Article

Neural Networks and Its Application in Engineering

Abstract and Figures

Neural Network (NN) has emerged over the years and has made remarkable contribution to the advancement of various fields of endeavor. The purpose of this work is to examine neural net-works and their emerging applications in the field of engineering, focusing more on Controls. In this work, we have examined the various architectures of NN and the learning process. The needs for neural networks, training of neural networks, and important algorithms used in realizing neu-ral networks have also been briefly discussed. Neural network application in control engineering has been extensively discussed, whereas its applications in electrical, civil and agricultural engi-neering were also examined. We concluded by identifying limitations, recent advances and prom-ising future research directions.
Content may be subject to copyright.
Proceedings of Informing Science & IT Education Conference (InSITE) 2009
Neural Networks and Its Application in
Engineering
Oludele Awodele and Olawale Jegede
Dept. of Computer Science and Mathematics,
Babcock University, Nigeria
delealways@yahoo.com; jegede1@yahoo.com
Abstract
Neural Network (NN) has emerged over the years and has made remarkable contribution to the
advancement of various fields of endeavor. The purpose of this work is to examine neural net-
works and their emerging applications in the field of engineering, focusing more on Controls. In
this work, we have examined the various architectures of NN and the learning process. The needs
for neural networks, training of neural networks, and important algorithms used in realizing neu-
ral networks have also been briefly discussed. Neural network application in control engineering
has been extensively discussed, whereas its applications in electrical, civil and agricultural engi-
neering were also examined. We concluded by identifying limitations, recent advances and prom-
ising future research directions.
Keywords. Neural Network, Artificial Neural Network
Introduction
Whenever we talk about a neural network, we should more properly say "artificial neural net-
work" (ANN), because that is what we mean most of the time. Artificial neural networks are
computers whose architecture is modeled after the brain. They typically consist of many hundreds
of simple processing units which are wired together in a complex communication network. Each
unit or node is a simplified model of a real neuron which fires (sends off a new signal) if it re-
ceives a sufficiently strong input signal from the other nodes to which it is connected.
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 highly interconnected processing elements (neurons) working in unison to solve
specific problems. ANNs, like people, learn by example. According to Michael Mozer of the Uni-
versity of Colorado, “The neural network is structured to perform nonlinear Bayesian classifica-
tion”.
A neural network could be also be de-
scribed as a system composed of many
simple processing elements operating in
parallel whose function is determined
by network structure, connection
strengths, and the processing performed
at computing elements or nodes
(DARPA Neural Network Study, 1988).
It resembles the brain in two respects:
Material published as part of this publication, either on-line or
in print, is copyrighted by the Informing Science Institute.
Permission to make digital or paper copy of part or all of these
works for personal or classroom use is granted without fee
provided that the copies are not made or distributed for profit
or commercial advantage AND that copies 1) bear this notice
in full and 2) give the full citation on the first page. It is per-
missible to abstract these works so long as credit is given. To
copy in all other cases or to republish or to post on a server or
to redistribute to lists requires specific permission and payment
of a fee. Contact Publisher@InformingScience.org to request
redistribution permission.
Neural Networks and Its Application in Engineering
84
1. Knowledge is acquired by the network through a learning process.
2. Interneuron connection strengths known as synaptic weights are used to store the knowledge
(Haykin, 1999).
Historical Background
The history of neural networks can be divided into several periods: from when developed models
of neural networks based on their understanding of neurology, to when neuroscience became in-
fluential in the development of neural networks. Psychologists and engineers also contributed to
the progress of neural network simulations. Neurally based chips are emerging and applications to
complex problems developing. Clearly, today is a period of transition for neural network technol-
ogy.
Why use neural networks?
Neural networks, with their remarkable ability to derive meaning from complicated or imprecise
data, can be used to extract patterns and detect trends that are too complex to be noticed by either
humans or other computer techniques. A trained neural network can be thought of as an "expert"
in the category of information it has been given to analyze. This expert can then be used to pro-
vide projections given new situations of interest and answer "what if" questions. Other advan-
tages include: Adaptive learning, Self-Organization, Real Time Operation and Fault Tolerance
via Redundant Information Coding
Neural networks process information in a similar way the human brain does. The network is
composed of a large number of highly interconnected processing elements (neurones) working in
parallel to solve a specific problem. Neural networks learn by example. They cannot be pro-
grammed to perform a specific task. The examples must be selected carefully otherwise useful
time is wasted or even worse the network might be functioning incorrectly. The disadvantage is
that because the network finds out how to solve the problem by itself, its operation can be unpre-
dictable.
Neural networks and conventional algorithmic computers are not in competition but complement
each other.
Architecture of Neural Networks
Neural networks are not only different in their learning processes but also different in their struc-
tures or topology. Bose (1996) has broadly classified neural networks into recurrent (involving
feedback) and nonrecurrent (without feedback) ones. In a little more details, Haykin has divided
the network architectures into the following three classes:
Feed-forward Networks
Feed-forward ANNs allow signals to travel one way only; from input to output. There is no feed-
back (loops) i.e. the output of any layer does not affect that same layer. Feed-forward ANNs tend
to be straight forward networks that associate inputs with outputs. They are extensively used in
pattern recognition. This type of organization is also referred to as bottom-up or top-down. Sin-
gle-layer perceptrons and Multi-layer perceptrons are classes of feed forward networks.
Single-layer perceptrons (feed forward networks)
The single-layer perceptrons was among the first and simplest learning machines that are train-
able. In Haykin’s book (1999), perceptron denotes the class of two-layer feed forward networks,
Awodele & Jegede
85
1) whose first-layer units have fixed function with fixed connection weights from the inputs, and
2) whose connection weights linking this first layer to the second layer of outputs are learnable.
Multi-layer perceptrons (feed forward networks)
Multi-layer feed forward structures are characterized by directed layered graphs and are the gen-
eralization of those earlier single layer structures (Bose, 1996).
Structure and features of MLP
Multi-layer perceptron (MLP) networks are feed forward nets with one of more layers of nodes
between the input and output nodes. The structure of an unadorned multilayer perception network
is shown in Figure 1.
Figure 1. Feed forward multi-layer perceptron architecture
(Pandya & Macy, 1996, p.74)
The capabilities of multi-layer perception stem from the nonlinearities used within nodes.
Feedback networks
Feedback networks (Figure 1) can have signals traveling in both directions by introducing loops
in the network. Feedback architectures are also referred to as interactive or recurrent, although the
latter term is often used to denote feedback connections in single-layer organizations. In the neu-
ral network literature, neural networks with one or more feedback loops are referred to as recur-
rent networks. A recurrent network distinguishes itself from a feed forward neural network in that
it has at least one feedback loop
.
Neural Networks and Its Application in Engineering
86
Figure 2. An example of a simple feedforward network
(Stergiou & Siganos, 1996)
Network Layers
The commonest type of artificial neural network consists of three groups, or layers, of units: a
layer of "input" units is connected to a layer of "hidden" units, which is connected to a layer of
"output" units.
The activity of the input units represents the raw information that is fed into the network.
The activity of each hidden unit is determined by the activities of the input units and the weights
on the connections between the input and the hidden units.
The behavior of the output units depends on the activity of the hidden units and the weights be-
tween the hidden and output units.
Training a Neural Network
For the most part, a network is trained by changing the weights of the connections between nodes.
These weights can be randomly chosen or individually chosen. Usually, a computer program ran-
domly generates values for connection weights. Then, the network is given an input, and it is al-
lowed to process the information through its nodes to produce an output.
The learning process
The memorization of patterns and the subsequent response of the network can be categorized into
two general paradigms:
Associative mapping in which the network learns to produce a particular pattern on the set of in-
put units whenever another particular pattern is applied on the set of input units.
Auto-association: an input pattern is associated with itself and the states of input and output units
coincide.
All learning methods used for adaptive neural networks can be classified into two major catego-
ries:
Awodele & Jegede
87
Supervised learning which incorporates an external teacher, so that each output unit is
told what its desired response to input signals ought to be.
Unsupervised learning uses no external teacher and is based upon only local information.
It is also referred to as self-organization, in the sense that it self-organizes data presented
to the network and detects their emergent collective properties.
The back-propagation algorithm
In order to train a neural network to perform some task, we must adjust the weights of each unit
in such a way that the error between the desired output and the actual output is reduced. This
process requires that the neural network compute the error derivative of the weights (EW). In
other words, it must calculate how the error changes as each weight is increased or decreased
slightly. The back propagation algorithm is the most widely used method for determining the
EW.
Applications of Neural Networks
A Simple Neuron
An artificial neuron is a device with many inputs and one output (Figure 3). The neuron has two
modes of operation; the training mode and the using mode. In the training mode, the neuron can
be trained to fire (or not), for particular input patterns. In the using mode, when a taught input
pattern is detected at the input, its associated output becomes the current output. If the input pat-
tern does not belong in the taught list of input patterns, the firing rule is used to determine
whether to fire or not.
Figure 3. A simple neuron
Firing Rules
The firing rule is an important concept in neural networks and accounts for their high flexibility.
A firing rule determines how one calculates whether a neuron should fire for any input pattern. It
relates to all the input patterns, not only the ones on which the node was trained. The firing rule
gives the neuron a sense of similarity and enables it to respond 'sensibly' to patterns not seen dur-
ing training.
Neural Networks in Practice
Neural networks have broad applicability to real world business problems. In fact, they have al-
ready been successfully applied in many industries. Since neural networks are best at identifying
patterns or trends in data, they are well suited for prediction or forecasting needs including:
sales forecasting,
industrial process control
customer research
Neural Networks and Its Application in Engineering
88
data validation
Risk management.
ANN are also used in the following specific paradigms: recognition of speakers in communica-
tions; diagnosis of hepatitis; undersea mine detection; texture analysis; three-dimensional object
recognition; hand-written word recognition; and facial recognition.
Typical applications of hardware NNWs are:
OCR (Optical Character Recognition)
Here, NN was employed in OCR by Caere Incorporation which recorded about 3million dollars
profit on 55million dollar revenue in 1997. The Adaptive Solutions ImageLink OCR Subsystem
captures the special high performance hardware required for high throughput. These days a pur-
chase of a new scanner typically includes a commercial OCR program. Ligature Ltd also has an
OCR-on-a-Chip example which illustrates a cheap dedicated chip for consumer products
Data Mining: A company named HNC made about 23million dollars profit on 110 million dollar
revenue in 1997, on their product called falcon. Falcon is a neural network based system that
examines transaction, cardholder, and merchant data to detect a wide range of credit card
fraud…”
Voice Recognition
Examples are the Sensory Inc. RSC Microcontrollers and ASSP speech recognition specific
chips.
Traffic Monitoring: an example is the Nestor TrafficVision Systems.
High Energy Physics: An example is an online data filter built by a group at the Max Planck Insti-
tute for the H11 electron-proton collider experiment in the Hamburg using Adaptive Solutions
CNAPS boards.
However, most NNW applications today are still run with the conventional software simulation
on PC’s and workstations with no special hardware add-ons.
Neural Networks in Control Engineering
The ever-increasing technological demands of our modern society require innovative approaches
to highly demanding control problems. Artificial neural networks with their massive parallelism
and learning capabilities offer the promise of better solutions, at least to some problems. By now,
the control community has heard of neural networks and wonders if these networks can be used to
provide better control solutions to old problems or perhaps solutions to control problems that
have withstood our best efforts.
Control system applications
Neural networks have been applied very successfully in the identification and control of dynamic
systems. The universal approximation capabilities of the multilayer perceptron have made it a
popular choice for modeling nonlinear systems and for implementing general-purpose nonlinear
controllers.
For the purposes of this work we will look at neural networks as function approximators. As
shown in Figure 4, we have some unknown function that we wish to approximate. We want to
adjust the parameters of the network so that it will produce the same response as the unknown
function, if the same input is applied to both systems. For our applications, the unknown function
may correspond to a system we are trying to control, in which case the neural network will be the
Awodele & Jegede
89
identified plant model. The unknown function could also represent the inverse of a system we are
trying to control, in which case the neural network can be used to implement the controller.
Figure 4. Neural Network as Function Approximator
(Hagan, Demuth, & De Jesús, 2002)
Fixed Stabilizing Controllers
Fixed stabilizing controllers (see Figure 5) have been proposed in (Kawato, 1990). This scheme
has been applied to the control of robot arm trajectory, where a proportional controller with gain
was used as the stabilizing feedback controller. We can see that the total input that enters the
plant is the sum of the feedback control signal and the feedforward control signal, which is calcu-
lated from the inverse dynamics model (neural network). That model uses the desired trajectory
as the input and the feedback control as an error signal. As the NN training advances, that input
will converge to zero. The neural network controller will learn to take over from the feedback
controller. The advantage of this architecture is that we can start with a stable system, even
though the neural network has not been adequately trained.
Figure 5. A Stabilizing Controller (Hagan et al., 2002)
Neural Networks and Its Application in Engineering
90
We have selected one type of network, the multilayer perceptron. We have demonstrated the ca-
pabilities of this network for function approximation, and have described how it can be trained to
approximate specific functions. We then presented control architecture which use neural network
function approximators as basic building blocks. Control engineering also involves robotics,
where Intelligent Control is the discipline that implements Intelligent Machines(IMs) to perform
anthropormorphic tasks with minimum supervision and interaction with a human operator
(Jegede, Awodele, Ajayi, & Ndong, 2007).
Agricultural Control System Engineering
Control and management of agricultural machinery offers many opportunities for application of
general purpose empirical models. The nature of agricultural machines creates the need for mod-
eling systems that are robust, noise tolerant, adaptable for multiple uses, and are extensible. Arti-
ficial Neural Networks (ANNs) have these characteristics and are attractive for use in control and
modeling in agricultural machinery.
Figure 6. Sprayer Sensor and Nozzle Element (Zhang, Yang, & El-Faki, 1994)
Weed Detection in Sprayers
Figure 6 presents a schematic of the sensor and spray nozzle element component of the sprayer.
The complete sprayer consisted of many of the sensor-nozzle elements placed in parallel on a
single spray boom.
A sensor was fabricated to detect color on the surface of the ground in a 7.5 by 50-cm wide im-
age. Three color bands; green, red, and near infra-red were sensed. The signals from the sensor
were digitized with a 68HC11 based controller using the on-chip 8-bit A/D converter. The
68HC11 based computer was also used to activate a solid-state switch that energized a solenoid
valve in the spray nozzle. The intent of control in the system was to sense the presence of a weed
by color and to activate the nozzle to spray the plant at the point in time that the plant was under
the nozzle. A time budget is shown in the figure. If computing time plus the time required for the
fluid to reach the ground once it emerges from the nozzle was insignificant, the sensor and nozzle
could be located together. Agricultural sprayers based on optical sensing and control of spray
nozzle activation currently exists on the market.
Weed identification
Zhang, Yang, & El-Faki (1994) reported the use of ANNs to process color images of weeds in a
winter-wheat environment with the objective of being able to distinguish between weeds and
Awodele & Jegede
91
other components of the image. They were particularly interested in detecting weeds with reddish
stems.
An ANN was also developed to allow color patterns to be recognized in an agricultural weed
sprayer application by Stone (1994).
Neural Networks in Electrical Engineering
Artificial Neural Network (ANN) is currently a 'hot' research area in electrical engineering. The
model used to simulate artificial neural networks is based on the biological nerve cell or neuron
shown in Figure 7. Electrical signals arising from impulses from our receptor organs (e.g. eyes,
ears) are carried into neurons on dendrites.
Signal classification with Perceptron
A problem of particular interest to electrical engineers is that of signal detection, particularly in a
noisy environment. Methods such as filtering and signal averaging have been used successfully.
Figure 7. A Biological Neuron (Howard, 2006)
Neural Networks and its application in Civil Engineering
Neural networks have gained a broad interest in civil engineering problems. They are used as an
alternative to statistical and optimization methods as well as in combination with numerical simu-
lation systems. Application areas in Civil Engineering are e.g. forecasting, water management,
control and decision support systems.
Limitations of Neural Networks
The major issues of concern today are the scalability problem, testing, verification, and integra-
tion of neural network systems into the modern environment. Neural network programs some-
times become unstable when applied to larger problems. The defence, nuclear and space indus-
tries are concerned about the issue of testing and verification. The mathematical theories used to
guarantee the performance of an applied neural network are still under development. The solution
for the time being may be to train and test these intelligent systems much as we do for humans.
Also there are some more practical problems like: the operational problem encountered when
attempting to simulate the parallelism of neural networks instability to explain any results that
they obtain. Networks function as "black boxes" whose rules of operation are completely un-
known.
Neural Networks and Its Application in Engineering
92
Likewise, in OCR, we find that one cannot claim Neural Networks (NNWs) are conquering the
world, because one does not feed the pixels of the picture file into a single giant NNW and out
pops the text. To turn a picture of text into a text file, a dozen or more steps must be completed
successfully by the OCR program. For example, an OCR system might follow the step in the dia-
gram in Figure 8.
Figure 8. (From Adaptive Solutions CNAPS User Guide).
Note that Adaptive Solution CNAPS is an example of a general, but expensive system that can be
reprogrammed for many kinds of tasks.
Designers of OCR programs may choose NNWs to accomplish one or more of these steps with
NNWs while using for other steps other techniques such as conventional AI (If-Then rules), sta-
tistical models, hidden Markov models, etc. The point is that NNWs are becoming commonly
used tools but, just like other techniques such as Fast Fourier Transform and least squares fit, they
are still only tools, not the whole solution. Few real problems of interest can be totally solved by a
single NNW. It is also true that implementing NNWs in Hardware and Software to run on them is
relatively expensive.
With the aforementioned, one quickly begins to see why the business of Neural Network hard-
ware has not boomed the way some in the field expected back in the 1980’s.
Conclusion
Prediction for the future rests on some sort of evidence or established trend which, with extrapo-
lation, clearly takes us into a new realm. Neural Networks will fascinate user-specific systems for
education, information processing, entertainment, genetic engineering, neurology and psychol-
ogy.
Programs could be developed which require feedback from the user in order to be effective but
simple and "passive" sensors (e.g. fingertip sensors, gloves, or wristbands to sense pulse, blood
pressure, skin ionization, and so on), could provide effective feedback into a neural control sys-
tem. NN’s ability to learn by example makes them very flexible and powerful. Perhaps the most
Awodele & Jegede
93
exciting aspect of neural networks is the possibility that some day 'conscious' networks might be
produced.
Recent advances and future applications of NNs include:
Integration of fuzzy logic into neural networks
Fuzzy logic is a type of logic that recognizes more than simple true and false values, hence better
simulating the real world. For example, the statement today is sunny might be 100% true if there
are no clouds, 80% true if there are a few clouds, 50% true if it's hazy, and 0% true if rains all
day. Hence, it takes into account concepts like -usually, somewhat, and sometimes.
Fuzzy logic and neural networks have been integrated for uses as diverse as automotive engineer-
ing, applicant screening for jobs, the control of a crane, and the monitoring of glaucoma.
Pulsed neural networks
"Most practical applications of artificial neural networks are based on a computational model in-
volving the propagation of continuous variables from one processing unit to the next. In recent
years, data from neurobiological experiments have made it increasingly clear that biological neu-
ral networks, which communicate through pulses, use the timing of the pulses to transmit
information and perform computation. This realization has stimulated significant research on
pulsed neural networks, including theoretical analyses and model development, neurobiological
modeling, and hardware implementation" (From http://www.tu-graz.ac.at/igi/maass/PNN.html).
Hardware specialized for neural networks
Some networks have been hardcoded into chips or analog devices? This technology will become
more useful as the networks we use become more complex.
The primary benefit of directly encoding neural networks onto chips or specialized analog de-
vices is SPEED!
NN hardware currently runs in a few niche areas, such as those areas where very high perform-
ance is required (e.g. high energy physics) and in embedded applications of simple, hardwired
networks (e.g. voice recognition).
Many NNs today use less than 100 neurons and only need occasional training. In these situations,
software simulation is usually found sufficient
When NN algorithms develop to the point where useful things can be done with 1000's of neu-
rons and 10000's of synapses, high performance NN hardware will become essential for practical
operation (From http://www.particle.kth.se/~lindsey/HardwareNNWCourse/).
Improvement of existing technologies
All current NN technologies will most likely be vastly improved upon in the future. Everything
from handwriting and speech recognition to stock market prediction will become more sophisti-
cated as researchers develop better training methods and network architectures.
NNs might, in the future, allow:
robots that can see, feel, and predict the world around them
improved stock prediction
common usage of self-driving cars
composition of music
Neural Networks and Its Application in Engineering
94
handwritten documents to be automatically transformed into formatted word processing
documents
trends found in the human genome to aid in the understanding of the data compiled by the
Human Genome Project
Self-diagnosis of medical problems using neural networks and much more!
In conclusion it should be stated that even though neural networks have a huge potential, we will
only get the best of them when they are integrated with computing, AI, fuzzy logic and related
subjects.
References
Bose, N. K.; & Liang P. (1996). Neural network fundamentals with graphs, algorithms, and applications.
McGraw-Hill.
DARPA Neural Network Study. (1988). AFCEA International Press, p. 60)
Hagan, M. T., Demuth, H. B. & De Jesús, O. (2002). An introduction to the use of neural networks in con-
trol systems. International Journal of Robust and Nonlinear Control, 12(11,) 959 – 985.
Haykin, S. (1999). Neural networks: A comprehensive foundation (2nd ed.). Upper Saddle River, New Jer-
sey: Prentice Hall.
Howard S. (2006). Neural networks in electrical engineering. Proceedings of the ASEE New England Sec-
tion 2006 Annual Conference (Session 1A - Electrical & Co mputer Engineering).
Jegede, O., Awodele, O., Ajayi, A., & Ndong M. (2007). Development of a microcontroller based robotic
arm. Proceedings of the 2007 CSITEd Conference” (Information Technology). Retrieved from
http://csited.org/2007/34OlawCSITEd.pdf
Kawato M. (1990). Computational schemes and neural network models for formation and control of multi-
joint arm trajectory. In T. Miller, R. S. Sutton, & P. J. Werbos (Eds.), Neural networks for control
(pp.197-228). Cambridge, MA: MIT Press.
Pandya, A. S., & Macy, R. B. (1996). Pattern recognition with neural networks in C++. CRC Press.
Stergiou, C., & Siganos, D. (1996). Neural networks. Retrieved from
http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html
Stone, M. L. (1994). Embedded neural networks in real time controls. SAE Paper 941067. 45th Annual
Earthmoving Industry Conference. SAE, Warrendale PA.
Zhang, N., Yang, Y., & El-Faki, M. (1994). Neural-network application in weed identification using color
digital images. ASAE Paper No. 94-3511.
Biographies
Oludele Awodele holds a Ph.D in Computer Science from the Univer-
sity of Agriculture, Abeokuta, Nigeria. He has several years experience
of teaching computer science courses at the university level. He is cur-
rently a lecturer in the department of Computer Science and Maths,
Babcock University, Nigeria. He is a full member of the Nigeria Com-
puter Society and the Computer Professional Registration Council of
Nigeria. His areas of interest are Artificial Intelligence and Computer
Architecture. He has published works in several journals of interna-
tional repute.
Awodele & Jegede
95
Olawale Jegede works with LM Ericsson Nigeria (Core Network En-
gineer: MPBN:IP/MPLS). He is a graduate of Babcock University,
Nigeria where he obtained a first class degree in Computer Engineer-
ing Technology. He is a Cisco Certified Network Professional. He is a
member of the Nigeria Society of Engineers and the Nigeria Computer
Society. His areas of interest include: Telecommunications and Net-
working, Artificial Intelligence, Digital Electronics, and Control. He
has published works in several journals of international repute.
... Now the RPT again given to the next round and performed the 15 more rounds. [5] After the completion of 16 rounds the Final Permutation is performed IV. NEURAL NETWORK ARCHITECTURES There are three network architectures: 1. Single Layer feed forward networks -In this layer, the input layer consists of source node that results the output in the form of neuron. ...
... It is feed forward type of network. [5] 2. Multilayer feed forward networks -It only adds an extra layer known as hidden layer. Because of this hidden layer higher level of statistic is obtained. ...
... Therefore, they are mathematically capable of teaching and learning any function related to mapping. Furthermore, it can also be proven that the obtained algorithm is almost universal [22,23,24,25,26]. Essentially, the susceptibility of prediction in the neural networks is due to the hierarchical or multilayer structure of the network (Figure 1). ...
Article
Full-text available
The correlation study of the electronic and spin properties in the buckled III-V monolayers using the transfer learning network approach is performed. Band engineering based on such approach has been applied to the target parameters of bandgap without spin–orbit coupling and with spin–orbit coupling, spin splitting at K-point in either of valence and conduction bands, and band splitting at Γ-point in the valence band. It is also found that some special nonlinear combination of Group-III and V atomic numbers together with their corresponding atomic mass can accurately describe the mentioned band engineering parameters of III-V monolayers. In this regard, a nonlinear descriptor relation as a function of atomic number and atomic mass is reported for every parameter. The maximum decoupling of Eg, WOS from other compounds is observed for InN, BSb and GaN. For this parameter, heavier compounds tend to have more correlation with the other ones. A similar pattern is observed for EgWS, although the correlation for heavier compounds is more evident. In addition, more compounds demonstrate discriminatory behavior for EgWS. Furthermore, the maximum correlating parameter among III-V compounds is valence band splitting. For heavier compounds, valence and conduction spin-splitting demonstrate sensible discrimination between the band engineering predictions and DFT calculations. Interestingly, for AlSb, a clear independent behavior for conduction band spin-splitting is also reported.
... In this loop, output of a neuron is fed back into its own input which increases learning capability. And it also increases performance [6] IV. BACKPROPAGATION There are so many restrictions in single layer feed forward network. ...
Article
Full-text available
Cryptography is a technique to encrypt simple message into cipher text for secure transmission over any channel , An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, one of the challenges to implement cryptography algorithm is execution time , An Artificial Neural Network (ANN) is a promising technique to improve the performance of RSA cryptography algorithm , In this paper we explore the implementation of RSA cryptography algorithm using ANN to reduce the execution time. This paper provides a fair comparison between normal RSA and ANN RSA .
... In this loop, output of a neuron is fed back into its own input which increases learning capability. And it also increases performance [6] IV. BACKPROPAGATION There are so many restrictions in single layer feed forward network. ...
... Artificial neural networks for engineering applications present current trends especially for the solution of complex engineering problems that cannot be solved through conventional methods. A properly trained neural network is considered to be an 'expert' in the category of information provided for analysis and can then be used to provide projections and answer 'what if' considering new information situations [28]. Especially in neural networks with incomplete data sets or fuzzy logic applications, the accurate modeling and the establishment of the right structures provide a high success rate [29][30][31]. ...
Article
Full-text available
The present study focuses on the organic Rankine cycle (ORC) integrated into an evacuated tube heat pipe (ETHP), whose systems are an alternative solar energy system to low-efficiency planary collectors. In this work, a detailed thermodynamic and artificial neural network (ANN) analysis was conducted to evaluate the solar energy system. One of the key parameters of sustainable approaches focused on exergy efficiency is application of thermal engineering. In addition to this, sustainable engineering approaches nowadays are a necessity for improving the efficiency of all of the engineering research areas. For this reason, the ANN model is used to forecast different types of energy efficiency problems in thermodynamic literature. The examined system consists of two main parts such as the ETHP system and the ORC system used for thermal energy production. With this system, it is aimed to evaluate energy and exergy analysis results by the ANN method in the case of integrating the ORC system to ETHP, which is one of the planar collectors suitable for the roofs of the buildings. Within the scope of this study, the exergy efficiency was evaluated on the developed ANN algorithm. The effect rates of parameters such as pressure, temperature and ambient temperature affecting the exergy efficiency of ORC integrated ETHP were calculated. Ambient temperature was found to be the most influential parameter on exergy efficiency. The exergy efficiency of the whole system has been calculated as ~23.39%. The most suitable BPNN architecture for this case study is recurrent networks with dampened feedback (Jordan–Elman nets). The success rate of the developed BPNN model is 95.4%.
... It can infer unseen relationships on unseen data making the system generalizes and predict on unseen data, can learn and does not need to be reprogrammed, has less sensitive to noise than others. ANN however, needs training to perform and for a wide neural network, high processing hours are required [16]. ...
Article
Full-text available
Behavioral pattern is the characteristic ways a person acts and has been recognized as a cause of many home accidents (h-accd). This study reviewed the types and prevalence of injuries among women in domestic works and proposes a model using Artificial Neural Network (ANN) function to forecast the safety level of women in domestic duty. The study was conducted in some parts of Western Nigeria among 340 subjects (171 married and 169 unmarried) using questionnaire. SPSS was used for data analysis. The ANN function was developed in MATLAB 2015a using the subjects’ behavioral patterns and the model was used to predict safety in domestic duties (d-duties) among some women. ‘Cuts/laceration’ (40%) and ‘skin contact with hot substance’ (35.6%) were commonly reported. Carelessness (26.5%) and distraction (22.1%) were the main leading factors across the groups. Marital status and h-accd (Chi-square =4.323 and p= .038); ‘hours spent on domestic works’ and ‘the h-accd’ were both significant among other tested groups variables. With the developed ANN function, the results of the MSE was 0.33626 indicating that the function predicted the exact value. The result of the predicted h-accd (safety= -0.5445, hazards= 1.0228) in d-duties of the tested variables with the ANN function, showed a very low level of safety. The article concludes that the developed model is reliable and a recommended ergonomic tool useful in all homes, most especially where women perform most domestic works.
Article
Full-text available
The Learning Machine is a data analysis method that automates the creation of an analytical model. It is an imaginary branch of knowledge that focuses on the assumption that machine data can be observed, that trends and decisions can be taken with a minimum of human capacity. Algorithms used for machine learning submitted data can be generated on the basis of new results.
Article
Full-text available
The design of this paper was to investigate comparatively the optimization techniques of response surface methodology (RSM) and artificial neural network (ANN) when applied to the conditions for chitosan production from Archachatina marginata shell and the % removal of methylene blue, MB, from synthetic textile wastewater. The proposed RSM and ANN models are optimized using genetic algorithm (GA). The optimum conditions for the extraction processes of chitosan and % removal of MB are determined and the derived chitosan at optimized conditions is characterized using analytical techniques. The ANN portrays better modeling abilities than RSM for the responses. The predicted values of % yield of chitosan, % DD and % removal of MB are obtained as 51.56, 98.68 and 94.71 respectively using the RSM-GA technique while the ANN-GA technique predicted 45.32%, 91.96% and 95.96% respectively. The experimental values of the responses are in excellent agreement with the ANN-GA predicted values with % errors being 1.8, 1.2 and 1.19 respectively. Hence, the conditions of chitosan production from Archachatina marginata shell and its bioremediation capacity of synthetic wastewater from textile industry can be adequately and accurately optimized and modeled using ANN-GA for routine seafood applications and treatment of industrial wastewater effluents.
Article
Full-text available
Robotic arm has become popular in the world of robotics. The essential part of the robotic arm is a programmable microcontroller based brick capable of driving basically three stepper motors design to form an anthropomorphic structure. The first design was for experimental use on a hu-man-size industrial robot arm called PUMA 560 used to explore issues in versatile object han-dling and compliance control in grasp actions (Bejczy & Jau, 1986). This paper explains the method of interfacing the robotic arm stepper motors with the programmed 8051-based micro-controller which are used to control the robot operations. We have employed the assembly lan-guage in programming our microcontroller. A sample robot which can grab (by magnetizing) and release small objects (by demagnetizing) is built for demonstrating the method explained.
Article
The purpose of this paper is to provide a quick overview of neural networks and to explain how they can be used in control systems. We introduce the multilayer perceptron neural network and describe how it can be used for function approximation. The backpropagation algorithm (including its variations) is the principal procedure for training multilayer perceptrons; it is briefly described here. Care must be taken, when training perceptron networks, to ensure that they do not overfit the training data and then fail to generalize well in new situations. Several techniques for improving generalization are discussed. The paper also presents three control architectures: model reference adaptive control, model predictive control, and feedback linearization control. These controllers demonstrate the variety of ways in which multilayer perceptron neural networks can be used as basic building blocks. We demonstrate the practical implementation of these controllers on three applications: a continuous stirred tank reactor, a robot arm, and a magnetic levitation system. Copyright © 2002 John Wiley & Sons, Ltd.
Neural-network application in weed identification using color digital images
  • N Zhang
  • Y Yang
  • M El-Faki
Zhang, N., Yang, Y., & El-Faki, M. (1994). Neural-network application in weed identification using color digital images. ASAE Paper No. 94-3511.
Neural networks in electrical engineering
  • S Howard
Howard S. (2006). Neural networks in electrical engineering. Proceedings of the ASEE New England Section 2006 Annual Conference (Session 1A -Electrical & Co mputer Engineering).