Development and Comparative Study of Effects of Training Algorithms on Performance of Artificial Neural Network Based Analog and Digital Automatic Modulation Recognition

Abstract

This paper proposes two new classifiers that automatically recognise twelve combined analog and digital modulated signals without any a priori knowledge of the modulation schemes and the modulation parameters. The classifiers are developed using pattern recognition approach. Feature keys extracted from the instantaneous amplitude, instantaneous phase and the spectrum symmetry of the simulated signals are used as inputs to the artificial neural network employed in developing the classifiers. The two developed classifiers are trained using scaled conjugate gradient (SCG) and conjugate gradient (CONJGRAD) training algorithms. Sample results of the two classifiers show good success recognition performance with an average overall recognition rate above 99.50% at signal-to-noise ratio (SNR) value from 0 dB and above with the two training algorithms employed and an average overall recognition rate slightly above 99.00% and 96.40% respectively at-5 dB SNR value for SCG and CONJGRAD training algorithms. The comparative performance evaluation of the two developed classifiers using the two training algorithms shows that the two training algorithms have different effects on both the response rate and efficiency of the two developed artificial neural networks classifiers. In addition, the result of the performance evaluation carried out on the overall success recognition rates between the two developed classifiers in this study using pattern recognition approach with the two training algorithms and one reported classifier in surveyed literature using decision-theoretic approach shows that the classifiers developed in this study perform favourably with regard to accuracy and performance probability as compared to classifier presented in previous study.

MCU Based Edge Computing Platform for Liquid Level Measurement

“…The performance of the AI model is often assessed using the confusion matrix, which categorizes predicted results into four classes: true positive (TP), false positive (FP), true negative (TN), and false negative (FN). These metrics are used to calculate various performance indicators, including accuracy as defined in formula (5), true positive rate (TPR), false positive rate (FPR), true negative rate (TNR), and false negative rate (FNR).…”

“…Furthermore, given the limited resources of the endpoint platform, careful consideration of AI model selection and hyperparameter optimization for edge computing is crucial. Artificial neural networks (ANN) model, is simple yet effective for classification tasks, represent a viable candidate for this study [5], [6]. Moreover, Bayesian optimization emerges as a popular method for efficient hyperparameter optimization, offering convenient and efficient.…”

Application of machine learning techniques and empirical mode decomposition for the classification of analog modulated signals

“…The monitoring and classification of analog communication signals play an important role in military and civilian applications regarding the monitoring of non-authorised transmitters; electronic surveillance; and cognitive radio and reconfigurable communication systems [1] [2].…”

“…In the second group, the classification is obtained by the pattern recognition of some features estimated in the time or frequency domain on the signal under investigation [1] [2][8]- [16]. Moreover, the classification performance of the statistical pattern recognition methods typically decreases along with the increasing ABSTRACT In this article, an automatic Analog Modulation Classifier based on Empirical mode decomposition and Machine learning approaches (AMC-EM) is proposed.…”

Performance of Feature-Based Techniques for Automatic Digital Modulation Recognition and Classification—A Review

“…However, these shortcomings can be addressed via automatic modulation recognition (AMR). AMR is more powerful than MMR because it integrates an automatic modulation recognizer into an electronic receiver [2].…”