SER of each model on the dataset.

<div><p>Traditional communication signal detection heavily relies on manually designed features, making it difficult to fully characterize the essential characteristics of the signal, resulting in limited detection accuracy. Based on this, the study innovatively combines Multiple Input M...

Full description

Saved in:
Bibliographic Details
Main Author: Yang Liu (4829) (author)
Other Authors: Peng Liu (120506) (author), Yu Shi (117923) (author), Xue Hao (5699042) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852020010116972544
author Yang Liu (4829)
author2 Peng Liu (120506)
Yu Shi (117923)
Xue Hao (5699042)
author2_role author
author
author
author_facet Yang Liu (4829)
Peng Liu (120506)
Yu Shi (117923)
Xue Hao (5699042)
author_role author
dc.creator.none.fl_str_mv Yang Liu (4829)
Peng Liu (120506)
Yu Shi (117923)
Xue Hao (5699042)
dc.date.none.fl_str_mv 2025-05-27T17:40:04Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0324916.g009
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/SER_of_each_model_on_the_dataset_/29157442
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
symbol error rate
simulation training set
simulation test set
resource consumption assessment
reducing resource consumption
ofdm systems effectively
modulation error rate
broad application prospects
50 &# 8201
missed detection rates
false detection rates
moderate memory usage
dnn cascade structure
achieved significant results
limited detection accuracy
improving detection accuracy
driven detection system
7 %, 18
enhanced signal detection
manually designed features
dcnet decoder based
4 &# 8201
signal detection accuracy
model loading time
1 %, 81
detection speed
system adopts
results showed
research model
dnn method
cpu usage
8 %,
3 %,
25 %,
time performance
suppress inter
subcarrier interference
optimizing real
fully characterize
essential characteristics
deep learning
channel estimation
average latency
4 ghz
006 %.
004 %.
dc.title.none.fl_str_mv SER of each model on the dataset.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Traditional communication signal detection heavily relies on manually designed features, making it difficult to fully characterize the essential characteristics of the signal, resulting in limited detection accuracy. Based on this, the study innovatively combines Multiple Input Multiple Output (MIMO) with orthogonal frequency division multiplexing technology to construct a data-driven detection system. The system adopts a Multi-DNN method with a dual-DNN cascade structure and mixed activation function design to optimize the channel estimation and signal detection coordination process of the MIMO part. At the same time, a DCNet decoder based on a convolutional neural network batch normalization mechanism is designed to suppress inter-subcarrier interference in OFDM systems effectively. The results showed that on the simulation training set, the accuracy of the research model was 93.8%, the symbol error rate was 17.6%, the throughput was 81.3%, and the modulation error rate was 0.004%. On the simulation test set, its accuracy, symbol error rate, throughput, and modulation error rate were 90.7%, 18.1%, 81.2%, and 0.006%. In both 2.4 GHz and 5 GHz WiFi signals, the signal detection accuracy of the research model reached 91.5% and 91.6%, with false detection rates of 1.9% and 1.5%, and missed detection rates of 1.6% and 4.2%. In resource consumption assessment, the detection speed of this model reached 120 signals/s, with an average latency of 50 ms. The model loading time was only 2.4 s, and the CPU usage was as low as 25%, with moderate memory usage. Overall, the research model has achieved significant results in improving detection accuracy, optimizing real-time performance, and reducing resource consumption. It has broad application prospects in the field of communication signal detection.</p></div>
eu_rights_str_mv openAccess
id Manara_9c1947a620caaf0d1a8536fff0982cb2
identifier_str_mv 10.1371/journal.pone.0324916.g009
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29157442
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling SER of each model on the dataset.Yang Liu (4829)Peng Liu (120506)Yu Shi (117923)Xue Hao (5699042)Science PolicySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedsymbol error ratesimulation training setsimulation test setresource consumption assessmentreducing resource consumptionofdm systems effectivelymodulation error ratebroad application prospects50 &# 8201missed detection ratesfalse detection ratesmoderate memory usagednn cascade structureachieved significant resultslimited detection accuracyimproving detection accuracydriven detection system7 %, 18enhanced signal detectionmanually designed featuresdcnet decoder based4 &# 8201signal detection accuracymodel loading time1 %, 81detection speedsystem adoptsresults showedresearch modeldnn methodcpu usage8 %,3 %,25 %,time performancesuppress intersubcarrier interferenceoptimizing realfully characterizeessential characteristicsdeep learningchannel estimationaverage latency4 ghz006 %.004 %.<div><p>Traditional communication signal detection heavily relies on manually designed features, making it difficult to fully characterize the essential characteristics of the signal, resulting in limited detection accuracy. Based on this, the study innovatively combines Multiple Input Multiple Output (MIMO) with orthogonal frequency division multiplexing technology to construct a data-driven detection system. The system adopts a Multi-DNN method with a dual-DNN cascade structure and mixed activation function design to optimize the channel estimation and signal detection coordination process of the MIMO part. At the same time, a DCNet decoder based on a convolutional neural network batch normalization mechanism is designed to suppress inter-subcarrier interference in OFDM systems effectively. The results showed that on the simulation training set, the accuracy of the research model was 93.8%, the symbol error rate was 17.6%, the throughput was 81.3%, and the modulation error rate was 0.004%. On the simulation test set, its accuracy, symbol error rate, throughput, and modulation error rate were 90.7%, 18.1%, 81.2%, and 0.006%. In both 2.4 GHz and 5 GHz WiFi signals, the signal detection accuracy of the research model reached 91.5% and 91.6%, with false detection rates of 1.9% and 1.5%, and missed detection rates of 1.6% and 4.2%. In resource consumption assessment, the detection speed of this model reached 120 signals/s, with an average latency of 50 ms. The model loading time was only 2.4 s, and the CPU usage was as low as 25%, with moderate memory usage. Overall, the research model has achieved significant results in improving detection accuracy, optimizing real-time performance, and reducing resource consumption. It has broad application prospects in the field of communication signal detection.</p></div>2025-05-27T17:40:04ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0324916.g009https://figshare.com/articles/figure/SER_of_each_model_on_the_dataset_/29157442CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/291574422025-05-27T17:40:04Z
spellingShingle SER of each model on the dataset.
Yang Liu (4829)
Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
symbol error rate
simulation training set
simulation test set
resource consumption assessment
reducing resource consumption
ofdm systems effectively
modulation error rate
broad application prospects
50 &# 8201
missed detection rates
false detection rates
moderate memory usage
dnn cascade structure
achieved significant results
limited detection accuracy
improving detection accuracy
driven detection system
7 %, 18
enhanced signal detection
manually designed features
dcnet decoder based
4 &# 8201
signal detection accuracy
model loading time
1 %, 81
detection speed
system adopts
results showed
research model
dnn method
cpu usage
8 %,
3 %,
25 %,
time performance
suppress inter
subcarrier interference
optimizing real
fully characterize
essential characteristics
deep learning
channel estimation
average latency
4 ghz
006 %.
004 %.
status_str publishedVersion
title SER of each model on the dataset.
title_full SER of each model on the dataset.
title_fullStr SER of each model on the dataset.
title_full_unstemmed SER of each model on the dataset.
title_short SER of each model on the dataset.
title_sort SER of each model on the dataset.
topic Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
symbol error rate
simulation training set
simulation test set
resource consumption assessment
reducing resource consumption
ofdm systems effectively
modulation error rate
broad application prospects
50 &# 8201
missed detection rates
false detection rates
moderate memory usage
dnn cascade structure
achieved significant results
limited detection accuracy
improving detection accuracy
driven detection system
7 %, 18
enhanced signal detection
manually designed features
dcnet decoder based
4 &# 8201
signal detection accuracy
model loading time
1 %, 81
detection speed
system adopts
results showed
research model
dnn method
cpu usage
8 %,
3 %,
25 %,
time performance
suppress inter
subcarrier interference
optimizing real
fully characterize
essential characteristics
deep learning
channel estimation
average latency
4 ghz
006 %.
004 %.