Traffific Prediction for Intelligent Transportation
' J4 E$ v) ]2 A$ \8 B) i E( ]* A! w
System using Machine Learning
, s3 c! K4 h7 [6 j0 L% a+ a 8 H+ E0 H/ K% P& H # x9 W; R# X1 V: g, v1 `1 T0 w2 d 8 z# Q+ s' y8 ~( u6 L, T1 b: d' g
: q" l q: A R) @2 F+ o K
This paper aims to develop a tool for predicting' [5 |4 v/ t& _) Y# q. ?5 P
accurate and timely traffific flflow Information. Traffific Environment * A" K( m! m! b7 L8 Q' O( cinvolves everything that can affect the traffific flflowing on the 7 U$ u; R' k, p$ Q3 Iroad, whether it’s traffific signals, accidents, rallies, even repairing3 Q0 P& S8 I% b0 d! H
of roads that can cause a jam. If we have prior information ! r1 m8 E* q w+ N7 g6 ?which is very near approximate about all the above and many. Y6 j0 {/ d* W' A. O
more daily life situations which can affect traffific then, a driver 0 J W J1 i$ y8 n+ b8 c/ yor rider can make an informed decision. Also, it helps in the" s0 J$ d1 H: g" | W
future of autonomous vehicles. In the current decades, traffific data , K! ]( [) I& p2 W! R6 M( Yhave been generating exponentially, and we have moved towards ) I7 W( ?# W5 L5 c, b/ ]the big data concepts for transportation. Available prediction! `7 }: G/ Q: a1 z& }
methods for traffific flflow use some traffific prediction models and 7 Z, f9 E+ m$ \are still unsatisfactory to handle real-world applications. This fact+ v+ b; J% D, f4 d
inspired us to work on the traffific flflow forecast problem build on. u4 Q( ^8 `, p, E; O; n, b; Q$ ~
the traffific data and models.It is cumbersome to forecast the traffific 7 Q4 Q9 A0 S0 a* J! Cflflow accurately because the data available for the transportation - Y: N/ A d9 D! j7 g: x. bsystem is insanely huge. In this work, we planned to use machine 5 A4 `9 |1 F/ u, |& }learning, genetic, soft computing, and deep learning algorithms ) [3 G/ `( `% k% j9 bto analyse the big-data for the transportation system with L( n. H6 g7 S; h( Gmuch-reduced complexity. Also, Image Processing algorithms are 0 E8 X# [( }* binvolved in traffific sign recognition, which eventually helps for the 0 o/ x# s' w' ?- C9 S, F: P5 kright training of autonomous vehicles. + Q7 P8 Y1 }$ { { L5 r K7 ^2 Q9 ?' H& m
: ?; d3 a; t( K0 n. h/ b" _; ?' `( k