Spike-based tactile pattern recognition using an extreme learning machine

Mahdi Rasouli, Chen Yi, Arindam Basu, Nitish V Thakor, Sunil Kukreja

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a biologically-inspired approach for tactile pattern recognition. Our aim is to develop a low-cost tactile module that can be applied to large areas by integrating sensors with processing circuits. To accomplish this goal a flexible tactile sensor array was developed using piezoresistive fabric material. The output of the tactile array was represented as a spatiotemporal spike pattern to emulate neural signals from mechanoreceptors in the skin. A hardware implemented Extreme Learning Machine (ELM) was used to process the tactile information. The ELM chip is an event-driven system that is massively parallel and energy-efficient. For these reasons, our proposed architecture offers a fast and energy-efficient alternative for processing spatiotemporal tactile patterns. The performance of the system was evaluated during a real-Time object classification task, where it achieved 90% accuracy for binary classification.

Original languageEnglish (US)
Title of host publicationIEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479972333
DOIs
StatePublished - Dec 4 2015
Event11th IEEE Biomedical Circuits and Systems Conference, BioCAS 2015 - Atlanta, United States
Duration: Oct 22 2015Oct 24 2015

Other

Other11th IEEE Biomedical Circuits and Systems Conference, BioCAS 2015
CountryUnited States
CityAtlanta
Period10/22/1510/24/15

Fingerprint

Physiological Pattern Recognition
machine learning
Touch
spikes
pattern recognition
Pattern recognition
Learning systems
mechanoreceptors
Sensor arrays
Processing
Skin
hardware
modules
chips
Hardware
energy
Networks (circuits)
output
sensors
Sensors

ASJC Scopus subject areas

  • Biotechnology
  • Instrumentation
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Cite this

Rasouli, M., Yi, C., Basu, A., Thakor, N. V., & Kukreja, S. (2015). Spike-based tactile pattern recognition using an extreme learning machine. In IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings [7348394] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BioCAS.2015.7348394

Spike-based tactile pattern recognition using an extreme learning machine. / Rasouli, Mahdi; Yi, Chen; Basu, Arindam; Thakor, Nitish V; Kukreja, Sunil.

IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. 7348394.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rasouli, M, Yi, C, Basu, A, Thakor, NV & Kukreja, S 2015, Spike-based tactile pattern recognition using an extreme learning machine. in IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings., 7348394, Institute of Electrical and Electronics Engineers Inc., 11th IEEE Biomedical Circuits and Systems Conference, BioCAS 2015, Atlanta, United States, 10/22/15. https://doi.org/10.1109/BioCAS.2015.7348394
Rasouli M, Yi C, Basu A, Thakor NV, Kukreja S. Spike-based tactile pattern recognition using an extreme learning machine. In IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. 7348394 https://doi.org/10.1109/BioCAS.2015.7348394
Rasouli, Mahdi ; Yi, Chen ; Basu, Arindam ; Thakor, Nitish V ; Kukreja, Sunil. / Spike-based tactile pattern recognition using an extreme learning machine. IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{47eb2ec576484ccf9bd66937c2e6175a,
title = "Spike-based tactile pattern recognition using an extreme learning machine",
abstract = "We present a biologically-inspired approach for tactile pattern recognition. Our aim is to develop a low-cost tactile module that can be applied to large areas by integrating sensors with processing circuits. To accomplish this goal a flexible tactile sensor array was developed using piezoresistive fabric material. The output of the tactile array was represented as a spatiotemporal spike pattern to emulate neural signals from mechanoreceptors in the skin. A hardware implemented Extreme Learning Machine (ELM) was used to process the tactile information. The ELM chip is an event-driven system that is massively parallel and energy-efficient. For these reasons, our proposed architecture offers a fast and energy-efficient alternative for processing spatiotemporal tactile patterns. The performance of the system was evaluated during a real-Time object classification task, where it achieved 90{\%} accuracy for binary classification.",
author = "Mahdi Rasouli and Chen Yi and Arindam Basu and Thakor, {Nitish V} and Sunil Kukreja",
year = "2015",
month = "12",
day = "4",
doi = "10.1109/BioCAS.2015.7348394",
language = "English (US)",
isbn = "9781479972333",
booktitle = "IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Spike-based tactile pattern recognition using an extreme learning machine

AU - Rasouli, Mahdi

AU - Yi, Chen

AU - Basu, Arindam

AU - Thakor, Nitish V

AU - Kukreja, Sunil

PY - 2015/12/4

Y1 - 2015/12/4

N2 - We present a biologically-inspired approach for tactile pattern recognition. Our aim is to develop a low-cost tactile module that can be applied to large areas by integrating sensors with processing circuits. To accomplish this goal a flexible tactile sensor array was developed using piezoresistive fabric material. The output of the tactile array was represented as a spatiotemporal spike pattern to emulate neural signals from mechanoreceptors in the skin. A hardware implemented Extreme Learning Machine (ELM) was used to process the tactile information. The ELM chip is an event-driven system that is massively parallel and energy-efficient. For these reasons, our proposed architecture offers a fast and energy-efficient alternative for processing spatiotemporal tactile patterns. The performance of the system was evaluated during a real-Time object classification task, where it achieved 90% accuracy for binary classification.

AB - We present a biologically-inspired approach for tactile pattern recognition. Our aim is to develop a low-cost tactile module that can be applied to large areas by integrating sensors with processing circuits. To accomplish this goal a flexible tactile sensor array was developed using piezoresistive fabric material. The output of the tactile array was represented as a spatiotemporal spike pattern to emulate neural signals from mechanoreceptors in the skin. A hardware implemented Extreme Learning Machine (ELM) was used to process the tactile information. The ELM chip is an event-driven system that is massively parallel and energy-efficient. For these reasons, our proposed architecture offers a fast and energy-efficient alternative for processing spatiotemporal tactile patterns. The performance of the system was evaluated during a real-Time object classification task, where it achieved 90% accuracy for binary classification.

UR - http://www.scopus.com/inward/record.url?scp=84962639330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962639330&partnerID=8YFLogxK

U2 - 10.1109/BioCAS.2015.7348394

DO - 10.1109/BioCAS.2015.7348394

M3 - Conference contribution

AN - SCOPUS:84962639330

SN - 9781479972333

BT - IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -