The artificial tactile perception system of this work utilizes a fully connected spiking neural network (SNN) comprising two layers. Its architecture is streamlined and energy-efficient as it directly integrates spiking tactile neurons with piezoresistive sensors and Pt/NbOx/TiN memristors as input neurons. These spiking tactile neurons possess the ability to perceive and integrate pressure stimuli from multiple sensors and encode the information into rate-coded electrical spikes, closely resembling the behavior of a biological tactile neuron. The system's real-time information processing capability is demonstrated through an artificial perceptual learning system that successfully encodes and decodes the Morse code; the artificial perceptual learning system accurately recognizes and displays 26 English letters. Furthermore, the artificial tactile perception system is evaluated for the recognition of the MNIST data set, achieving a classification accuracy of 85.7% with the supervised spiking-rate-dependent plasticity learning rule. The key advantages of this artificial tactile perception system are its simple structure and high efficiency, which contributes to its practicality for various real-world applications.
Keywords: Morse code; artificial tactile perception system; spiking neural network; spiking neuron; spiking tactile neuron; threshold switching memristor.