Recurrent Neural Detection of Time–Frequency Overlapped . . .
75
5 Conclusion
In this paper, a more robust method is proposed for wireless signal interference
detection at low SINR and is capable of localizing to each interference signal
sampling point. The results show that the model can implement the interference detection which not applicable to traditional methods, and the detection
accuracy is better than other neural network models in the time–frequency overlapped interfering signal. We believe the result can be used in interference detection in complex communication environments. However, the experiment proves
that the detection result is relatively poor for the case where the SINR is lower
than 6 db. So we will work on how to improve detection performance under low
SINR condition next.
References
1. Rayanchu S, Patro A, Banerjee S (2011) Airshark: detecting non-WiFi RF devices
using commodity WiFi hardware. In: ACM SIGCOMM conference on internet
measurement conference
2. Lakshminarayanan K, Sapra S, Seshan S, Steenkiste P (2009) RFDump: an architecture for monitoring the wireless ether. In: International conference on emerging
networking experiments & technologies
3. Chen X, Chen H, Chen Y (2011) Spectrum sensing for cognitive ultra-wideband
based on fractal dimensions. In: Fourth international workshop on Chaos-fractals
theories & applications
4. Merchant K, Revay S, Stantchev G, Nousain B (2018) Deep learning for RF device
fingerprinting in cognitive communication networks. IEEE J Sel Top Sig Process
12(1):160–167
5. Sainath TN, Li B (2016) Modeling time-frequency patterns with LSTM vs. convolutional architectures for LVCSR tasks. In: Interspeech
6. Mirza AH, Cosan S (2018) Computer network intrusion detection using sequential
LSTM neural networks autoencoders. In: 2018 26th signal processing and communications applications conference (SIU), May 2018, pp 1–4
7. O’Shea TJ, Clancy TC, McGwier RW (2016) Recurrent neural radio anomaly
detection. CoRR, arXiv:1611.00301
8. Malhotra P, Vig L, Shroff G, Agarwal P (2015) Long short term memory networks
for anomaly detection in time series. In: Proceedings. Presses universitaires de
Louvain, p 89
9. Xiao Q, Si Y (2017) Time series prediction using graph model. In: 2017 3rd IEEE
international conference on computer and communications (ICCC), pp 1358–1361
10. Cui Z, Ke R, Wang Y (2018) Deep bidirectional and unidirectional LSTM recurrent
neural network for network-wide traffic speed prediction. CoRR, arXiv:1801.02143
11. Chen Y, Qian J, Yang J, Jin Z (2016) Face alignment with cascaded bidirectional
LSTM neural networks. In: 2016 23rd international conference on pattern recognition (ICPR), pp 313–318
12. Kolbk M, Tan Z, Jensen J (2016) Speech enhancement using long short-term memory based recurrent neural networks for noise robust speaker verification. In: 2016
IEEE spoken language technology workshop (SLT), pp 305–311
75
5 Conclusion
In this paper, a more robust method is proposed for wireless signal interference
detection at low SINR and is capable of localizing to each interference signal
sampling point. The results show that the model can implement the interference detection which not applicable to traditional methods, and the detection
accuracy is better than other neural network models in the time–frequency overlapped interfering signal. We believe the result can be used in interference detection in complex communication environments. However, the experiment proves
that the detection result is relatively poor for the case where the SINR is lower
than 6 db. So we will work on how to improve detection performance under low
SINR condition next.
References
1. Rayanchu S, Patro A, Banerjee S (2011) Airshark: detecting non-WiFi RF devices
using commodity WiFi hardware. In: ACM SIGCOMM conference on internet
measurement conference
2. Lakshminarayanan K, Sapra S, Seshan S, Steenkiste P (2009) RFDump: an architecture for monitoring the wireless ether. In: International conference on emerging
networking experiments & technologies
3. Chen X, Chen H, Chen Y (2011) Spectrum sensing for cognitive ultra-wideband
based on fractal dimensions. In: Fourth international workshop on Chaos-fractals
theories & applications
4. Merchant K, Revay S, Stantchev G, Nousain B (2018) Deep learning for RF device
fingerprinting in cognitive communication networks. IEEE J Sel Top Sig Process
12(1):160–167
5. Sainath TN, Li B (2016) Modeling time-frequency patterns with LSTM vs. convolutional architectures for LVCSR tasks. In: Interspeech
6. Mirza AH, Cosan S (2018) Computer network intrusion detection using sequential
LSTM neural networks autoencoders. In: 2018 26th signal processing and communications applications conference (SIU), May 2018, pp 1–4
7. O’Shea TJ, Clancy TC, McGwier RW (2016) Recurrent neural radio anomaly
detection. CoRR, arXiv:1611.00301
8. Malhotra P, Vig L, Shroff G, Agarwal P (2015) Long short term memory networks
for anomaly detection in time series. In: Proceedings. Presses universitaires de
Louvain, p 89
9. Xiao Q, Si Y (2017) Time series prediction using graph model. In: 2017 3rd IEEE
international conference on computer and communications (ICCC), pp 1358–1361
10. Cui Z, Ke R, Wang Y (2018) Deep bidirectional and unidirectional LSTM recurrent
neural network for network-wide traffic speed prediction. CoRR, arXiv:1801.02143
11. Chen Y, Qian J, Yang J, Jin Z (2016) Face alignment with cascaded bidirectional
LSTM neural networks. In: 2016 23rd international conference on pattern recognition (ICPR), pp 313–318
12. Kolbk M, Tan Z, Jensen J (2016) Speech enhancement using long short-term memory based recurrent neural networks for noise robust speaker verification. In: 2016
IEEE spoken language technology workshop (SLT), pp 305–311