CHAPTER But usually, the traffic congestion have a pattern




We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

2.1       Introduciton Prediction

            Prediction is a scientific process in order to get the
knowledge systematically based on physical data.  The more accurate the data and the method
used, the better prediction result can be obtained.  The prediction itself, is not 100% accurate,
some of the prediction can also fail to meet expectation.

to Herdianto (2013), prediction is a
systematic estimating process about something that is most likely to happen in
the future based on the information of the future then and now owned, in order
for his mistake (the difference between something that is occur with predicted
results) can be minimized.  Prediction
does not have to deliver the exact answer to events that will happen, but rather
to strive for looking for answers as closely as possible that will happen.

the traffic congestion problem that occur in the big city is already become
major problem. Usually this happen in the any place and any time.  But usually, the traffic congestion have a
pattern that can be learned about, based on the time or the place.  Traffic congestion problem can be predicted
to analyze the possibility for some of the place that might become a traffic




2.2       Introduction
To Artificial Neural Network (ANN)

            Artificial Neural Network (ANN) is a group of small
processing unit in network that are modeled based on human neural system. ANN
is a type of adaptive system that can change the structure based on the
external and internal information that flowing through  the network to solve the problem.

to Ramadhani(2016), ANN
is a network architecture modelling based on the work of human nervous system (brain) when it is
carrying out specific tasks.
This model has the human brain ability to organize its constituent cells (neurons) by carry out certain tasks, especially with the effectiveness of the network pattern recognition which is
very high.

            The Artificial Neural Network (ANN)
structure is parallel and able to adapt and learn to give expected output
correctly for input that hasn’t been trained. The learning ability to produce
the correct result make an Artificial Neural Network (ANN) as an indenpence

            Artificial Neural Network (ANN), is
divided into 3 things :

Structure of relationship between
neurons (Network Architecture)

Method for link weight (Training or
Learning Algorithm)

Activation Function


Figure 2.1 Is an example of a feed forward network with multiple layers
Da Silva(2016)

From figure above, it’s also
explain if the Artificial Neural Network (ANN) has 3 layer, which is :


This layer is the one who will receive any information
data from external environment.  The
input will be normalize by activation functions with a limit value that will
give a better numerical precision result in mathematics operation that being
held by network.


This layer is focus to extracting patterns that
related to process or a system that are being analyze.


This layer is the layer that will given a produce and
present the final network outputs that has been performed by the some of the
layer before.


2.2.1    Backpropagation

            Based on Werbos(1990) Backpropagation is the
most widely used tool in the field of
artificial neural networks.  At the core of backpropagation is a method
for calculating derivatives exactly and efficiently in any large system made up of elementary subsystems or
calculations which are represented by known, differentiable
functions; thus, backpropagation has many
applications which do not involve neural
networks as such.

            An example of backpropagation network architecture can be
seen in Figure 2.2

2.2 General Structure of
Backpropagation Gunawan(2009)  Backpropagation

            There are three different Artificial Neural Network
(ANN) training algorithms, Levenberg-Marquardt, conjugate gradient and
resilient backpropagation, which are used in the present study.  This is done to see which algorithm produces
better results and has faster training for the application under construction



The aim for the
training algorithm is focus to reduce the global error, (E) that can be determine as :


While P is the total of training pattern and Ep is the error for training
pattern p. That can put into formula


While N as number of output nodes, Oi as network output and ti as target output. For in
training algorithm, a test is created to reduce the global error by configurate
the weight and biases.




Algorithm is created to gain second-training speed without compute for Hessian
matrix. The function has a form as sum of the squares, then Hessian matrix can
be calculated as :

H=JTJ                                                                (1.3)

As for gradient
will be calculate :

g=JTe                                                                 (1.4)

While J as Jacobian matrix, that have first
derivate of network errors by weight and biases and e as network vector error.

Levenberg-Marquardt Algorithm is concentrate to calculate the Hessian matrix by
using based on newton, that can be form :


If µ is large, gradient will decresease
with a small step-size. µ will
decrease after each complete step and also increase if tentative step will
increase the performance function.

Levenberg-Marquardt is better than conventional gradient descent techniques


Gradient Algorithm

Gradient Algorithm is performed alongside conjugate directions, which is can
have faster convergence than steepest descent directions.

Gradient Algorithm, begin by searching steepest descent directions for the
first iteration , then the line searching is used to decide for optimal
distance to move along for the current search direction.  After that, the next searching is decided to
previous search directions. The new search direction will start to combine
between new steepest descent and previous search direction.  Various version for this, are differentiate
by the step of in that will be constant ?k
is computed.


Backpropagation Algorithm

Backpropagation Algorithm main focus to reduce and decrease the negative
effects of magnitude partial derivate. 
Just only the mark of derivative that will be used to decide the
direction for the weight update, but magnitude of derivate will not changing the
weight update.  The size for weight
change will be known by separate update value. 
Update value for each weight and bias will be increase from a factor
everytime derivative from performance function which is related to the weight
has a same mark for two successive iteration. The update values will be
decrease by a factor if the derivate which is related to the weight change mark
from previous iteration. If devirative is zero, update value will be same.  Activation

There are some
of the choices for activation function that can be used inside Backpropagation
method such as Sigmoid Biner Function, Sigmoid Bipolar and Tangen
Hiperbolik.  Characteristics that must
have for activation function are continuous, differencial with ease and a
function that not down. Nyura(2016)

Some of the activation
function that usually use in Backpropagation method are :

Sigmoid Biner

Function Sigmoid
Biner is used for neural network that will be training in Backpropagation
method.  The Function Sigmoid Biner has a
range value (0,1). This function usually used for neural network that have
interval for output value from 0 until

Function Sigmoid
Biner can be state as :


With derivative


Sigmoid Bipolar

Function Sigmoid
Bipolar is almost similar to Function Sigmoid Biner but the range of the output
is (-1,1).



For Functionn
Linear, output from this function is same as input for this function


2.2.2      Backpropagation
Training Algorithm

There is steps
of standar backpropagation algorithm : 
Training Algorithm

of intial system

the weight, epoch = 1 and MSE = 1

the maximum epoch, learning rate (?) and also error target

into step 4 until step 12 as long Epoch is less than maximum epoch and MSI is
more than error target

= Epoch + 1


every input unit xi sends to the input signal to all unit in the
input layer.

each unit that in hidden layer zj


Hidden layer signal will be calculate by using
activation function to sum the weight input signal xi


After that, will be sent to the output layer

every unit in output layer yk will be calculate same by using
activation function to sum the weight input signal zj


Then, it will be using
activation function to calculate the signal output



every output yk wil
receive tk the target
pattern.  After that error information in
output layer (

) will be calculated. 

 will be sending
to the hidden layer and to calculate the weight and bias correction between
hidden and output layer




each hidden layer unit, the error information in stop layer


 will be used to
calculate the weight and bias correction between input and hidden layer.




connection weight and bias

10.  For the updating connection weight and bias for each
output unit y_k, bias and the weight will be update.  Then bias and the weight will become new bias
and new weight.

 (new) =

 (old) +


11.  After that, first until p-unit in hidden layer will be
update the bias and the weight.

 (new) =

 (old) +


12.  After complete, the test condition will be stop


2.2.3      Normalization
and Denormalization Data

Normalization data is type of process to convert the
original data into the data that have value range from 0 until 1.  The target for normalize the data in
Artificial Neural Network (ANN) in order to make easy to recognize the pattern
of data.  The formula used for
normalization data is :



Explaination :

x’ = Normalized data

x = Input data

a = smallest value in input data

b = largest value in input data


After process training and testing, the output value
from Artificial Neural Network (ANN) need to return back to the original
value.  This process know as
denormalization data.  The formula used
for denormalization data is :


Explaination :

x = the original value

x’ = value of the test

a = smallest value of all data

b = largest value of all data


2.3       Previous Research About Traffic

many kind of method that have been used to predict the traffic congestion in
the big city.  One of the method that has
been used for traffic congestion prediciton is Backpropagation method from
Artificial Neural Network (ANN).  Research
by Xiaojian(2009) used Backpropagation for traffic flow, by making a model
construction based on crossroad/intersection to maximize the flow of crossroad
traffic and the waiting time.  The
outcome showed the Artificial Neural Network (ANN) is stable after reaching 300
cycle training without clear accuracy change. 
But, time for training is same as index training with prediction
accuracy 85% that can help traffic flow and able to optimize the time.

research about traffic congestion is done by More(2016) using Jordan Neural Network
to predict and control traffic congestion. 
That research proposes the significance of Jordan sequential
network for prediction of
future values, depending on the current value aggregate past values and also
guarantees prediction of traffic
flow with accuracy of about 92-98% using Jordan’s Sequential
Network.  The result is quite satisfying for every
analysis over different parameter of Jordan Neural Network certain points are
concluded as :

Accuracy obtained is maximum at 0.5 learning rate.

Structure of neural network determines the output, thus hidden layer should contain
square of the number of
input neurons.

Considering the error factor instead of iterations gives almost 98% accuracy for most of the

Thus, overall objective of accurate road traffic
prediction is
met using Jordan’s Neural Network with proper structure.



This chapter covered briefly about prediction of
traffic congestion and Artificial Neural Network.  The prediction traffic application for
similiar problem like traffic congestion is able to give good estimation and
prediction for traffic congestion with highly efficient result.  Backpropagation and Jordan Neural Network,
fill out the target and satisfies every analysis from any parameter.  This chapter also, has examined and explained
about the basic concepts of Artificial Neural Network (ANN) with method that
being used is backpropagation.  Some of
the concept from Artificial Neural Network (ANN) like architecture of ANN, the
activation function are explained.  Normalization
and denormalization data make easy understand for the pattern of the data.  Decision made based on this chapter will be
used to planned ahead for development of the system based on the methodology
that will be discussed in the next chapter.