Skip to main content

On the data analysis for classification of elementary upper limb movements

Biomedical Engineering Letters volume 4, pages 403–413 (2014)Cite this article

Abstract

Purpose

Body worn inertial sensors could be used to assess rehabilitation of patients with impaired upper limb motor control by detecting and classifying how many times particular arm movements (exercises) are made during normal activities. We present a systematic exploration to determine such a system.

Methods

Kinematic data was collected from 18 healthy subjects using tri-axial inertial sensors (accelerometers and gyroscopes) located at two positions on the dominant arm as four fundamental arm movements were repeated 20 times each. Ten time domain features were extracted from individual and combinations of sensor axes data, and were used to train a classifier. Three different classifiers were investigated: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and support vector machine (SVM). Each was verified using a leave-one-subject-out technique for a generalized classification model, and a ten-fold cross validation technique for a personalized classification model.

Results

LDA repeatedly gave the better results when using features extracted from individual sensor axes data. When a personalized learning model is used with LDA, only a single tri-axial sensor (accelerometer or gyroscope) is required to classify all four of the upper limb movements with a sensitivity in the range 92–100%, using as few as 6-10 time-domain features. By comparison, the generalized model using LDA exhibited lower sensitivity and generally required more features (12–18), reflecting the greater variability inherent in a training set comprised of more than one individual’s data.

Conclusions

We demonstrate that body worn inertial sensors can classify elementary arm movements using a low complexity algorithm.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

£ 29.95

Price includes VAT (United Kingdom)
Tax calculation will be finalised during checkout.

References

  1. Fong DT-P, Chan Y-Y, The use of wearable inertial motion sensors in human lower limb biomechanics studies: a systematic review. Sensors. 2010; 10(12):11556–65.

    Article  Google Scholar 

  2. Hadjidj A, Bouabdallah A, Challal Y. Rehabilitation supervision using wireless sensor networks. Conf Proc IEEE World Wirel Mobi. 2011; 1:1–3.

    Google Scholar 

  3. Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J, Korhonen I. Activity classification using realistic data from wearable sensors. IEEE T Inf Technol Biomed. 2006; 10(1):119–28.

    Article  Google Scholar 

  4. Ermes M, Parkka J, Mantyjarvi J, Korhonen I. Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE T Inf Technol Biomed. 2008; 12(1):20–6.

    Article  Google Scholar 

  5. Najafi B, Aminian K, Paraschiv-Ionescu A, Loew F, Bula CJ, Robert P. Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly. IEEE T Biomed Eng. 2003; 50(6):711–23.

    Article  Google Scholar 

  6. Maharatna K, Mazomenos EB, Morgan J, Bonfiglio S. Towards the development of next-generation remote healthcare system: some practical considerations. Conf Proc IEEE Circ S. 2012; 1:1–4.

    Google Scholar 

  7. Armstrong S. Wireless connectivity for health and sports monitoring: a review. Brit J Sport Med. 2007; 41(5):285–9.

    Article  Google Scholar 

  8. Raisinghania MS, Benoit A, Ding J, Gomez M, Gupta K, Gusila V, Power D, Schmedding O. Ambient intelligence: changing forms of human-computer interaction and their social implications. J Digital Inf. 5(4):2–1.

  9. Merrill D, Kalanithi J, Maes P. Siftables: towards sensor network user interfaces. Conf Proc Tangible Embed Interact. 2007; 75–8.

    Chapter  Google Scholar 

  10. Banos O, Damas M, Pomares H, Prieto A, Rojas I. Daily living activity recognition based on statistical feature quality group selection. Expert Syst Appl. 2012; 39(9):8013–21.

    Article  Google Scholar 

  11. Chernbumroong S, Cang S, Atkins A, Yu H. Elderly activities recognition and classification for applications in assisted living. Expert Syst Appl. 2013; 40(5):1662–74.

    Article  Google Scholar 

  12. Zhu C, Sheng W. Motion- and location-based online human daily activity recognition. Pervasive Mob Comput. 2011; 7(2):256–69.

    Article  Google Scholar 

  13. Fleury A, Vacher M, Noury N. SVM-based multimodal classification of activities of daily living in health smart homes: sensors, algorithms, and first experimental results. IEEE T Inf Technol Biomed. 2010; 14(2):274–83.

    Article  Google Scholar 

  14. Hong Y-J, Kim I-J, Ahn SC, Kim H-G. Mobile health monitoring system based on activity recognition using accelerometer. Simul Model Pract Theory. 2010; 18(4):446–55.

    Article  Google Scholar 

  15. Martýnez-Pérez FE, González-Fraga JA, Cuevas-Tello JC, Rodrýguez MD. Activity inference for ambient intelligence through handling artifacts in a healthcare environment. Sensors. 2012; 12(1):1072–99.

    Article  Google Scholar 

  16. Fuentes D, Gonzalez-Abril L, Angulo C, Ortega JA. Online motion recognition using an accelerometer in a mobile device. Expert Syst Appl. 2012; 39(3):2461–5.

    Article  Google Scholar 

  17. Kim D, Song J, Kim D. Simultaneous gesture segmentation and recognition based on forward spotting accumulative HMMs. Pattern Recogn. 2007; 40(11):3012–26.

    Article  MATH  Google Scholar 

  18. Junker H, Amft O, Lukowicz P, Tröster G. Gesture spotting with body-worn inertial sensors to detect user activities. Pattern Recogn. 2008; 41(6):2010–24.

    Article  MATH  Google Scholar 

  19. Altun K, Barshan B, Tuncel O. Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recogn. 2010; 43(10):3605–20.

    Article  MATH  Google Scholar 

  20. Wolf SL, Newton H, Maddy D, Blanton S, Zhang Q, Winstein CJ, Morris DM, Light K. The Excite trial: relationship of intensity of constraint induced movement therapy to improvement in the wolf motor function test. Restor Neurol Neurosci. 2007; 25(5–6):549–62.

    Google Scholar 

  21. Wolf SL, Mc Junkin JP, Swanson ML, Weiss PS. Pilot normative database for the wolf motor function test. Arch Phys Med Rehabil. 2006; 87(3):443–5.

    Article  Google Scholar 

  22. Morris DM, Uswatte G, Crago JE, Cook III EW, Taub E. The reliability of the Wolf Motor Function Test for assessing upper extremity function after stroke. Arch Phys Med Rehabil. 2001; 82(6):750–5.

    Article  Google Scholar 

  23. Burns A, Greene BR, McGrath MJ, O'Shea TJ, Kuris B, Ayer SM, Stroiescu F, Cionca V. Shimmer — a wireless sensor platform for non-invasive biomedical research. IEEE Sens J. 2010; 10(9):1527–34.

    Article  Google Scholar 

  24. Kendell C, Lemaire ED. Effect of mobility devices on orientation sensors that contain magnetometers. J Rehabil Res Dev. 2009; 46(7):957–62.

    Article  Google Scholar 

  25. Kim I-J, Im S, Hong E, Ahn SC, Kim H-G. ADL classification using triaxial accelerometers and RFID. Conf Proc Ubiquitous Comput Converg Technol. 20–7.

  26. Patel S, Hughes R, Hester T, Stein J, Akay M, Dy JG, Bonato P. A novel approach to monitor rehabilitation outcomes in stroke survivors using wearable technology. Proc IEEE. 2010; 98(3):450–61.

    Article  Google Scholar 

  27. Sun Y, Wu D. Feature extraction through local learning. Stat Anal Data Min. 2009; 2(1):34–47.

    Article  MATH  MathSciNet  Google Scholar 

  28. Guyon I, Elisseeff A. An introduction to variable and feature selection. J. Mach Learn. 2003; 3:1157–82.

    MATH  Google Scholar 

  29. Wang W, Jones P, Partridge D. Assessing the impact of input features in a feedforward neural network. Neural Comput Appl. 2000; 9(2):101–12.

    Article  Google Scholar 

  30. Wang W, Jones P, Partridge D. A comparative study of featuresalience ranking techniques. Neural Comput. 2001; 13(7):1603–23.

    Article  MATH  Google Scholar 

  31. Theodoridis S, Koutroumbas K. Pattern Recognition. 4th ed. Amsterdam: Elsevier; 20–8.

  32. Hsu C-H, Lin C-J. A comparison of methods for multiclass support vector machines. IEEE T Neural Netw. 2002; 13(2):415–25.

    Article  Google Scholar 

  33. Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM T Intell Syst Technol. 2011; doi:10.1145/1961189.1961199.

    Google Scholar 

  34. Caballero JCF, Martinez FJ, Hervas C, Gutierrez PA. Sensitivity versus accuracy in multiclass problems using memetic pareto evolutionary neural networks. IEEE T Neural Netw. 2010; 21(5):750–70.

    Article  Google Scholar 

  35. Chen T, Mazomenos E, Maharatna K, Dasmahapatra S, Niranjan M. On the trade-off of accuracy and computational complexity for classifying normal and abnormal ECG in remote CVD monitoring systems. Conf Proc IEEE Wrk Sig Pro Sys. 2012; 37–42.

    Google Scholar 

Download references

Author information

Affiliations

  1. School of Electronics and Computer Science, University of Southampton, Hampshire, UK

    Dwaipayan Biswas, Andy Cranny, Ahmed F. Rahim, Nayaab Gupta, Koushik Maharatna & Nick R. Harris

  2. Leibniz-Institute for Innovative Microelectronics, IHP, Frankfurt (Oder), Germany

    Steffen Ortmann

Authors
  1. Dwaipayan Biswas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andy Cranny
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ahmed F. Rahim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nayaab Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Koushik Maharatna
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Nick R. Harris
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Steffen Ortmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dwaipayan Biswas.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Biswas, D., Cranny, A., Rahim, A.F. et al. On the data analysis for classification of elementary upper limb movements. Biomed. Eng. Lett. 4, 403–413 (2014). https://doi.org/10.1007/s13534-014-0160-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13534-014-0160-0

Keywords

  • Accelerometer
  • Activity recognition
  • Gyroscope
  • movement classification
  • Remote health monitoring
  • Wireless body area network (WBAN)