Recurrent Neural Detection
of Time–Frequency Overlapped
Interference Signals
Qianqian Wu, Zhuo Sun
(B) , and Xue Zhou
Wireless Signal Processing and Network Laboratory, Beijing University of Posts
and Telecommunications, Beijing 100876, China
{wuqq, zhuosun, 277210680}@bupt.edu.cn
Abstract. For interfering signals overlap with normal signals in both
time and frequency domain, it is difficult to detect them. Therefore,
this paper proposes a novel bidirectional recurrent neural network-based
interference detection method. By utilizing the ability of recurrent neural
network of extracting the nonlinear features of the time series context,
the model can get a prediction of following signal samples and calculate
the difference between prediction signal and original signal to do interference detection. The proposed method can achieve a better sensitivity
and determine the exact location of the complete interfering signal. In the
experiment part, we demonstrate the efficacy of this method in multiple
typical scenarios of time–frequency overlapped wireless signals.
1 Introduction
The development of wireless communication makes it be widely used in various
fields, but the electromagnetic environment is complex and changeable, and the
reliability of the communication system is still threatened by interference. Therefore, the anti-interference technology is necessary to ensure the communication
reliability, and the interference detection technology is the basis and key of the
communication anti-interference technology.
The purpose of interference detection is to determine whether there are interfering signals in received signals and then feed back to the transmitter or command center to take effective anti-interference measures. Traditional wireless
interference detection approaches include time domain and transform domainbased energy detection algorithm (e.g., consecutive mean excision (CME) and
forward consecutive mean excision (FCME)). Some approaches analyze the
received signal strength indicator (RSSI) samples in the frequency and time
domain [1,2] or to perform a cyclostationary signal analysis and blind signal
detection and other spectrum sensing techniques [3]. These methods can well
detect many kinds of interfering signals. However, there are many interfering
signals whose power is small and frequency is the same as original signals in the
c
Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 67–75, 2020.
https://doi.org/10.1007/978-981-15-0187-6_8
of Time–Frequency Overlapped
Interference Signals
Qianqian Wu, Zhuo Sun
(B) , and Xue Zhou
Wireless Signal Processing and Network Laboratory, Beijing University of Posts
and Telecommunications, Beijing 100876, China
{wuqq, zhuosun, 277210680}@bupt.edu.cn
Abstract. For interfering signals overlap with normal signals in both
time and frequency domain, it is difficult to detect them. Therefore,
this paper proposes a novel bidirectional recurrent neural network-based
interference detection method. By utilizing the ability of recurrent neural
network of extracting the nonlinear features of the time series context,
the model can get a prediction of following signal samples and calculate
the difference between prediction signal and original signal to do interference detection. The proposed method can achieve a better sensitivity
and determine the exact location of the complete interfering signal. In the
experiment part, we demonstrate the efficacy of this method in multiple
typical scenarios of time–frequency overlapped wireless signals.
1 Introduction
The development of wireless communication makes it be widely used in various
fields, but the electromagnetic environment is complex and changeable, and the
reliability of the communication system is still threatened by interference. Therefore, the anti-interference technology is necessary to ensure the communication
reliability, and the interference detection technology is the basis and key of the
communication anti-interference technology.
The purpose of interference detection is to determine whether there are interfering signals in received signals and then feed back to the transmitter or command center to take effective anti-interference measures. Traditional wireless
interference detection approaches include time domain and transform domainbased energy detection algorithm (e.g., consecutive mean excision (CME) and
forward consecutive mean excision (FCME)). Some approaches analyze the
received signal strength indicator (RSSI) samples in the frequency and time
domain [1,2] or to perform a cyclostationary signal analysis and blind signal
detection and other spectrum sensing techniques [3]. These methods can well
detect many kinds of interfering signals. However, there are many interfering
signals whose power is small and frequency is the same as original signals in the
c
Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 67–75, 2020.
https://doi.org/10.1007/978-981-15-0187-6_8