eprintid: 10051757
rev_number: 21
eprint_status: archive
userid: 608
dir: disk0/10/05/17/57
datestamp: 2018-07-17 14:33:24
lastmod: 2021-09-25 23:27:48
status_changed: 2018-07-17 14:33:24
type: article
metadata_visibility: show
creators_name: Patel, JS
creators_name: Fioranelli, F
creators_name: Ritchie, M
creators_name: Griffiths, H
title: Multistatic radar classification of armed vs unarmed personnel using neural networks
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F46
keywords: Multistatic Radar, Classification, Deep Neural Networks,
Auto-Encoders, Micro-Doppler, Data Ensembling
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: This paper investigates an implementation of an array of distributed neural networks, operating together to classify between unarmed and potentially armed personnel in areas under surveillance using ground based radar. Experimental data collected by the University College London (UCL) multistatic radar system NetRAD is analysed. Neural networks are applied to the extracted micro-Doppler data in order to classify between the two scenarios, and accuracy above 98% is demonstrated on the validation data, showing an improvement over methodologies based on classifiers where human intervention is required. The main advantage of using neural networks is the ability to bypass the manual extraction process of handcrafted features from the radar data, where thresholds and parameters need to be tuned by human operators. Different network architectures are explored, from feed-forward networks to stacked auto-encoders, with the advantages of deep topologies being capable of classifying the spectrograms (Doppler-time patterns) directly. Significant parameters concerning the actual deployment of the networks are also investigated, for example the dwell time (i.e. how long the radar needs to focus on a target in order to achieve classification), and the robustness of the networks in classifying data from new people, whose signatures were unseen during the training stage. Finally, a data ensembling technique is also presented which utilises a weighted decision approach, established beforehand, utilising information from all three sensors, and yielding stable classification accuracies of 99% or more, across all monitored zones.
date: 2018-06
date_type: published
official_url: https://doi.org/10.1007/s12530-017-9208-6
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
article_type_text: Journal Article
verified: verified_manual
elements_id: 1562160
doi: 10.1007/s12530-017-9208-6
lyricists_name: Griffiths, Hugh
lyricists_name: Ritchie, Matthew
lyricists_id: HDGRI98
lyricists_id: MARIT18
actors_name: Ritchie, Matthew
actors_id: MARIT18
actors_role: owner
full_text_status: public
publication: Evolving Systems
volume: 9
number: 2
pagerange: 135-144
issn: 1868-6486
citation:        Patel, JS;    Fioranelli, F;    Ritchie, M;    Griffiths, H;      (2018)    Multistatic radar classification of armed vs unarmed personnel using neural networks.                   Evolving Systems , 9  (2)   pp. 135-144.    10.1007/s12530-017-9208-6 <https://doi.org/10.1007/s12530-017-9208-6>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10051757/1/multistatic-radar-classification.pdf