Accurate Phase Detection for ZigBee Using Artificial Neural Network

The IEEE802.15.4 standard has been widely used in modern industry due to its several benefits for stability, scalability, and enhancement of wireless mesh networking. This uses a physical layer binary phase-shift keying (BPSK) modulation can be operated with two frequency bands, 868 915 MHz. noise could interfere the BPSK signal, which causes distortion signal before arrival at receiver. Therefore, filtering from is essential ensure carrying sender receiver less error. removing necessary mitigate negative sequences increase capability industrial sensor networks. Moreover, researchers have reported positive impact utilizing Kalmen filter detecting modulated side different communication systems, including ZigBee. Meanwhile, artificial neural network (ANN) machine learning (ML) models outperformed results predicting signals detection classification purposes. paper develops predictive method enhance performance modulation. First, simulation-based model generate personal area (WPAN) standard. Then, Gaussian was injected into simulation model. To reduce phase signals, recurrent networks (RNN) implemented integrated estimate BPSK’s signal. We evaluated our predictive-detection RNN using mean square error (MSE), correlation coefficient, recall, F1-score metrics. result shows that superior existing low MSE coefficient (R-value) metric signal-to-noise (SNR) values. In addition, RNN-based scored 98.71% 96.34% based on recall F1-score, respectively.