OKRELM: online kernelized and regularized extreme learning machine for wearable-based activity recognition

  • Lisha Hu
  • Yiqiang Chen
  • Jindong Wang
  • Chunyu Hu
  • Xinlong Jiang
Original Article

Abstract

Miscellaneous mini-wearable devices (Jawbone Up, Apple Watch, Google Glass, et al.) have emerged in recent years to recognize the user’s activities of daily living (ADLs) such as walking, running, climbing and bicycling. To better suits a target user, a generic activity recognition (AR) model inside the wearable devices requires to adapt itself according to the user’s personality in terms of wearing styles and so on. In this paper, an online kernelized and regularized extreme learning machine (OKRELM) is proposed for wearable-based activity recognition. A small-scale but important subset of every incoming data chunk is chosen to go through the update stage during the online sequential learning. Therefore, OKRELM is a lightweight incremental learning model with less time consumption during the update and prediction phase, a robust and effective classifier compared with the batch learning scheme. The performance of OKRELM is evaluated and compared with several related approaches on a UCI online available AR dataset and experimental results show the efficiency and effectiveness of OKRELM.

Keywords

Extreme learning machine Kernel Activity recognition Online learning Wearable computing 

Notes

Acknowledgements

The authors are much grateful to Prof. Xingyu Gao from Institute of Software Chinese Academy of Sciences for his constructive comments and suggestions that have helped to improve the quality of this paper. This work is supported by Natural Science Foundation of China under Grant Nos. 61572471 and 61210010, Chinese Academy of Sciences Research Equipment Development Project under Grant No. YZ201527 and Science and Technology Planning Project of Guangdong Province under Grant No. 2015B010105001.

References

  1. 1.
    Chen Z, Chen Y, Hu L et al (2014) ContextSense: unobtrusive discovery of incremental social context using dynamic Bluetooth data[C]// International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication. ACM, 23–26Google Scholar
  2. 2.
    Hu L, Chen Y, Wang S et al (2013) A nonintrusive and single-point infrastructure-mediated sensing approach for water-use activity recognition[C]//International Conference on embedded and ubiquitous computing (EUC). IEEE, 2120–2126Google Scholar
  3. 3.
    Wang S, Zhou G, Hu L et al (2015) CARE: chewing activity recognition using noninvasive single axis accelerometer[C]// International Joint Conference on pervasive and ubiquitous computing: Adjunct Publication. ACM, 109–112Google Scholar
  4. 4.
    Chen YQ, Yu HC, Miao CY et al (2015) Using motor patterns for stroke detection[J]. Science (Advances in Computational Psychophysiology) 350(6256):12–14Google Scholar
  5. 5.
    Wang R, Chen F, Chen Z et al (2014) StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones[C]// International Joint Conference on pervasive and ubiquitous computing. ACM, 3–14Google Scholar
  6. 6.
    https://getpebble.com/steel . Accessed 2 June 2014
  7. 7.
    https://jawbone.com/up. Accessed 2 June 2014
  8. 8.
  9. 9.
    Zhao Q, Hu B, Shi Y et al (2014) Automatic identification and removal of ocular artifacts in EEG—improved adaptive predictor filtering for portable applications[J]. IEEE Trans NanobioScience 13(2):109–117CrossRefGoogle Scholar
  10. 10.
    Hu B, Majoe D, Ratcliffe M et al (2011) EEG-based cognitive interfaces for ubiquitous applications: developments and challenges[J]. IEEE Intell Syst 26(5):46–53CrossRefGoogle Scholar
  11. 11.
    Bao L, Intille SS (2004) Activity recognition from user-annotated acceleration data[C]//International Conference on pervasive computing. Springer, Berlin Heidelberg, 1–17Google Scholar
  12. 12.
    Berlin E, Van Laerhoven K (2012) Detecting leisure activities with dense motif discovery[C]//International Conference on ubiquitous computing. ACM, 250–259Google Scholar
  13. 13.
    Hu L (2014) A lightweight and low-power activity recognition system for mini-wearable devices[C]//International Conference on pervasive computing and communications Workshops (PERCOM Workshops). IEEE, 166–167Google Scholar
  14. 14.
    Pärkkä J, Cluitmans L, Ermes M (2010) Personalization algorithm for real-time activity recognition using PDA, wireless motion bands, and binary decision tree[J]. IEEE Trans Inf Technol Biomed 14(5):1211–1215CrossRefGoogle Scholar
  15. 15.
    Qian H, Mao Y, Xiang W et al (2010) Recognition of human activities using SVM multi-class classifier[J]. Pattern Recognit Lett 31(2):100–111CrossRefGoogle Scholar
  16. 16.
    Hu L, Lu S, Wang X (2013) A new and informative active learning approach for support vector machine[J]. Inf Sci 244:142–160MathSciNetCrossRefMATHGoogle Scholar
  17. 17.
    Hu L, Chen Y, Wang S et al (2014) b-COELM: A fast, lightweight and accurate activity recognition model for mini-wearable devices[J]. Pervasive Mob Comput 15:200–214CrossRefGoogle Scholar
  18. 18.
    Zeng Z, Ji Q (2010) Knowledge based activity recognition with dynamic Bayesian network[C]//European Conference on computer vision. Springer Berlin Heidelberg, 532–546Google Scholar
  19. 19.
    Gaikwad K (2012) HMM classifier for human activity recognition[J]. Comput Sci Eng 2(4):27Google Scholar
  20. 20.
    Song Y, Lu Z, Leung CW et al (2013) Collaborative boosting for activity classification in microblogs[C]// International Conference on knowledge discovery and data mining. ACM, 482–490Google Scholar
  21. 21.
    Gu B, Sheng VS (2016) A robust regularization path algorithm for ν-support vector classification. IEEE Trans Neural Netw Learn Syst 99. doi:10.1109/TNNLS.2016.2527796
  22. 22.
    Gu B, Sun X, Sheng VS (2016) Structural minimax probability machine[J].IEEE Trans Neural Netw Learn Syst 99. doi:10.1109/TNNLS.2016.2544779
  23. 23.
    Gu B, Sheng VS, Wang Z et al (2015) Incremental learning for ν-support vector regression[J]. Neural Netw 67:140–150CrossRefGoogle Scholar
  24. 24.
    Gu B, Sheng VS, Tay KY et al (2015) Incremental support vector learning for ordinal regression[J]. IEEE Trans Neural Netw Learn Syst 26(7):1403–1416MathSciNetCrossRefGoogle Scholar
  25. 25.
    Gu B, Sheng V S, Li S (2015) Bi-parameter space partition for cost-sensitive SVM[C]//IJCAI 3532–3539.Google Scholar
  26. 26.
    Zhang Y, Sun X, Wang B (2016) Efficient algorithm for k-barrier coverage based on integer linear programming[J]. China Commun 13(7):16–23CrossRefGoogle Scholar
  27. 27.
    Wen X, Shao L, Xue Y et al (2015) A rapid learning algorithm for vehicle classification[J]. Inf Sci 295:395–406CrossRefGoogle Scholar
  28. 28.
    Kong Y, Zhang M, Ye D (2017) A belief propagation-based method for task allocation in open and dynamic cloud environments[J]. Knowl Based Syst 115:123–132CrossRefGoogle Scholar
  29. 29.
    Zheng Y, Jeon B, Xu D et al (2015) Image segmentation by generalized hierarchical fuzzy C-means algorithm[J]. J Intell Fuzzy Syst 28(2):961–973Google Scholar
  30. 30.
    Fu Z, Wu X, Guan C et al (2016) Toward efficient multi-keyword fuzzy search over encrypted outsourced data with accuracy improvement[J]. IEEE Trans Inf Forensics Secur 11(12):2706–2716CrossRefGoogle Scholar
  31. 31.
    Gao X, Hoi S C H, Zhang Y et al (2014) SOML: sparse online metric learning with application to image retrieval. In: Twenty-eighth AAAI conference on artificial intelligence. AAAI PublicationsGoogle Scholar
  32. 32.
    Chen Z, Chen Y, Gao X et al (2015) Unobtrusive sensing incremental social contexts using fuzzy class incremental learning[C]// International Conference on data mining (ICDM). IEEE, 71–80Google Scholar
  33. 33.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications[J]. Neurocomputing 70(1):489–501CrossRefGoogle Scholar
  34. 34.
    Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks[C]// International Joint Conference on Neural Networks. IEEE 2:985–990Google Scholar
  35. 35.
    Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Trans Neural Networks 17(4):879–892CrossRefGoogle Scholar
  36. 36.
    Schmidt WF, Kraaijveld MA, Duin R P W (1992) Feedforward neural networks with random weights[C]// International Conference on Pattern Recognition. IEEE, 1–4Google Scholar
  37. 37.
    Huang G, Huang GB, Song S et al (2015) Trends in extreme learning machines: a review[J]. Neural Netw 61:32–48CrossRefMATHGoogle Scholar
  38. 38.
    Huang GB, Zhou H, Ding X et al (2012) Extreme learning machine for regression and multiclass classification[J]. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(2):513–529CrossRefGoogle Scholar
  39. 39.
    An S, Liu W, Venkatesh S (2007) Face recognition using kernel ridge regression[C]//International Conference on Computer Vision and Pattern Recognition. IEEE, 1–7Google Scholar
  40. 40.
    Saunders C, Gammerman A, Vovk V (1998) Ridge regression learning algorithm in dual variables[C]//ICML 98:515–521Google Scholar
  41. 41.
    Liu H, Qin J, Sun F et al (2016) Extreme kernel sparse learning for tactile object recognition[J]. IEEE Trans Cybern 99. doi:10.1109/TCYB.2016.2614809
  42. 42.
    Hu L, Chen Y, Wang S et al (2016) Less Annotation on Personalized Activity Recognition Using Context Data[C]//International Conference on Ubiquitous Intelligence and Computing(UIC) 327–332.Google Scholar
  43. 43.
    Liu H, Liu Y, Sun F (2015) Robust exemplar extraction using structured sparse coding[J]. IEEE Trans Neural Netw Learn Syst 26(8):1816–1821MathSciNetCrossRefGoogle Scholar
  44. 44.
    Liu H, Guo D, Sun F (2016) Object recognition using tactile measurements: kernel sparse coding methods[J]. IEEE Trans Instrum Meas 65(3):656–665CrossRefGoogle Scholar
  45. 45.
    Liu H, Yu Y, Sun F et al (2016) Visual-tactile fusion for object recognition[J]. IEEE Trans Autom Sci EngGoogle Scholar
  46. 46.
    Liang NY, Huang GB, Saratchandran P et al (2006) A fast and accurate online sequential learning algorithm for feedforward networks[J]. IEEE Trans Neural Netw 17(6):1411–1423CrossRefGoogle Scholar
  47. 47.
    Wang X, Han M (2014) Online sequential extreme learning machine with kernels for nonstationary time series prediction[J]. Neurocomputing 145:90–97CrossRefGoogle Scholar
  48. 48.
    Zhou X, Liu Z, Zhu C (2014) Online regularized and kernelized extreme learning machines with forgetting mechanism[J]. Math Probl Eng 2014:938548. doi:10.1155/2014/938548
  49. 49.
    Zhou XR, Wang CS (2016) Cholesky factorization based online regularized and kernelized extreme learning machines with forgetting mechanism[J]. Neurocomputing 174:1147–1155CrossRefGoogle Scholar
  50. 50.
    Scardapane S, Comminiello D, Scarpiniti M et al (2015) Online sequential extreme learning machine with kernels[J]. IEEE Trans Neural Netw Learn Syst 26(9):2214–2220MathSciNetCrossRefGoogle Scholar
  51. 51.
    Deng WY, Zheng QH, Wang ZM (2014) Cross-person activity recognition using reduced kernel extreme learning machine[J]. Neural Netw 53:1–7CrossRefGoogle Scholar
  52. 52.
    Guo L, Hao JH, Liu M (2014) An incremental extreme learning machine for online sequential learning problems[J]. Neurocomputing 128:50–58CrossRefGoogle Scholar
  53. 53.
    Hager WW (1989) Updating the inverse of a matrix[J]. SIAM Rev 31(2):221–239MathSciNetCrossRefMATHGoogle Scholar
  54. 54.
    Henderson HV, Searle SR (1981) On deriving the inverse of a sum of matrices[J]. SIAM Rev 23(1):53–60MathSciNetCrossRefMATHGoogle Scholar
  55. 55.
    Barshan B, Yüksek MC (2014) Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units[J]. Comput J 57(11):1649–1667CrossRefGoogle Scholar
  56. 56.
    Altun K, Barshan B (2010) Human activity recognition using inertial/magnetic sensor units[C]//International Workshop on Human Behavior Understanding. Springer Berlin Heidelberg, 38–51Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  1. 1.Institute of Computing TechnologyChinese Academy of SciencesBeijingChina
  2. 2.Beijing Key Laboratory of Mobile Computing and Pervasive DeviceBeijingChina
  3. 3.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations