A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces

Yi Chen; Enyi Yao; Arindam Basu

doi:10.1109/ISCAS.2015.7169319

A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces

Yi Chen
, Enyi Yao
, Arindam Basu

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

21 Citations (Scopus)

Abstract

A machine learning co-processor in 0.35μm CMOS for motor intention decoding in the brain-machine interfaces is presented in this paper. Using Extreme Learning Machine algorithm, time delayed sample based feature dimension enhancement, low-power analog processing and massive parallelism, it achieves an energy efficiency of 290 GMACs/W at a classification rate of 50 Hz. A portable external unit based on the proposed co-processor is verified with neural data recorded in monkey finger movements experiment, achieving a decoding accuracy of 99.3%. With time-delayed feature dimension enhancement, the classification accuracy can be increased by 5% with limited number of input channels.

Original language	English
Title of host publication	2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015
Publisher	IEEE
Pages	3004-3007
Volume	2015-July
ISBN (Print)	9781479983919
DOIs	https://doi.org/10.1109/ISCAS.2015.7169319
Publication status	Published - 27 Jul 2015
Externally published	Yes
Event	IEEE International Symposium on Circuits and Systems, ISCAS 2015 - Lisbon, Portugal Duration: 24 May 2015 → 27 May 2015

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	2015-July
ISSN (Print)	0271-4310

Conference

Conference	IEEE International Symposium on Circuits and Systems, ISCAS 2015
Place	Portugal
City	Lisbon
Period	24/05/15 → 27/05/15

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access Output

10.1109/ISCAS.2015.7169319

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Chen, Y., Yao, E., & Basu, A. (2015). A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces. In 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015 (Vol. 2015-July, pp. 3004-3007). Article 7169319 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2015-July). IEEE. https://doi.org/10.1109/ISCAS.2015.7169319

@inproceedings{251910ee9f7f4d03884f3644c5ed36c6,

title = "A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces",

abstract = "A machine learning co-processor in 0.35μm CMOS for motor intention decoding in the brain-machine interfaces is presented in this paper. Using Extreme Learning Machine algorithm, time delayed sample based feature dimension enhancement, low-power analog processing and massive parallelism, it achieves an energy efficiency of 290 GMACs/W at a classification rate of 50 Hz. A portable external unit based on the proposed co-processor is verified with neural data recorded in monkey finger movements experiment, achieving a decoding accuracy of 99.3\%. With time-delayed feature dimension enhancement, the classification accuracy can be increased by 5\% with limited number of input channels.",

author = "Yi Chen and Enyi Yao and Arindam Basu",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; IEEE International Symposium on Circuits and Systems, ISCAS 2015 ; Conference date: 24-05-2015 Through 27-05-2015",

year = "2015",

month = jul,

day = "27",

doi = "10.1109/ISCAS.2015.7169319",

language = "English",

isbn = "9781479983919",

volume = "2015-July",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "IEEE",

pages = "3004--3007",

booktitle = "2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015",

address = "United States",

}

Chen, Y, Yao, E & Basu, A 2015, A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces. in 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015. vol. 2015-July, 7169319, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2015-July, IEEE, pp. 3004-3007, IEEE International Symposium on Circuits and Systems, ISCAS 2015, Lisbon, Portugal, 24/05/15. https://doi.org/10.1109/ISCAS.2015.7169319

A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces. / Chen, Yi; Yao, Enyi; Basu, Arindam.
2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015. Vol. 2015-July IEEE, 2015. p. 3004-3007 7169319 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2015-July).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces

AU - Chen, Yi

AU - Yao, Enyi

AU - Basu, Arindam

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2015/7/27

Y1 - 2015/7/27

N2 - A machine learning co-processor in 0.35μm CMOS for motor intention decoding in the brain-machine interfaces is presented in this paper. Using Extreme Learning Machine algorithm, time delayed sample based feature dimension enhancement, low-power analog processing and massive parallelism, it achieves an energy efficiency of 290 GMACs/W at a classification rate of 50 Hz. A portable external unit based on the proposed co-processor is verified with neural data recorded in monkey finger movements experiment, achieving a decoding accuracy of 99.3%. With time-delayed feature dimension enhancement, the classification accuracy can be increased by 5% with limited number of input channels.

AB - A machine learning co-processor in 0.35μm CMOS for motor intention decoding in the brain-machine interfaces is presented in this paper. Using Extreme Learning Machine algorithm, time delayed sample based feature dimension enhancement, low-power analog processing and massive parallelism, it achieves an energy efficiency of 290 GMACs/W at a classification rate of 50 Hz. A portable external unit based on the proposed co-processor is verified with neural data recorded in monkey finger movements experiment, achieving a decoding accuracy of 99.3%. With time-delayed feature dimension enhancement, the classification accuracy can be increased by 5% with limited number of input channels.

UR - https://www.scopus.com/pages/publications/84946205168

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84946205168&origin=recordpage

U2 - 10.1109/ISCAS.2015.7169319

DO - 10.1109/ISCAS.2015.7169319

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781479983919

VL - 2015-July

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 3004

EP - 3007

BT - 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015

PB - IEEE

T2 - IEEE International Symposium on Circuits and Systems, ISCAS 2015

Y2 - 24 May 2015 through 27 May 2015

ER -

A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this