2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019
DOI: 10.1109/spawc.2019.8815481
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

Abstract: 1 We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi. We employ deep learning algorithms trained on received samples taken from a 10 MHz band in the 2.4 GHz ISM Band. We obtain a classification accuracy of around 89.5% using any of four different deep neural network architectures: CNN, ResNet, CLDNN, and LSTM, which demonstrate the generality of the effectiveness o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
19
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 44 publications
(20 citation statements)
references
References 7 publications
0
19
0
Order By: Relevance
“…RF signal classification with DL has mostly been studied in the context of either Automatic Modulation Classification (AMC) [13], [14], [18] or Wireless Interference Identification (WII) [6]- [8]. These are essentially the same tasks with the difference being the signals involved.…”
Section: Literature Reviewmentioning
confidence: 99%
See 1 more Smart Citation
“…RF signal classification with DL has mostly been studied in the context of either Automatic Modulation Classification (AMC) [13], [14], [18] or Wireless Interference Identification (WII) [6]- [8]. These are essentially the same tasks with the difference being the signals involved.…”
Section: Literature Reviewmentioning
confidence: 99%
“…For WII, frequency domain representations have performed better since the frequency components of a signal remain more distinctive even under lower SNR. WII can appear as different use cases, such as classifying different UAVs [4], [9], [11], [20], detecting/classifying different Radar Waveforms [2], [21], identifying specific technologies in the ISM band [8], securing Global Navigation Satellite Systems (GNSS) signals [22], and more. Like time-domain representations, frequencydomain representations can also be kept as a vector of values (such as DFT coefficients) used in [4] or further transforms can be applied to make a PSD image, or STFT image (also known as a spectrogram), used in [9], [11] and others.…”
Section: Literature Reviewmentioning
confidence: 99%
“…This method exploits realtime extraction of envelope and model-aided spectral features, specifically designed considering the physical properties of the signals captured with commercial off-the-shelf (COTS) hardware. [7] studies the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies, i.e., Bluetooth, Zigbee, and WiFi. Four different deep neural network architectures, i.e., CNN, ResNet, CLDNN, and LSTM are used as the classifier, the research demonstrated the generality of the effectiveness of deep learning at the considered task.…”
Section: Introductionmentioning
confidence: 99%
“…The dataset contains received signals corresponding to 15 different channels of WiFi, Bluetooth, and ZigBee. Efficient training algorithms for this problem were investigated in [6] through training with only a subset of frequency bands, a subset of input vector samples, and a subset of SNR values.…”
Section: Introductionmentioning
confidence: 99%
“…We use the aforementioned datasets for modulation classification and channel identification to validate the proposed methods and obtained insights. We first start by improving the preliminary results on training SNR selection of [4] and [6], obtained through training with only the test SNR value. We then show that if we can only estimate a test SNR range, it is better to train with optimistic estimates.…”
mentioning
confidence: 99%