ]* Q+ |! @6 olearning, genetic, soft computing, and deep learning algorithms
1 `- x+ \! U8 M- Eto analyse the big-data for the transportation system with
$ r/ j8 {& T3 a% u# smuch-reduced complexity. Also, Image Processing algorithms are
# k; _. y+ a6 L7 R8 K; c5 Hinvolved in traffific sign recognition, which eventually helps for the
5 }$ G( i$ ]& H! K8 d7 ~right training of autonomous vehicles.
/ c; W$ s$ G, m$ t+ w7 P* U9 Z& p# @; g- Y8 X/ c
2 E2 V) Z/ E( k2 ~: c5 G4 Q; H
|