|
Traffific Prediction for Intelligent Transportation ! k/ ]/ o! s5 E# G0 W3 s) k
System using Machine Learning 6 E5 J2 y' ?5 d0 I
$ e0 X) x3 J3 x" L V' \
) a- X1 ~& o+ ~% P; i; D! ?% ^. Q1 @1 P
# Z R; t$ ?% \# d. T+ K$ n
This paper aims to develop a tool for predicting1 i/ b7 Y* ^. n" V1 m6 ^. H6 l
accurate and timely traffific flflow Information. Traffific Environment
/ v ~! B( F: |# D( a2 linvolves everything that can affect the traffific flflowing on the1 q4 O, l+ G0 m" r( l3 m
road, whether it’s traffific signals, accidents, rallies, even repairing
" d; |, ]0 M2 \of roads that can cause a jam. If we have prior information
% ^8 z {3 h0 e! J: M, xwhich is very near approximate about all the above and many6 ?8 ?& n9 g& e" C/ O f. p4 a
more daily life situations which can affect traffific then, a driver! T- J/ m, _/ ^% o* c
or rider can make an informed decision. Also, it helps in the
* [/ H; ]( v) H% [2 afuture of autonomous vehicles. In the current decades, traffific data
# i9 a. `( N( Q/ P" Rhave been generating exponentially, and we have moved towards
& ?4 ^ h- `# r) Q5 q' U+ D! dthe big data concepts for transportation. Available prediction# |% O5 Z7 Z+ W1 ?2 e
methods for traffific flflow use some traffific prediction models and
9 U6 b; d, } ^( D1 I/ aare still unsatisfactory to handle real-world applications. This fact
1 C0 y; y3 f% k( o) k4 Y: n) tinspired us to work on the traffific flflow forecast problem build on
7 F k+ M2 O& _/ b1 f3 fthe traffific data and models.It is cumbersome to forecast the traffific, |$ N" m+ V" D( I) e/ x
flflow accurately because the data available for the transportation
1 Z* H0 K; x% o+ y- x1 `# lsystem is insanely huge. In this work, we planned to use machine0 @0 I3 x7 F) D3 x/ R6 \& k
learning, genetic, soft computing, and deep learning algorithms
3 Q2 H; [' r7 A L" T# h# i4 \$ c4 D: Yto analyse the big-data for the transportation system with
0 r' k" r) J% A' U0 L# zmuch-reduced complexity. Also, Image Processing algorithms are
P9 b5 G+ T9 r2 I, D* I' r; f# H5 n. Tinvolved in traffific sign recognition, which eventually helps for the+ Q8 x3 J% ^0 R8 |6 I
right training of autonomous vehicles.
# r7 L0 U# s5 ^/ H& k# _, p1 N2 e. m7 ~+ B
5 g+ `! N c" x3 I
% A4 j2 B' D$ b
' Z2 Z; J7 B s' V f
4 d4 h: E7 I7 m V) _# h |