A Cognitive Radio Spectrum Sensing Method for an OFDM Signal Based on Deep Learning and Cycle Spectrum

Pan, Guangliang; Li, Jun; Lin, Fei

doi:10.1155/2020/5069021

Cited by 25 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The K nearest neighbors (KNN) were harnessed for its efficacy in classification tasks, using data proximity as a metric. , Encoders were incorporated to harness their ability to distill information and represent data more compactly . CNN was chosen to leverage its proficiency in identifying spatial patterns . We treat each column as a sample, with each row representing fluorescence intensity at a specific wavelength, and we read the data sequentially.…”

Section: Resultsmentioning

confidence: 99%

Machine-Learning-Enhanced Fluorescent Nanosensor Based on Carbon Quantum Dots for Heavy Metal Detection

Tian,

Lee,

Song

et al. 2024

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

Fluorescent nanomaterials such as carbon quantum dots (CQDs) have been widely utilized as optical nanosensors for the detection and imaging of chemical or biological species with their superior sensitivity and spatiotemporal monitoring capabilities. Even though the nanosensors originally provide high sensitivity, the potential limit of detection (LOD) could not be accurately utilized for real-world applications due to the absence of signal extraction near the noise level, which is significantly influenced by various environmental factors and conventional statistical methods. To address this issue, we have developed an optical signal processing technique based on machine learning to enhance the practical sensing performance of CQD nanosensors for heavy metal ion detection. Fluorescence spectra of the nanosensor are acquired under both normal conditions (absence of analytes, n = 786) and analyte conditions (presence of analytes with varying concentrations, n = 288). Seven different types of machine learning algorithms are systematically applied to a training data set of fluorescence features (n = 200). Our best model could distinguish the spectra of 10 nM and 100 pM Cu 2+ from just noise signals without analytes, which are 10 4 and 10 6 times enhanced LOD compared to the original detection limit (95 μM) providing accuracies of 90.69 and 70.41%, respectively. We further demonstrate that this technique could be universally applied for different types of analytes such as Hg 2+ , Pb 2+ , Cr 6+ , and Fe 3+ ions with distinct sensing performances. This technique can be up to 10 6 times lower than the LOD of the fluorescent nanosensors. Our approach is not limited to CQD nanosensors or metal ions but can also be directly applied to various types of fluorescent nanosensors and biochemical analytes.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine-Learning-Enhanced Fluorescent Nanosensor Based on Carbon Quantum Dots for Heavy Metal Detection

Tian,

Lee,

Song

et al. 2024

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

show abstract

“…Learning style Model Input feature PU prior information Pan et al [18] supervised CNN cycle spectrum OFDM frame Xie et al [19] supervised CNN covariance matrix -Ozdes et al [20] supervised CNN power spectrum -Zheng et al [21] supervised CNN power spectrum -Chew et al [22] supervised CNN spectrogram OFDM frame Liu et al [23] supervised CNN covariance matrix primary activity statistics Xie et al [24] supervised LSTM+CNN covariance matrix primary activity statistics Subekti et al [25] supervised DAE+SVM RGB image -…”

Section: Methodsmentioning

confidence: 99%

“…In [18−23], a convolutional neural network(CNN) is applied to spectrum sensing. Pan et al proposed a spectrum sensing method for orthogonal frequency division multiplexing (OFDM) signals based on deep learning and cyclic spectrum [18]. In that paper, the cyclic autocorrelation characteristics of the OFDM signal were analyzed, and the cyclic spectrum was obtained by using the time domain smooth fast Fourier transform accumulation algorithm.…”

Section: Introductionmentioning

confidence: 99%

Limited Data Spectrum Sensing Based on Semi-Supervised Deep Neural Network

Zhang

Zhao

2021

IEEE Access

View full text Add to dashboard Cite

Spectrum sensing methods based on deep learning require massive amounts of labeled samples. To address the scarcity of labeled samples in a real radio environment, this paper presents a spectrum sensing method based on semi-supervised deep neural network (SSDNN). Firstly, a deep neural network is established to extract the features of signals by using small amounts of labeled samples; Then, plenty of unlabeled samples are used for self-training process, and the ones with high confidence are marked with pseudo-label to expand the labeled dataset. Finally, the extended dataset is used to retrain the network. Plentiful experiments are carried out on a dataset of 124,800 samples. The results demonstrate that the proposed algorithm has good detection performance over multi-path fading channel and additive white Gaussian noise channel due to the utilization of a great deal of unlabeled dataset. When the labeled samples account for only 5% of the traditional fully supervised deep learning model and the SNR is higher than −13 dB, the detection probability of SSDNN is higher than 90%.

show abstract

“…In the context of using multiple modulation modes for signal transmission, the ability to correctly identify the modulated signal is the basis for demodulation. Since the cyclic spectrum distribution of the modulated signal presents a cyclostationary discrete characteristic on the cyclic frequency axis, modulation recognition can be achieved by utilizing the modulated signal with a sizeable cyclic spectrum amplitude value at the non-zero cyclic frequency and no amplitude value or small amplitude value of noise [26].…”

Section: B Adaptive Modulation Recognition Schemementioning

confidence: 99%

Model-Driven Deep Learning Scheme for Adaptive Transmission in MIMO-SCFDE System

Qiao

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Adaptive transmission (AT) is considered as one of the critical technologies to enhance the effectiveness of communication systems. In this paper, we propose a model-driven deep learning (DL) scheme for AT in multiple-input multiple-output single-carrier frequency-domain equalization (MIMO-SCFDE) systems, in which the adaptive modulation network (AMNet) and adaptive demodulation network (ADNet) are adopted to complete the modulation of the signal and the modulation recognition of the receiver. Under the target bit error rate (BER), the adaptive modulation (AM) scheme can adjust the modulation mode selection of different transmitting antennas adaptively according to the estimated channel information to improve the throughput. The features required by the AMNet are extracted from the received signal, and the labels are assigned according to the optimal modulation scheme got by analyzing the signal detection performance. Since the spectral correlation function has a powerful ability to suppress noise and the cyclic spectrum varies with the modulation mode, we take the preprocessed cyclic spectrogram as the input of ADNet to achieve the adaptive modulation recognition (AMR). Comparative experiments demonstrate that the proposed scheme gets better performance in terms of throughput and reliability in MIMO-SCFDE systems than the traditional scheme and the existing DL scheme.

show abstract

A Cognitive Radio Spectrum Sensing Method for an OFDM Signal Based on Deep Learning and Cycle Spectrum

Cited by 25 publications

References 26 publications

Machine-Learning-Enhanced Fluorescent Nanosensor Based on Carbon Quantum Dots for Heavy Metal Detection

Machine-Learning-Enhanced Fluorescent Nanosensor Based on Carbon Quantum Dots for Heavy Metal Detection

Limited Data Spectrum Sensing Based on Semi-Supervised Deep Neural Network

Model-Driven Deep Learning Scheme for Adaptive Transmission in MIMO-SCFDE System

Contact Info

Product

Resources

About