Traffific Prediction for Intelligent Transportation
. G6 i* O: n8 C1 A6 j# Y4 }
System using Machine Learning
2 q% V: d' {4 t8 j. _5 ^0 I% H1 J0 v
# `% i0 s; l. e3 b- x- F9 W( C ' \! _: c3 w2 x. _3 k4 o) y * O8 X/ ?4 x: K2 F! J' Z; a* nThis paper aims to develop a tool for predicting 4 L. f1 @6 v% F. w) E) i2 i1 Waccurate and timely traffific flflow Information. Traffific Environment # y3 k. m$ ?- [" K2 V* @5 Z, minvolves everything that can affect the traffific flflowing on the1 |5 P+ P0 M/ c
road, whether it’s traffific signals, accidents, rallies, even repairing 0 V* P, }7 W; S, a: G% x1 Vof roads that can cause a jam. If we have prior information 2 D: u5 Z+ i# bwhich is very near approximate about all the above and many1 l* A4 h( ]* i
more daily life situations which can affect traffific then, a driver5 h6 k& l; {* p8 |. r4 ?% `1 ^
or rider can make an informed decision. Also, it helps in the 6 c6 B- j+ \6 Afuture of autonomous vehicles. In the current decades, traffific data / ]8 C; e7 U/ i1 uhave been generating exponentially, and we have moved towards 3 r3 n% e8 _* u9 N% S( Xthe big data concepts for transportation. Available prediction% E$ B$ i# }' j5 \0 P
methods for traffific flflow use some traffific prediction models and: d% _% j( [8 W" m& k
are still unsatisfactory to handle real-world applications. This fact( H' X( X; c- ]% q. _$ T$ Z
inspired us to work on the traffific flflow forecast problem build on 2 A! ]6 s8 P* C! x4 f* othe traffific data and models.It is cumbersome to forecast the traffific6 u9 I4 T5 S& j8 ?/ ?
flflow accurately because the data available for the transportation" S! L; Z( K8 w* p* S$ I# A7 _
system is insanely huge. In this work, we planned to use machine- `( ], [/ q; i, }! n j+ }- s
learning, genetic, soft computing, and deep learning algorithms0 |0 M: M8 ~( Z9 z" U( V* ]8 I2 |
to analyse the big-data for the transportation system with / k- z# S( N, k, j# e+ Pmuch-reduced complexity. Also, Image Processing algorithms are( l g4 |2 x9 l: O
involved in traffific sign recognition, which eventually helps for the T* k/ U4 G$ f
right training of autonomous vehicles. 8 q6 q9 K, s ]3 n: b$ c% y " p" N$ Q4 T( y1 b' p3 q2 T1 `. j1 b$ E5 e/ e8 M* t