Smarter Traffic Prediction Using Big Data, In-Memory Computing, Deep Learning and GPUs

. 2019 May 13;19(9):2206. doi: 10.3390/s19092206

Algorithm 1 Input dataset parsing.

Input: Multiple data files from PeMS archived datasets.

Output: Parsed sub-datasets files to be used as training, testing, and prediction datasets.

n \leftarrow n u m b e r o f i n p u t d a t a f i l e s

2: for

i = 1, i + +, i \leq n

x_{i} \leftarrow l o a d D a t a (f i l e = i)

r a w D a t a \leftarrow m e r g e D a t a F i l e s (x_{i})

5: end for

X \leftarrow E x t r a c t R e q u i r e d I n p u t P a r a m e t e r s (r a w D a t a)

7: for

j = 1, t o e n d_o f_d a t a s e t

h o u r s_{j}, m i n_{j} \leftarrow e x t r a c t T i m e (t i m e s t a m p_{j})

d a t e_{j} \leftarrow e x t r a c t D a t e (t i m e s t a m p_{j})

10:

d a t e_{j} \leftarrow p r o c e s s D a t e V a l s (d a t e_{j})

11:

d a y_{j}, m o n t h_{j}, y e a r_{j} \leftarrow e x t r a c t D M Y (d a t e_{j})

12: end for

13:

C o n v e r t D a t a F r o m L o n g T o W i d e F o r m a t ()

14:

w e e k D a y s \leftarrow G e t W e e k D a y s F r o m D a t e (d a t e)

15: for

c = 1, c + +, c \leq c o l s C o u n t

16: for

r = 1, r + +, r \leq r o w s C o u n t

17: if

v a l_{c r}

is NA then

18:

\begin{matrix} v a l_{c r} \leftarrow a v e r a g e (v a l_{c (r - 2)}, v a l_{c (r - 1)}, v a l_{c (r + 1)}, v a l_{c (r + 2)}) \end{matrix}

19: end if

20: end for

21: end for

22: for

c = 1, c + +, c \leq c o l s C o u n t

23:

c o l M a x \leftarrow g e t C o l M a x V a l u e (c)

24: for

r = 1, r + +, r \leq r o w s C o u n t

25:

v a l_{c r} \leftarrow v a l_{c r} \div c o l M a x

26: end for

27: end for

28:

S p l i t D a t a I n t o T r a i n i n g T e s t i n g P r e d S u b s e t s ()

29:

w r i t e D a t a O n F i l e s ()