Classification of neural action potentials using mean shift clustering

Thanh Nguyen; Abbas Khosravi; Imali Hettiarachchi; Douglas Creighton; Saeid Nahavandi

doi:10.1109/SMC.2014.6974085

Classification of neural action potentials using mean shift clustering

Thanh Nguyen, Abbas Khosravi, Imali Hettiarachchi, Douglas Creighton, Saeid Nahavandi

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

Understanding neural functions requires the observation of the activities of single neurons that are represented via electrophysiological data. Processing and understanding these data are challenging problems in biomedical engineering. A microelectrode commonly records the activity of multiple neurons. Spike sorting is a process of classifying every single action potential (spike) to a particular neuron. This paper proposes a combination between diffusion maps (DM) and mean shift clustering method for spike sorting. DM is utilized to extract spike features, which are highly capable of discriminating different spike shapes. Mean shift clustering provides an automatic unsupervised clustering, which takes extracted features from DM as inputs. Experimental results show a noticeable dominance of the features extracted by DM compared to those selected by wavelet transformation (WT). Accordingly, the proposed integrated method is significantly superior to the popular existing combination of WT and superparamagnetic clustering regarding spike sorting accuracy.

Original language	English
Title of host publication	2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1247-1252
Number of pages	6
Volume	2014-January
Edition	January
DOIs	https://doi.org/10.1109/SMC.2014.6974085
Publication status	Published - 2014
Externally published	Yes
Event	IEEE International Conference on Systems, Man and Cybernetics 2014 - San Diego, United States of America Duration: 5 Oct 2014 → 8 Oct 2014 https://ieeexplore.ieee.org/xpl/conhome/6960119/proceeding (Proceedings)

Conference

Conference	IEEE International Conference on Systems, Man and Cybernetics 2014
Abbreviated title	SMC 2014
Country/Territory	United States of America
City	San Diego
Period	5/10/14 → 8/10/14
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6960119/proceeding (Proceedings)

Keywords

Diffusion maps
Mean shift clustering
Neural action potentials
Spike sorting
Superparamagnetic clustering
Wavelet transformation

Access to Document

10.1109/SMC.2014.6974085

Cite this

Nguyen, T., Khosravi, A., Hettiarachchi, I., Creighton, D., & Nahavandi, S. (2014). Classification of neural action potentials using mean shift clustering. In 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (January ed., Vol. 2014-January, pp. 1247-1252). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SMC.2014.6974085

@inproceedings{aef85e1e73b44c10b2a309e30500f60d,

title = "Classification of neural action potentials using mean shift clustering",

abstract = "Understanding neural functions requires the observation of the activities of single neurons that are represented via electrophysiological data. Processing and understanding these data are challenging problems in biomedical engineering. A microelectrode commonly records the activity of multiple neurons. Spike sorting is a process of classifying every single action potential (spike) to a particular neuron. This paper proposes a combination between diffusion maps (DM) and mean shift clustering method for spike sorting. DM is utilized to extract spike features, which are highly capable of discriminating different spike shapes. Mean shift clustering provides an automatic unsupervised clustering, which takes extracted features from DM as inputs. Experimental results show a noticeable dominance of the features extracted by DM compared to those selected by wavelet transformation (WT). Accordingly, the proposed integrated method is significantly superior to the popular existing combination of WT and superparamagnetic clustering regarding spike sorting accuracy.",

keywords = "Diffusion maps, Mean shift clustering, Neural action potentials, Spike sorting, Superparamagnetic clustering, Wavelet transformation",

author = "Thanh Nguyen and Abbas Khosravi and Imali Hettiarachchi and Douglas Creighton and Saeid Nahavandi",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; IEEE International Conference on Systems, Man and Cybernetics 2014, SMC 2014 ; Conference date: 05-10-2014 Through 08-10-2014",

year = "2014",

doi = "10.1109/SMC.2014.6974085",

language = "English",

volume = "2014-January",

pages = "1247--1252",

booktitle = "2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

edition = "January",

url = "https://ieeexplore.ieee.org/xpl/conhome/6960119/proceeding",

}

Nguyen, T, Khosravi, A, Hettiarachchi, I, Creighton, D & Nahavandi, S 2014, Classification of neural action potentials using mean shift clustering. in 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC). January edn, vol. 2014-January, IEEE, Institute of Electrical and Electronics Engineers, pp. 1247-1252, IEEE International Conference on Systems, Man and Cybernetics 2014, San Diego, California, United States of America, 5/10/14. https://doi.org/10.1109/SMC.2014.6974085

Classification of neural action potentials using mean shift clustering. / Nguyen, Thanh; Khosravi, Abbas; Hettiarachchi, Imali et al.
2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Vol. 2014-January January. ed. IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 1247-1252.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Classification of neural action potentials using mean shift clustering

AU - Nguyen, Thanh

AU - Khosravi, Abbas

AU - Hettiarachchi, Imali

AU - Creighton, Douglas

AU - Nahavandi, Saeid

PY - 2014

Y1 - 2014

N2 - Understanding neural functions requires the observation of the activities of single neurons that are represented via electrophysiological data. Processing and understanding these data are challenging problems in biomedical engineering. A microelectrode commonly records the activity of multiple neurons. Spike sorting is a process of classifying every single action potential (spike) to a particular neuron. This paper proposes a combination between diffusion maps (DM) and mean shift clustering method for spike sorting. DM is utilized to extract spike features, which are highly capable of discriminating different spike shapes. Mean shift clustering provides an automatic unsupervised clustering, which takes extracted features from DM as inputs. Experimental results show a noticeable dominance of the features extracted by DM compared to those selected by wavelet transformation (WT). Accordingly, the proposed integrated method is significantly superior to the popular existing combination of WT and superparamagnetic clustering regarding spike sorting accuracy.

AB - Understanding neural functions requires the observation of the activities of single neurons that are represented via electrophysiological data. Processing and understanding these data are challenging problems in biomedical engineering. A microelectrode commonly records the activity of multiple neurons. Spike sorting is a process of classifying every single action potential (spike) to a particular neuron. This paper proposes a combination between diffusion maps (DM) and mean shift clustering method for spike sorting. DM is utilized to extract spike features, which are highly capable of discriminating different spike shapes. Mean shift clustering provides an automatic unsupervised clustering, which takes extracted features from DM as inputs. Experimental results show a noticeable dominance of the features extracted by DM compared to those selected by wavelet transformation (WT). Accordingly, the proposed integrated method is significantly superior to the popular existing combination of WT and superparamagnetic clustering regarding spike sorting accuracy.

KW - Diffusion maps

KW - Mean shift clustering

KW - Neural action potentials

KW - Spike sorting

KW - Superparamagnetic clustering

KW - Wavelet transformation

UR - http://www.scopus.com/inward/record.url?scp=84938060362&partnerID=8YFLogxK

U2 - 10.1109/SMC.2014.6974085

DO - 10.1109/SMC.2014.6974085

M3 - Conference Paper

AN - SCOPUS:84938060362

VL - 2014-January

SP - 1247

EP - 1252

BT - 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE International Conference on Systems, Man and Cybernetics 2014

Y2 - 5 October 2014 through 8 October 2014

ER -

Classification of neural action potentials using mean shift clustering

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this