Advertisement

Research on an olfactory neural system model and its applications based on deep learning

  • Jin Zhang
  • Tiantian Tian
  • Shengchun Wang
  • Xiaofei Liu
  • Xuanyu Shu
  • Ying WangEmail author
Advances in Parallel and Distributed Computing for Neural Computing
  • 127 Downloads

Abstract

The idea of constructing the biological neural system model as realistic as possible can not only provide a new artificial neural network (ANN), but also offer an effective object to study biological neural systems. As a very meaningful attempt about the idea, a bionic model of olfactory neural system, KIII model, is introduced in this paper. There are the unique characteristics of KIII model different from those of general ANNs. The KIII model realistically simulates the structure of the real olfactory neural system and the process of odor molecules gradually transformed by the core components of the olfactory system including olfactory receptor, olfactory bulb and olfactory cortex. The neuron model of the KIII model is constructed and optimized based on neurophysiological experimental data and accurately reflects the response of olfactory neurons to odor stimulation. In particular, the noise introduced to KIII model can further improve the performance of the model. In addition, the KIII model is analyzed based on the idea of deep learning. The qualitative analysis shows that there are obvious similarities between the KIII model and the deep learning model. Furthermore, with the epileptic electroencephalograph (EEG) recognition task, two groups of experiments are designed to comprehensively analyze the performance of the KIII model. In the first group of experiments, a typical pattern recognition experiment with feature extraction stage is shown. The features of epileptic EEG were extracted based on Empirical Mode Decomposition (EMD), and the KIII model was used as a classifier. The experimental results show that the KIII model only needs a small number of iterations to memorize different modes and has a high recognition rate, over 91%. In the second group of experiments, a direct recognition experiment without feature extraction stage is shown. The original epileptic EEG signals as KIII model inputs directly were recognized. The experimental results show that there is still an excellent performance in the KIII model, over 96%, and the recognition result is similar to the characteristics of the deep learning model. The theoretical analysis and experimental results prove that KIII model with the idea of deep learning is an excellent bionic model of olfactory neural system and gets a good balance between high bionics and good performance, which is a good reference for related research.

Keywords

Olfactory neural system EEG recognition KIII model Deep learning 

Notes

Acknowledgements

This work was supported by the education and research projects of Hunan Provincial Education Department (15K082, JG2018A012, XiangJiaoTong [2018]-107) and the education and research projects of Ministry of Education of the People’s Republic of China (201702001043, 201801037136).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Li ZP, Hopfield J (1989) A model of the olfactory bulb and its oscillatory processing. Biol Cybern 61:379–392zbMATHCrossRefGoogle Scholar
  2. 2.
    Li ZP, Hertz J (1998) Odor recognition and segmentation by coupled olfactory bulb and cortical network. Neurocomputing 61(26–27):789–794zbMATHGoogle Scholar
  3. 3.
    Liljenstrom H (1991) Modeling the dynamics of olfactory cortex using simplified network units and realistic architecture. Int J Neural Syst 2(1–2):1–15CrossRefGoogle Scholar
  4. 4.
    Liljenstrom H, Wu XB (1995) Noise-enhanced performance in a cortical associative memory model. Int J Neural Syst 6(1):19–29CrossRefGoogle Scholar
  5. 5.
    Aronsson P, Liljenstrom H (2000) Non-synaptic modulation of cortical network dynamics. Neurocomputing 32–33:285–290CrossRefGoogle Scholar
  6. 6.
    Gu Y, Halnes G, Liljenstrom H, Rosen D, Wahlund B, Liang H (2006) Modeling ECT effects by connectivity changes in cortical neural networks. Neurocomputing 69(10–12):1341–1347CrossRefGoogle Scholar
  7. 7.
    Chang HJ, Freeman WJ, Burke BC (1998) Optimization of olfactory model in software to give 1/f power spectra reveals numerical instabilities in solutions governed by aperiodic (chaotic) attractors. Neural Netw 11(3):449–466CrossRefGoogle Scholar
  8. 8.
    Liu JW, Liu Y, Luo XL (2014) Research and development on deep learning. Appl Res Comput 31(7):1921–1942Google Scholar
  9. 9.
    Londhe ND, Kshirsagar GB, Tekchandani H (2018) Deep convolution neural network based speech recognition for Chhattisgarhi. In: 2018 5th international conference on signal processing and integrated networks (SPIN), pp 667–671Google Scholar
  10. 10.
    Mazumdar M, Sarasvathi V, Kumar A (2017) Object recognition in videos by sequential frame extraction using convolutional neural networks and fully connected neural networks. In: 2017 International conference on energy, communication, data analytics and soft computing (ICECDS), pp 1485–1488Google Scholar
  11. 11.
    Cheng FC, Zhang H, Fan WJ, Harris B (2018) Image recognition technology based on deep learning. Wirel Pers Commun 102:1917–1933CrossRefGoogle Scholar
  12. 12.
    Lin YO, Lei H, Li XY et al (2017) Deep learning in NLP: methods and applications. J Univ Electron Sci Technol China 46(6):919zbMATHGoogle Scholar
  13. 13.
    Zhang J, Li G, Freeman WJ (2008) Algorithm for texture image generation based on a bionic model of olfactory neural networks. J Image Graph 05:977–983Google Scholar
  14. 14.
    Li G, Zhang J, Freeman WJ (2006) Face recognition using a neural network simulating olfactory systems. Proc Third Int Symp Neural Netw 3972:93–97Google Scholar
  15. 15.
    Zhang J (2007) Research on bionic model of olfactory nerve system and its application. Zhejiang University, HangzhouGoogle Scholar
  16. 16.
    Yao Y, Freeman WJ (1990) Model of biological pattern recognition with spatially chaotic dynamics. Neural Netw 3(2):153–170CrossRefGoogle Scholar
  17. 17.
    Yao Y, Freeman WJ (1989) Pattern recognition in olfactory systems: modeling and simulation. In: International joint conference on neural networks. pp 699–704Google Scholar
  18. 18.
    Chang HJ, Freeman WJ, Burke BC (1998) Biologically modeled noise stabilizing neurodynamics for pattern recognition. Int J Bifurc Chaos 08(2):321–345zbMATHCrossRefGoogle Scholar
  19. 19.
    Li X, Li G, Wang L, Freeman WJ (2006) A study on a bionic pattern classifier based on olfactory neural system. Int J Bifurc Chaos 16(8):2425–2434MathSciNetzbMATHCrossRefGoogle Scholar
  20. 20.
    Freeman WJ, Yao Y, Burke B (1988) Central pattern generating and recognizing in olfactory-bulb: a correlation learning rule. Neural Netw 1(4):277–288CrossRefGoogle Scholar
  21. 21.
    Zhang J, Li SD, Li G (2008) KIII model and its application to face recognition. Comput Eng Appl 44(13):245–248Google Scholar
  22. 22.
    Yang X, Fu J, Lou Z et al (2006) Tea classification based on artificial olfaction using bionic olfactory neural network. In: Wang J, Yi z, Zurada JM, Lu BL, Yin H (eds) Advances in neural networks, vol 3972. Springer, Berlin, pp 343–348Google Scholar
  23. 23.
    Zhang TL, Dai LS, Wang Y et al (2015) EEG spatiotemporal pattern classification of the stimuli on different fingers. In: Liljenström H (ed) Advances in cognitive neurodynamics (IV). Springer, Dordrecht, pp 147–153CrossRefGoogle Scholar
  24. 24.
    Vijaykumar P, Sunitha R, Pradhan N et al (2018) Simulation of cortical epileptic discharge using Freeman’s KIII model. In: Hemanth D, Smys S (eds) Computational vision and bio inspired computing, vol 28. Springer, Cham, pp 280–290CrossRefGoogle Scholar
  25. 25.
    Garcia Rosa JL, Piazentin DRM (2016) A new cognitive filtering approach based on Freeman K3 Neural Networks. Appl Intell 45(2):363–382CrossRefGoogle Scholar
  26. 26.
    Bengio Y, Delalleau O (2011) On the expressive power of deep architectures. In: International conference on algorithmic learning theory, pp 18–36Google Scholar
  27. 27.
    Bottou L, Chapelle O, Decoste D et al (2007) Scaling learning algorithms toward AI. MIT Press, London, pp 321–359Google Scholar
  28. 28.
    Chen YD, Li KL, Yang WD et al (2019) Performance-aware model for sparse matrix-matrix multiplication on the Sunway TaihuLight supercomputer. IEEE Trans Parallel Distrib Syst 30(4):923–938CrossRefGoogle Scholar
  29. 29.
    Xiao GQ et al (2017) Efficient monochromatic and bichromatic probabilistic reverse top-k query processing for uncertain big data. J Comput Syst Sci 89:92–113MathSciNetzbMATHCrossRefGoogle Scholar
  30. 30.
    Xiao GQ et al (2017) Reporting l most influential objects in uncertain databases based on probabilistic reverse Top-k queries. Inf Sci 405:207–226CrossRefGoogle Scholar
  31. 31.
    Chen JG et al (2019) A bi-layered parallel training architecture for large-scale convolutional neural networks. IEEE Trans Parallel Distrib Syst 30(5):965–976CrossRefGoogle Scholar
  32. 32.
    Chen JG et al (2019) Distributed deep learning model for intelligent video surveillance systems with edge computing. IEEE Trans Ind Inf.  https://doi.org/10.1109/TII.2019.2909473 CrossRefGoogle Scholar
  33. 33.
    Andrzejak RG, Lehnertz K, Mormann F et al (2001) Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E Stat Nonlinear Soft Matter Phys 64(6):61907CrossRefGoogle Scholar
  34. 34.
    Chen SS (2013) Epileptic seizure detection based on Gradient Boosting algorithm. Shandong University, Shandong, pp 33–43Google Scholar
  35. 35.
    Xiao GQ, Wu F, Zhou X, Li KL (2016) Probabilistic top-k range query processing for uncertain databases. J Intell Fuzzy Syst 31(2):1109–1120zbMATHCrossRefGoogle Scholar
  36. 36.
    Yuan Q, Zhou W, Liu Y, Wang J (2012) Epileptic seizure detection with linear and nonlinear features. Epilepsy Behav 24(4):415–421CrossRefGoogle Scholar
  37. 37.
    Li SF, Zhou WD, Yuan Q et al (2013) Feature extraction and recognition of ictal EEG using EMD and SVM. Comput Biol Med 43(7):807–816CrossRefGoogle Scholar
  38. 38.
    Ur RN, Xia Y, Mandic DP (2010) Application of multivariate empirical mode decomposition for seizure detection in EEG signals. In: 32nd annual international conference of the IEEE EMBS Buenos Aires, pp 1650–1651Google Scholar
  39. 39.
    Zhang TH, Fan GH, Sun HY (2008) The detection of weak pulse laser echo signal by the kurtosis based on FPGA. Chin J Sci Instrum 29(4):288–291Google Scholar
  40. 40.
    Xiong B, Pan Q, Wen SP, Wang XD (2016) Diagnosis method based on the standard deviation and skewness of IDDT. Electron Meas Technol 39(5):163–166Google Scholar
  41. 41.
    Tian B (2013) The rank and test of Kruskal–Wallis and its application. J Tonghua Normal Univ 34(5):13–14Google Scholar
  42. 42.
    Wang CM (2010) Research on feature extraction and automatic detection of epileptic EEG. East China University of Science and Technology, Shanghai, pp 70–84Google Scholar
  43. 43.
    Lin CF (2016) Chaotic visual cryptosystem using empirical mode decomposition algorithm for clinical EEG signals. J Med Syst 40(3):40–52Google Scholar
  44. 44.
    Zhang J, Wei JH, Liu XF et al (2016) A novel application of empirical mode decomposition (EMD) to feature extraction of epileptic EEG. Int J Simul Syst Sci Technol 17(29):39.1–39.6Google Scholar
  45. 45.
    Guo TX, Ding XQ, Dong XQ et al (2013) New method of preprocessing IR remote sensing spectrum signals based on EMD. Infrared Laser Eng 42(12):3196–3200Google Scholar
  46. 46.
    Chen JG, Li KL (2018) Parallel protein community detection in large-scale PPI networks based on multi-source learning. IEEE ACM Trans Comput Biol Bioinf.  https://doi.org/10.1109/TCBB.2018.2868088 CrossRefGoogle Scholar
  47. 47.
    Chen C et al (2019) Gated residual recurrent graph neural networks for traffic prediction. In: Proceedings of the 33th AAAI conference on artificial intelligence (AAAI 2019), pp 485–492CrossRefGoogle Scholar
  48. 48.
    Xiao GQ, Li KL (2019) CASpMV: a customized and accelerative SpMV framework for the Sunway TaihuLight. IEEE Trans Parallel Distrib Syst.  https://doi.org/10.1109/TPDS.2019.2907537 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Information Science and EngineeringHunan Normal UniversityChangshaChina
  2. 2.College of Mathematics and StatisticsHunan Normal UniversityChangshaChina
  3. 3.School of Humanities and ManagementHunan University of Chinese MedicineChangshaChina

Personalised recommendations