Random Graph-Based M-QAM Classification for MIMO Systems

Sarfraz, Mubashar; Alam, S M Shafiul; Ghauri, Sajjad A.; Mahmood, Asad; Akram, Muhammad Nadeem; Rehman, Muhammad Javvad ur; Sohail, Muhammad Farhan; Kebedew, Teweldebrhan Mezgebo

doi:10.1155/2022/9419764

Cited by 5 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e input symbols are rst modulated and passed through a channel that adds the additive white Gaussian noise. At the receiver end, the rst received signal is preprocessed; demodulation of the received signal and detection of the transmitted signal (information-bearing symbols) are executed after the modulation format is classi ed [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification

AlJubayrin

Sarfraz

Ghauri

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Modulation classification is one of the essential requirements in the various cognitive radio applications where prior information about the incoming signal is unknown. The modulation classification using a pattern recognition approach can be achieved in 2 modules: first, parameters are extracted from the noisy signal, and then feature selection is carried out using a Gabor filter network (GFN). In the second module, features are exploited for classification purposes. The modulation formats considered for the purpose of classification are BPSK, QPSK, 8PSK, 16PSK, 64PSK, 4FSK, 8FSK, 16FSK, QAM, 8QAM, 16QAM, 32QAM, and 64QAM. The Gabor filter parameters and weights of the adaptive filter are attuned using the Delta rule and recursive least square (RLS) algorithm until the cost function is minimized. In the end, the artificial bee colony (ABC) algorithm is used to optimize the Gabor parameters as well as the classifier’s performance. The simulation results show the supremacy of the proposed classifier structure.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification

AlJubayrin

Sarfraz

Ghauri

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…The reliability of any method is dependent on accuracy; if the accuracy is higher, the method is considered accurate and reliable. Cumulants are widely adopted in classification problems such as modulation recognition [ 54 , 55 ]. To the best of our knowledge, this approach is seldom explored for fMRI analysis.…”

Section: Experimental Methodologymentioning

confidence: 99%

A Cumulants-Based Human Brain Decoding

Zafar

Rehman

Alam

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Human cognition is influenced by the way the nervous system processes information and is linked to this mechanical explanation of the human body’s cognitive function. Accuracy is the key emphasis in neuroscience which may be enhanced by utilising new hardware, mathematical, statistical, and computational methodologies. Feature extraction and feature selection also play a crucial function in gaining improved accuracy since the proper characteristics can identify brain states efficiently. However, both feature extraction and selection procedures are dependent on mathematical and statistical techniques which implies that mathematical and statistical techniques have a direct or indirect influence on prediction accuracy. The forthcoming challenges of the brain-computer interface necessitate a thorough critical understanding of the complicated structure and uncertain behavior of the brain. It is impossible to upgrade hardware periodically, and thus, an option is necessary to collect maximum information from the brain against varied actions. The mathematical and statistical combination could be the ideal answer for neuroscientists which can be utilised for feature extraction, feature selection, and classification. That is why in this research a statistical technique is offered together with specialised feature extraction and selection methods to increase the accuracy. A score fusion function is changed utilising an enhanced cumulants-driven likelihood ratio test employing multivariate pattern analysis. Functional MRI data were acquired from 12 patients versus a visual test that comprises of pictures from five distinct categories. After cleaning the data, feature extraction and selection were done using mathematical approaches, and lastly, the best match of the projected class was established using the likelihood ratio test. To validate the suggested approach, it is compared with the current methods reported in recent research.

show abstract

“…They introduced a softdecision fusion technique to find the classification result. In [28], a classifier based on random graph theory is employed to identify M-Quadrature Amplitude Modulation (QAM) signals for MIMO Systems under unsatisfactory channel conditions. In this approach, the features obtained using discrete Fourier transform and sparse transform are used by the undirected random graph for classifying the M-QAM signals.…”

Section: Related Workmentioning

confidence: 99%

A Semi-Supervised Modulation Identification in MIMO Systems: A Deep Learning Strategy

et al. 2022

View full text Add to dashboard Cite

Accurate modulation identification of the received signals is undoubtedly a central component in multiple-input multiple-output (MIMO) communication systems, facilitating the demodulation task. This study presents a flexible and semi-supervised deep learning-driven strategy for automatic modulation identification. To this end, the multiclass classification problem is treated as multiple binary discrimination problems to address modulation identification challenges. Here, we merge the features extraction ability of the Generative Adversarial Network (GAN) model and the semi-supervised anomaly detection scheme, the one-class Support Vector Machine (1SVM). Essentially, a single GAN-based 1SVM detector is trained using training data of each class, with the samples of that class as inlier and all other samples as anomalies (i.e., one-vs.-rest). The 1SVM is trained using the features learned by the GAN model. A dataset consisting of three digital modulations (i.e., BFSK, CPFSK, and PAM4) and three analog modulations (i.e., AM-DSB, AM-SSB, and WB-FM), widely used in wireless communications systems, is employed to demonstrate the performance of the considered deep learning-based methods. Compared to Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN)-based 1SVM, the conventional GAN, DBN, and RBM with softmax layer as discriminator layer, the proposed GAN-based 1SVM detector offers superior discrimination performance of modulation types by achieving an averaged accuracy of 0.951 and F1-Score of 0.954. Results also showed that the GAN-1SVM detector dominates the state-of-the-art modulation classification techniques.

show abstract

Random Graph-Based M-QAM Classification for MIMO Systems

Cited by 5 publications

References 46 publications

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification

A Cumulants-Based Human Brain Decoding

A Semi-Supervised Modulation Identification in MIMO Systems: A Deep Learning Strategy

Contact Info

Product

Resources

About