Remote concealed threat detection by novel classification algorithms applied to multi-polarimetric UWB radar

O'Reilly, Dean; Bowring, Nicholas; Rezgui, Nacer Ddine; Andrews, David; Harmer, Stuart

doi:10.1117/12.2016586

Cited by 2 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The radar signals are analysed on the laptop using pattern recognition applied to the time resolved signals in the form of an ANN, this set-up has been illustrated in Figure 24. This method has been discussed in detail in a previous publication [28]. One of the shortcomings of this method is that the optimisation of the ANN architecture has previously been performed using trial and error.…”

Section: Application To Weapon Detectionmentioning

confidence: 99%

“…The performance of the optimised ANN is compared to previously published data [28], the experimental methodology used to obtain this data is explained here in.…”

Section: Comparison To Existing Solutionmentioning

confidence: 99%

“…The radar used in [28] is a novel multi-polarimetric frequency modulated continuous wave radar operating in the K Band . The radar illuminates a person using two linear polarisations which are switched.…”

Section: Comparison To Existing Solutionmentioning

confidence: 99%

“…The radar illuminates a person using two linear polarisations which are switched. The use of two illuminating polarisations has been shown to significantly improve detection rates [28]. The reflected signal is then recorded in four polarisations, which are co and cross polar to each of the illuminating polarisations.…”

Section: Comparison To Existing Solutionmentioning

confidence: 99%

“…The large amounts of data obtained in the collection of training scans makes the problem difficult for the ANN to converge to a solution that is robust but without over training the ANN. In [28] a Principal Component Analysis (PCA) data reduction technique was integrated into the classification algorithm. The PCA data reduction was applied to the time resolved radar signals to obtain a set of Eigenvalues and Eigenvectors.…”

Section: Comparison To Existing Solutionmentioning

confidence: 99%

See 4 more Smart Citations

A novel preference articulation operator for the Evolutionary Multi-Objective Optimisation of classifiers in concealed weapons detection

Rostami

O'Reilly

Shenfield

et al. 2015

Information Sciences

Self Cite

View full text Add to dashboard Cite

This document is the author deposited version. You are advised to consult the publisher's version if you wish to cite from it. Published versionROSTAMI, Shahin, O'REILLY, Dean, SHENFIELD, Alex and BOWRING, Nicholas (2015). A novel preference articulation operator for the Evolutionary Multi-Objective Optimisation of classifiers in concealed weapons detection. Information Sciences, 295, 494-520. Copyright and re-use policy AbstractThe incorporation of decision maker preferences is often neglected in the Evolutionary MultiObjective Optimisation (EMO) literature. The majority of the research in the field and the development of EMO algorithms is primarily focussed on converging to a Pareto optimal approximation close to or along the true Pareto front of synthetic test problems. However, when EMO is applied to real-world optimisation problems there is often a decision maker who is only interested in a portion of the Pareto front (the Region of Interest) which is defined by their expressed preferences for the problem objectives. In this paper a novel preference articulation operator for EMO algorithms is introduced (named the Weighted Z-score Preference Articulation Operator) with the flexibility of being incorporated a priori, a posteriori or progressively, and as either a primary or auxiliary fitness operator. The Weighted Z-score Preference Articulation Operator is incorporated into an implementation of the Multi-Objective Evolutionary Algorithm Based on Decomposition (named WZ-MOEA/D) and benchmarked against MOEA/D-DRA on a number of bi-objective and five-objective test problems with test cases containing preference information. After promising results are obtained when comparing WZ-MOEA/D to MOEA/D-DRA in the presence of decision maker preferences, WZ-MOEA/D is successfully applied to a real-world optimisation problem to optimise a classifier for Concealed Weapon Detection, producing better results than previously published classifier implementations.

show abstract

Section: Application To Weapon Detectionmentioning

confidence: 99%

“…The performance of the optimised ANN is compared to previously published data [28], the experimental methodology used to obtain this data is explained here in.…”

Section: Comparison To Existing Solutionmentioning

confidence: 99%

Section: Comparison To Existing Solutionmentioning

confidence: 99%

Section: Comparison To Existing Solutionmentioning

confidence: 99%

Section: Comparison To Existing Solutionmentioning

confidence: 99%

See 3 more Smart Citations

A novel preference articulation operator for the Evolutionary Multi-Objective Optimisation of classifiers in concealed weapons detection

Rostami

O'Reilly

Shenfield

et al. 2015

Information Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

A fast hypervolume driven selection mechanism for many-objective optimisation problems

Rostami

Neri

2017

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

Solutions to real-world problems often require the simultaneous optimisation of multiple conflicting objectives. In the presence of four or more objectives, the problem is referred to as a "many-objective optimisation problem". A problem of this category introduces many challenges, one of which is the e↵ective and e cient selection of optimal solutions.The hypervolume indicator (or s-metric), i.e. the size of dominated objective space, is an e↵ective selection criterion for many-objective optimisation. The indicator is used to measure the quality of a nondominated set, and can be used to sort solutions for selection as part of the contributing hypervolume indicator. However, hypervolume based selection methods can have a very high, if not infeasible, computational cost.The present study proposes a novel hypervolume driven selection mechanism for many-objective problems, whilst maintaining a feasible computational cost. This approach, named the Hypervolume Adaptive Grid Algorithm (HAGA), uses two-phases (narrow and broad) to prevent population-wide calculation of the contributing hypervolume indicator. Instead, HAGA only calculates the contributing hypervolume indicator for grid populations, i.e. for a few solutions, which are close in proximity (in the objective space) to a candidate solution when in competition for survival. The result is a trade-o↵ between complete accuracy in selecting the fittest individuals in regards to hypervolume quality, and a feasible computational time in many-objective space. The real-world e ciency of the proposed selection mechanism is demonstrated within the optimisation of a classifier for concealed weapon detection.

show abstract

Remote concealed threat detection by novel classification algorithms applied to multi-polarimetric UWB radar

Cited by 2 publications

References 9 publications

A novel preference articulation operator for the Evolutionary Multi-Objective Optimisation of classifiers in concealed weapons detection

A novel preference articulation operator for the Evolutionary Multi-Objective Optimisation of classifiers in concealed weapons detection

A fast hypervolume driven selection mechanism for many-objective optimisation problems

Contact Info

Product

Resources

About