access icon openaccess Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

Inspec keywords: acceleration measurement; decision trees; signal classification; accelerometers; body sensor networks; feature extraction; medical signal processing; biomedical measurement; support vector machines

Other keywords: fourth-order cumulants; time-domain features; multilayer perceptron; third-order cumulants; supports vector machine; cumulant extraction; hierarchical decision tree classifier; second-order cumulants; human activity classification; single waist-mounted triaxial accelerometer; naive Bayes; fall event classification algorithm; SVM classifiers; optimal detection; triaxial accelerometer-based fall event detection; acceleration signals; fifth-order cumulants; lowest false alarm rate; ACC signals

Subjects: Velocity, acceleration and rotation measurement; Patient diagnostic methods and instrumentation; Sensing and detecting devices; Biomedical measurement and imaging; Biomedical communication; Digital signal processing; Sensing devices and transducers; Biology and medical computing; Signal processing and detection; Medical and biomedical uses of fields, radiations, and radioactivity; health physics; Wireless sensor networks; Knowledge engineering techniques; Velocity, acceleration and rotation measurement

References

    1. 1)
      • 21. Li, Y., Ho, K.C., Popescu, M.: ‘Microphone array system for automatic fall detection’, IEEE Trans. Biomed. Eng., 2012, 59, (2), pp. 12911301.
    2. 2)
    3. 3)
    4. 4)
      • 25. Nikias, L., Petropulu, A.P.: ‘Higher-order spectral analysis – a nonlinear signal processing framework’ (Prentice-Hall, Englewood Cliffs, NJ, 1993).
    5. 5)
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
      • 11. Tolkiehn, M., Atallah, L., Lo, B., Yang, G.-Z.: ‘Direction sensitive fall detection using a triaxial accelerometer and a barometric pressure sensor’. Proc. 33rd IEEE EMBS, Boston, August – September 2011, pp. 369372.
    26. 26)
    27. 27)
http://iet.metastore.ingenta.com/content/journals/10.1049/htl.2015.0018
Loading

Related content

content/journals/10.1049/htl.2015.0018
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading