Advertisement

Evaluation of artificial intelligence techniques for the classification of different activities of daily living and falls

  • Ivanoe De Falco
  • Giuseppe De Pietro
  • Giovanna Sannino
Intelligent Biomedical Data Analysis and Processing
  • 49 Downloads

Abstract

Automatic detection of falls is extremely important, especially in the remote monitoring of elderly people, and will become more and more critical in the future, given the constant increase in the number of older adults. Within this framework, this paper deals with the task of evaluating several artificial intelligence techniques to automatically distinguish between different activities of daily living (ADLs) and different types of falls. To do this, UniMiB SHAR, a publicly available data set containing instances of nine different ADLs and of eight kinds of falls, is considered. We take into account five different classes of classification algorithms, namely tree-based, discriminant-based, support vector machines, K-nearest neighbors, and ensemble mechanisms, and we consider several representatives for each of these classes. These are all the classes contained in the Classification Learner app contained in MATLAB, which serves as the computational basis for our experiments. As a result, we apply 22 different classification algorithms coming from artificial intelligence under a fivefold cross-validation learning strategy, with the aim to individuate which the most suitable is for this data set. The numerical results show that the algorithm with the highest classification accuracy is the ensemble based on subspace as the ensemble method and on KNN as learner type. This shows an accuracy equal to 86.0%. Its results are better than those in the other papers in the literature that face this specific 17-class problem.

Keywords

Artificial intelligence Classification Fall detection Activities of daily living 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare that the writing of this paper does not cause any competing interests to them.

References

  1. 1.
    Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46(3):175–185MathSciNetGoogle Scholar
  2. 2.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefzbMATHGoogle Scholar
  3. 3.
    Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth & Brooks/Cole Advanced Books and Software, DonohozbMATHGoogle Scholar
  4. 4.
    Bulling A, Blanke U, Schiele B (2014) A tutorial on human activity recognition using body-worn inertial sensors. ACM Comput Surv (CSUR) 46(3):33CrossRefGoogle Scholar
  5. 5.
    Centers for Disease Control and Prevention (2006) Fatalities and injuries from falls among older adults—United States, 1993–2003 and 2001–2005. MMWR Morb Mortal Wky Rep 55(45):1221–1224Google Scholar
  6. 6.
    Chaudhuri S, Thompson H, Demiris G (2014) Fall detection devices and their use with older adults: a systematic review. J Geriatr Phys Therapy (2001) 37(4):178CrossRefGoogle Scholar
  7. 7.
    De Falco I (2013) Differential evolution for automatic rule extraction from medical databases. Appl Soft Comput 13(2):1265–1283CrossRefGoogle Scholar
  8. 8.
    De Falco I, Della Cioppa A, Tarantino E (2006) Automatic classification of handsegmented image parts with differential evolution. In: Workshops on applications of evolutionary computation, pp 403–414. SpringerGoogle Scholar
  9. 9.
    Feldhorst S, Masoudenijad M, ten Hompel M, Fink GA (2016) Motion classification for analyzing the order picking process using mobile sensors. In: Proceedings of the 5th international conference on pattern recognition applications and methods, pp 706–713. SCITEPRESS-Science and Technology Publications, LdaGoogle Scholar
  10. 10.
    Harris A, True H, Hu Z, Cho J, Fell N, Sartipi M (2016) Fall recognition using wearable technologies and machine learning algorithms. In: IEEE international conference on big data (big data), 2016, pp 3974–3976. IEEEGoogle Scholar
  11. 11.
    He H, Ma Y (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley, HobokenCrossRefzbMATHGoogle Scholar
  12. 12.
    Ivascu T, Cincar K, Dinis A, Negru V (2017) Activities of daily living and falls recognition and classification from the wearable sensors data. In: E-health and bioengineering conference (EHB), 2017, pp 627–630. IEEEGoogle Scholar
  13. 13.
    John G.H, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the eleventh conference on uncertainty in artificial intelligence, pp 338–345Google Scholar
  14. 14.
    Kannus P, Parkkari J, Niemi S, Palvanen M (2005) Fall-induced deaths among elderly people. Am J Public Health 95(3):422–424CrossRefGoogle Scholar
  15. 15.
    Lara OD, Labrador MA et al (2013) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 15(3):1192–1209CrossRefGoogle Scholar
  16. 16.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  17. 17.
    Li F, Shirahama K, Nisar MA, Köping L, Grzegorzek M (2018) Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18(2):679CrossRefGoogle Scholar
  18. 18.
    Liu J, Sohn J, Kim S (2017) Classification of daily activities for the elderly using wearable sensors. J Healthc Eng 2017:1–7Google Scholar
  19. 19.
    Malhotra A, Schizas ID, Metsis V (2018) Correlation analysis-based classification of human activity time series. IEEE Sens J 18(3):1–11CrossRefGoogle Scholar
  20. 20.
    Melillo P, Castaldo R, Sannino G, Orrico A, De Pietro G, Pecchia L (2015) Wearable technology and ecg processing for fall risk assessment, prevention and detection. In: Engineering in medicine and biology society (EMBC), 2015 37th annual international conference of the IEEE, pp 7740–7743. IEEEGoogle Scholar
  21. 21.
    Mellone S, Tacconi C, Schwickert L, Klenk J, Becker C, Chiari L (2012) Smartphone-based solutions for fall detection and prevention: the farseeing approach. Zeitschrift für Gerontologie und Geriatrie 45(8):722–727CrossRefGoogle Scholar
  22. 22.
    Micucci D, Mobilio M, Napoletano P (2017) Unimib shar: a dataset for human activity recognition using acceleration data from smartphones. Appl Sci 7(10):1–19CrossRefGoogle Scholar
  23. 23.
    Micucci D, Mobilio M, Napoletano P, Tisato F (2017) Falls as anomalies? An experimental evaluation using smartphone accelerometer data. J Ambient Intell Hum Comput 8(1):87–99CrossRefGoogle Scholar
  24. 24.
    Narsky I, Porter FC (2013) Statistical analysis techniques in particle physics: fits. Density estimation and supervised learning. Wiley, HobokenCrossRefGoogle Scholar
  25. 25.
    Ngu AH, Tseng PT, Paliwal M, Carpenter C, Stipe W (2018) Smartwatch-based IoT fall detection application. Open J Internet Things (OJIOT) 4(1):87–98Google Scholar
  26. 26.
    Ordonez FJ, Englebienne G, De Toledo P, Van Kasteren T, Sanchis A, Krose B (2014) In-home activity recognition: Bayesian inference for hidden Markov models. IEEE Pervasive Comput 13(3):67–75CrossRefGoogle Scholar
  27. 27.
    Ordóñez FJ, Roggen D (2016) Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115CrossRefGoogle Scholar
  28. 28.
    Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schölkopf B, Burges CJC, Smola AJ (eds) Advances in Kernel methods—support vector learning. MIT Press, Cambridge, pp 185–208Google Scholar
  29. 29.
    Public Health Agency of Canada (2005) Division of aging and seniors: report on seniors’ falls in Canada. Division of Aging and Seniors, Public Health Agency of Canada, OttawaGoogle Scholar
  30. 30.
    Quiroz JC, Banerjee A, Dascalu SM, Lau SL (2017) Feature selection for activity recognition from smartphone accelerometer data. Intell Autom Soft Comput.  https://doi.org/10.1080/10798587.2017.1342400 Google Scholar
  31. 31.
    Reyes-Ortiz JL, Oneto L, Samà A, Parra X, Anguita D (2016) Transition-aware human activity recognition using smartphones. Neurocomputing 171:754–767CrossRefGoogle Scholar
  32. 32.
    Roggen D, Cuspinera LP, Pombo G, Ali F, Nguyen-Dinh LV (2015) Limited-memory warping lcss for real-time low-power pattern recognition in wireless nodes. In: European conference on wireless sensor networks, pp 151–167. SpringerGoogle Scholar
  33. 33.
    Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33(1–2):1–39CrossRefGoogle Scholar
  34. 34.
    Rubenstein L.Z (2006) Falls in older people: epidemiology, risk factors and strategies for prevention. Age Ageing 35(\(\text{suppl}\_2\)): ii37–ii41Google Scholar
  35. 35.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representation by back-propagation errors. Nature 323:533–536CrossRefzbMATHGoogle Scholar
  36. 36.
    Saez Y, Baldominos A, Isasi P (2016) A comparison study of classifier algorithms for cross-person physical activity recognition. Sensors 17(1):66CrossRefGoogle Scholar
  37. 37.
    Salguero AG, Espinilla M, Delatorre P, Medina J (2018) Using ontologies for the online recognition of activities of daily living. Sensors 18(4):1202CrossRefGoogle Scholar
  38. 38.
    Sannino G, De Falco I, De Pietro G (2014) Effective supervised knowledge extraction for an mhealth system for fall detection. In: XIII Mediterranean conference on medical and biological engineering and computing 2013, pp 1378–1381. SpringerGoogle Scholar
  39. 39.
    Sannino G, De Falco I, De Pietro G (2015) A supervised approach to automatically extract a set of rules to support fall detection in an mhealth system. Appl Soft Comput 34:205–216CrossRefGoogle Scholar
  40. 40.
    Sannino G, De Falco I, De Pietro G (2016) Easy fall risk assessment by estimating the mini-bes test score. In: IEEE 18th international conference on e-health networking, applications and services (Healthcom), 2016, pp 1–5. IEEEGoogle Scholar
  41. 41.
    Sannino G, De Falco I, De Pietro G (2017) Detection of falling events through windowing and automatic extraction of sets of rules: preliminary results. In: IEEE 14th international conference on networking, sensing and control (ICNSC), 2017, pp 661–666. IEEEGoogle Scholar
  42. 42.
    Sannino G, De Falco I, De Pietro G (2017) A statistical analysis for the evaluation of the use of wearable and wireless sensors for fall risk reduction. In: HEALTHINF, pp 508–516Google Scholar
  43. 43.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117CrossRefGoogle Scholar
  44. 44.
    Taramasco C, Rodenas T, Martinez F, Fuentes P, Munoz R, Olivares R, Albuquerque VHC, Demongeot J (2018) A novel low-cost sensor prototype for nocturia monitoring in older people. IEEE Access 6:52500–52509CrossRefGoogle Scholar
  45. 45.
    Taramasco C, Rodenas T, Martinez F, Fuentes P, Munoz R, Olivares R, De Albuquerque VHC, Demongeot J (2018) A novel monitoring system for fall detection in older people. IEEE Access 6:43563–43574CrossRefGoogle Scholar
  46. 46.
    The Mathworks, Inc. (2017) MATLAB version 9.3.0.713579 (R2017b). NatickGoogle Scholar
  47. 47.
    Van Thanh P, Tran DT, Nguyen DC, Anh ND, Dinh DN, El-Rabaie S, Sandrasegaran K (2018) Development of a real-time, simple and high-accuracy fall detection system for elderly using 3-dof accelerometers. Arab J Sci Eng.  https://doi.org/10.1007/s13369-018-3496-4 Google Scholar
  48. 48.
    World Health Organization (2018) WHO global report on falls prevention in older age. World Health Organization, GenevaGoogle Scholar
  49. 49.
    Yao R, Lin G, Shi Q, Ranasinghe DC (2018) Efficient dense labelling of human activity sequences from wearables using fully convolutional networks. Pattern Recognit 78:252–266CrossRefGoogle Scholar
  50. 50.
    Yoo S, Oh D (2018) An artificial neural network-based fall detection. Int J Eng Bus Manag 10:1847979018787905CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.ICARNational Research Council of ItalyNaplesItaly

Personalised recommendations