Content

 Introduction
 Background
 Difference between ANN & BNN
 ANN architecture
 Types of ANN
 How it works
 Principle & theory of ANN
 Advantage & Disadvantages
 Application of ANN in textile
 Conclusion
Introduction: Indian textile industry is one of the leading textile industries in the world.
The textile industry, being the second largest employment generator after agriculture, it
earns about 27% of its total foreign exchange through textile exports. It is achieved by
producing competitive fabrics at minimizing production cost and time. The competition
enhancement depends mainly on productivity and quality of the fabrics produced by each
industry. In order to obtain good-quality products with high-efficiency production lines,
clothing companies have established advanced laboratories to measure fabric properties
by using artificial neural network thus controlling production processes and fabric
quality.
Although quality levels have been greatly improved with the continuous improvement of
materials and technologies, most weavers still find it necessary to perform 100%
inspection because customer expectations have also increased and the risk of delivering
inferior quality fabrics without inspection is not acceptable. It means that the quality is
the most important parameter despite the increase in one or both of the other parameters.
Scientifically, a process quality control is attained by conducting observations, tests and
inspections and thereby making decisions which improve its performance says Abdel
(2012). Practically no production or manufacturing process is 100% defect-free, the
success of a weaving mill is significantly highlighted by its success in reducing fabric
defects and achieve optimum potential benefits as quality, cost, comfort, accuracy,
precision and speed. To imitate the wide variety of human functions, technology was the
magic stick that advanced humanity from manual to mechanical and then from
mechanical to automatic.
ANN: It is an efficient computing system whose central theme is borrowed from the
analogy of biological neural networks. ANNs are also named as “artificial neural
systems,” or “parallel distributed processing systems,” or “connectionist systems”.
Artificial Neural Networks are a special type of machine learning algorithms that are
modeled after the human brain. That is, just like how the neurons in our nervous system
are able to learn from the past data, similarly, the ANN is able to learn from the data and
provide responses in the form of predictions or classifications. ANNs are nonlinear
statistical models which display a complex relationship between the inputs and outputs to
discover a new pattern. A variety of tasks such as image recognition, speech recognition,
machine translation as well as medical diagnosis makes use of these artificial neural
networks.
Today, ANN is being applied to increasing number of real world problems of
considerable complexity.
History of ANN: The first step towards neural networks took place in 1943, when Warren
McCulloch, a neurophysiologist, and a young mathematician, Walter Pitts, wrote a paper
on how neurons might work. They modeled a simple neural network with electrical
circuits.
1949: Donald Hebb reinforced the concept of neurons in his book, The Organization of
Behavior. It pointed out that neural pathways are strengthened each time they are used.
1950: Nathanial Rochester from the IBM research laboratories led the first effort to
simulate a neural network.
1956: the Dartmouth Summer Research Project on Artificial Intelligence provided a boost
to both artificial intelligence and neural networks. This stimulated research in AI and in
the much lower level neural processing part of the brain.
1957: John von Neumann suggested imitating simple neuron functions by using telegraph
relays or vacuum tubes.
1958: Frank Rosenblatt, a neuro-biologist of Cornell, began work on the Perceptron. He
was intrigued with the operation of the eye of a fly. Much of the processing which tells a
fly to flee is done in its eye. The Perceptron, which resulted from this research, was built
in hardware and is the oldest neural network still in use today. A single-layer perceptron
was found to be useful in classifying a continuous-valued set of inputs into one of two
classes. The perceptron computes a weighted sum of the inputs, subtracts a threshold, and
passes one of two possible values out as the result.
1959: Bernard Widrow and Marcian Hoff of Stanford developed models they called
ADALINE and MADALINE. These models were named for their use of Multiple
adaptive linear elements. MADALINE was the first neural network to be applied to a real-
world problem. It is an adaptive filter which eliminates echoes on phone lines. This neural
network is still in commercial use.
1982: John Hopfield presented a paper to the national Academy of Sciences. His approach
to create useful devices.
1985: American Institute of Physics began what has become an annual meeting — Neural
Networks for Computing.
1987: The Institute of Electrical and Electronic Engineer’s (IEEE) first International
Conference on Neural Networks drew more than 1,800 attendees.
1997: A recurrent neural network framework, Long Short-Term Memory (LSTM) was
proposed by Schmidhuber & Hochreiter.
1998: Yann LeCun published  Gradient-Based Learning Applied to Document
Recognition.

What is ANN: Artificial Neural Networks or ANN is an information processing paradigm

that is inspired by the way the biological nervous system such as brain process
information. It is composed of large number of highly interconnected processing elements
(neurons) working in unison to solve a specific problem.
What is neurons: Biological Neurons (also called nerve cells) or simply neurons are the
fundamental units of the brain and nervous system, the cells responsible for receiving
sensory input from the external world via dendrites, process it and gives the output
through Axons.
Cell body (Soma): The body of the neuron cell contains the nucleus and carries out
biochemical transformation necessary to the life of neurons.
Dendrites: Each neuron has fine, hair-like tubular structures (extensions) around it. They
branch out into a tree around the cell body. They accept incoming signals.
Axon: It is a long, thin, tubular structure that works like a transmission line.
Synapse: Neurons are connected to one another in a complex spatial arrangement. When
axon reaches its final destination it branches again called terminal arborization. At the end
of the axon are highly complex and specialized structures called synapses. The connection
between two neurons takes place at these synapses.
Dendrites receive input through the synapses of other neurons.
The soma processes these incoming signals over time and
converts that processed value into an output, which is sent out to
other neurons through the axon and the synapses.

Similarities based on the terminology

between ANN & BNN

Artificial neural network(ANN) Biological neural network(BNN)

Soma
Node

Dendrites
Input

Synapse
Weights or Interconnections

Axon
Output

Comparison between ANN & BNN

Criteria ANN BNN

Processing Massively parallel, slow but Massively parallel, fast but

superior than ANN inferior than BNN

Size 1011 neurons and 102 to 104 nodes

1015 interconnections

Learning They can tolerate ambiguity Very precise, structured

and formatted data is
required to tolerate
ambiguity
 Fault tolerance Performance degrades with It is capable of robust
even partial damage performance, hence has the
potential to be fault tolerant

Storage capacity Stores the information in the Stores the information in

synapse continuous memory
locations

AN ARTIFICIAL NEURON
The artificial neuron simulates four basic functions of a biological neuron.
In this various inputs to the network are represented by the mathematical symbol, x(n).
Each of these inputs is multiplied by a connection weight. The weights are represented by
w(n). In the simplest case, these products are summed, fed to a transfer function
(activation function) to generate a result, and this result is sent as output. This is also
possible with other network structures, which utilize different summing functions as well
as different transfer functions.
Major Components of an Artificial Neuron: This section describes the seven major
components which make up an artificial neuron.
1. Weighting Factors: A neuron usually receives many simultaneous inputs. Each input
has its own relative weight, which gives the input the impact that it needs on the
processing element's summation function. Some inputs are made more important than
others to have a greater effect on the processing element as they combine to produce a
neural response. Weights are adaptive coefficients that determine the intensity of the
input signal as registered by the artificial neuron. They are a measure of an input's
connection strength. These strengths can be modified in response to various training
sets and according to a network's specific topology or its learning rules.
2. Summation Function: The inputs and corresponding weights are vectors which can
be represented as (i1, i2 . . . in) and (w1, w2 . . . wn). The total input signal is the dot
product of these two vectors. The result; (i1 * w1) + (i2 * w2) +…….. + (in * wn) ; is
a single number. The summation function can be more complex than just weight sum
of products. The input and weighting coefficients can be combined in many different
ways before passing on to the transfer function. In addition to summing, the
summation function can select the minimum, maximum, majority, product or several
normalizing algorithms. The specific algorithm for combining neural inputs is
determined by the chosen network architecture and paradigm. Some summation
functions have an additional ‘activation function’ applied to the result before it is
passed on to the transfer function for the purpose of allowing the summation output to
vary with respect to time.
3. Transfer Function: The result of the summation function is transformed to a
working output through an algorithmic process known as the transfer function. In the
transfer function the summation can be compared with some threshold to determine
the neural output. If the sum is greater than the threshold value, the processing
element generates a signal and if it is less than the threshold, no signal (or some
 inhibitory signal) is generated. Both types of response are significant. The threshold,
or transfer function, is generally non-linear. Linear functions are limited because the
output is simply proportional to the input.
The step type of transfer function would output zero and one, one and minus one, or
other numeric combinations. Another type, the ‘threshold’ or ramping function, can
mirror the input within a given range and still act as a step function outside that range.
It is a linear function that is clipped to minimum and maximum values, making it
non-linear. Another option is a ‘S’ curve, which approaches a minimum and
maximum value at the asymptotes. It is called a sigmoid when it ranges between 0
and 1, and a hyperbolic tangent when it ranges between -1 and 1. Both the function
and its derivatives are continuous.
4. Scaling and Limiting: After the transfer function, the result can pass through
additional processes, which scale and limit. This scaling simply multiplies a scale
factor times the transfer value and then adds an offset. Limiting is the mechanism
which insures that the scaled result does not exceed an upper, or lower bound. This
limiting is in addition to the hard limits that the original transfer function may have
performed.
5. Output Function (Competition): Each processing element is allowed one output
signal, which it may give to hundreds of other neurons. Normally, the output is
directly equivalent to the transfer function's result. Some network topologies modify
the transfer result to incorporate competition among neighboring processing elements.
Neurons are allowed to compete with each other inhibiting processing elements
unless they have great strength. Competition can occur at one or both levels. First,
competition determines which artificial neuron will be active or provides an output.
Second, competitive inputs help determine which processing element will participate
in the learning or adaptation process.
6. Error Function and Back-Propagated Value: In most learning networks the
difference between the current output and the desired output is calculated as an error
which is then transformed by the error function to match a particular network
architecture. Most basic architectures use this error directly but some square the error
while retaining its sign, some cube the error, other paradigms modify the error to fit
their specific purposes. The error is propagated backwards to a previous layer. This
back-propagated value can be either the error, the error scaled in some manner (often
by the derivative of the transfer function) or some other desired output depending on
the network type. Normally, this back-propagated value, after being scaled by the
learning function, is multiplied against each of the incoming connection weights to
modify them before the next learning cycle.
7. Learning Function: Its purpose is to modify the weights on the inputs of each
processing element according to some neural based algorithm.
The first step is to multiply each of these inputs by their respective weighting factor
[w(n)]. These modified inputs are then fed into the summing function, which usually
sums these products, however, many different types of operations can be selected.
These operations can produce a number of different values, which are then
propagated forward; values such as the average, the largest, the smallest etc. Other
types of summing functions can also be created and sometimes they may be further
 complicated by the addition of an activation function which enables the summing
function to operate in a time sensitive way.
The output of the summing function is then sent into a transfer function, which turns
this number into a real output (a 0 or a 1, -1 or +1 or some other number) via some
algorithm. The transfer function can also scale the output or control its value via
thresholds. This output is then sent to other processing elements or an outside
connection, as dictated by the structure of the network.
Layer arrangement in neural network:
Neural networks are the simple clustering of artificial neurons by creating layers and
interconnections
Basically, a neural network is the grouping of neurons into layers, the connections
between these layers, and the summation and transfer functions that comprises a
functioning neural network. Most applications require networks that contain at least
the three layers - input, hidden, and output.
Input Layers
The input layer is the first layer of an ANN that receives the input information in the
form of various texts, numbers, audio files, image pixels, etc.  Input data has to be
numerical. This means it might have to take something that is non-numerical and find
a way to make it numerical.  The process of manipulating data before inputting it into
the neural network is called data processing and often times will be the most time
consuming part to making machine learning models.
Hidden Layers
In the middle of the ANN model are the hidden layers. There can be a single hidden
layer, as in the case of a perceptron or multiple hidden layers. The hidden layers are
composed of most of the neurons in the neural network and is the heart of
manipulating the data to get a desired output. Data will pass through the hidden layers
and be manipulated by many weights and biases. 
Output Layer
The output layer is the final product that is obtained from manipulating the data in the
neural network performed by the middle layer and can represent different things. Often
times, the output layer consists of neurons that each represents an object and the
numerical value attached is the probability that it is that specific object.

Processing of ANN: It mainly depends upon the following three building blocks

a) Network Topology
b) Adjustments of Weights or Learning
c) Activation Functions

Network Topology: A network topology is the arrangement of a network along with its
nodes and connecting lines. According to the topology, ANN can be classified as the
following kinds

a) Feed-forward Network: It is a non-recurrent network having processing

units/nodes in layers and all the nodes in a layer are connected with the nodes of the
 previous layers. The connection has different weights upon them. There is no
feedback loop means the signal can only flow in one direction, from input to output.
It is prepared to process large amounts of noise. This type of ANN computational
model is used in technologies such as facial recognition and computer vision.

It may be divided into the following

two types −
Single layer feedforward
network − The concept is of
feedforward ANN having only
one weighted layer. In other
words, we can say the input layer
is fully connected to the output layer.

Multilayer feedforward network − The concept is of feedforward ANN having more

than one weighted layer. As this network has one or more layers between the input and
the output layer, it is called hidden layers. The
function of hidden neurons is to interact between the
external input and network output in some useful
manner and to extract higher order statistics. The
source nodes in input layer of network supply the
input signal to neurons in the second layer (1st
hidden layer). The output signals of 2nd layer are
used as inputs to the third layer and so on. The set of
output signals of the neurons in the output layer of
network constitutes the overall response of network
to the activation pattern supplied by source nodes in the input first layer.

b) Feedback Network: As the name suggests, a feedback

network has feedback paths, which means the signal can flow in
both directions using loops. This makes it a non-linear dynamic
system, which changes continuously until it reaches a state of
equilibrium. It may be divided into the following types −
Recurrent networks: A feed forward neural network having one or more hidden layers
with atleast one feedback loop is known as recurrent network. The feedback may be a
self feedback, i.e., where output of neuron is fed back to its own input. Sometimes,
feedback loops involve the use of
unit delay elements, which results
in nonlinear dynamic behaviour,
assuming that neural network
contains non linear units.
Fully recurrent network − It is the simplest neural network architecture because all
nodes are connected to all other nodes and each node works as both input and output.
Adjustments of Weights or Learning:
Learning, in artificial neural network, is the method of modifying the weights of
connections between the neurons of a specified network. Learning in ANN can be
classified into three categories namely supervised learning, unsupervised learning, and
reinforcement learning.
Supervised Learning: As the name
suggests, this type of learning is done
under the supervision of a teacher.
This learning process is dependent.
During the training of ANN under
supervised learning, the input vector
is presented to the network, which
will give an output vector. This output vector is compared with the desired output
vector. An error signal is generated, if there is a difference between the actual output and
the desired output vector. On the basis of this error signal, the weights are adjusted until
the actual output is matched with the desired output.
Unsupervised Learning: As the name suggests, this type of learning is done without
the supervision of a teacher. This learning process is independent. During the training of
ANN under unsupervised learning, the input vectors of similar type are combined to
form clusters. When a new input pattern is applied, then the neural network gives an
output response indicating the class to which the input pattern belongs. There is no
feedback from the environment as to what should be the desired output and if it is
correct or incorrect. Hence, in this type of learning, the network itself must discover the
patterns and features from the input data, and the relation for the input data over the
output.
Reinforcement Learning: As the name suggests, this type of learning is used to
reinforce or strengthen the network over some critic information. This learning process
is similar to supervised learning, however we might have very less information. During
the training of network under reinforcement learning, the network receives some
feedback from the environment. This makes it
somewhat similar to supervised learning.
However, the feedback obtained here is
evaluative not instructive, which means there
is no teacher as in supervised learning. After
receiving the feedback, the network performs adjustments of the weights to get better
critic information in future.
LEARNING RATES: The rate at which ANNs learn depends upon several controllable
factors. A slower rate means more time to spend in producing an adequately trained
system. With faster learning rates, however, the network may not be able to make the
fine discriminations that are possible with a system learning slowly.
Most learning functions have some provision for a learning rate (learning constant).
Usually this term is positive and between 0 and 1. If the learning rate is greater than 1, it
is easy for the learning algorithm to overshoot in correcting the weights, and the network
will oscillate. Small values of the learning rate will not correct the current error as
quickly, but if small steps are taken in correcting errors, there is a good chance of
arriving at the best minimum convergence.
LEARNING LAWS (ALGORITHMS) Many learning laws are in common use. Most
of them are some sort of variation of the best known and oldest ‘Hebb's Rule’.
Hebb's Rule: This was introduced by Donald Hebb in ‘Organization of Behavior’. The
basic rule is: If a neuron receives an input from another neuron and if both are highly
active (same sign), the weight between the two neurons should be strengthened.
Hopfield Law: If the desired output and the input are both active or both inactive,
increment the connection weight by the learning rate, otherwise decrement the weight by
the learning rate.
The Delta Rule: This rule is based on the simple idea of continuously modifying the
strengths of the input connections to reduce the difference (the delta) between the
desired output value and the actual output of a processing element.
The Gradient Descent Rule: This is similar to Delta Rule in that, the derivative of the
transfer function is still used to modify the delta error before it is applied to the
connection weights. However, an additional proportional constant tied to the learning
rate is appended to the final modifying factor acting upon the weight.
Kohonen's Law: In this, the processing elements compete for the opportunity to learn
or update their weights. The element with largest output is declared the winner and has
the capability of inhibiting its competitors as well as exciting its neighbors. Only the
winner is permitted an output and only the winner plus its neighbors are allowed to
adjust their connection weights.
Activation Functions: It may be defined as the extra force or effort applied over the
input to obtain an exact output. In ANN, we can also apply activation functions over the
input to get the exact output. Followings are some activation functions of interest –
Linear Activation Function: It is also called the identity function as it performs no
input editing. It can be defined as –
F(x)=xF(x)=x
Sigmoid Activation Function
It is of two type as follows −
  Binary sigmoidal function − This activation function performs input editing between 0
and 1. It is positive in nature. It is always bounded, which means its output cannot be
less than 0 and more than 1. It is also strictly increasing in nature, which means more the
input higher would be the output. It can be defined as

F(x)=sigm(x)=11+exp(−x)F(x)=sigm(x)=11+exp(−x)

 Bipolar sigmoidal function − This activation function performs input editing between
-1 and 1. It can be positive or negative in nature. It is always bounded, which means its
output cannot be less than -1 and more than 1. It is also strictly increasing in nature like
sigmoid function. It can be defined as

F(x)=sigm(x)=21+exp(−x)−1=1−exp(x)1+exp(x)

Network selection:Because all artificial neural networks are based on the concept of
neurons, connections, and transfer functions, there is a similarity between the different
structures, or architectures, of neural networks. The majority of the variations stems from
the various learning rules and how those rules modify a network's typical topology.
Basically, most applications of neural networks fall into the following five categories:

a) prediction
b) classification
c) data association
d) data conceptualization
e) data filtering

Advantages:

a) By implementing appropriate learning algorithms, an ANN can be made to learn without

reprogramming.
b) ANN learns itself from the structure of training dataset and predicts the future data.
c) ANN uses dimensionless numbers in its input and output variables.
d) User feed input and get output without thinking about the dimensionality in computation
inside the hidden layer.
e) Information is stored on an entire network, not just a database.
f) The ability to learn and model nonlinear, complex relationships helps model the real life
relationships between input and output.
g) Gradual corruption means the network will slowly degrade over time, instead of a
problem destroying the network instantly.
h) The ability to produce output with incomplete knowledge with the loss of performance
being based on how important the missing information is.
i) No restrictions are placed on the input variables, such as how they should be distributed.
j) The ability to learn hidden relationships in the data without commanding any fixed
relationship means an ANN can better model highly volatile data and non-constant
variance.
Disadvantages
 a) All the parallel processing requires a huge amount of processing power and time.
b) There is a requirement for a “training” period before real-world implementation.
c) The lack of rules for determining the proper network structure means the appropriate
artificial neural network architecture can only be found through trial and error and
experience.
d) The requirement of processors with parallel processing abilities makes neural networks
hardware dependent.
e) The network works with numerical information, therefore all problems must be translated
into numerical values before they can be presented to the ANN.
f) The lack of explanation behind probing solutions is one of the biggest disadvantages in
ANNs. The inability to explain the why or how behind the solution generates a lack of
trust in the network.

Application of neural network in textile: Basically, most applications of NN in textiles fall

into five categories: Prediction, classification, data association, data conceptualization and data
filtering.
a) Prediction: refers to predicting some output from inputs using ANN. ex. picking
best stocks in the market
b) Classification: used to identify an unknown pattern that exists in a data
c) Data association: refers to recognizing data that contains error. It can be used
both for identifying the characters that were scanned and also for identifying
scanner when it is not working properly. (Feature extraction)
d) Data conceptualization: it is inferring grouping relationships from the input data.
(System modeling, Synthesis etc)
e) Data filtering: it is concerned with the smoothening of input data. It can also be
used for taking noise from the input data.
Fiber:

1. An ANN is used for the prediction of copolymer composition very correctly, as a

function of reaction conditions and conversions.

2. Classication of the animal fibers is one of the most typical problems. It has been resolved
successfully using ANNs.
She et al., 2002 developed an intelligent fiber classification system to objectively identify
and classify two types of animal fibers, merino and mohair, by two different methods
based on image processing and artificial neural network. There are considerable
variations in the shape and contour of the scale cells and their arrangement within the
cuticle. They used these two systems based on how the scale features of the animal fibers
were extracted. The data was cast images of fibers captured by optical microscopy. Then
they applied principal component analysis (PCA) to reduce the dimension of input
images and extract an optimal linear feature before applying neural network. Furthermore
neural network classifiers generalize better when they have a small number of
independent inputs. Finally they used an unsupervised neural network in which the
 outputs used as inputs in the supervised network (a multilayer perception with a back
propagation algorithm) for classification while the fiber classes were the outputs of the
output layer. For the unsupervised network, learning rate at 0.005 (step size) was set
which linearly decayed to 0.0005 within the first 100 epochs and three different numbers
of units in the hidden layer (80, 50, and 20) was used. Multilayer perception used for
fiber classification had a hyperbolic tangent activation function in the processing
elements of the hidden layer and output layer. They also compared their two systems and
concluded that neural network system was more robust since only raw images were used
and by developing more powerful learning strategies, the classification accuracy of model
would be improved (She et al., 2002).

3. ANN is used in cotton grading more perfectly.

Kang and Kim (2002) developed an image system for the current cotton grading system
of raw cotton involving a trained artificial neural network with a good classifying ability.
Trash from a raw cotton image can be characterized by a captured color by a color CCD
camera and acquire color parameters. The number of trash particles and their content,
size, size distribution, and spatial density can be evaluated after raw cotton images of the
physical standards are thresholded and connectivity was checked. The color grading of
raw cotton can be influenced by trash. Therefore, the effect of trash on color grading was
investigated using a color difference equation that measured the color difference between
a trash-containing image and a trash-removed image. The artificial neural network, which
has eight color parameters as input data, was a highly reliable and useful tool for
classifying color grades automatically and objectively.

4. ANNs have supported to identify the production control parameters and the prediction of
the properties of the melt spun bers in the case of synthetic fibers.
Kuo et al., (2004) applied neural network theory to consider the extruder screw speed,
gear pump gear speed, and winder winding speed of a melt spinning system as the inputs
and the tensile strength and yarn count of spun fibers as the outputs. The data from the
experiments were used as learning information for the neural network to establish a
reliable prediction model that can be applied to new projects. The neural network model
can predict the tensile strength and yarn count of spun fibers so that it can provide a very
good and reliable reference for spun fiber processing.

5. ANNs have been used in conjunction with NIR` spectroscopy for the identication of the
textile fibers.
Durand et al., (2007) studied different approaches for variable selection in the context of
near-infrared (NIR) multivariate calibration of the cotton–viscose textiles composition.
First, a model-based regression method was proposed. It consisted of genetic algorithm
optimization combined with partial least squares regression (GA–PLS). The second
approach was a relevance measure of spectral variables based on mutual information
 (MI), which can be performed independently of any given regression model. As MI made
no assumption on the relationship between X and Y, non-linear methods such as feed-
forward artificial neural network (ANN) were thus encouraged for modeling in a
prediction context (MI–ANN). GA–PLS and MI–ANN models were developed for NIR
quantitative prediction of cotton content in cotton–viscose textile samples. The results
were compared to full spectrum (480 variables) PLS model (FS-PLS). The model
required 11 latent variables and yielded a 3.74% RMS prediction error in the range 0–
100%. GA–PLS provided more robust model based on 120 variables and slightly
enhanced prediction performance (3.44% RMS error). Considering MI variable selection
procedure, great improvement can be obtained as 12 variables only were retained. On the
basis of these variables, a 12 inputs of ANN model was trained and the corresponding
prediction error was 3.43% RMS error.

Yarn:

1. ANN can help in imparting the better control on yarn quality during carding process.
Beltran et al., (2004) developed an artificial neural network (ANN) trained with
back-propagation encompassed all known processing variables that existed in
different spinning mills, and then generalized this information to accurately predict
yarn quality of worsted spinning performance for an individual mill. The ANN was
then subsequently trained with commercial mill data to assess the feasibility of the
method as a mill-specific performance prediction tool. The ANN was a suitable tool
for predicting worsted yarn quality for a specific mill.

2. ANN is used in auto leveling in the draw frame for imparting desired linear density
control.
Farooq and Cherif (2008) have reported a method of predicting the leveling action
point, which was one of the important auto-leveling parameters of the drawing frame
and strongly influences the quality of the manufactured yarn, by using artificial neural
networks (ANN). Various leveling action point affecting variables were selected as
inputs for training the artificial neural networks, which was aimed to optimize the
auto-leveling by limiting the leveling action point search range. The Levenberg–
Marquardt algorithm was incorporated into the back-propagation to accelerate the
training and Bayesian regularization was applied to improve the generalization of the
networks. The results obtained were quite promising that the accuracy in computation
can lead to better sliver CV% and better yarn quality.
3. ANN used in optimization of the top roller diameter as well as the study of the
spinning balloon in the main spinning phase is important for controlling yarn quality.
Ghane et al., 2008 revealed that cotton and cotton/polyester yarns regularity
improved by optimising front top rollers diameter of the ring machine using a self-
 organised Kohonen neural network. The diameter of top roller has been reduced in
stages and in each stages yarns are produced. The uneveness as well as the
imperfections of the produced yarns have been measured. The results showed that the
uneveness decrase with the decrease in the top rollers diameter up to optimum
diameter beyond which the uneveness of yarns increase rapidly as the top roller
diameter decreases,. These optimum values are different in the cases of cotton /
cotton polyester yarns. Kohonen neural network has been applied to observe optimum
values of top rollers diameter in case of each type yarn. The optimum diameter of top
rollers as estimated by neural network is found to be 27.5mm for the most of the
cotton and cotton/polyester (35:75) yarns.
4. Application of ANN, warp breakage rate reduce during the weaving.
Yao et al., (2005) investigated the predictability of the warp breakage rate from a
sizing yarn quality index using a feed-forward back-propagation network in an
artificial neural network system. An eight-quality index (size add-on, abrasion
resistance, abrasion resistance irregularity, hairiness beyond 3 mm, breaking strength,
breaking strength irregularity, breaking elongation, and breaking elongation
irregularity) and warp breakage rates were rated in controlled conditions. A good
correlation between predicted and actual warp breakage rates indicated that warp
breakage rates can be predicted by neural networks. A model with a single sigmoid
hidden layer with four neurons was able to produce better predictions than the other
models of this particular data set in the study.
5. ANNs have been used for the prediction of hairiness of worsted wool yarns.
Khan et al., (2009) studied the performance of multilayer perceptron (MLP) and
multivariate linear regression (MLR) models for predicting the hairiness of worsted-
spun wool yarns objectively by examining 75 sets of yarns consisting of various top
specifications and processing parameters of shrink-resist treated, single-ply, pure
wool worsted yarns. The results indicated that the MLP model predicted yarn
hairiness was more accurately than the MLR model and showed that a degree of
nonlinearity existed in the relationship between yarn hairiness and the input factors
considered. Therefore, the artificial neural network (ANN) model had the potential
for wide mill specific applications for high precision prediction of hairiness of a yarn
from limited top, yarn and processing parameters. The use of the ANN model as an
analytical tool may facilitate the improvement of current products by offering
alternative material specification and/or selection and improved processing
parameters governed by the predicted outcomes of the model. On sensitivity analysis
on the MLP model, yarn twist, ring size, average fiber length (hauteur) had the
greatest effect on yarn hairiness with twist having the greatest impact on yarn
hairiness.
6. The spinning of the staple fibers for the production of the yarns is a multistage
procedure including many parameters, which influence the characteristics of the end
product, viz; the spun yarn. ANN is the excellent method for predictors. The cost
 minimization of cotton fiber is also ensured by using classical linear programming
approach in combination with ANN.
Zeng et al., (2004) tried to predict the tensile properties (yarn tenacity) of air-jet spun
yarns produced from 75/25 polyester on an air-jet spintester by two models, namely
neural network model and numerical simulation. Fifty tests were undergone to obtain
average yarn tenacity values for each sample. A neural network model provided
quantitative predictions of yarn tenacity by using the following parameters as inputs:
first and second nozzle pressures, spinning speed, distance between front roller nip
and first nozzle inlet, and the position of the jet orifice in the first nozzle so that the
effects of parameters on yarn tenacity can be determined. Meanwhile, a numerical
simulation provided a useful insight into the flow characteristics and wrapping
formation process of edge fibers in the nozzle of an air-jet spinning machine; hence,
the effects of nozzle parameters on yarn tensile properties can be predicted. The result
showed that excellent agreement was obtained between these two methods.
Moreover, the predicted and experimental values agreed well to indicate that the
neural network was an excellent method for predictors.
7. ANNs have been used for the prediction of hairiness of worsted wool yarns and of
cotton yarns. In a same way, ANNs have been used for the prediction of the evenness
of ring spun worsted yarns and cotton yarns or the evenness of blended rotor yarns.
Khan et al., (2009) studied the performance of multilayer perceptron (MLP) and
multivariate linear regression (MLR) models for predicting the hairiness of worsted-
spun wool yarns objectively by examining 75 sets of yarns consisting of various top
specifications and processing parameters of shrink-resist treated, single-ply, pure
wool worsted yarns. The results indicated that the MLP model predicted yarn
hairiness was more accurately than the MLR model and showed that a degree of
nonlinearity existed in the relationship between yarn hairiness and the input factors
considered. Therefore, the artificial neural network (ANN) model had the potential
for wide mill specific applications for high precision prediction of hairiness of a yarn
from limited top, yarn and processing parameters. The use of the ANN model as an
analytical tool may facilitate the improvement of current products by offering
alternative material specification and/or selection and improved processing
parameters governed by the predicted outcomes of the model. On sensitivity analysis
on the MLP model, yarn twist, ring size, average fiber length (hauteur) had the
greatest effect on yarn hairiness with twist having the greatest impact on yarn
hairiness.
8. ANN also used in splicing of two yarn ends more perfectly.
Ünal et al., (2010) investigated the retained spliced diameter with regard to splicing
parameters and fiber and yarn properties. The yarns were produced from eight
different cotton types in three yarn counts (29.5, 19.7 and 14.8 tex) and three different
twist coefficients (αTex 3653, αTex 4038, αTex 4423). To investigate the effects of
splicing parameters on the retained spliced diameter, opening air pressure, splicing air
 pressure and splicing air time were set according to an orthogonal experimental
design. The retained spliced diameter was calculated and predicted by using an
artificial neural network (ANN) and response surface methods. Analyses showed that
ANN models were more powerful compared with response surface models in
predicting the retained spliced diameter of ring spun cotton yarns.
9. The image processing technology is interfaced with neural networks to extract the
defects in yarn packages and thereby used to classify the quality grades of the yarn
packages.
10. ANN is useful in defining relationship between process variables and molecular
structure for synthetic yarns.
11. ANNs have also been used for the appearance analysis of false twist textured yarn
packages, for the prediction of yarn shrinkage or for the modelling of the relaxation
behaviour of yarns.
Lin (2007) studied the shrinkages of warp and weft yarns of 26 woven fabrics
manufactured by air jet loom by using neural net model which were used to determine
the relationships between the shrinkage of yarns and the cover factors of yarns and
fabrics. The shrinkages were affected by various factors such as loom setting, fabric
type, and the properties of warp and weft yarns. The neural net was trained with 13
experimental data points. A test on 13 data points showed that the mean errors
between the known output values and the output values calculated using the neural
net were only 0.0090 and 0.0059 for the shrinkage ratio of warp (S1) and weft (S2)
yarn, respectively. There was a close match between the actual and predicted
shrinkage of the warp (weft) yarn. The test results gave R2 values of 0.85 and 0.87
for the shrinkage of the warp (i.e., S1) and weft (i.e., S2), respectively. This showed
that the neural net produced good results for predicting the shrinkage of yarns in
woven fabrics. Different woven fabrics manufactured on different looms like rapier,
gripper, etc., raw material yarn ingredients (e.g., T/C × T/R, T/R × T/R, T/C × C,
etc.), and fabric structural class (e.g., twill, satin, etc.) were examined to measure the
shrinkage ratio of warp and weft yarns. The developed neural net model was then
used to train the obtained data and the result showed that the prediction of yarn
shrinkage in the off-loomed fabrics can be fulfilled through a prediction model
constructed with neural net.

Fabric:

1. ANN is used to inspect fabric for the detection of faults.

Jeffrey et al., 2009 an image system is used as a tool for dynamic inspection of
fabrics, and the inspection sample is a piece of plain white fabric. The four defects
are holes, oil stains, warp-lacking, and weft-lacking. The image treatment
employs a high-resolution linear scan digital camera. Fabric images are acquired
first, then the images are transferred to a computer for analysis. Finally, the data
 are adopted as input data for a neural network, which is obtained from readings
after treating the images. In this system, there are three feedforward networks, an
input layer, one hidden layer, and an output layer. Because it has the ability to
cope with the nonlinear regression property, this method can reinforce the effects
of image identification.
2. Fabrics can be engineered either by weaving, knitting or bonding. Neural
networks are successfully implemented in all three to optimise the input
parameters.
3. The detection and recognition of the patterns on a fabric is of the same complex
category of problems and thus resolved by the implementation of ANNs.
4. ANN is used to the prediction of the fabric drape.
Payvandy 2011 studied the application of an imaging system to the detailed objective
measurement of the drape profiles of a range of woven fabrics, captured from a
common drape tester, was investigated. Drape coefficient values collected via the
image processing technique correlate strongly with those established using the
common cut and weigh approach. In next fractal dimension based on count boxing
method was used to evaluate the image fabric drape. The result shows that fractal
dimension method can be used to determine the fabric drape as well as common drape
coefficient.
5. By the application of ANNs fabric handle become increase.
Shyr et al., (2004) have taken new approaches in using a one-step transformation
process to establish translation equations for total hand evaluations of fabrics by
employing a stepwise regression method and an artificial neural network. The key
mechanical properties selected from sixteen fabric mechanical properties based on a
KES system, using the stepwise regression selection method, were the parameters.
The translation equations were developed directly with parameters without a primary
hand value transformation process. 114 polyester/cotton blended woven fabrics were
selected for investigation. Four mechanical properties LC, 2HG, B, and WT were the
parameters for developing the translation equations. The correlation coefficients of
the translation equations developed from the stepwise regression and artificial neural
network methods were 0.925 and 0.955, respectively. Both translation equations had
high correlation coefficients between the calculated and practical values. The
approaches were identified effectively to develop translation equations for new
fabrics in the textile industry.
6. ANNs in combination with fuzzy logic have been used in the case of the prediction of the
sensory properties of the fabrics.
Wong et al., (2004) investigated the process of human psychological perceptions of
clothing related sensations and comfort to develop an intellectual understanding of and
methodology for predicting clothing comfort performance from fabric physical
properties. Various hybrid models were developed using different modeling techniques
by studying human sensory perception and judgement processes. By combining the
 strengths of statistics (data reduction and information summation), a neural network (self-
learning ability), and fuzzy logic (fuzzy reasoning ability), hybrid models were developed
to simulate different stages of the perception process. Results showed that the TS-TS-
NN-FL model had the highest ability to predict overall comfort performance from fabric
physical properties. The three key elements in predicting psychological perceptions of
clothing comfort from fabric physical properties were data reduction and summation,
self-learning, and fuzzy reasoning. The model was shown that these three elements can
generated the best predictions compared with other hybrid models.
7. ANNs have been used for the prediction of the tensile strength and for the initial stress-
strain curve of the fabrics.
Hadizadeh et al., (2010) introduced a new model based on an adaptive neuro-fuzzy
inference system (ANFIS) for predicting initial load–extension behavior of plain-woven
fabrics. Input values defined as combination expressions of geometrical parameters of
fabric and yarn flexural rigidity, yarn-spacing, weave angle and yarn modular length,
which were extracted from Leaf’s mathematical model. The results showed that the
neuro-fuzzy system can be used for modeling initial modulus in the warp and weft
directions of plain-woven fabrics. Outputs of the neuro-fuzzy model were also compared
with results obtained by Leaf’s models. The calculated results were in good agreement
with the real data upon finding the importance of inputs.
8. Shear stiffness and compression properties of the worsted fabrics has been successfully
modelled.
Chen et al., 2009 revealed that the artificial neural network technique was used to model
the relationship between the yarn properties, fabric parameters and weft shear stiffness of
worsted fabrics. At first, the yarn properties and fabric parameters was selected using an
input variable selection method. This method takes both the human knowledge on the
weft shear stiffness of fabrics and the data sensitivity into account. Then the artificial
neural network model of the relationship between the yarn properties, fabric parameters
and weft shear stiffness of fabrics was established. The results show that the artificial
neural network model yields accurate prediction and a reasonably good artificial neural
network model can be achieved with relatively few data points by integrated with the
input variable selecting method.
9. Prediction of bursting strength using ANNs for woven and knitted fabrics has been
achieved with satisfactory results.
Ertugrul and Ucar (2000) have shown how the bursting strength of cotton plain knitted
fabrics can be predicted before manufacturing by using intelligent techniques of neural
network and neuro-fuzzy approaches. Fabric bursting strength affected by fabric weight,
yarn breaking strength, and yarn breaking elongation were input elements for the
predictions. Both the multi-layer feed-forward neural network and adaptive network
based fuzzy inference system, a combination of a radial basis neural network and the
Sugeno-Takagi fuzzy system, were studied. Both systems had the ability to learn training
 data successfully, and testing errors can give an approximate knowledge of the bursting
strength which fabric can be knitted.
10. Permeability of the woven fabrics has been modelled using ANNs as well as, the impact
permeability has been studied and the quality of the neural models has been assessed.
Behera et al., 2010 predict the air permeability of cotton woven fabrics from their
construction variables by using a feed-forward back-propagation network in an artificial
neural network (ANN) system. The fabrics are conditioned and tested for constructional
particulars and air permeability. A multiple linear regression based approach for
modelling is attempted. For neural network modelling, a three layer feed-forward
network is formed and trained by using the Broyden– Fletcher–Goldfarb–Shanno (BFGS)
quasi-Newton algorithm. The predictive ability of the neural model was examined by
comparing their results with experimental data. From the results, it was seen that high
correlation exists between the actual and predicted values of the neural network model.
The overall predictability of the model is good.
11. Pilling propensity of the fabrics has been predicted and the pilling of the fabrics has been
evaluated.
Beltran 2009 uses artificial neural networks to model the multi-linear relationships
between fiber, yarn and fabric properties and their effect on the pilling propensity of pure
wool knitted fabrics. This tool shall enable the user to gauge the expected pilling
performance of a fabric from a number of given inputs. It will also provide a means of
improving current products by offering alternative material specification and/or selection.
In addition to having the capability to predict pilling performance, the model will allow
for clarification of major fiber, yarn and fabric attributes affecting fabric pilling.
12. The presence of fuzz fibers has been modelled by ANN.
Ucar et al.,2007 predict the fuzz value on the fabric surface before producing the fabric.
The amount of fuzz on the fabric surface, as has been determined by image processing
techniques, can be predicted by two different methods, the Artificial Neural Network
(ANN) and Regression Analysis. During knitting, the yarn used is abraded to an
uncertain degree, depending on the knitting conditions and yarn properties, and this
situation can lead to poor prediction results. However it has been demonstrated that the
prediction results obtained by Artificial Neural Networks look more promising than that
of Regression Analyses.
13. ANN is used in evaluating wrinkled fabrics with image analysis.
14. Prediction of the spirality of the relaxed knitted fabrics as well as knit global quality and
subjective assessment of the knit fabrics have been implemented using ANNs.
Murrells et al., (2009) employed an artificial neural network (ANN) model and a
standard multiple linear regression model for the prediction of the degree of spirality
of single jersey fabrics made from a total of 66 fabric samples produced from three
types of 100% cotton yarn samples including conventional ring yarns, low torque ring
yarns and plied yarns. The data were randomly divided into 53 and 13 sets of data
that were used for training and evaluating the performance of the predictive models.
 A statistical analysis was undertaken to check the validity by comparing the results
obtained from the two types of model with relatively good agreement between
predictions and actual measured values of fabric spirality with a correlation
coefficient, R, of 0.976 in out-of-sample testing. Therefore, the results demonstrated
that the neural network model produced superior results to predict the degree of fabric
spirality after three washing and drying cycles. Both the ANN and the regression
approach showed that twist liveliness, tightness factor and yarn linear density were
the most important factors in predicting fabric spirality. Twist liveliness was the
major contributor to spirality with the other factors such as yarn type, the number of
feeders, rotational direction and gauge (needles/inch) of the knitting machine and
dyeing method having a minor influence.
15. Prediction of the thermal resistance and the thermal conductivity of the textile fabrics
have been realized with the help of ANNs.
16. Moisture and heat transfer in knitted fabrics has been studied with ANN modelling
successfully.
Kannat et al., 2018 ANNs were used to predict thermal resistance of wetted fabrics. Two
different architectures were experienced and high regression coefficient (R²) between the
predicted (training and testing) and observed thermal resistance values were obtained
from both models. The obtained regression coefficient values were over 90% for both
models. Then it can be said that ANNs could be used for predicting thermal resistance of
wetted fabrics successfully.
17. Engineering of fabrics used in safety and protection applications is supported by ANNs.
Behera and Goyal (2009) described the method of applying the artificial neural network
for the prediction performance parameters for airbag fabrics. The results of the ANN
performance prediction had low prediction error of 12% with all the samples and the
artificial neural network based on Error Back-propagation were found promising for a
new domain of design prediction technique. The prediction performance of the neural
network was based on the amount of training. The diversity of the data and the amount of
data resulted in better the mapping of the network, and better predictions. Therefore,
airbag fabrics could be successfully engineered using artificial neural network.
18. Prediction of the fabrics end use is also possible via ANN method.
Chen et al., (2001) proposed a neural network computing technique to predict fabric
enduse. One hundred samples of apparel fabrics for suiting, shirting, and blouse uses
were selected and fabric properties of extension, shear, bending, compression, and
friction and roughness were measured by using the Kawabata KES instruments.
Instrumental data of the fabric properties and information on fabric end-uses were input
into neural network software to train a multilayer perceptron model. The prediction error
rate from the established neural network model was estimated by using a cross-validation
method. The estimated error rate for prediction was 0.07. The established neural network
model could be upgraded by inputting new fabric samples and be implemented for
applications in garment design and manufacture.
 19. Optimization of the application of a repellent coating has also been approached by the
ANN model.
Allan et al., 2002 use plasma and neural modelling to optimise the application of a
repellent coating to disposable surgical garments. He designed experiments to vary three
parameters for the plasma process, gas concentration, power and duration, and to measure
the resulting degrees of hydrophobic behaviour at the cotton surface by means of
observing water droplets. Neural networks can provide rapid development of simulation
models of processes by adaptation to observed conditions as inputs and the results as
outputs. The data from the plasma trials has been used to develop a neural model to
predict surface hydrophobic behaviour. The model is itself optimised for interpolative
ability, and allows a search to be made through the data space to find the best possible
combination of the process parameters to encourage optimal surface treatment, and thus
make the cotton most hydrophobic. It indicate how the environmentally-friendly
approach of plasma treatment can be used to provide garments and drapes for surgery
which are comfortable but also protective.

20. Colour measurement, evaluation, comparison and prediction are major actions in the
dyeing and finishing field of the textile process. It is done by ANNs.

Apparel:

1. Resolving prediction problem: RGI involves various predictions during production

process, like; fabric manufacturing performance, sewing thread consumption, fashion
sensory comfort, cutting time, apparel sales, etc.
2. Resolving classication problems: It involves classication at various levels, just for
an example; fabric online classication, fabric defect classication, fabric end-use
classication and seam feature classication etc.
3. Model identication problems.
4. The thread consumption is predicted via an ANN model.
5. The seam puckering is evaluated and the sewing thread is optimized through ANN
models, respectively.
Hui and Ng (2009) investigated the capability of artificial neural networks based on a
back propagation algorithm with weight decay technique and multiple logarithm
regression (MLR) methods for modeling seam performance of fifty commercial
woven fabrics used for the manufacture of men’s and women’s outerwear based on
seam puckering, seam flotation and seam efficiency. The developed models were
assessed by verifying Mean Square Error (MSE) and Correlation Coefficient (R-
value) of test data prediction. The results indicated that the artificial neural network
(ANN) model has better performance in comparison with the multiple logarithm
regression model. The difference between the MSE of predicting in these two models
for predicting seam puckering, seam flotation, and seam efficiency was 0.0394,
0.0096, and 0.0049, respectively. Thus, the ANN model was found to be more
accurate than MLR, and the prediction errors of ANNs were low despite the
availability of only a small training data set. However, the difference in prediction
errors made by both models was not significantly high. It was found that MLR
models were quicker to construct, more transparent, and less likely to overfit the
minimal amount of data available. Therefore, both models were effectively predicting
the seam performance of woven fabrics.
6. The prediction of the sewing performance is also possible using ANNs.
Hui et al., (2007) investigated the use of artificial neural networks (ANN) to
predict the sewing performance of woven fabrics for efficient planning and
control for the sewing operation. This was based on the physical and mechanical
properties of fabrics such as the critical parameters of a fabric constructional and
behavioural pattern as all input units and to verify the ANN techniques as human
decision in the prediction of sewing performance of fabrics by testing 109 data
sets of fabrics through simple testing system and the sewing performance of each
fabric’s specimen by the domain experts. Among 109 input-output data pairs, 94
were used to train the proposed back-propagation (BP) neural network for the
prediction of the unknown sewing performance of a given fabric, and 15 were
used to test the proposed BP neural network. A three-layered BP neural network
that consists of 21 input units, 21 hidden units, and 16 output units was
developed. The output units of the model were the control levels of sewing
performance in the areas of puckering, needle damages, distortion, and
overfeeding. After 10,000 iterations of training of BP neural network, the neural
network converged to the minimum error level. The evaluation of the model
showed that the overall prediction accuracy of the developed BP model was at 93
per cent which was the same as the accuracy of prediction made by human
assessment. The predicted values of most fabrics were found to be in good
agreement with the results of sewing tests carried out by domain experts.
7.Prediction of the performance of the fabrics in garment manufacturing and fit
garment design has been realized based on ANN systems.
Hu et al., (2009) developed a system to utilize the successful experiences and
help the beginners of garment pattern design (GPD) through optimization
methods by proposing a hybrid system (NN-ICEA) based on neural network (NN)
and immune co-evolutionary algorithm (ICEA) to predict the fit of the garments
and search optimal sizes. ICEA takes NN as fitness function and procedures
including clonal proliferation, hypermutation and coevolution search the optimal
size values. A series of experiments with a dataset of 450 pieces of pants was
conducted to demonstrate the prediction and optimization capabilities of
NNICEA. In the comparative studies, NN-ICEA was compared with NN-genetic
algorithm to show the value of immune-inspired operators. Four types of GPD
method have been summarized and compared. The research was a feasible and
effective attempt aiming at a valuable problem and provides key algorithms for fit
 prediction and size optimization. The algorithms can be incorporated into garment
computer-aided design system (CAD).

Non-Woven:

1. The non-woven fabrics undergo a process of inspection in order to ensure

quality of the delivered material. A visual inspection system has been based
on wavelet texture analysis and robust Bayesian ANNs.
Hu and Tsai (2000) used best wavelet packet bases and an artificial neural
network (ANN) to inspect four kinds of fabric defects. Multi-resolution
representation of an image using wavelet transform was a new and effective
approach for analyzing image information content. The values and positions
for the smallest-six entropy were found in a wavelet packet best tree that
acted as the feature parameters of the ANN for identifying fabric defects.
They explored three basic considerations of the classification rate of fabric
defect inspection comprising wavelets with various maximum vanishing
moments, different numbers of resolution levels, and differently scaled fabric
images. The results showed that the total classification rate for a wavelet
function with a maximum vanishing moment of four and three resolution
levels can reach 100%, and differently scaled fabric images had no obvious
effect on the classification rate.
2. A neuro-fractal approach has been used for the recognition and classication of
non-woven web images.
3. Many quality issues are inspected via ANN methods, like structure properties
relations of the non-woven fabrics, construction of a quality prediction system,
modelling of the compression properties of needle-punched nonwoven fabrics, the
simulation of the drawing of spun bonding nonwoven process and also the
objective evaluation of the pilling on nonwoven fabrics.
Future: In the future research, the following issues shall be taken into
consideration to the application of ANN in textiles and clothing industries.
a. improve the data collection method for training ANNs such as online data
captured from the process
b. improve the feature-extraction procedures before the data can be fed to an ANN
c. improve extrapolation ability of the system to strengthen the prediction
capability
d. improve the user-friendly interface between user and machine
These issues are important for further development of using ANN in textiles and
clothing industries.

Conclusion: In summary, artificial neural networks is an ability to perform tasks outside the
scope of traditional processors. They can recognize patterns within vast data sets and then
generalize those patterns into recommended courses of action. Neural networks requires an "art."
This art involves the understanding of the various network topologies, current hardware, current
software tools, the application to be solved, and a strategy to acquire the necessary data to train
the network. This art further involves the selection of learning rules, transfer functions,
summation functions, and how to connect the neurons within the network. Then, the art of neural
networking requires a lot of hard work as data is fed into the system, performances are
monitored, processes tweaked, connections added, rules modified, and on and on until the
network achieves the desired results. These desired results are statistical in nature. The network
is not always right. It is for that reason that neural networks are finding themselves in
applications where humans are also unable to always be right.

In this modern era, ANN is being used in many areas to solve various problems with intelligence
similar to human being. The application of ANN was not widely accepted in the labor-intensive
clothing production. However, the global competitive environment and a target to achieve low
cost of production are the main reasons for the AI’s wider applications in apparel industry
starting from material selection and sourcing, through manufacturing till retailing. ANN can be
used in various processes of textile production such as fiber grading, prediction of yarn
properties, detection of fabric faults, and dye recipe prediction. Similarly, ANN can be applied in
all the stages of garment production such as preproduction, production, and postproduction
operations. Developed countries have already started using ANN to improve quality of garment,
enhanced customer service, and hence increased sales. Much progress is undergoing in AI
rapidly and in near future it will become an important tool for the garment manufacturers for
enhancing quality, increasing production, lowering operating costs, and exercising in house
control over production, leading to quick response and just-in-time concept.

References:

1. Brief History of Neural Networks. Retrived on 25 march 2020 from

https://medium.com/analytics-vidhya/brief-history-of-neural-networks-
44c2bf72eec(Katestrachnyi).
2. Abdel Salam Malek 2012. A Thesis on "Online Fabric inspection by Image Processing
Technology" University of Halte Alsace.
3. Neha Chauhan, Nirmal Yadav and Nisha Arya. 2018. Applications of Artificial Neural
Network in Textiles. Int.J.Curr.Microbiol.App.Sci. 7(04): 3134-3143.
4. Introduction to Artificial Neural Networks(ANN) Retrived on 25 March 2020 from
https://towardsdatascience.com/introduction-to-artificial-neural-networks-ann-
1aea15775ef9 (Nagesh singh chauhan)
5. Artificial Neural Network - Basic Concepts. Retrived on 25 march 2020 from
https://www.tutorialspoint.com/artificial_neural_network/artificial_neural_network_basic
_concepts.htm
6. Behera, B.K. and Goyal, Y. 2009. Artificial Neural Network System for the Design of
Airbag Fabrics. Journal of Industrial Textiles, 39(1): 45-55.
7. Behera and Guruprasad 2010 Modelling Air Permeability of Woven Fabrics by Artificial
Neural Networks. Research Journal of Textile and Apparel, 14(3):77-84.
8. Beltran, R.; Wang, L. & Wang, X. 2004. Predicting Worsted Spinning Performance with
an Artificial Neural Network Model. Textile Research Journal, 74(9): 757-763.
9. Chen, Y., Zhao, T. and Collier, B.J. 2001. Prediction of Fabric End-use Using a Neural
Network Technique. Journal of the Textile Institute, 92(2): 157-163.
10. Chen, T.; Zhang, C.; Chen, X. & Li, L. 2009. An Input Variable Selection Method for the
Artificial Neural Network of Shear Stiffness of Worsted Fabrics. Statistical Analysis and
Data Mining, 1(2): 287-295.
11. Durand, A., Devos, O., Ruckebusch, C. and Huvenne, J.P. 2007. Genetic algorithm
optimisation combined with partial least squares regression and mutual information
variable selection procedures in near-infrared quantitative analysis of cotton–viscose
textiles. Analytica Chimica Acta, 595(1-2): 72-79.
12. Ertugrul, S. and Ucar, N. 2000. Predicting Bursting Strength of Cotton Plain Knitted
Fabrics Using Intelligent Techniques. Textile Research Journal, 70(10): 845-851.
13. Farooq, A. and Cherif, C. 2008. Use of Artificial Neural Networks for Determining the
Leveling Action Point at the Auto-leveling Draw Frame. Textile Research Journal, 78(6):
502-509.
14. G Allan, A Fotheringham & P Weedall 2002. The use of plasma and neural modelling to
optimise the application of a repellent coating to disposable surgical garments. Autex
Research Journal, 2(2):12-16.
15. Hadizadeh, M., Tehran, M.A. and Jeddi, A.A.A. 2010. Application of an Adaptive
Neuro-fuzzy System for Prediction of Initial Load--Extension Behavior of Plain-woven
Fabrics. Textile Research Journal, 80(10): 981-990.
16. Hu, M.C. and Tsai, I.S. 2000. Fabric Inspection Based on Best Wavelet Packet Bases.
Textile Research Journal, 70(8): 662-670.
17. Huang, C.C. and Chen, I.C. 2001. Neural-Fuzzy Classification for Fabric Defects. Textile
Research Journal, 71(3): 220-224.
18. Hui, C.L.P., Chan, C.C.K., Yeung, K.W. and Ng, S.F.F. 2007. Application of artificial
neural networks to the prediction of sewing performance of fabrics. International Journal
of Clothing Science and Technology, 19(5): 291-318.
19. Hui, C.L. and Ng, S.F. 2009. Predicting Seam Performance of Commercial Woven
Fabrics Using Multiple Logarithm Regression and Artificial Neural Networks. Textile
Research Journal, 79(18): 1649-1657.
20. Kanat and Ozdil 2018. Application of artificial neural network (ANN) for the prediction
of thermal resistance of knitted fabrics at different moisture content. Journal of textile
institue. 109(3):1-7.
21. Kang, T.J. and Kim, S.C. 2002. Objective Evaluation of the Trash and Color of Raw
Cotton by Image Processing and Neural Network. Textile Research Journal, 72(9): 776-
782.
22. Khan, Z., Lim, A.E.K., Wang, L., Wang, X. and Beltran, R. 2009. An Artificial Neural
Network based Hairiness Prediction Model for Worsted Wool Yarns. Textile Research
Journal, 79(8): 714-720.
23. Kuo, C.F.J., Hsiao, K.I. and Wu, Y.S. 2004. Using Neural Network Theory to Predict the
Properties of Melt Spun Fibers. Textile Research Journal, 74(9), 840-843.
24. Lin, J.J. 2007. Prediction of Yarn Shrinkage using Neural Nets. Textile Research Journal,
77(5): 336-342.
25. Murrells, C.M., Tao, X.M., Xu, B.G. and Cheng, K.P.S. 2009. An Artificial Neural
Network Model for the Prediction of Spirality of Fully Relaxed Single Jersey Fabrics.
Textile Research Journal, 79(3): 227-234.
26. She, F.H., Kong, L.X., Nahavandi, S. and Kouzani, A.Z. 2002. Intelligent Animal Fiber
Classification with Artificial Neural Networks. Textile Research Journal, 72(7): 594-600.
27. Shyr, T.W., Lai, S.S. and Lin, J.Y. 2004. New Approaches to Establishing Translation
Equations for the Total Hand Value of Fabric. Textile Research Journal, 74(6): 528-534.
28. Ucar and Ertugrul 2010 Prediction of fuzz fibers on fabric surface by using neural
network and regression analysis. Fibres and Textiles in Eastern Europe, 15(2):58-61.
29. Wong, A.S.W., Li, Y., Yeung, P.K.W. 2004. Predicting Clothing Sensory Comfort with
Artificial Intelligence Hybrid Models. Textile Research Journal, 74(1): 13-19.
30. Xu, B., Dong, B. and Chen, Y. 2007. Neural Network Technique for Fiber Image
Recognition. Journal of Industrial Textiles, 36(4): 329-336.
31. Yao, G., Guo, J. and Zhou, Y. 2005. Predicting the Warp Breakage Rate in Weaving by
Neural Network Techniques. Textile Research Journal, 75(3): 274-278.
32. Yousef, Abdel-Hamid & AliHilal-Alnaqbi 2011. Prediction of the Mechanical Properties
of PE/PP Blends Using Artificial Neural Networks, Procedia engineering 10(2):2713-
2718.
33. Zeng, Y.C., Wang, K.F. and Yu, C.W. 2004. Predicting the Tensile Properties of Air-Jet
Spun Yarns. Textile Research Journal, 74(8): 689-694.
34. Zhang, Y.; Zhaoyang, L. & Li, J. 2010. Fabric Defect Classification using Radial Basis
Function Network. Pattern Recognition Letters, 31(3) : 2033-2042.
35.