Technical Seminar Presentation

National Institute of Science & Technology

Technical Seminar Presentation

APPLICATIONS OF ANN IN MICROWAVE ENGINEERING Presented by Amit Kumar Das Roll# EC200147223 At NIST,Berhampur Under the guidance of Mr. Rowdra Ghatak Amit Kumar Das

Roll#EC200147223

[1]

National Institute of Science & Technology

Technical Seminar Presentation Introduction 

ANNs are neuroscience -inspired computational tools.

Learn from experience/examples (training) & not the example itself. 

Generalize automatically as a results of their structure (not by using human intelligence embedded in the form of ad hoc computer programs). 

Used extensively for visual pattern recognition, speech understanding, and more recently, for modeling and simulation of complex processes. 

Recently it has been applied to different branches of Microwave Engineering 

Amit Kumar Das

Roll#EC200147223

[2]

National Institute of Science & Technology

Technical Seminar Presentation When To Apply ANN



When the problem is poorly understood



When observations are difficult to carry out using noisy or incomplete data



When problem is complex, particularly while dealing with nonlinear systems

Amit Kumar Das

Roll#EC200147223

[3]

National Institute of Science & Technology

Technical Seminar Presentation Feedforward Neural Model Output lines

Hidden layer

Input lines Amit Kumar Das

Roll#EC200147223

[4]

National Institute of Science & Technology

Technical Seminar Presentation Topics Covered

 

Smart antennae modeling Demand node concept 1. 2. 3.

Initialization & selection Adaptation Optimization

Amit Kumar Das

Roll#EC200147223

[5]

National Institute of Science & Technology

Technical Seminar Presentation Smart Antenna Modeling

•A smart antenna consists of an antenna array combined with signal processing in both space and time. •These systems of antennas include a large number of techniques that attempt to enhance the received signal, suppress all interfering signals, and increase capacity, in general.

Amit Kumar Das

Roll#EC200147223

[6]

National Institute of Science & Technology

Technical Seminar Presentation ANN Model for Resonant Frequency Rectangular Patch Antenna

Amit Kumar Das

Roll#EC200147223

[7]

National Institute of Science & Technology

Technical Seminar Presentation Training/Network Parameters

     

Network size: Learning Rate: Momentum: Time Step for integration: Training Time: No. of Epochs:

Amit Kumar Das

5 × 40 × 1 0.08 0.205 5 × 10-10 6.4 min. 15000

Roll#EC200147223

[8]

National Institute of Science & Technology

Technical Seminar Presentation Bandwidth of Patch Antenna Rectangular Patch Antenna

Amit Kumar Das

Roll#EC200147223

[9]

National Institute of Science & Technology

Technical Seminar Presentation Rectangular Patch Antenna Algorithm’s used • Back Propagation • Delta – Bar – Delta (DBD) • Extended DBD (EDBD) • Quick Propagation

Other Details •ANN structure: 3× 4× 8× 1 •Max. no. of iterations: 5,00,000 •Tolerance (RMS Error): 0.015

Amit Kumar Das

Roll#EC200147223

[10]

National Institute of Science & Technology

Technical Seminar Presentation Network Parameters BP Parameters • Learning Coefficients: – 0.3 for the 1st hidden layer – 0.25 for the 2nd hidden layer – 0.15 for the output layer • momentum coefficient : 0.4 DBD Parameters • k = 0.01, φ = 0.5, θ = 0.7, a = 0.2 • Momentum coefficient = 0.4 • The sequential and/or random training procedure follows

Amit Kumar Das

EDBD Parameters • kα = 0.095, kµ = 0.01, gm = 0.0, gα = 0.0 • φ m = 0.01, φ α = 0.1, θ = 0.7, l = 0.2, • The sequential and/or random training procedure follows QP Parameters • δ = 0.0001 • a = 0.1 • ε = 1.0 • m = 2.0

Roll#EC200147223

[11]

National Institute of Science & Technology

Technical Seminar Presentation Demand Node Concept

Demand Node Concept Amit Kumar Das

Roll#EC200147223

[12]

National Institute of Science & Technology

Technical Seminar Presentation Input

Geographical map

Morphology model Land use categories interference distance

Stochastic channel characteristics

Step

Output Radio network definition Estimated tx location

Propagation analysis Coverage

Frequency allocation Freq plan Radio network analysis Network performance Mobile network

Amit Kumar Das

Roll#EC200147223

[13]

National Institute of Science & Technology

Technical Seminar Presentation Initialization

&

Selection Start •Distribute sensory neurons. •Place transmitting stations •Determine initial temperature. Determine supplying areas.

Random selection of a Sensory neuron N N N No supply? Multiply supplied? No.of selection Y Y Values=preset Change position for Change position for Val.? Y attraction repulsion or Or increasing power. Decreasing power.

Amit Kumar Das

Roll#EC200147223

[14]

National Institute of Science & Technology

Technical Seminar Presentation Adaptation

E1=Energy of current system State z1 Determine transmitting Station tworst Displace T

N

Change Power

Y Change position Determine supplying areas

Amit Kumar Das

Roll#EC200147223

[15]

National Institute of Science & Technology

Technical Seminar Presentation Optimization E2=Energy of current System state z2 E1— e2<0 ?

N

P:=prob(znew =zp)

Y N

N Steady state System ?

Choose random Number r

P
Reduce temperature

Y

Amit Kumar Das

End

Roll#EC200147223

[16]

National Institute of Science & Technology

Technical Seminar Presentation Displacement:Case Of Attraction

D1 D2 D3 D4

D5

D6

Sensory neuron

Base station Area of coverage Amit Kumar Das

Roll#EC200147223

[17]

National Institute of Science & Technology

Technical Seminar Presentation Displacement:Case Of Repulsion Base station locations

BEFORE

Amit Kumar Das

Sensory neurons

Borders of supplying areas.

AFTER

Roll#EC200147223

[18]

National Institute of Science & Technology

Technical Seminar Presentation Power Enhancement

Sensory neurons.

BEFORE

Amit Kumar Das

Base station locations

Borders of the supplying areas.

AFTER

Roll#EC200147223

[19]

National Institute of Science & Technology

Technical Seminar Presentation Power Decrement Borders of the supplying areas

Sensory neurons

Base station

Before Amit Kumar Das

After Roll#EC200147223

[20]

National Institute of Science & Technology

Technical Seminar Presentation Emerging Trends / Future Applications 

  

To find the optimized compact structures for low-profile antennas Applications in reconfigurable antennas/arrays Applications in fractal antennas To increase the efficiency of numerical algorithms used in antenna analysis like MoM, FDTD, FEM etc.

Amit Kumar Das

Roll#EC200147223

[21]

National Institute of Science & Technology

Technical Seminar Presentation Conclusion Neural networks mimics brain’s problem solving process & this has been the motivating factor for the use of ANN where 

huge amount of data is involved.



the sources vary.



decision making is critical.



environment is complex.

Amit Kumar Das

Roll#EC200147223

[22]

National Institute of Science & Technology

Technical Seminar Presentation REFERENCES [1]Haykin, S., 1999.Neural Networks A Comprehensive Foundation, 2nd edition, Pearson Education. [2]Freeman James A. & Skapura David M., Neural Networks, Pearson Education. [3]Yuhas, Ben & Ansari Nerman. Neural Networks in Telecommunications. [4]B.Yegnanarayana. 1999.Artificial Neural Networks. Prentice Hall of India. [5]G.A. Carpenter and S.Grossberg, ‘The ART of adaptive pattern recognition by a self-organization neural network’, IEEE Computer, vol. 21, pp. 77-88, 1988. [6]N.K. Bose and P.Liang, Neural Network Fundamentals with Graphs, Algorithms and Applications,McGraw-Hill,Int. Amit Kumar Das

Roll#EC200147223

[23]

National Institute of Science & Technology

Technical Seminar Presentation

Thank You Amit Kumar Das

Roll#EC200147223

[24]