TY - GEN
T1 - Power-efficient VLSI implementation of a feature extraction engine for spike sorting in neural recording and signal processing
AU - Wu, Tong
AU - Yang, Zhi
PY - 2014/1/1
Y1 - 2014/1/1
N2 - This paper presents a power-efficient VLSI implementation of a feature extraction engine for the applications of real-time spike sorting. Traditional method like principal components analysis (PCA) works in a batch mode by diagonalizing the covariance matrix constructed from the whole bunch of input data, which is computationally prohibitive and does not favor real-time processing. The proposed hardware framework does not require large volumes of memories by incrementally adjusting the number of estimated principal components in an automatic fashion. Low-voltage circuit design technique has been introduced to achieve significant power saving. The VLSI implementation of the system has a peak power dissipation of 8.59 μW with a 0.5 V supply voltage, and occupies an area of 0.268 mm2.
AB - This paper presents a power-efficient VLSI implementation of a feature extraction engine for the applications of real-time spike sorting. Traditional method like principal components analysis (PCA) works in a batch mode by diagonalizing the covariance matrix constructed from the whole bunch of input data, which is computationally prohibitive and does not favor real-time processing. The proposed hardware framework does not require large volumes of memories by incrementally adjusting the number of estimated principal components in an automatic fashion. Low-voltage circuit design technique has been introduced to achieve significant power saving. The VLSI implementation of the system has a peak power dissipation of 8.59 μW with a 0.5 V supply voltage, and occupies an area of 0.268 mm2.
UR - http://www.scopus.com/inward/record.url?scp=84949924540&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949924540&partnerID=8YFLogxK
U2 - 10.1109/ICARCV.2014.7064270
DO - 10.1109/ICARCV.2014.7064270
M3 - Conference contribution
AN - SCOPUS:84949924540
T3 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
SP - 7
EP - 12
BT - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
Y2 - 10 December 2014 through 12 December 2014
ER -