skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: 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.  more » « less
Award ID(s):
1849417
PAR ID:
10277343
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Proceedings of IEEE Biomedical Circuits and Systems
Page Range / eLocation ID:
1 to 4
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; (, Soft Robotics)
    null (Ed.)
    The compliant nature of soft fingers allows for safe and dexterous manipulation of objects by humans in an unstructured environment. A soft prosthetic finger design with tactile sensing capabilities for texture discrimination and subsequent sensory stimulation has the potential to create a more natural experience for an amputee. In this work, a pneumatically actuated soft biomimetic finger is integrated with a textile neuromorphic tactile sensor array for a texture discrimination task. The tactile sensor outputs were converted into neuromorphic spike trains, which emulate the firing pattern of biological mechanoreceptors. Spike-based features from each taxel compressed the information and were then used as inputs for the support vector machine classifier to differentiate the textures. Our soft biomimetic finger with neuromorphic encoding was able to achieve an average overall classification accuracy of 99.57% over 16 independent parameters when tested on 13 standardized textured surfaces. The 16 parameters were the combination of 4 angles of flexion of the soft finger and 4 speeds of palpation. To aid in the perception of more natural objects and their manipulation, subjects were provided with transcutaneous electrical nerve stimulation to convey a subset of four textures with varied textural information. Three able-bodied subjects successfully distinguished two or three textures with the applied stimuli. This work paves the way for a more human-like prosthesis through a soft biomimetic finger with texture discrimination capabilities using neuromorphic techniques that provide sensory feedback; furthermore, texture feedback has the potential to enhance user experience when interacting with their surroundings. 
    more » « less
  2. ; ; ; ; ; ; ; ; (, IEEE Sensors)
    null (Ed.)
    Soft robotic fingers provide enhanced flexibility and dexterity when interacting with the environment. The capability of soft fingers can be further improved by integrating them with tactile sensors to discriminate various textured surfaces. In this work, a flexible 3x3 fabric-based tactile sensor array was integrated with a soft, biomimetic finger for a texture discrimination task. The finger palpated seven different textured plates and the corresponding tactile response was converted into neuromorphic spiking patterns, mimicking the firing pattern of mechanoreceptors in the skin. Spike-based feature metrics were used to classify different textures using the support vector machine (SVM) classifier. The sensor was able to achieve an accuracy of 99.21% when two features, mean spike rate and average inter-spike interval, from each taxel were used as inputs into the classifier. The experiment showed that an inexpensive, soft, biomimetic finger combined with the flexible tactile sensor array can potentially help users perceive their environment better. 
    more » « less
  3. ; ; ; ; ; (, Scientific Reports)
    Abstract Trial-by-trial texture classification analysis and identifying salient texture related EEG features during active touch that are minimally influenced by movement type and frequency conditions are the main contributions of this work. A total of twelve healthy subjects were recruited. Each subject was instructed to use the fingertip of their dominant hand’s index finger to rub or tap three textured surfaces (smooth flat, medium rough, and rough) with three levels of movement frequency (approximately 2, 1 and 0.5 Hz). EEG and force data were collected synchronously during each touch condition. A systematic feature selection process was performed to select temporal and spectral EEG features that contribute to texture classification but have low contribution towards movement type and frequency classification. A tenfold cross validation was used to train two 3-class (each for texture and movement frequency classification) and a 2-class (movement type) Support Vector Machine classifiers. Our results showed that the total power in the mu (8–15 Hz) and beta (16–30 Hz) frequency bands showed high accuracy in discriminating among textures with different levels of roughness (average accuracy > 84%) but lower contribution towards movement type (average accuracy < 65%) and frequency (average accuracy < 58%) classification. 
    more » « less
  4. ; ; (, IEEE Neural Engineering)
    State-of-the-art tactile sensing arrays are not scalable to large numbers of sensing units due to their raster-scanned process. This interface process results in a high degree of wiring complexity and a tradeoff between spatial and temporal resolution. In this paper, we present a new neuromimetic tactile sensing scheme that allows for single-wire signal transduction and asynchronous signal transmission - without the incorporation of electronics into each sensing element. A prototype device with spatial frequency encoding was developed using flexible fabric-based e-textile materials, and the ability of this new sensing scheme was demonstrated through a texture discrimination task. Overall, the neuromimetic spatial frequency encoded sensor array had comparable performance to the state-of-the-art tactile sensor array and achieved a classification accuracy of 86.58%. Future tactile sensing systems and electronic skins can emulate the spatial frequency encoding architecture presented here to become dense and numerous while retaining excellent temporal resolution. 
    more » « less
  5. ; (, Neuromorphic Computing and Engineering)
    Abstract Spike-timing-dependent plasticity (STDP) is an unsupervised learning mechanism for spiking neural networks that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve 24.56% higher accuracy and 3.5 × faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to ak-means clustering approach. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email