Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network

The accurate identification of channel-coding types plays a crucial role in wireless communication systems. The recognition of convolutional codes presents challenges, primarily due to their strong temporal dependencies, varying constraint lengths, and additional contamination from noise. However, e...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu Xu, Yixin Ma, Rui Shi, Juanjuan Li, Yijia Zhang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1000
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850229679054651392
author Lu Xu
Yixin Ma
Rui Shi
Juanjuan Li
Yijia Zhang
author_facet Lu Xu
Yixin Ma
Rui Shi
Juanjuan Li
Yijia Zhang
author_sort Lu Xu
collection DOAJ
description The accurate identification of channel-coding types plays a crucial role in wireless communication systems. The recognition of convolutional codes presents challenges, primarily due to their strong temporal dependencies, varying constraint lengths, and additional contamination from noise. However, existing algorithms often rely on manual feature extraction or are limited to a restricted number of coding types, rendering them inadequate for practical applications. To tackle this problem, we propose ConvLSTM-TFN (temporal feature network), an innovative blind-recognition network that integrates convolutional layers, long short-term memory (LSTM) networks, and a self-attention mechanism. The proposed approach enhances the acquisition of features from soft-decision sequence information, leading to improved recognition performance without necessitating prior knowledge of coding parameters, sequence starting positions, or other metadata. The experimental results demonstrate that our method is effective within a signal-to-noise ratio (SNR) range of 0 to 20 dB, achieving more than 90% recognition accuracy across 17 convolutional code types, with an average accuracy of 98.7%. Our method effectively distinguishes diverse coding features, surpassing existing models and establishing a new benchmark for channel-coding recognition.
format Article
id doaj-art-ebdce971deca4871a8fc9698bdd93dce
institution OA Journals
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-ebdce971deca4871a8fc9698bdd93dce2025-08-20T02:04:07ZengMDPI AGSensors1424-82202025-02-01254100010.3390/s25041000Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature NetworkLu Xu0Yixin Ma1Rui Shi2Juanjuan Li3Yijia Zhang4School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaThe accurate identification of channel-coding types plays a crucial role in wireless communication systems. The recognition of convolutional codes presents challenges, primarily due to their strong temporal dependencies, varying constraint lengths, and additional contamination from noise. However, existing algorithms often rely on manual feature extraction or are limited to a restricted number of coding types, rendering them inadequate for practical applications. To tackle this problem, we propose ConvLSTM-TFN (temporal feature network), an innovative blind-recognition network that integrates convolutional layers, long short-term memory (LSTM) networks, and a self-attention mechanism. The proposed approach enhances the acquisition of features from soft-decision sequence information, leading to improved recognition performance without necessitating prior knowledge of coding parameters, sequence starting positions, or other metadata. The experimental results demonstrate that our method is effective within a signal-to-noise ratio (SNR) range of 0 to 20 dB, achieving more than 90% recognition accuracy across 17 convolutional code types, with an average accuracy of 98.7%. Our method effectively distinguishes diverse coding features, surpassing existing models and establishing a new benchmark for channel-coding recognition.https://www.mdpi.com/1424-8220/25/4/1000channel-coding recognitionconvolutional codeswireless communicationtemporal feature networkdeep learning
spellingShingle Lu Xu
Yixin Ma
Rui Shi
Juanjuan Li
Yijia Zhang
Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
Sensors
channel-coding recognition
convolutional codes
wireless communication
temporal feature network
deep learning
title Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
title_full Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
title_fullStr Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
title_full_unstemmed Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
title_short Blind Recognition of Convolutional Codes Based on the ConvLSTM Temporal Feature Network
title_sort blind recognition of convolutional codes based on the convlstm temporal feature network
topic channel-coding recognition
convolutional codes
wireless communication
temporal feature network
deep learning
url https://www.mdpi.com/1424-8220/25/4/1000
work_keys_str_mv AT luxu blindrecognitionofconvolutionalcodesbasedontheconvlstmtemporalfeaturenetwork
AT yixinma blindrecognitionofconvolutionalcodesbasedontheconvlstmtemporalfeaturenetwork
AT ruishi blindrecognitionofconvolutionalcodesbasedontheconvlstmtemporalfeaturenetwork
AT juanjuanli blindrecognitionofconvolutionalcodesbasedontheconvlstmtemporalfeaturenetwork
AT yijiazhang blindrecognitionofconvolutionalcodesbasedontheconvlstmtemporalfeaturenetwork