Pattern Analysis and Applications

, Volume 21, Issue 1, pp 119–138 | Cite as

The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition

  • Bilal M’hamed Abidine
  • Lamya Fergani
  • Belkacem Fergani
  • Mourad Oussalah
Theoretical Advances


Two serious problems affecting the implementation of human activity recognition algorithms have been acknowledged. The first one corresponds to non-informative sequence features. The second is the class imbalance in the training data due to the fact that people do not spend the same amount of time on the different activities. To address these issues, we propose a new scheme based on a combination of principal component analysis, linear discriminant analysis (LDA) and the modified weighted support vector machines. First we added the most significant principal components to the set of features extracted using LDA. This work shows that a suitable sequence feature set combined with the modified WSVM based on our criterion classifier achieves good improvement and efficiency over the traditional used methods.


Activity recognition PCA LDA SVM Imbalanced data classification 


  1. 1.
    Tapia EM, Intille SS, Larson K (2004) Activity recognition in the home using simple and ubiquitous sensors, vol 3001. Springer, Berlin, pp 158–175Google Scholar
  2. 2.
    Van Kasteren T, Noulas A, Englebienne G, Kröse B (2008) Accurate activity recognition in a home setting. In: Proceedings of UbiComp’08. ACM, New York, NY, pp 1–9Google Scholar
  3. 3.
    Ordóñez FJ, de Toledo P, Sanchis A (2013) Activity recognition using hybrid generative/discriminative models on home environments using binary sensors. Sensors 13:5460–5477CrossRefGoogle Scholar
  4. 4.
    Logan B, Healey J, Philipose M, Tapia EM, Intille S (2007) A long-term evaluation of sensing modalities for activity recognition. In: Proceedings of the 9th international conference on ubiquitous computing. Springer, Berlin, pp 483–500Google Scholar
  5. 5.
    Chen L, Hoey J, Nugent C, Cook D, Yu Z (2012) Sensor based activity recognition. IEEE Trans Syst Man Cybern Part C 42(6):790–808CrossRefGoogle Scholar
  6. 6.
    Kidd CD, Orr R, Abowd GD, Atkeson CG, Essa IA, MacIntyre B, Mynatt ED, Starner T, Newstetter W (1999) The aware home: a living laboratory for ubiquitous computing research. In: Proceedings of the second international workshop on cooperative buildings, integrating information, organization, and architecture, CoBuild’99. Springer, London, pp 191–198Google Scholar
  7. 7.
    Kasteren TLM, Englebienne G, Krose BJA (2011) Human activity recognition from wireless sensor network data: benchmark and software. In: Activity recognition in pervasive intelligent environments. Atlantis Press, Paris, pp 165–186Google Scholar
  8. 8.
    Cook DJ, Augusto JC, Jakkula VR (2009) Ambient intelligence: technologies, applications, and opportunities. Pervasive Mob Comput 5(4):277–298CrossRefGoogle Scholar
  9. 9.
    Barger T, Alwan M, Kell S, Turner B, Wood S, Naidu A (2002) Objective remote assessment of activities of daily living: analysis of meal preparation patterns. Poster presentation, Medical Automation Research Center, University of Virginia Health SystemGoogle Scholar
  10. 10.
    Cook D, Schmitter-Edgecombe M, Crandall A, Sanders C, Thomas B (2009) Collecting and disseminating smart home sensor data in the CASAS project. In: Proceedings of CHI09 workshop on developing shared home behavior datasets to advance HCI and ubiquitous computing researchGoogle Scholar
  11. 11.
    Oppurtunity EU project. Accessed April 2015
  12. 12.
  13. 13.
    The Aware Home. Accessed April 2015
  14. 14.
  15. 15.
    Aggrawal JK, Ryoo MS (2011) Human activity analysis: a review. ACM Comput Surv 43(3):16:1–16:43Google Scholar
  16. 16.
    Krishnan NC, Cook DJ (2014) Activity recognition on streaming sensor data. Pervasive Mob Comput 10:138–154CrossRefGoogle Scholar
  17. 17.
    Andreu J, Angelov P (2010) Real-time human activity recognition from wireless sensors using evolving fuzzy systems. In: Proceedings of IEEE World Congress on computational intelligence, pp 2652–2659Google Scholar
  18. 18.
    Chen L, Nugent CD, Wang H (2012) A knowledge-driven approach to activity recognition in smart homes. IEEE Trans Knowl Data Eng 24:961–974CrossRefGoogle Scholar
  19. 19.
    Bishop C (2006) Pattern recognition and machine learning. Springer, New York. ISBN: 978-0-387-31073-2Google Scholar
  20. 20.
    Huang W, Zhang J, Liu Z (2007) Activity recognition based on hidden Markov models. In: Knowledge science, engineering and management. Springer, Berlin, pp 532–537Google Scholar
  21. 21.
    Vail DL, Veloso MM, Lafferty JD (2007) Conditional random fields for activity recognition. In: International conference on autonomous agents and multi-agent systems (AAMAS)Google Scholar
  22. 22.
    Abidine MB, Fergani B (2012) Evaluating C-SVM, CRF and LDA classification for daily activity recognition. In: Proceedings of IEEE ICMCS, Tangier-Morocco. IEEE, pp 272–277Google Scholar
  23. 23.
    Liu S, Gao RX, John D, Staudenmayer J, Freedson PS (2012) Classification of physical activities based on sparse representation. In: 2012 annual international conference of the IEEE engineering in medicine and biology society (EMBC), 28 August–1 September, pp 6200–6203Google Scholar
  24. 24.
    Fang H, He L (2012) BP neural network for human activity recognition in smart home. In: 2012 international conference on computer science & service system (CSSS), 11–13 August, pp 1034–1037Google Scholar
  25. 25.
    Fleury A, Vacher M, Noury N (2010) SVM-based multi-modal classification of activities of daily living in health smart homes: sensors, algorithms and first experimental results. IEEE Trans Inf Technol Biomed 14(2):274–283CrossRefGoogle Scholar
  26. 26.
    Abidine MB, Fergani B, Clavier L (2013) Importance-weighted the imbalanced data for C-SVM classifier to human activity recognition. In: Proceedings of IEEE WOSSPA’13, pp 330–335Google Scholar
  27. 27.
    Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, CambridgeMATHGoogle Scholar
  28. 28.
    Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(115):1–25Google Scholar
  29. 29.
    Plotz T, Hammerla NY, Olivier P (2011) Feature learning for activity recognition in ubiquitous computing. In: IJCAI proceedings—international joint conference on artificial intelligence, vol 22, no 1, pp 1729–1735Google Scholar
  30. 30.
    Pechenizkiy M, Tsymbal A, Puuronen S (2005). On combining principal components with parametric LDA-based feature extraction for supervised learning. In: Morzy T et al (eds) Proceedings of 1st international workshop on data mining and knowledge discovery, ADMKD’05, Estonia, pp 47–56Google Scholar
  31. 31.
    Guyon I, Gunn S, Nikravesh M, Zadeh LA (2006) Feature extraction: foundations and applications. Springer, BerlinCrossRefMATHGoogle Scholar
  32. 32.
    Chawla NV (2010) Data mining for imbalanced datasets: an overview. In: Data mining and knowledge discovery handbook. Springer, pp 875–886Google Scholar
  33. 33.
    Akbani R, Kwek S, Japkowicz N (2004) Applying support vector machines to imbalanced datasets. In: Machine learning: ECML 2004. Springer, Berlin, pp 39–50Google Scholar
  34. 34.
    Hulse JV, Khoshgoftaar TM, Napolitano A (2007) Experimental perspectives on learning from imbalanced data. In: Proceedings of the 24th international conference on machine learning, Corvallis, OR, pp 143–146Google Scholar
  35. 35.
    Wu G, Chang E (2005) Y, KBA: kernel boundary alignment considering imbalanced data distribution. IEEE Trans Knowl Data Eng 17(6):786–795CrossRefGoogle Scholar
  36. 36.
    Raskutti B, Kowalczyk A (2004) Extreme re-balancing for SVMs: a case study. SIGKDD Explor 6(1):60–69CrossRefGoogle Scholar
  37. 37.
    Huang YM, Du SX (2005) Weighted support vector machine for classification with uneven training class sizes. In: Proceedings of the IEEE international conference on machine learning and cybernetics, vol 7, pp 4365–4369Google Scholar
  38. 38.
    Abidine MB, Fergani L, Fergani B, Fleury A (2015) Improving human activity recognition in smart homes. Int J E-Health Med Commun (IJEHMC) 6(3):19–37CrossRefGoogle Scholar
  39. 39.
    Frank A, Asuncion A (2010) UCI machine learning repositoryGoogle Scholar
  40. 40.
    Datasets for Activity Recognition. Accessed 09 Feb 2012
  41. 41.
  42. 42.
  43. 43.
    Jolliffe IT (2010) Principal component analysis, 2nd edn. Springer, NewYork, NYMATHGoogle Scholar
  44. 44.
    Peterek T, Penhaker M, Gajdoš P, Dohnálek P (2014) Comparison of classification algorithms for physical activity recognition. In: Innovations in bio-inspired computing and applications. Springer International Publishing, pp 123–131Google Scholar
  45. 45.
    Duda RO, Hart PE, Stork DG (2001) Pattern classification. Willy, HobokenMATHGoogle Scholar
  46. 46.
    Dargham JA, Chekima A, Moung EG Fusion of PCA and LDA based face recognition system. In: International conference on software and computer applications (ICSCA 2012), vol 41, pp 111–116Google Scholar
  47. 47.
    Marcialis GL, Roli F (2002) Fusion of LDA and PCA for face verification. In: Proceedings of the workshop on machine vision and perception, 8th workshop of the Italian association for artificial intelligence (ALLA 02)Google Scholar
  48. 48.
    Cortes C, Vapnik V (1995) Support vector network. Mach Learn 20:1–25MATHGoogle Scholar
  49. 49.
    Osuna E, Freund R, Girosi F (1997) Support vector machines: training and applications. Massachusetts Institute of Technology, Cambridge, MAGoogle Scholar
  50. 50.
    Veropoulos K, Campbell C, Cristianini N (1999) Controlling the sensitivity of support vector machines. In: Proceedings of the international joint conference on AI, pp 55–60Google Scholar
  51. 51.
    Hsu CW, Chang CC, Lin CJ (2008) A practical guide to support vector classification.
  52. 52.
    Chathuramali M, Rodrigo R (2012) Faster human activity recognition with SVM. In: Proceedings of international conference of advances in ICT for emerging regions. IEEE, pp 197–203Google Scholar
  53. 53.
    Rabiner LR (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286CrossRefGoogle Scholar
  54. 54.
    Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  55. 55.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27.
  56. 56.
    Chen PH, Lin CJ, Scholköpf B (2005) A tutorial on nu-support vector machines. Appl Stoch Models Bus Indus 21:111–136CrossRefMATHGoogle Scholar
  57. 57.
    Katz S, Down TD, Cash HR (1970) Progress in the development of the index of ADL. Gerontologist 10:20–30CrossRefGoogle Scholar
  58. 58.
    Abidine MB, Fergani B (2015) News schemes for activity recognition systems using PCA–WSVM, ICA–WSVM, and LDA–WSVM. Information 6(3):505–521CrossRefGoogle Scholar
  59. 59.
    Van Kasteren T, Alemdar H, Ersoy C (2011) Effective performance metrics for evaluating activity recognition methods. In: Proceedings of the ARCS 2011—24th international conference on architecture of computing systems, Comot, Italy, 24–25 Feb 2011, p 10Google Scholar
  60. 60.
    Van Kasteren T, Englebienne G, Kröse BJ (2010) An activity monitoring system for elderly care using generative and discriminative models. Pers Ubiquitous Comput 14:489–498CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  1. 1.Laboratoire d’Ingénierie des Systèmes Intelligents et Communicants, LISIC Laboratory, Electronics and Computer Sciences DepartmentUniversity of Science and Technology Houari Boumediene (USTHB)Bab Ezzouar, AlgiersAlgeria
  2. 2.Electrical and Computer Engineering DepartmentUniversity of BirminghamBirminghamUK
  3. 3.Centre for Ubiquitous ComputingUniversity of OuluOuluFinland

Personalised recommendations