DocumentToPDF trial version, to remove this mark, please register this software.
ABSTRACT:
This Report is an introduction to
Artificial Neural networks. It also deals
with an interesting application of neural
network called “Electronic Nose”.
Electronic/artificial noses are
being developed as systems for the
automated detection and classification of
odors, vapors, and gases. An electronic
nose is generally composed of
chemical sensing system (e.g., sensor
array or spectrometer) and a pattern
recognition system (e.g., artificial neural
network). We are developing Electronic
noses for the automated identification of
volatile chemicals for environmental and
medical applications. In this paper, we
briefly describe an electronic nose, show
some results from a prototype electronic
nose, and discuss applications
electronic noses in the environmental,
medical, and food industries.
1. Introduction to neural
networks
DEFINITION:
Neural Networks are form of
Artificial Intelligence that, through
pattern matching, predict the outcome
from a given set of inputs. The neural
network trains using a pattern file. In
training, it converges on a proper set of
weights, or coefficients that lead from
input / output. After training the
network, simply computes an arithmetic
expression that is a function of inputs
and weight coefficients, to obtain the
output.
a 1.1 A Neural Network
An Artificial Neural Network
(ANN) is an information processing
paradigm that is inspired by the way
biological nervous systems, such as the
brain, process information. The key
element of this paradigm is the novel
structure of the information processing
system. It is composed of a large number
of of highly interconnected processing
elements (neurones) working in unison
to solve specific problems. ANNs, like
people, learn by example. An ANN is
configured for a specific application,
such as pattern recognition or data
classification, through a learning
process. Learning in biological systems
involves adjustments to the synaptic
connections that exist between the
neurones. This is true of ANNs as well.
1
DocumentToPDF trial version, to remove this mark, please register this software.

The first artificial neuron was produced 3. Real Time Operation: ANN
in 1943 by the neurophysiologist Warren computations may be carried out
McCulloch and the logician Walter Pits. in parallel, and special hardware
But the technology available at that time devices are being designed and
did not allow them to do too much. manufactured which take
advantage of this capability.
1.2 Why to use neural networks?
4. Fault Tolerance via Redundant
Information Coding: Partial
Neural networks, with their
destruction of a network leads to
remarkable ability to derive meaning
the corresponding degradation of
from complicated or imprecise data, can
performance. However, some
be used to extract patterns and detect
network capabilities may be
trends that are too complex to be noticed
retained even with major network
by either humans or other computer
damage.
techniques. A trained neural network can
be thought of as an "expert" in the
1.3 Neural networks versus
category of information it has been given
conventional computers
to analyze. This expert can then be used
to provide projections given new Neural networks take a different
situations of interest and answer "what approach to problem solving than that of
if"questions. conventional computers. Conventional
Other advantages include: computers use an algorithmic approach
i.e. the computer follows a set of
1. Adaptive learning: An ability to
instructions in order to solve a problem.
learn how to do tasks based on
Unless the specific steps that the
the data given for training or
computer needs to follow are known the
initial experience.
computer cannot solve the problem. That
2. Self-Organization: An ANN can
restricts the problem solving capability
create its own organization or
of conventional computers to problems
representation of the information
that we already understand and know
it receives during learning time.
how to solve. But computers would be
so much more useful if they could do

2
DocumentToPDF trial version, to remove this mark, please register this software.

things that we don't exactly know how to Neural networks and

do. conventional algorithmic computers are
not in competition but complement each
Neural networks process
other. There are tasks are more suited to
information in a similar way the human
an algorithmic approach like arithmetic
brain does. The network is composed of
operations and tasks that are more suited
a large number of highly interconnected
to neural networks. Even more, a large
processing elements (neurons) working
number of tasks, require systems that use
in parallel to solve a specific problem.
a combination of the two approaches
Neural networks learn by example. They
(normally a conventional computer is
cannot be programmed to perform a
used to supervise the neural network) in
specific task. The examples must be
order to perform at maximum efficiency.
selected carefully otherwise useful time
is wasted or even worse the network Neural networks do not perform
might be functioning incorrectly. The miracles. But if used sensibly they can
disadvantage is that because the network produce some amazing results
finds out how to solve the problem by
itself, its operation can be unpredictable.

On the other hand, conventional

computers use a cognitive approach to
problem solving; the way the problem is
to solved must be known and stated in
small unambiguous instructions. These
instructions are then converted to a high
level language program and then into
machine code that the computer can
understand. These machines are totally FIG: 1 NEURON
predictable; if anything goes wrong is
due to a software or hardware fault.

3
DocumentToPDF trial version, to remove this mark, please register this software.

1.4 From Human Neurons to Artificial to fire (or not), for particular input
Neurons patterns.

We conduct these neural In the using mode, when a

networks by first trying to deduce the taught input pattern is detected at the
essential features of neurons and their input, its associated output becomes the
interconnections. We then typically current output. If the input pattern does
program a computer to simulate these not belong in the taught list of input
features. However because our patterns, the firing rule is used to
knowledge of neurons is incomplete and determine whether to fire or not.
our computing power is limited, our
models are necessarily gross
idealizations of real networks of
neurons.

FIG: 3 A simple neuron

Laboratory (PNNL). PNNL is a

FIG: 2 Neuron model multiprogram national laboratory
operated by Battelle Memorial Institute
1.5 A simple neuron
for the U.S. Department of Energy under

An artificial neuron is a device Contract DE-AC06-76RLO 1830.

with many inputs and one output. The

neuron has two modes of operation; the
training mode and the using mode. In the
training mode, the neuron can be trained

4
DocumentToPDF trial version, to remove this mark, please register this software.

2. ELECTRONIC NOSES AND chemical analysis of data in an

THEIR APPLICATIONS automated fashion difficult.

One approach to chemical vapor
.
identification is to build an array of
The two main components of an
sensors, where each sensor in the array is
electronic nose are the sensing system
designed to respond to a specific
and the automated pattern recognition
chemical. With this approach, the
system. The sensing system can be an
number of unique sensors must be at
array of several different sensing
least as great as the number of chemicals
elements (e.g.,chemical sensors), where
being monitored. It is both expensive
each element measures a different
and difficult to build highly selective
property of the sensed chemical, or it can
chemical sensors.
be a single sensing device (e.g.,
Artificial neural networks
spectrometer) that produces an array of
(ANNs), which have been used to
measurements for each chemical, or it
analyze complex data and to recognize
can be a combination.
patterns, are showing promising results
Each chemical vapor presented to
in chemical vapor recognition. When an
the sensor array produces a signature or
ANN is combined with a sensor array,
pattern characteristic of the vapor. By
the number of detectable chemicals is
presenting many different chemicals to
generally greater than the number of
the sensor array, a database of signatures
sensors [1]. Also, less selective sensors
is built up. This database of labeled
which are generally less expensive can
signatures is used to train the pattern
be used with this approach. Once the
recognition system. The goal of this
ANN is trained for chemical vapor
training process is to configure the
recognition, operation consists of
recognition system to produce unique
propagating the sensor data through the
classifications of each chemical so that
network. Since this is simply a series of
an automated identification can
vector- matrix multiplications, unknown
beimplemented. The quantity and
chemicals can be rapidly identified in the
complexity of the data collected by
field. Electronic noses that incorporate
sensors array can make conventional

5
DocumentToPDF trial version, to remove this mark, please register this software.

ANNs have been demonstrated in standard multilayer feed-forward

various applications. network trained with the
Some of these applications will be backpropagation algorithm and the fuzzy
discussed later in the paper. Many ANN ARTmap algorithm [2]. During
configurations and training algorithms operation a chemical vapor is blown
have been used to build electronic noses across the array, the sensor signals are
including backpropagation-trained, feed- digitized and fed into the computer, and
forward networks; fuzzy ARTmaps; the ANN (implemented in software) then
Kohonen’s self-organizing maps identifies the chemical. This
(SOMs); learning vector quantizers identification time is limited only by the
(LVQs); Hamming networks; Boltzmann response time of the chemical sensors,
machines; and Hopfield networks. which is on the order of seconds. This
Figure 1 illustrates the basic schematic prototype nose has been used to identify
of an electronic nose. common household chemicals by their
odor [3].

FIG:4 Schematic diagram of EN

2.1 PROTOTYPE ELECTRONIC FIG: 5 Photograph of the prototype

NOSE electronic nose
One of our prototype electronic Figure 3 illustrates the structure of the
noses, shown in Figure 2, is composed ANN. The nine tin-oxide sensors are
of an array of nine tinoxide vapor commercially available Taguchi-type
sensors, a humidity sensor, and a gas sensors obtained from Figaro Co.
temperature sensor coupled with an Ltd. (Sensor 1, TGS 109; Sensors 2 and
ANN. 3, TGS 822; Sensor 4, TGS 813; Sensor
Two types of ANNs were 5, TGS 821; Sensor 6, TGS 824; Sensor
constructed for this prototype: the 7, TGS 825; Sensor 8, TGS 842; and

6
DocumentToPDF trial version, to remove this mark, please register this software.

Sensor 9, TGS 880). Exposure of a tin- are presented to the system. By training
oxide sensor to a vapor produces a large on samples of various chemicals, the
change in its electrical resistance. ANN learns to recognize the different
The humidity sensor (Sensor 10: NH-02) chemicals. This prototype nose has been
and the temperature sensor (Sensors 11: tested on a variety of household and
5KD-5) are used to monitor the office supply chemicals including
conditions of the experiment and are also acetone, ammonia, ethanol, glass
fed into the ANN. cleaner, contact cement, correction fluid,
iso-propanol, lighter fluid, methanol,
rubber cement and vinegar. For the
results shown in the paper, five of these
chemicals were used: acetone, ammonia,
isopropanol, lighter fluid, and vinegar.
Another category, “none” was used to
denote the absence of all chemicals
except those normally found in the air
which resulted in six output categories
from the ANN. Table 1 lists the training
Parameters for one backpropagation and
one fuzzy ARTmap network.
FIG:6 Structure of the
Backpropagation
backpropagation ANN used in the
Architecture: 11-11-6 feedforward
prototype to identifyhousehold
Activation: Logistic Sigmoidal
chemicals
Learning Rate: 0.10
Although each sensor is designed
Momentum: 0.90
for a specific chemical, each responds to
No. of Epochs: 1369
a wide variety of chemicals.
Fuzzy ARTMap
Collectively, these sensors respond with
Training Vigilance: 0.98
unique signatures (patterns) to different
Testing Vigilance: 0.80
chemicals.
No. of Epochs: 3
During the training process,
ANN training parameters
various chemicals with known mixtures

7
DocumentToPDF trial version, to remove this mark, please register this software.

Both networks were trained using Fluid 92.6

randomly selected sample sensor inputs. 66 21 Vinegar 81.0
95.2
The ANNs used here were not trained to 68 26 Amm & 92.3
quantify the concentration level of the Vinegar 76.9
1 2 Isopr & 00.0
identified analytes, but were trained with Vinegar 00.0
samples with different concentrations of
the analytes. This allowed the ANN to Table 1: ANN performance for

This paper was presented at the IEEE backpropagation (BP) and fuzzy

Northcon/Technical Applications ARTmap (FA)

Conference (TAC’95) in Portland, OR, Figures 4 and 5 illustrate the responses

USA on 12 October 1995. generalize of the sensors and the ANN

well on the test data set. Performance classification for a variety of test

levels of the two networks were chemicals presented to the ANNs. The

basically equivalent ranging from 89.7% ANN was able to correctly classify the

to 98.2% correct identification on the test samples with only small residual

test set depending on the random errors. While the ANN used here was

selection of training patterns. Table 2 not trained to quantify the concentration

summarizes one set of network level of the identified analytes, it was

performances for novel sensor inputs. trained with samples with different
concentrations of the analytes. This
Num Num Input % allowed the ANN to generalize well on
Train Test Substance Correct
BP the test data set. From the responses of
FA the sensors to the analytes, one can
67 28 None 96.4
easily see that the individual sensors in
96.4
75 22 Acetone 100 the array are not selective (Figure 4). In
100
addition, when a mixture of two or more
64 14 Ammonia 100
100 chemicals is presented to the sensor
93 28 Isopropanol 92.9
array, the resultant pattern (sensor
100
5 3 Ammonia 00.0 values) may be even harder to analyze
&Isopr 66.7 (see Figure 5: c, d, and e). Thus,
106 25 Lighter 100
Fluid 96.0 analyzing the sensor responses
74 27 Amm & Lig 100

8
DocumentToPDF trial version, to remove this mark, please register this software.
separately may not be adequate to yield
the classification accuracy achieved by
analyzing the data in parallel.
2.2 ELECTRONIC NOSES FOR
ENVIRONMENTAL MONITORING
Enormous amounts of hazardous waste
(nuclear, chemical, and mixed wastes)
were generated by more than 40 years of
weapons’ production in the U.S.
Department of Energy’s weapons’
complex. The Pacific Northwest
National Laboratory is exploring the
technologies required to perform
environmental restoration and waste
management in a cost effective manner.
This effort includes the development of
portable, inexpensive systems capable of
real-time identification of contaminants
in the field. Electronic noses fit this
category.
Environmental applications
electronic noses include analysis of fuel
mixtures [4], detection of oil leaks [5],
testing ground water for odors, and
identification of household odors [3].
Potential applications include
identification of toxic wastes, air quality
monitoring, and monitoring factory
emissions.
2.3 ELECTRONIC NOSES FOR
MEDICINE
Because the sense of smell is an
important sense to the physician, an
electronic nose has applicability as a
diagnostic tool. An electronic nose can
examine odors from the body (e.g.,
breath, wounds, body fluids, etc.) and
identify possible problems. Odors in the
breath can be indicative of
gastrointestinal problems, sinus
problems, infections, diabetes, and liver
problems. Infected wounds and tissues
emit distinctive odors that can be
detected by an electronic nose. Odors
coming from body fluids can indicate
liver and bladder problems. Currently,
an electronic nose for examining wound
infections is being tested at South
Manchester University Hospital.
A more futuristic application of
of electronic noses has been recently
proposed for telesurgery. While the
inclusion of visual, aural, and tactile
senses into telepresent systems is
widespread, the sense of smell has been
largely ignored. An electronic nose will
potentially be a key component in an
olfactory input to telepresent virtual
reality systems including telesurgery.
9
DocumentToPDF trial version, to remove this mark, please register this software.
The electronic nose would
identify odors in the remote surgical
environment. These identified odors
would then be electronically transmitted
to another
site where an odor generation system
would recreate them.
2.4 ELECTRONIC NOSES FOR THE
FOOD INDUSTRY
Currently, the biggest market for
electronic noses is the food industry.
Applications of electronic noses in the
food industry include quality assessment
in food production , inspection of food
quality by odor, control of food cooking
processes, inspection of fish, monitoring
the fermentation process, checking
rancidity of mayonnaise, verifying if
orange juice is natural, monitoring food
and beverage odors, grading whiskey,
inspection of beverage containers,
checking plastic wrap for containment of
onion odor, and automated flavor control
to name a few. In some instances
electronic noses can be used to augment
or replace panels of human experts. In
other cases, electronic noses can be used
to reduce the amount of analytical
chemistry that is performed in food
production especially when qualitative
results will do.
10
3. CONCLUSION
Thus an “Artificial Neural
Network” is developed to make the
computer think like a human brain. And
an electronic nose is a device intended to
detect odors or flavors. Over the last
decade, “electronic sensing” or “e-
sensing” technologies have undergone
important developments from a technical
and commercial point of view. The
expression “electronic sensing” refers to
the capability of reproducing human
senses using sensor arrays and pattern
recognition systems. For the last 15
years as of 2007, research has been
conducted to develop technologies,
commonly referred to as electronic
noses, that could detect and recognize
odors and flavors.
These devices have undergone
much development and are now used to
fulfill industrial needs.
DocumentToPDF trial version, to remove this mark, please register this software.

REFERENCES
[1] B.S. Hoffheins, Using Sensor Arrays
and Pattern Recognition to Identify
Organic Compounds.
MS-Thesis, The University of
Tennessee, Knoxville, TN, 1989.
[2] G.A. Carpenter, S. Grossberg, N.
Markuzon, J.H. Reynolds, and D.B.
Rosen, “Fuzzy ARTMAP: A
Neural Network Architecture for
Incremental Supervised Learning of
Analog Multidimensional Maps,” IEEE
Transactions on Neural Networks, vol. 3,
698 -713.
[3] P.E. Keller, R.T. Kouzes, and L.J.
Kangas, “Three Neural Network Based
Sensor Systems for Environmental
Monitoring,” IEEE Electro 94
Conference Proceedings, Boston, MA,
1994, pp.
377-382.
[4] R.J. Lauf and B.S. Hoffheins,
“Analysis of Liquid Fuels Using a Gas
Sensor Array,” Fuel , vol.
70, pp. 935-940, 1991.
[5] H.V. Shurmur, “The fifth sense: on
the scent of the electronic nose,” IEE
Review, pp. 95-58,

11