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.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
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.
Hadjidj A, Bouabdallah A, Challal Y. Rehabilitation supervision using wireless sensor networks. Conf Proc IEEE World Wirel Mobi. 2011; 1:1–3.
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.
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.
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.
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.
Armstrong S. Wireless connectivity for health and sports monitoring: a review. Brit J Sport Med. 2007; 41(5):285–9.
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.
Merrill D, Kalanithi J, Maes P. Siftables: towards sensor network user interfaces. Conf Proc Tangible Embed Interact. 2007; 75–8.
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.
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.
Zhu C, Sheng W. Motion- and location-based online human daily activity recognition. Pervasive Mob Comput. 2011; 7(2):256–69.
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.
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.
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.
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.
Kim D, Song J, Kim D. Simultaneous gesture segmentation and recognition based on forward spotting accumulative HMMs. Pattern Recogn. 2007; 40(11):3012–26.
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.
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.
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.
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.
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.
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.
Kendell C, Lemaire ED. Effect of mobility devices on orientation sensors that contain magnetometers. J Rehabil Res Dev. 2009; 46(7):957–62.
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.
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.
Sun Y, Wu D. Feature extraction through local learning. Stat Anal Data Min. 2009; 2(1):34–47.
Guyon I, Elisseeff A. An introduction to variable and feature selection. J. Mach Learn. 2003; 3:1157–82.
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.
Wang W, Jones P, Partridge D. A comparative study of featuresalience ranking techniques. Neural Comput. 2001; 13(7):1603–23.
Theodoridis S, Koutroumbas K. Pattern Recognition. 4th ed. Amsterdam: Elsevier; 20–8.
Hsu C-H, Lin C-J. A comparison of methods for multiclass support vector machines. IEEE T Neural Netw. 2002; 13(2):415–25.
Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM T Intell Syst Technol. 2011; doi:10.1145/1961189.1961199.
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.
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.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13534-014-0160-0