Transcript Performance of OOK with ANN Equalization in Indoor Optical

1
The Performance of PPM using Neural
Network and Symbol Decoding for Diffused
Indoor Optical Wireless Links
S. Rajbhandari, Z. Ghassemlooy, and
M. Angelova †
Optical Communications Research Group
† Intelligent Modelling Lab
School of Computing, Engineering and Information
Sciences
Northumbria University, Newcastle upon Tyne
UK.
ICTON 2007, Rome, Italy
Why Optical Wireless?
 Licence free spectrum
 Secure links
 Free from electromagnetic interference
 Low cost transmitter/receiver
 Small cell size
 Most importantly potential unlimited
bandwidth, 10 millions times that of RF
(which could solve the problem of bandwidth
congestion in mobile system for an
foreseeable future)
ICTON 2007, Rome, Italy
Challenges in Indoor Optical Wireless
 Strict link set-up for direct line-of-sight links
 Shadowing effects
 Lack of mobility
 Power limitation : due to eye and skin safety
 Intersymbol interference due to multipath
propagations in diffused links
 Intense ambient light noise
 Large area photo-detectors - limits the data
rate.
ICTON 2007, Rome, Italy
Digital Modulation Schemes
 On-off Keying (OOK)
 Pulse position modulation (PPM)
 Subcarrier modulation
 Digital pulse interval modulation (DPIM)
 Dual-header pulse interval modulation (DHPIM)
ICTON 2007, Rome, Italy
Diffuse Links
Rx
Tx
1.2
Received signal for non-LOS Links
1
Amplitude
0.8
 Multipath path
 ISI, which in indoor depends
on the room design and size.
 Delay spread Drms is used to
approximate the dispersion in
optical channel.
0.6
0.4
0.2
0
-0.2
-0.4
0
2
4
6
8
10
Normalized Time
ICTON 2007, Rome, Italy
Techniques to Mitigate the ISI
 Optimal solution - Maximum likelihood sequence
detector
 Sub-optimal solution - Linear or decision feedback
equalizer based on the finite impulse response
(FIR) filter
- The impulse response of filter c(f)= 1/h(f), where h(f) is
the frequency response of channel.
- Need to have pre-knowledge of channel
- Difficult to realize if channel is non-linear.
- Sometime the inverse filter may not exist …. What is the
alternative?
ICTON 2007, Rome, Italy
ANN Based Equalization
 Redefine the problem of equalization as
geometric classification problem in a complex
plane.
 Use artificial neural network (ANN) for
classification.
Optical
Receiver
Artificial
Neural Network
Threshold
Detector
Pattern
Classification
ICTON 2007, Rome, Italy
Advantages of ANN Equalization
 Parallel processing
 Universal approximates
 No assumptions are made on the channel model or
modulation techniques
 Adaptive processing
 Channel non-linearity: not a problem
ICTON 2007, Rome, Italy
ANN: Basics
 Fundamental unit : a
neuron
 Based on biological
neuron
 Capability to learn
 Output is function of
weight inputs and a bias
as given by
f(.)
n
y  f (b   xk .wk )
k 1
ICTON 2007, Rome, Italy
ANN: Basics
 Neuron layers
1 Input layer
Input
Layer
Hidden Hidden
Layer 1 Layer 2
Output
1 or more hidden layer(s)
1 output layer
 Learning Method
Supervised or unsupervised
ICTON 2007, Rome, Italy
Proposed System
n(t)
M
0100
M
0010
PPM
Encoder
PPM
Decoder
Xj
Optical
Transmitter
Decision
Device
X(t)
Z(t)
h(t)
Yj
Neural
Network
∑
Optical
Receiver
Zj
Zj-1
Zj
Matched
Filter
.
Zj-n
Ts = M/LRb
.
 A feedforward back propagation neural network .
 ANN is trained using a training sequence at the operating SNR.
 Trained AAN is used for equalization
ICTON 2007, Rome, Italy
Impulse Response of Equalized Channel
Impulse response of unequalized
channel
impulse response of equalized
channel
• Pulse are spread to adjust pulse .
• Equalized response in a delta
function which is equivalent to a
impulse response of the ideal
channel
• ISI depends on pulse spread
ICTON 2007, Rome, Italy
Results and Discussion (1)
Slot error rate performance of 8- PPM in diffuse channel with Drms of 5ns at 50
Mbps
Adaptive linear equalizer with
least mean square (LMS)
algorithm is used.

The
performance of ANN
equalizer is almost identical to
the linear equalizer.
ICTON 2007, Rome, Italy
Results and Discussion (2)
Slot error rate performance of 8- PPM in diffuse channel with Drms of 5ns at 100
Mbps
Unequalized performance at
higher data rate is unacceptable at
all SNR range

Linear and neural equalization
give almost identical performance.

ICTON 2007, Rome, Italy
Further Work
 Using ANN as decoder and equalizer to
reduce system complexity.
 Practical implementation.
 ANN with wavelet transform
ICTON 2007, Rome, Italy
Conclusions
 ANN is an effective equalizer for indoor optical wireless
environment.
 No need for a prior knowledge of the channel for
equalization.
 Performance of ANN is identical to or better than the
traditional equalizer.
 The advantage of ANN over the traditional equalizer is
its adaptability .
ICTON 2007, Rome, Italy
Acknowledgment
 My PhD students, Sujan, Rob, Maryam,
Popoola
 Northunmbria University for the research
funding
ICTON 2007, Rome, Italy
Thank you!
ICTON 2007, Rome, Italy
Questions and suggestions
ICTON 2007, Rome, Italy