QAM classification methods by SVM machine learning for improved optical interconnection

Wang, Chang; Du, Jiangbing; Chen, Guoyao; Wang, Haoyang; Sun, Lin; Xu, Ke; Liu, Bo; He, Zuyuan

doi:10.1016/j.optcom.2019.03.058

Cited by 22 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this technique required high SNR to achieve high accuracy. Wang et al [36] introduced MC by using ML techniques. The features in the given signal were extracted via discrete wavelet transform (DWT) and given as input to SVM.…”

Section: Amc With MLmentioning

confidence: 99%

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

et al. 2021

View full text Add to dashboard Cite

The automatic modulation classification (AMC) of a detected signal has gained considerable prominence in recent years owing to its numerous facilities. Numerous studies have focused on feature-based AMC. However, improving accuracy under low signal-to-noise ratio (SNR) rates is a serious issue in AMC. Moreover, research on the enhancement of AMC performance under low and high SNR rates is limited. Motivated by these issues, this study proposes AMC using a feature clustering-based two-lane capsule network (AMC2N). In the AMC2N, accuracy of the MC process is improved by designing a new two-layer capsule network (TL-CapsNet), and classification time is reduced by introducing a new feature clustering approach in the TL-CapsNet. Firstly, the AMC2N executes blind equalization, sampling, and quantization in trilevel preprocessing. Blind equalization is executed using a binary constant modulus algorithm to avoid intersymbol interference. To extract features from the preprocessed signal and classify signals accurately, the AMC2N employs the TL-CapsNet, in which individual lanes are incorporated to process the real and imaginary parts of the signal. In addition, it is robust to SNR variations, that is, low and high SNR rates. The TL-CapsNet extracts features from the real and imaginary parts of the given signal, which are then clustered based on feature similarity. For feature extraction and clustering, the dynamic routing procedure of the TL-CapsNet is adopted. Finally, classification is performed in the SoftMax layer of the TL-CapsNet. This study proves that the AMC2N outperforms existing methods, particularly, convolutional neural network(CNN), Robust-CNN (R-CNN), curriculum learning(CL), and Local Binary Pattern (LBP), in terms of accuracy, precision, recall, F-score, and computation time. All metrics are validated in two scenarios, and the proposed method shows promising results in both.

show abstract

Section: Amc With MLmentioning

confidence: 99%

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recognizing and classifying the vibration events along the sensing fiber is a typical multi-classification problem. There are several kinds of multi-class strategies have been successfully used for multi-class recognition and classification [28]. Based on the sample numbers, a kind of one-versus-one (OVO) multi-class strategy is used to realize the event recognition in this paper [29].…”

Section: B Feature Extractionmentioning

confidence: 99%

Variational Mode Decomposition-Based Event Recognition in Perimeter Security Monitoring With Fiber Optic Vibration Sensor

et al. 2019

View full text Add to dashboard Cite

Recognition of different kinds of human intrusions from the environmental disturbance with high efficiency is still a challenging task in perimeter security monitoring with fiber optic vibration sensor, since the vibration signals induced by these events are highly similar to each other, and it can not be directly discriminated by the signals. In this paper, an intelligent event recognition scheme is proposed to improve its performance in complicated environmental applications. In this event recognition scheme, a variational mode decomposition based kurtosis feature combined with a zero crossing rate feature is used as the input feature vectors. A support vector machine is used to classify the input feature vectors into the corresponding categories. A series of field tests show that the proposed scheme can accurately and rapidly classify wind disturbance and three typical patterns of human intrusions such as waggling the fence, climbing the fence and knocking the fence. The average identification rate of 100.0% and 96.9% are achieved for the wind disturbance and human intrusion events, respectively. The recognition processing time can be controlled less than 0.4 s. Thus, the intelligent event recognition scheme can fully satisfy the online monitoring requirements for practical applications.

show abstract

“…An SVM classifier was first trained and applied in nonlinearity compensation for combating nonlinear phase noise in amplitude phase-shift keying (APSK) system [14]. Recently, five SVM methods including: 1) the one versus rest (OvR) where the multi-classifiers are built one by one considering the rest belonging to the other class with the concept of binary SVM; 2) the symbol encoding; 3) the binary encoding (BE) is based on whether each bit of label feature is 0 or 1; 4) the constellation rows and columns (RC); and 5) the in-phase and quadrature components (IQC) were investigated and IQC indicates the optimal results among all five in terms of computing resource and hardware storage [15].…”

Section: B Support Vector Machinementioning

confidence: 99%

Machine Learning for Fiber Nonlinearity Mitigation in Long-Haul Coherent Optical Transmission Systems : Invited Paper

Liu

Yang

2019

2019 IEEE 11th International Conference on Advanced Infocomm Technology (ICAIT)

View full text Add to dashboard Cite

Fiber nonlinearities from Kerr effect are considered as major constraints for enhancing the transmission capacity in current optical transmission systems. Digital nonlinearity compensation techniques such as digital backpropagation can perform well but require high computing resources. Machine learning can provide a low complexity capability especially for high-dimensional classification problems. Recently several supervised and unsupervised machine learning techniques have been investigated in the field of fiber nonlinearity mitigation. This paper offers a brief review of the principles, performance and complexity of these machine learning approaches in the application of nonlinearity mitigation.

show abstract

QAM classification methods by SVM machine learning for improved optical interconnection

Cited by 22 publications

References 20 publications

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

Variational Mode Decomposition-Based Event Recognition in Perimeter Security Monitoring With Fiber Optic Vibration Sensor

Machine Learning for Fiber Nonlinearity Mitigation in Long-Haul Coherent Optical Transmission Systems : Invited Paper

Contact Info

Product

Resources

About