Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention
Spectrum sensing is recognized as a viable strategy to alleviate the scarcity of spectrum resources and to optimize their usage. In this paper, considering the time-varying characteristics and the dependence on various timescales within a time series of samples composed of in-phase (I) and quadratur...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/528 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587486483709952 |
|---|---|
| author | Song Hong Weiqiang Xu |
| author_facet | Song Hong Weiqiang Xu |
| author_sort | Song Hong |
| collection | DOAJ |
| description | Spectrum sensing is recognized as a viable strategy to alleviate the scarcity of spectrum resources and to optimize their usage. In this paper, considering the time-varying characteristics and the dependence on various timescales within a time series of samples composed of in-phase (I) and quadrature (Q) component signals, we propose a multi-scale time-correlated perceptual attention model named MSTC-PANet. The model consists of multiple parallel temporal correlation perceptual attention (TCPA) modules, enabling us to extract features at different timescales and identify dependencies among features across various timescales. Our simulations show that MSTC-PANet significantly improves the detection of channel occupancy at low signal-to-noise ratios (SNR), particularly in untrained scenarios with lower SNR conditions and modulation uncertainties. The analysis of the ROC curve indicates that at an SNR of -20 dB, the proposed MSTC-PANet achieves a detection rate of 98% with a false alarm rate of 10%. Furthermore, MSTC-PANet, which has been trained using digital modulation techniques, also demonstrates applicability to analog modulation. |
| format | Article |
| id | doaj-art-34c06222505e4c038e7ca83203f00d40 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-34c06222505e4c038e7ca83203f00d402025-01-24T13:49:14ZengMDPI AGSensors1424-82202025-01-0125252810.3390/s25020528Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual AttentionSong Hong0Weiqiang Xu1School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSpectrum sensing is recognized as a viable strategy to alleviate the scarcity of spectrum resources and to optimize their usage. In this paper, considering the time-varying characteristics and the dependence on various timescales within a time series of samples composed of in-phase (I) and quadrature (Q) component signals, we propose a multi-scale time-correlated perceptual attention model named MSTC-PANet. The model consists of multiple parallel temporal correlation perceptual attention (TCPA) modules, enabling us to extract features at different timescales and identify dependencies among features across various timescales. Our simulations show that MSTC-PANet significantly improves the detection of channel occupancy at low signal-to-noise ratios (SNR), particularly in untrained scenarios with lower SNR conditions and modulation uncertainties. The analysis of the ROC curve indicates that at an SNR of -20 dB, the proposed MSTC-PANet achieves a detection rate of 98% with a false alarm rate of 10%. Furthermore, MSTC-PANet, which has been trained using digital modulation techniques, also demonstrates applicability to analog modulation.https://www.mdpi.com/1424-8220/25/2/528spectrum sensingmulti-scalecorrelationattentiondeep learning |
| spellingShingle | Song Hong Weiqiang Xu Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention Sensors spectrum sensing multi-scale correlation attention deep learning |
| title | Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention |
| title_full | Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention |
| title_fullStr | Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention |
| title_full_unstemmed | Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention |
| title_short | Spectrum Sensing in Very Low SNR Environment Using Multi-Scale Temporal Correlation Perception with Residual Attention |
| title_sort | spectrum sensing in very low snr environment using multi scale temporal correlation perception with residual attention |
| topic | spectrum sensing multi-scale correlation attention deep learning |
| url | https://www.mdpi.com/1424-8220/25/2/528 |
| work_keys_str_mv | AT songhong spectrumsensinginverylowsnrenvironmentusingmultiscaletemporalcorrelationperceptionwithresidualattention AT weiqiangxu spectrumsensinginverylowsnrenvironmentusingmultiscaletemporalcorrelationperceptionwithresidualattention |