Unsupervised Learning and Adaptive Classification of Neuromorphic Tactile Encoding of Textures.

In this work, we investigated the classification of texture by neuromorphic tactile encoding and an unsupervised learning method. Additionally, we developed an adaptive classification algorithm to detect and characterize the presence of new texture data. The neuromorphic tactile encoding of textures from a multilayer tactile sensor was based on the physical structure and afferent spike signaling of human glabrous skin mechanoreceptors. We explored different neuromorphic spike pattern metrics and dimensionality reduction techniques in order to maximize classification accuracy while improving computational efficiency. Using a dataset composed of 3 textures, we showed that unsupervised learning of the neuromorphic tactile encoding data had high classification accuracy (mean=86.46%, sd=5.44%). Moreover, the adaptive classification algorithm was successful at determining that there were 3 underlying textures in the training dataset. In this work, tactile information is transformed into neuromorphic spiking activity that can be used as a stimulation pattern to elicit texture sensation for prosthesis users. Furthermore, we provide the basis for identifying new textures adaptively which can be used to actively modify stimulation patterns to improve texture discrimination for the user.