What have I done on my PhD?
Started to consider what is meant by multiperspectiveclassification in the case of the uDS.
Investigated how clutter can be removed from databeing processed
Used a method based on the CLEAN algorithms
Used the zero Doppler removal technique fromturntable ISAR.
Gathered a set of multistatic data from trials at Shenley
Work out how to process the data
Fusing of the data from all nine bistatic paths
This is still in progress
Cration of the reconstructed signals
The range-FFT plots
Conducted the trials
Measured the biometric data of persontargets.
Gathered the data
Map of the range
Planned out the trials
Decison of what target to investigate
Decision on radar parameters to use
Concerns over multipath
Consideration of SNR/SCR
Classification of Thales data usingother techniques
Artificial neural network
Hidden Markov Model
Bayesian classification
Statistical classification/kernal estimation
Frequency domain processing of data
This is currently in progress for Thales data
Analysis of classification output
Contrasted the impact of adding extra perspectivesto the library for the classifier.
The crazy plots of parameter variationwith frame-duration and correlation-level
The performance evaluation parameters
R
Pgen
Pfa
Pd
Pcc
Used ROC curves to assess the unknown thresholds
Time domain processing of data
Classification of Thales data using k-nn
Explored two types of library
Monperspective
Implemented a version of the k-nn algorithm
Classification of Thales data using DTW
Explored three types of library
Sparsely populated
Biperspective
Monoperspective
Implemented two version of DTW
Need to implement can't declare
Allowed for unknown input
Type II
Type 0
Investigated how the library and testdata can beselected based on correlation distance of thesignal.
The results using these libraries should becompared with the conventional randomselection method that is often used.
More investigation of this is required baseon the idea that k-nn forced me to add extraentries to the library.
Developed a set of libraries based on thedecorrelation distance.
Assessed the correlation distance of theseframes.
Broke the data into a number of sub framesto better emulate a radar's dwell time.
Analysis of the Thales data
Feature extraction from the data
Looked at how this may be analysed through FFT & STFT
Processed the data to form the reconstructed target signal
Developed a procedure for reading the data into matlab
Produced a basic simulation of the micro-Doppler effect
Matlab simulation of walking person
Matlab simulation of propeller
Matlab simiulation of multiple vibrating scatterers
