This study, conducted by Zhang et al., studied how fiber memristor-based technology can be utilized to monitor sleep patterns and its accuracy. The fiber memristor was synthesized with Ag/MoS2 fiber, and atomic force microscopy (AFM) was used to assess the film morphology. To assess sleep analytics, EEG signals were processed through a Markov transition field (MTF) and snoring was processed through Mel-frequency cepstral coefficients. This allowed for feature classification through a convolutional neural network-based audio classifier. In detecting snoring, accuracy was 94.8%, and in sleep stage classification, accuracy was 95.4%. In multimodal classification, accuracy was 93.5%. The results also supported that fiber memristor-based sleep monitoring systems are more dependable and energy-saving.