Format

Send to

Choose Destination
J Comput Neurosci. 2019 Feb;46(1):107-124. doi: 10.1007/s10827-018-0694-8. Epub 2018 Sep 12.

Ensembles of change-point detectors: implications for real-time BMI applications.

Xiao Z1,2, Hu S1,2, Zhang Q3, Tian X1,4, Chen Y1,4, Wang J3,5, Chen Z6,7.

Author information

1
Department of Instrument Science and Technology, Zhejiang University, Hangzhou, Zhejiang, 310027, China.
2
Department of Psychiatry, New York University School of Medicine, New York, NY, 10016, USA.
3
Department of Anesthesiology, Perioperative Care and Pain Medicine, New York University School of Medicine, New York, NY, 10016, USA.
4
Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Key Laboratory for Biomedical Engineering of Ministry of Education of China, Zhejiang University, Hangzhou, Zhejiang, 310027, China.
5
Department of Neuroscience and Physiology, New York University School of Medicine, New York, NY, 10016, USA.
6
Department of Psychiatry, New York University School of Medicine, New York, NY, 10016, USA. zhe.chen3@nyumc.org.
7
Department of Neuroscience and Physiology, New York University School of Medicine, New York, NY, 10016, USA. zhe.chen3@nyumc.org.

Abstract

Brain-machine interfaces (BMIs) have been widely used to study basic and translational neuroscience questions. In real-time closed-loop neuroscience experiments, many practical issues arise, such as trial-by-trial variability, and spike sorting noise or multi-unit activity. In this paper, we propose a new framework for change-point detection based on ensembles of independent detectors in the context of BMI application for detecting acute pain signals. Motivated from ensemble learning, our proposed "ensembles of change-point detectors" (ECPDs) integrate multiple decisions from independent detectors, which may be derived based on data recorded from different trials, data recorded from different brain regions, data of different modalities, or models derived from different learning methods. By integrating multiple sources of information, the ECPDs aim to improve detection accuracy (in terms of true positive and true negative rates) and achieve an optimal trade-off of sensitivity and specificity. We validate our method using computer simulations and experimental recordings from freely behaving rats. Our results have shown superior and robust performance of ECPDS in detecting the onset of acute pain signals based on neuronal population spike activity (or combined with local field potentials) recorded from single or multiple brain regions.

KEYWORDS:

Acute pain; Brain machine interface; Change point detection; Ensemble learning; Event-related potential; Poisson linear dynamical system; Population codes; Support vector machine

PMID:
30206733
PMCID:
PMC6414295
[Available on 2020-02-01]
DOI:
10.1007/s10827-018-0694-8

Supplemental Content

Full text links

Icon for Springer Icon for NYU School of Medicine
Loading ...
Support Center