Multimedia Tools and Applications

, Volume 76, Issue 8, pp 10701–10719 | Cite as

Towards unsupervised physical activity recognition using smartphone accelerometers

  • Yonggang Lu
  • Ye Wei
  • Li Liu
  • Jun Zhong
  • Letian Sun
  • Ye Liu


The development of smartphones equipped with accelerometers gives a promising way for researchers to accurately recognize an individual’s physical activity in order to better understand the relationship between physical activity and health. However, a huge challenge for such sensor-based activity recognition task is the collection of annotated or labelled training data. In this work, we employ an unsupervised method for recognizing physical activities using smartphone accelerometers. Features are extracted from the raw acceleration data collected by smartphones, then an unsupervised classification method called MCODE is used for activity recognition. We evaluate the effectiveness of our method on three real-world datasets, i.e., a public dataset of daily living activities and two datasets of sports activities of race walking and basketball playing collected by ourselves, and we find our method outperforms other existing methods. The results show that our method is viable to recognize physical activities using smartphone accelerometers.


Physical activity recognition Unsupervised method Accelerometer Smartphone 



This work is supported by the National Science Foundation of China (Grants No. 61272213, 61370219), Cuiying Grant of China Telecom, Gansu Branch(grant no. lzudxcy-2013-3), Science and Technology Planning Project of Chengguan District, Lanzhou grant no. 2013-3-1), and Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry (grant no. 44th). The authors want to thank the volunteers for their time and effort to help us collecting data.


  1. 1.
    Alshurafa N, Xu W, Liu JJ, Huang MC, Mortazavi B, Roberts CK, Sarrafzadeh M (2014) Designing a robust activity recognition framework for health and exergaming using wearable sensors. IEEE Journal of Biomedical and Health Informatics 18(5):1636–1646CrossRefGoogle Scholar
  2. 2.
    Arthur D (2007) Vassilvitskii, S.: k-means++: The advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. pp. 1027–1035. Society for Industrial and Applied MathematicsGoogle Scholar
  3. 3.
    Ashton D (1993) mondiale de la santé. Bureau régional de l’Europe, O.: Exercise: health benefits and risks. WHO. Regional Office for EuropeGoogle Scholar
  4. 4.
    Bader GD, Hogue CW (2003) An automated method for finding molecular complexes in large protein interaction networks. BMC Bioinf 4(1):2CrossRefGoogle Scholar
  5. 5.
    Bulling A, Ward JA, Gellersen H (2012) Multimodal recognition of reading activity in transit using body-worn sensors. ACM Transactions on Applied Perception (TAP) 9(1):2Google Scholar
  6. 6.
    Bulling A, Blanke U, Schiele B (2014) A tutorial on human activity recognition using body-worn inertial sensors. ACM Comput Surv 46(3):33CrossRefGoogle Scholar
  7. 7.
    Casale P, Pujol O, Radeva P (2012) Personalization and user verification in wearable systems using biometric walking patterns. Pers Ubiquit Comput 16(5):563–580CrossRefGoogle Scholar
  8. 8.
    Dempster AP, Laird NM, Rubin DB, other (1977) Maximum likelihood from incomplete data via the em algorithm. J R Stat Soc 39(1):1–38MathSciNetMATHGoogle Scholar
  9. 9.
    De Vries SI, Garre FG, Engbers LH, Hildebrandt VH, Van Buuren S (2011) Evaluation of neural networks to identify types of activity using accelerometers. Med Sci Sports Exerc 43(1):101–7CrossRefGoogle Scholar
  10. 10.
    Ermes M, Parkka J, Mantyjarvi J, Korhonen I (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans Inf Technol Biomed 12(1):20–26CrossRefGoogle Scholar
  11. 11.
    Fowlkes EB, Mallows CL (1983) A method for comparing two hierarchical clusterings. J Am Stat Assoc 78(383):553–569CrossRefMATHGoogle Scholar
  12. 12.
    Hong YJ, Kim IJ, Ahn SC, Kim HG (2010) Mobile health monitoring system based on activity recognition using accelerometer. Simul Model Pract Theory 18(4):446–455CrossRefGoogle Scholar
  13. 13.
    Hospedales TM, Li J, Gong S, Xiang T (2011) Identifying rare and subtle behaviors: A weakly supervised joint topic model. IEEE TPAMI 33(12):2451–2464CrossRefGoogle Scholar
  14. 14.
    Hubert L, Arabie P (1985) Comparing partitions. J Classif 2(1):193–218CrossRefMATHGoogle Scholar
  15. 15.
    Kaufman L, Rousseeuw P (1987) Clustering by means of medoids. North-HollandGoogle Scholar
  16. 16.
    Khan AM, Lee YK, Lee SY, Kim TS (2010) A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. IEEE Trans Inf Technol Biomed 14(5):1166–1172CrossRefGoogle Scholar
  17. 17.
    Kirkup JA, Rowlands DD, Thiel DV (2014) Dynamic tracking of a 2.4 ghz waist mounted beacon for indoor basketball player positioning. Procedia Engineering 72:108–113CrossRefGoogle Scholar
  18. 18.
    Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12(2):74–82CrossRefGoogle Scholar
  19. 19.
    Lee JB, Mellifont RB, Burkett BJ, James DA (2013) Detection of illegal race walking: a tool to assist coaching and judging. Sensors 13(12):16065–16074CrossRefGoogle Scholar
  20. 20.
    Lester J, Choudhury T, Borriello G (2006) A practical approach to recognizing physical activities. In: Pervasive Computing. Springer, pp 1–16Google Scholar
  21. 21.
    Nie L, Akbari M, Li T, Chua TS (2014) A joint local-global approach for medical terminology assignment. In: Medical Information Retrieval Workshop at SIGIR 2014. p. 24Google Scholar
  22. 22.
    Nie L, Li T, Akbari M, Shen J, Chua TS (2014) Wenzher: Comprehensive vertical search for healthcare domain. In: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval. pp. 1245–1246. ACMGoogle Scholar
  23. 23.
    Nie L, Wang M, Zhang L, Yan S, Bo Z, Chua TS (2014) Disease inference from health-related questions via sparse deep learning. IEEE Trans Knowl Data Eng 27(8):2107–2119CrossRefGoogle Scholar
  24. 24.
    Liu Y, Nie L, Han L, Zhang L, Rosenblum DS (2015) Action2activity: Recognizing complex activities from sensor data. In: Artificial Intelligence (IJCAI), 2015 International Joint Conference on. pp. 1–8Google Scholar
  25. 25.
    Liu L, Peng Y, Liu M, Huang Z (2015) Sensor-based human activity recognition system with a multilayered model using time series shapelets. Knowl-Based Syst 90:138–152CrossRefGoogle Scholar
  26. 26.
    Nie L, Zhang L, Yang Y, Wang M (2015) Hong, Richang, C.T.S.: Beyond doctors: Future health prediction from multimedia and multimodal observations. In: Proceedings of the 2015 ACM conference on Multimedia. pp. 1–9. ACMGoogle Scholar
  27. 27.
    Nie L, Zhao YL, Akbari M, Shen J, Chua TS (2015) Bridging the vocabulary gap between health seekers and healthcare knowledge. IEEE Trans Knowl Data Eng 27(2):396–409CrossRefGoogle Scholar
  28. 28.
    Patterson DJ, Fox D, Kautz H, Philipose M (2005) Fine-grained activity recognition by aggregating abstract object usage. In: IEEE International Symposium on Wearable Computers. pp. 44–51Google Scholar
  29. 29.
    Ravi N, Dandekar N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data. In: AAAI. vol. 5, pp. 1541–1546Google Scholar
  30. 30.
    Revelle W (1979) Hierarchical cluster analysis and the internal structure of tests. Multivar Behav Res 14(1):57–74CrossRefGoogle Scholar
  31. 31.
    Sun L, Liu L, Wei Y, Zhong J, Luo D, Liu M, Monkaresi H (2014) Apply autocorrelation and forward difference to measure vital signs using ordinary camera. In: Smart Health, pp. 150–159. SpringerGoogle Scholar
  32. 32.
    Taniguchi A, Watanabe K, Kurihara Y (2012) Measurement and analyze of jump shoot motion in basketball using a 3-d acceleration and gyroscopic sensor. In: SICE annual conference (SICE), 2012 Proceedings of. pp. 361–365. IEEEGoogle Scholar
  33. 33.
    Vail DL, Veloso MM, Lafferty JD (2007) Conditional random fields for activity recognition. In: International joint conference on autonomous agents and multiagent systems. p. 235Google Scholar
  34. 34.
    Van Kasteren T, Krose B (2007) Bayesian activity recognition in residence for eldersGoogle Scholar
  35. 35.
    Von Luxburg U (2007) A tutorial on spectral clustering. Stat Comput 17 (4):395–416MathSciNetCrossRefGoogle Scholar
  36. 36.
    Wei Y, Liu L, Zhong J, Lu Y, Sun L (2015) Unsupervised race walking recognition using smartphone accelerometers. In: Knowledge Science, Engineering and Management. Springer, pp 691–702Google Scholar
  37. 37.
    Yan Y, Liu G, Ricci E, Sebe N (2013) Multi-task linear discriminant analysis for multi-view action recognition. In: Image Processing (ICIP), 2013 20th IEEE International Conference on. pp. 2842–2846. IEEEGoogle Scholar
  38. 38.
    Yan Y, Ricci E, Subramanian R, Lanz O, Sebe N (2013) No matter where you are: Flexible graph-guided multi-task learning for multi-view head pose classification under target motion. In: Computer Vision (ICCV), 2013 IEEE International Conference on. pp. 1177–1184. IEEEGoogle Scholar
  39. 39.
    Yan Y, Ricci E, Liu G, Sebe N (2015) Egocentric daily activity recognition via multitask clustering. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society 24(10):2984–2995MathSciNetCrossRefGoogle Scholar
  40. 40.
    Yan Y, Yang Y, Meng D, Liu G, Tong W, Hauptmann AG, Sebe N (2015) Event oriented dictionary learning for complex event detection. IEEE Trans Image Process 24(6):1867–1878MathSciNetCrossRefGoogle Scholar
  41. 41.
    Zhang M, Sawchuk AA (2013) Human daily activity recognition with sparse representation using wearable sensors. IEEE Journal of Biomedical and Health Informatics 17(3):553–560CrossRefGoogle Scholar
  42. 42.
    Zhang L, Gao Y, Ji R, Xia Y, Dai Q, Li X (2014) Actively learning human gaze shifting paths for semantics-aware photo cropping. IEEE Trans Image Process 23(5):2235–2245MathSciNetCrossRefGoogle Scholar
  43. 43.
    Zhang L, Gao Y, Xia Y, Dai Q, Li X (2015) A fine-grained image categorization system by cellet-encoded spatial pyramid modeling. IEEE Trans Ind Electron 62(1):564–571CrossRefGoogle Scholar
  44. 44.
    Zhang L, Gao Y, Xia Y, Lu K, Shen J, Ji R (2014) Representative discovery of structure cues for weakly-supervised image segmentation. IEEE Trans Multimedia 16(2):470–479CrossRefGoogle Scholar
  45. 45.
    Zhang L, Han Y, Yang Y, Song M, Yan S, Tian Q (2013) Discovering discriminative graphlets for aerial image categories recognition. IEEE Trans Image Process 22(12):5071–5084MathSciNetCrossRefGoogle Scholar
  46. 46.
    Zhang L, Xia Y, Mao K, Ma H, Shan Z (2015) An effective video summarization framework toward handheld devices. IEEE Trans Ind Electron 62 (2):1309–1316CrossRefGoogle Scholar
  47. 47.
    Zhang L, Yang Y, Gao Y, Yu YT, Wang C, Li X (2014) A probabilistic associative model for segmenting weakly supervised images. IEEE Trans Image Process 23(9):4150–4159MathSciNetCrossRefGoogle Scholar
  48. 48.
    Zheng Y, Wong WK, Guan X, Trost S (2013) Physical activity recognition from accelerometer data using a multi-scale ensemble method. In: IAAIGoogle Scholar
  49. 49.
    Zhong J, Liu L, Wei Y, Luo D, Sun L, Lu Y (2014) Personalized activity recognition using molecular complex detection clustering. In: Ubiquitous Intelligence and Computing, 2014 IEEE 11th Intl Conf on and IEEE 11th Intl Conf on and Autonomic and Trusted Computing, and IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UTC-ATC-ScalCom). pp. 850–854. IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.School of Information Science and EngineeringLanzhou UniversityGansuChina
  2. 2.School of Software EngineeringChongqing UniversityChongqingChina
  3. 3.School of ComputingNational University of SingaporeSingaporeSingapore

Personalised recommendations