Traffific Prediction for Intelligent Transportation
6 Q' Y2 z* a3 Z' r
System using Machine Learning
+ _. I$ i q S! Y7 T4 _
+ C5 i9 v) X- i6 x9 ?+ {5 {, ]6 P- M5 X, Z& E* I
, M% r; D% I3 _8 i1 ~! e+ S8 D& ~2 O( D& ~* W' u/ L F& j {! y
$ k, C* z; \2 p! L
This paper aims to develop a tool for predicting + x6 C& ]; ?% Gaccurate and timely traffific flflow Information. Traffific Environment" d7 f1 u. E: u2 P* B
involves everything that can affect the traffific flflowing on the , P6 \. ?6 g7 B, ]5 troad, whether it’s traffific signals, accidents, rallies, even repairing " Q9 M9 ~' ~5 J- Yof roads that can cause a jam. If we have prior information' V0 X' T; G5 M7 g
which is very near approximate about all the above and many ( w3 E$ t* w: M& l3 emore daily life situations which can affect traffific then, a driver + p4 Y! J! [2 y- L6 ^or rider can make an informed decision. Also, it helps in the. f! J' h4 R0 d V- r
future of autonomous vehicles. In the current decades, traffific data * C+ Y8 K- h6 u# p& k1 U* L8 X' g& Hhave been generating exponentially, and we have moved towards / e" ~) b8 H! v3 }the big data concepts for transportation. Available prediction 3 @+ }3 b6 b; u0 r/ p6 q; Mmethods for traffific flflow use some traffific prediction models and 4 V$ O5 ]0 D/ l: r3 y/ qare still unsatisfactory to handle real-world applications. This fact 4 E9 x. I$ g1 e1 W& |& Y. E Tinspired us to work on the traffific flflow forecast problem build on9 |4 q2 ?) {! C- T6 w; @
the traffific data and models.It is cumbersome to forecast the traffific 4 [0 Q4 z5 L* A- n9 o; w7 L* Q4 Dflflow accurately because the data available for the transportation , n4 J) H& m! f" o* r' ysystem is insanely huge. In this work, we planned to use machine I6 W% [9 j. }9 m% N6 r
learning, genetic, soft computing, and deep learning algorithms 1 [) S- C* S2 rto analyse the big-data for the transportation system with 9 ^ a1 a' U, q, @2 J: ?much-reduced complexity. Also, Image Processing algorithms are 3 }( n2 Z7 J# E1 kinvolved in traffific sign recognition, which eventually helps for the " l3 J9 W1 g, T. z: T Gright training of autonomous vehicles. S+ d. ?% K& t% I. l. Z; v
8 w5 m0 \( x* v, y% C2 ]. Q