Journal of Computational Neuroscience

, Volume 46, Issue 1, pp 107–124 | Cite as

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

  • Zhengdong Xiao
  • Sile Hu
  • Qiaosheng Zhang
  • Xiang Tian
  • Yaowu Chen
  • Jing Wang
  • Zhe ChenEmail author


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.


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



The authors thank Eric J. Robinson for English proofreading. The work was supported by the NSF-CRCNS grant IIS-130764 (Z.C.), NSF-NCS grant #1835000 (Z.C., J.W.), NIH grants R01-NS100016 (Z.C., J.W.), R01-MH118928 (Z.C.) and R01-GM115384 (J.W.), as well as the China’s Natural Science Foundation #31627802 and Fundamental Research Funds for the Central Universities (Y.C.).

Compliance with Ethical Standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. Aminikhanghahi, S., & Cook, D.J. (2017). A survey of methods for time series change point detection. Knowledge Information Systems, 51(2), 339–367.CrossRefGoogle Scholar
  2. Bushnell, M.C., Ceko, M., Low, L.A. (2013). Cognitive and emotional control of pain and its disruption in chronic pain. Nature Review Neuroscience, 14, 502–511.CrossRefGoogle Scholar
  3. Buzsaki, G., Anastassiou, C.A., Koch, C. (2012). The origin of extracellular fields and currents—EEG, ECoG, LFP, and spikes. Nature Reviews Neuroscience, 13, 407–420.CrossRefPubMedCentralGoogle Scholar
  4. Chen, Z. (Ed.). (2015). Advanced State Space Methods in Neural and Clinical Data. Cambridge: Cambridge University Press.Google Scholar
  5. Chen, Z., & Wang, J. (2016). Statistical analysis of neuronal population codes for encoding acute pain. In Proceedings of IEEE ICASSP (pp. 829–833).Google Scholar
  6. Chen, Z., Zhang, Q., Tong, A.P.S., Manders, T.R., Wang, J. (2017a). Deciphering neuronal population codes for acute thermal pain. Journal of Neural Engineering, 14(3), 036023.CrossRefPubMedCentralGoogle Scholar
  7. Chen, Z., Hu, S., Zhang, Q., Wang, J. (2017b). Quickest detection for abrupt changes in neuronal ensemble spiking activity using model-based and model-free approaches. In Proceedings of 8th International IEEE/EMBS Conference on Neural Engineering (NER’17) (pp. 481–484).Google Scholar
  8. Cheppudira, B.P. (2006). Characterization of hind paw licking and lifting to noxious radiant heat in the rat with and without chronic inflammation. Journal of Neuroscience Methods, 155, 122–125.CrossRefGoogle Scholar
  9. Copits, B.A., Pullen, M.Y., Gereau R.W. IV. (2016). Spotlight on pain: optogenetic approaches for interrogating somatosensory circuits. Pain, 157, 2424–2433.CrossRefPubMedCentralGoogle Scholar
  10. Daou, I., Tuttle, A.H., Longo, G., Wieskopf, J.S., Bonin, R.P., Ase, A.R., Wood, J.N., De Koninck, Y., Ribeiro-da Silva, A., Mogil, J.S., Sgula, P. (2013). Remote optogenetic activation and sensitization of pain pathways in freely moving mice. The Journal of Neuroscience, 33, 18631–18640.CrossRefGoogle Scholar
  11. Deuis, J.R., Dvorakova, L.S., Vetter, I. (2017). Methods used to evaluate pain behaviors in rodents. Frontiers in Molecular Neuroscience, 10, 284.CrossRefPubMedCentralGoogle Scholar
  12. Dietterich, T.G., & Roli, F. (2000). Ensemble methods in machine learning. In Gayar, N.E., & Kittler, J. (Eds.) Multiple Classifier Systems: Springer.Google Scholar
  13. Fraser, G.W., Chase, S.M., Whitford, A., Schwartz, A.B. (2009). Control of a brain-computer interface without spike sorting. Journal of Neural Engineering, 6, 055004.CrossRefGoogle Scholar
  14. Goodman, I.N., & Johnson, D.H. (2008). Information theoretic bounds on neural prosthesis effectiveness: The importance of spike sorting. In Proceedings of ICASSP’08 (pp. 5204–5207).Google Scholar
  15. Gross, J., Schnitzler, A., Timmermann, L., Ploner, M. (2007). Gamma oscillations in human primary somatosensory cortex reflect pain perception. PLoS Biology, 5, e133.CrossRefPubMedCentralGoogle Scholar
  16. Gu, L., Uhelski, M.L., Anand, S., Romero-Ortega, M., Kim, Y.T., Fuchs, P.N., Mohanty, S.K. (2015). Pain inhibition by optogenetic activation of specific anterior cingulate cortical neurons. PLoS ONE, 10, e0117746.CrossRefPubMedCentralGoogle Scholar
  17. Harris-Bozer, A.L., & Peng, Y.B. (2016). Inflammatory pain by carrageenan recruits low-frequency local field potential changes in the anterior cingulate cortex. Neuroscience Letters, 632, 8–14.CrossRefGoogle Scholar
  18. Hu, S., Zhang, Q., Wang, J., Chen, Z. (2017). A real-time rodent neural interface for deciphering acute pain signals from neuronal ensemble spike activity. In Proceedings of 51st Asilomar Conference of Signals, Systems, and Computers (pp. 93–97).Google Scholar
  19. Hu, S., Zhang, Q., Wang, J., Chen, Z. (2018). Real-time particle filtering and smoothing algorithms for detecting abrupt changes in neural ensemble spike activity. Journal of Neurophysiology, 149(4), 1394–1410.CrossRefGoogle Scholar
  20. Iyer, S.M., Vesuna, S., Ramakrishnan, C., Huynh, K., Young, S., Berndt, A., Lee, S.Y., Gorini, C.J., Deisseroth, K., Delp, S.L. (2016). Optogenetic and chemogenetic strategies for sustained inhibition of pain. Scientific Reports, 6, 30570.CrossRefPubMedCentralGoogle Scholar
  21. Jaffe, A., Nadler, B., Kluger, Y. (2015). Estimating the accuracies of multiple classifiers without labeled data. In AISTAT’15.Google Scholar
  22. Kittler, J., Hatef, M., Duin, R.P.W., Matas, J. (1998). On combining classifiers. IEEE Transactions of the Pattern Analysis of Machine Intelligence, 20(3), 226–239.CrossRefGoogle Scholar
  23. Kopepcke, L., Ashida, G., Kretzberg, J. (2016). Single and multiple change point detection in spike trains: comparison of different CUSUM, methods. Frontiers in Systems Neuroscience, 10, 51.Google Scholar
  24. Kuncheva, L.I. (2004). Combining pattern classifiers. Wiley: Methods and Algorithms.CrossRefGoogle Scholar
  25. Kuo, C.C., & Yen, C.T. (2005). Comparison of anterior cingulate and primary somatosensory neuronal responses to noxious laser-heat stimuli in conscious, behaving rats. Journal of Neurophysiology, 94, 1825–1836.CrossRefGoogle Scholar
  26. Lee, M., Manders, T.R., Eberle, S.E., Su, C., D’amour, J., Yang, R., Lin, H.Y., Deisseroth, K., Froemke, R.C., Wang, J. (2015). Activation of corticostriatal circuitry relieves chronic neuropathic pain. Journal of Neuroscience, 35(13), 5247–5259.CrossRefGoogle Scholar
  27. Liu, Y., & Yao, X. (1999). Ensemble learning via negative correlation. Neural Networks, 12(10), 1399–1404.CrossRefGoogle Scholar
  28. Macke, J.H., Buesing, L., Sahani, M. (2015). Estimating state and parameters in state space models of spike trains. In Chen, Z. (Ed.) Advanced State Space Methods in Neural and Clinical Data. Cambridge: Cambridge University Press.Google Scholar
  29. Mallat, S. (2008). A Wavelet Tour of Signal Processing: the Sparse Way, 3rd edn. Cambridge: Academic Press.Google Scholar
  30. Parisi, F., Strino, F., Nadler, B., Kluger, Y. (2014). Ranking and combining multiple predictors without labeled data. Proceedings of the National Academy of Science USA, 111(4), 1253–1258.CrossRefGoogle Scholar
  31. Peng, W.W., Xia, X.L., Yi, M., Huang, G., Zhang, Z., Iannetti, G., Hu, L. (2017). Brain oscillations reflecting pain-related behavior in freely-moving rats. Pain, 159(1), 106–118.CrossRefPubMedCentralGoogle Scholar
  32. Perl, E.R. (2007). Ideas about pain, a historical view. Nature Reviews Neuroscience, 8, 71–80.CrossRefGoogle Scholar
  33. Pillow, J.W., Ahmadian, Y., Paninski, L. (2011). Model-based decoding, information estimation, and change-point detection techniques for multineuron spike trains. Neural Computation, 23(1), 1–45.CrossRefGoogle Scholar
  34. Raykar, V.C., Shipeng, Y., Zhao, L.H., Valdez, G.H., Florin, C., Bogoni, L., Moy, L. (2010). Learning with crowds. Journal of Machine Learning Research, 11, 1297–1322.Google Scholar
  35. Scholkopf, B., & Smola, A.J. (2001). Learning with kernels: Support vector machines regularization, Optimization, and Beyond. Cambridge: MIT Press.Google Scholar
  36. Taesler, P., & Rose, M. (2016). Prestimulus theta oscillations and connectivity modulate pain perception. Journal of Neuroscience, 36, 5026–5033.CrossRefGoogle Scholar
  37. Urien, L., Xiao, Z., Dale, J., Bauer, E.P., Chen, Z., Wang, J. (2018). Rate and temporal coding mechanisms in the anterior cingulate cortex for pain anticipation. Scientific Reports, 8, 8298.CrossRefPubMedCentralGoogle Scholar
  38. Vierck, C.J., Whitsel, B.L., Favorov, O.V., Brown, A.W., Tommerdahl, M. (2013). Role of primary somatosensory cortex in the coding of pains. Pain, 154, 334–344.CrossRefGoogle Scholar
  39. Vogt, B.A. (2005). Pain and emotion interactions in subregions of the cingulate gyrus. Nature Reviews Neuroscience, 6(7), 533–544.CrossRefPubMedCentralGoogle Scholar
  40. Xie, Y., Huang, J., Willett, R. (2013). Change-point detection for high-dimensional time series with missing data. IEEE Journal of Selected Topics in Signal Processing, 7(1), 12–27.CrossRefGoogle Scholar
  41. Xu, J., & Brennan, T.J. (2011). The pathophysiology of acute pain: animal models. Current Opinion in Anaesthesiology, 24(5), 508–514.CrossRefPubMedCentralGoogle Scholar
  42. Zhang, Y., Wang, N., Wang, J.-Y., Chang, J.-Y., Woodward, D.J., Luo, F. (2011). Ensemble encoding of nociceptive stimulus intensity in the rat medial and lateral pain systems. Molecular Pain, 7, 64.CrossRefPubMedCentralGoogle Scholar
  43. Zhang, Q., Manders, T., Tong, A.P.S., Yang, R., Garg, A., Martinez, E., Zhou, H., Dale, J., Goyal, A., Urien, L., Yang, G., Chen, Z., Wang, J. (2017). Chronic pain induces generalized enhancement of aversion. eLife, 6, e25302.CrossRefPubMedCentralGoogle Scholar
  44. Zhang, Q., Xiao, Z., Hu, S., Kulkarni, P., Martinez, E., Tong, A., Garg, A., Zhou, H., Chen, Z., Wang, J. (2018). Local field potential decoding of the onset and intensity of acute thermal pain in rats. Scientific Reports, 8, 8299.CrossRefPubMedCentralGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Instrument Science and TechnologyZhejiang UniversityHangzhouChina
  2. 2.Department of PsychiatryNew York University School of MedicineNew YorkUSA
  3. 3.Department of Anesthesiology, Perioperative Care and Pain MedicineNew York University School of MedicineNew YorkUSA
  4. 4.Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Key Laboratory for Biomedical Engineering of Ministry of Education of ChinaZhejiang UniversityHangzhouChina
  5. 5.Department of Neuroscience and PhysiologyNew York University School of MedicineNew YorkUSA

Personalised recommendations