Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks
<span style="color: windowtext;">Recent studies showed that the performance of the modulation classification (MC) is considerably improved by using multiple sensors deployed in a cooperative manner. Such cooperative MC solutions are based on the centralized fusion of independent feat...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/19/4339 |
id |
doaj-8465467ebf8f48779b30630e4204add3 |
---|---|
record_format |
Article |
spelling |
doaj-8465467ebf8f48779b30630e4204add32020-11-25T01:27:37ZengMDPI AGSensors1424-82202019-10-011919433910.3390/s19194339s19194339Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor NetworksGoran B. Markovic0Vlada S. Sokolovic1Miroslav L. Dukic2School of Electrical Engineering, University of Belgrade, Bul. Kralja Aleksandra 73, 11120 Belgrade, SerbiaUniversity of Defence in Belgrade, Military Academy, Generala Pavla Jurišića Šturma 33, 11000 Belgrade, SerbiaSchool of Electrical Engineering, University of Belgrade, Bul. Kralja Aleksandra 73, 11120 Belgrade, Serbia<span style="color: windowtext;">Recent studies showed that the performance of the modulation classification (MC) is considerably improved by using multiple sensors deployed in a cooperative manner. Such cooperative MC solutions are based on the centralized fusion of independent features or decisions made at sensors. Essentially, the cooperative MC employs multiple uncorrelated observations of the unknown signal to gather more complete information, compared to the single sensor reception, which is used in the fusion process to refine the MC decision. However, the non-cooperative nature of MC inherently induces large loss in cooperative MC performance due to the unreliable measure of quality for the MC results obtained at individual sensors (which causes the partial information loss while performing centralized fusion). In this paper, the distributed two-stage fusion concept for the cooperative MC using multiple sensors is proposed. It is shown that the proposed distributed fusion, which combines feature (cumulant) fusion and decision fusion, facilitate preservation of information during the fusion process and thus considerably improve the MC performance. The clustered architecture is employed, with the influence of mismatched references restricted to the intra-cluster data fusion in the first stage. The adopted distributed concept represents a flexible and scalable solution that is suitable for implementation of large-scale networks.</span>https://www.mdpi.com/1424-8220/19/19/4339cognitive radio networksdata fusionfeature fusionhybrid fusionmulti-sensor fusionmodulation classificationwireless sensor networks |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Goran B. Markovic Vlada S. Sokolovic Miroslav L. Dukic |
spellingShingle |
Goran B. Markovic Vlada S. Sokolovic Miroslav L. Dukic Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks Sensors cognitive radio networks data fusion feature fusion hybrid fusion multi-sensor fusion modulation classification wireless sensor networks |
author_facet |
Goran B. Markovic Vlada S. Sokolovic Miroslav L. Dukic |
author_sort |
Goran B. Markovic |
title |
Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks |
title_short |
Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks |
title_full |
Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks |
title_fullStr |
Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks |
title_full_unstemmed |
Distributed Hybrid Two-Stage Multi-Sensor Fusion for Cooperative Modulation Classification in Large-Scale Wireless Sensor Networks |
title_sort |
distributed hybrid two-stage multi-sensor fusion for cooperative modulation classification in large-scale wireless sensor networks |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-10-01 |
description |
<span style="color: windowtext;">Recent studies showed that the performance of the modulation classification (MC) is considerably improved by using multiple sensors deployed in a cooperative manner. Such cooperative MC solutions are based on the centralized fusion of independent features or decisions made at sensors. Essentially, the cooperative MC employs multiple uncorrelated observations of the unknown signal to gather more complete information, compared to the single sensor reception, which is used in the fusion process to refine the MC decision. However, the non-cooperative nature of MC inherently induces large loss in cooperative MC performance due to the unreliable measure of quality for the MC results obtained at individual sensors (which causes the partial information loss while performing centralized fusion). In this paper, the distributed two-stage fusion concept for the cooperative MC using multiple sensors is proposed. It is shown that the proposed distributed fusion, which combines feature (cumulant) fusion and decision fusion, facilitate preservation of information during the fusion process and thus considerably improve the MC performance. The clustered architecture is employed, with the influence of mismatched references restricted to the intra-cluster data fusion in the first stage. The adopted distributed concept represents a flexible and scalable solution that is suitable for implementation of large-scale networks.</span> |
topic |
cognitive radio networks data fusion feature fusion hybrid fusion multi-sensor fusion modulation classification wireless sensor networks |
url |
https://www.mdpi.com/1424-8220/19/19/4339 |
work_keys_str_mv |
AT goranbmarkovic distributedhybridtwostagemultisensorfusionforcooperativemodulationclassificationinlargescalewirelesssensornetworks AT vladassokolovic distributedhybridtwostagemultisensorfusionforcooperativemodulationclassificationinlargescalewirelesssensornetworks AT miroslavldukic distributedhybridtwostagemultisensorfusionforcooperativemodulationclassificationinlargescalewirelesssensornetworks |
_version_ |
1725104264711241728 |