Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications
Recurrent neural networks have been shown to outperform other architectures when processing temporally correlated data, such as from wireless communication signals. However, compared to other architectures, such as convolutional neural networks, recurrent neural networks can suffer from drastically...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/13/4706 |
| _version_ | 1797408224999112704 |
|---|---|
| author | Megan O. Moore R. Michael Buehrer William Chris Headley |
| author_facet | Megan O. Moore R. Michael Buehrer William Chris Headley |
| author_sort | Megan O. Moore |
| collection | DOAJ |
| description | Recurrent neural networks have been shown to outperform other architectures when processing temporally correlated data, such as from wireless communication signals. However, compared to other architectures, such as convolutional neural networks, recurrent neural networks can suffer from drastically longer training and evaluation times due to their inherent sample-by-sample data processing, while traditional usage of both of these architectures assumes a fixed observation interval during both training and testing, the sample-by-sample processing capabilities of recurrent neural networks opens the door for alternative approaches. Rather than assuming that the testing and observation intervals are equivalent, the observation intervals can be “decoupled” or set independently. This can potentially reduce training times and will allow for trained networks to be adapted to different applications without retraining. This work illustrates the benefits and considerations needed when “decoupling” these observation intervals for spectrum sensing applications, using modulation classification as the example use case. The sample-by-sample processing of RNNs also allows for the relaxation of the typical requirement of a fixed time duration of the signals of interest. Allowing for variable observation intervals is important in real-time applications like cognitive radio where decisions need to be made as quickly and accurately as possible as well as in applications like electronic warfare in which the sequence length of the signal of interest may be unknown. This work examines a real-time post-processing method called “just enough” decision making that allows for variable observation intervals. In particular, this work shows that, intuitively, this method can be leveraged to process less data (i.e., shorter observation intervals) for simpler inputs (less complicated signal types or channel conditions). Less intuitively, this works shows that the “decoupling” is dependent on appropriate training to avoid bias and ensure generalization. |
| first_indexed | 2024-03-09T03:55:19Z |
| format | Article |
| id | doaj.art-2703ec98341e4943a072616760c9411f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:55:19Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2703ec98341e4943a072616760c9411f2023-12-03T14:21:40ZengMDPI AGSensors1424-82202022-06-012213470610.3390/s22134706Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing ApplicationsMegan O. Moore0R. Michael Buehrer1William Chris Headley2Hume Center for National Security and Technology, Virginia Tech, Blacksburg, VA 24061, USADepartment of Electrical & Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USAHume Center for National Security and Technology, Virginia Tech, Blacksburg, VA 24061, USARecurrent neural networks have been shown to outperform other architectures when processing temporally correlated data, such as from wireless communication signals. However, compared to other architectures, such as convolutional neural networks, recurrent neural networks can suffer from drastically longer training and evaluation times due to their inherent sample-by-sample data processing, while traditional usage of both of these architectures assumes a fixed observation interval during both training and testing, the sample-by-sample processing capabilities of recurrent neural networks opens the door for alternative approaches. Rather than assuming that the testing and observation intervals are equivalent, the observation intervals can be “decoupled” or set independently. This can potentially reduce training times and will allow for trained networks to be adapted to different applications without retraining. This work illustrates the benefits and considerations needed when “decoupling” these observation intervals for spectrum sensing applications, using modulation classification as the example use case. The sample-by-sample processing of RNNs also allows for the relaxation of the typical requirement of a fixed time duration of the signals of interest. Allowing for variable observation intervals is important in real-time applications like cognitive radio where decisions need to be made as quickly and accurately as possible as well as in applications like electronic warfare in which the sequence length of the signal of interest may be unknown. This work examines a real-time post-processing method called “just enough” decision making that allows for variable observation intervals. In particular, this work shows that, intuitively, this method can be leveraged to process less data (i.e., shorter observation intervals) for simpler inputs (less complicated signal types or channel conditions). Less intuitively, this works shows that the “decoupling” is dependent on appropriate training to avoid bias and ensure generalization.https://www.mdpi.com/1424-8220/22/13/4706modulation classificationradio frequency machine learningrecurrent neural networksspectrum sensing |
| spellingShingle | Megan O. Moore R. Michael Buehrer William Chris Headley Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications Sensors modulation classification radio frequency machine learning recurrent neural networks spectrum sensing |
| title | Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications |
| title_full | Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications |
| title_fullStr | Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications |
| title_full_unstemmed | Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications |
| title_short | Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications |
| title_sort | decoupling rnn training and testing observation intervals for spectrum sensing applications |
| topic | modulation classification radio frequency machine learning recurrent neural networks spectrum sensing |
| url | https://www.mdpi.com/1424-8220/22/13/4706 |
| work_keys_str_mv | AT meganomoore decouplingrnntrainingandtestingobservationintervalsforspectrumsensingapplications AT rmichaelbuehrer decouplingrnntrainingandtestingobservationintervalsforspectrumsensingapplications AT williamchrisheadley decouplingrnntrainingandtestingobservationintervalsforspectrumsensingapplications |