International Journal of Scientific & Engineering Research, Volume 4, Issue 12, December-2013 489
ISSN 2229-5518
Snuti Kumari
Department of Electronics and Communication Engineering
Dronacharya College of Engineering
Mahamaya Technical University, India km.snuti@gmail.com
Garima Rathi
Department of computer science Engineering Institute of information technology and management Guru Gobind Singh Indraprastha University garimarathi11@gmail.com
Abstract— In recent years, the use of neural networks (NNs) for wireless-communication becoming wider and has been getting momentum. The basic purpose of applying neural network is to change from the lengthy analysis and design cycles required to develop high-performance systems to very short product- development times. There is an overview of different applications of neural network techniques for wireless communication and a description of future research in this field.
The term biological neural networks , made up of real biological neurons, or artificial neural networks, for solving artificial intelligence problems. A biological neural network is composed of a group or groups of chemically connected or functionally associated
IJSEneurons. R
Keywords— Neural networks, applications of neural network, land
mobile radio cellular systems, antennas, microstrip antennas, antenna arrays, multi-band antennas, wideband antennas.
I. INTRODUCTION
The term neural network was traditionally used to refer to a network or circuit of biological neurons.
.
IJSER © 2013 http://www.ijser.org
A single neuron may be connected to many other neurons and the total number of neurons and connections in a network may be extensive. It resembles the brain in two respects:
1. Knowledge is acquired by the network through a learning process.
2. Interneuron connection strengths known as synaptic weights are
used to store the experiential knowledge.
International Journal of Scientific & Engineering Research, Volume 4, Issue 12, December-2013 490
ISSN 2229-5518
substrate) on a ground plane. Patches may be photoetched making them adapted for low-cost, mass production.
A. Antennas
• Antenna (radio), also known as an aerial, a transducer designed to transmit or receive electromagnetic (e.g. TV or radio) wave.
• Television antenna (or TV aerial), is an antenna specifically designed for the reception of broadcast television signals.
• Antennae Galaxies, the name of two colliding galaxies
NGC 4038 and NGC 4039.
An antenna designed to operate on several bands. These antennas
often use designs where one part of the antenna is active for one band, and another part is active for a different band. A multiband antenna may have lower than average gain or may be physically larger in compensation.
• Antenna array (electromagnetic) a group of isotropic radiators such that the currents running through them are of different amplitudes and phases.
These antennas are popular for low-profile applications at frequencies above 100MHz (λ<3).They commonly consist of a rectangular square metal patch on a thin layer of dielectric (called the
In communications, a system is wideband when the message bandwidth significantly exceeds the coherence bandwidth of the channel. A wideband antenna is one with approximately or exactly the same operating characteristics over a very
wide passband. It is distinguished from broadband antennas,
where the passband is large, but the antenna
gain and/or radiation pattern need not stay the same over the passband.
IJSER © 2013 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 4, Issue 12, December-2013 491
ISSN 2229-5518
Block diagram for methods,techniques and algorithm
On observing any wireless engineering phenomenon- the design or
analysis of antennas, estimation of direction of arrival, adaptive beamforming techniques, etc. - it is noted
That these always have a quite nonlinear relationship with their
corresponding input variables. The inherent nonlinearities associated with these phenomena makes them ideally suited for neural networks. Multilayer neural networks are employed to model such nonlinear
relationships.
IJSER
The use of neural networks can considerably reduce the complexity.
A straightforward application of a neural network uses the data
derived from this complex mathematical
Procedures to train a neural network. After proper training, these neural models can be used in place of the computationally intensive physics/EM--based models to speed up the analysis.
ANN can be used efficiently to design of various types microstrip
antenna. In study a comparative evaluation of different variants of back propagation training algorithm has done for the design of
rectangular microstrip antenna. ANN can also be used to calculate different
Parameters of circular microstrip antenna such as resonant frequency, input impedance etc. Sufficient amount of work indicates how ANN can be used efficiently to Design circular and
rectangular microstrip antennas. Also ANN can be used to calculate different parameters of rectangular microstrip antenna such as radiation efficiency, resonating frequency ,directivity ,feed position ,
resonant frequencies of triangular and rectangular microstrip antennas , resonant resistance calculation of electrically thin and thick rectangular microstrip antennas input impedance of rectangular microstrip antennas.
• 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.
IJSER © 2013 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 4, Issue 12, December-2013 492
ISSN 2229-5518
• Fuzzy logic and neural networks have been integrated for uses as diverse as automotive engineering, applicant screening for jobs, the control of a crane, and the monitoring of glaucoma.
• "Most practical applications of artificial neural networks are based on a computational model involving the
1. In using neural network, first problem we come across is to be
checked for its suitability neural-network implementation.
Sol. It is advisable not to resort to neural network techniques for simple linear functions, or for problems that can be implemented
through a direct, closed-form formula.
2. The accuracy of a properly trained network depends on the accuracy of the data used to train the network. Sol. Care should be taken while generating training data, whether the data are generated
• theoretical analyses and model development, neurobiological modeling, and hardware implementation.
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
o Improved stock prediction.
o Common usage of self-driving cars.
o Composition of music.
o Handwritten documents to be automatically transformed
into formatted word processing documents.
o Trends found in the human genome to aid in the understanding of the data compiled by the Human Genome Project.
o Self-diagnosis of medical problems using neural networks.
Conclusions
High-performance antennas are being developed to satisfy the competing demands of emerging wireless applications.This article reviewed the current applications of neural networks in
These high-priority areas, and traced the further avenues in which
IJSEneural networks coRuld play a major role. Recently, the possibility of
• 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 devices is SPEED!
• NN hardware currently runs in a few niche areas, such as those areas where very high performance 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 neurons and 10000's of synapses, high performance NN hardware will become essential for practical operation.
• 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 sophisticated as researchers develop better training methods and network architectures.
o Robots that can see, feel, and predict the world around them.
developing antenna designs that in some way exploit the properties of fractals to achieve the goals of compact size, low profile, conformal, and multi-hand antennas, at least in part, has attracted a lot of attention. Neural networks can also find suitable places for analysis of these antennas.
REFERENCES
1. S. Sagiroglu and K. Guney, “Calculation of Resonant Frequency
For an Equilateral Triangular Microstrip Antenna Using
Artificial Neural Networks,” Microwave Opt. Tech. Letters, 14, 2,
1997, pp. 89-93.
2., S. Sagiroglu, K. Guney, and M. Erler, “Resonant Frequency
Calculation for Circular Microstrip Antennas Using Artificial Neural
Neural
Networks,” International Journal of RF and-Gcrowave Computer- Aided Engineering, 8, 1998, pp. 270-277.
Antennas with the Use of Multilayered Perceptions,” International
Journal of RF and Microwave Computer-Aided Engineering, 9,
1999, pp. 277-286.
4. D. Karaboga, K. Guney, S. Sagiroglu, and M. Erler, “Neural
Computation of Resonant Frequency of Electrically Thin and
Thick Rectangular Microstrip Antennas,” IEE Proceedings, PI. H,
1 4 6 , 1 9 9 , ~1~5.5 -159.
5. K. Guney, M. Erler, and S. Sagiroglu, “Artificial Neural Networks for the Resonant Resistance Calculation of Electrically Thin
And Thick Rectangular Microstrip Antennas,” Electromagnetics,
20, 2000, pp. 387-400.
IJSER © 2013 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 4, Issue 12, December-2013 493
ISSN 2229-5518
6. K. Guney, S. Sagiroglu, and M. Erler, “Comparison of Neural Networks for Resonant Frequency Computation of Electrically Thin and Thick Rectangular Microstrip Antennas,” Journal of Electromagnetic Waves and Applications, 15, 2001, pp. 1121-
1145.
7. R. K. Mishra and A. Patnaik, “Designing Rectangular Patch Antenna Using the Neurospectral Method,” IEEE Transactions on Antennas and Propagation, AP-51, 8, August 2003, pp. 1914-
1921.
8. R. K. Mishra and A. Patnaik, “Neurospectral Analysis of Coaxial Fed Rectan”eu Lar Patch Antenna.” IEEE International Symposium on Antennas and Propagation Digest, 2, July 2000, pp.
1062-1065.
9. P. R. Chang, W. H. Yang and K. K. Chan, “A Neural Network
Approach to MVDR Beamfonning Problem,” lEEE Transactions
On Antennas and Propagation, AP-40,3, 1992, pp. 31 3-322.
10. A. H. El Zooghby, C. G. Christodoulou and M. Georgiopoulos, “Neural Network-Based Adaptive Beamforming for One- and
Two-Dimensional Antenna Arrays,” IEEE Transactions on
AntennasandPropagation,
11. P. M. Watson, G. L. Creech and K. C. Gupta, “Knowledge
Based EM-ANN Models for the Design of Wide Bandwidth CPW
PatcWslot Antennas,” IEEE International Symposium on Antennas
And Propagation Digest, 4, July 1999, pp. 2588-2594.
IJSER
IJSER © 2013 http://www.ijser.org