Skip to main content
SpringerLink
Log in

Multi-sensor Fusion Based on Asymmetric Decision Weighting for Robust Activity Recognition

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

The recognition of human activity has been deeply explored during the recent years. However, most proposed solutions are mainly devised to operate in ideal conditions, thus not addressing crucial real-world issues. One of the most prominent challenges refers to common sensor technological anomalies. Sensor faults and failures introduce variations in the measured sensor data with respect to the equivalent observations in ideal conditions. As a consequence, predefined recognition systems may potentially fail to identify actions in the anomalous sensor data. This paper presents a novel model devised to cope with the effects introduced by sensor technological anomalies. The model builds on the knowledge gained from multi-sensor configurations, through asymmetrically weighting the decisions provided at both activity and sensor levels. Insertion and rejection weighting metrics are particularly used to eventually yield a unique recognized activity. For the sake of comparison, the tolerance to sensor faults and failures of standard activity recognition systems and the new proposed model are evaluated. The results prove classic activity-aware systems to be incapable of recognition under the effects of sensor technological anomalies, while the proposed model demonstrates to be robust against both sensor faults and failures.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. Other approaches as the one-versus-one may be similarly applied; however, the one-versus-rest model is particularly recommended here to minimize the number of classification entities.

  2. In machine learning, insertions (hits) and rejections (deletions) respectively refer to positive and negative classifications. For the one-versus-rest decision strategy, an insertion is observed when the classifier recognizes a class to belong to its class of specialization, while a rejection is generated when the class is identified to belong to any of the rest of the classes.

  3. Dataset files and description could be obtained at http://architecture.mit.edu/house_n/data/Accelerometer/BaoIntilleData04.htm.

References

  1. Adidas\(^{\textregistered }\) (2013) Adidas micoach. http://micoach.adidas.com/

  2. Albert MV, Toledo S, Shapiro M, Kording K (2012) Using mobile phones for activity recognition in Parkinsons patients. Front Neurol 3:158

  3. Altun K, Barshan B (2010) Human activity recognition using inertial/magnetic sensor units. In: Salah AA, Ruiz-del-Solar J, Çetin M, Oudeyer P-Y (eds) Human behavior understanding. Proceedings of the third international workshop, HBU 2012, Vilamoura, Portugal, October 7, 2012. Lecture notes in computer science, pp. 38–51. Springer, Berlin

  4. Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Statist Surv 4:40–79

    Article  MathSciNet  MATH  Google Scholar 

  5. Atallah L, Lo B, King R, Yang GZ (2011) Sensor positioning for activity recognition using wearable accelerometers. IEEE Trans Biomed Circ Syst 5(4):320–329

    Article  Google Scholar 

  6. Avci A, Bosch S, Marin-Perianu M, Marin-Perianu R, Havinga P (2010) Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: a survey. In: 23rd international conference on architecture of computing systems, pp 1–10

  7. Banos O, Damas M, Pomares H, Prieto A, Rojas I (2012) Daily living activity recognition based on statistical feature quality group selection. Expert Syst Appl 39(9):8013–8021

    Article  Google Scholar 

  8. Banos O, Damas M, Pomares H, Rojas F, Delgado-Marquez B, Valenzuela O (2013) Human activity recognition based on a sensor weighting hierarchical classifier. Soft Comput 17:333–343

    Article  Google Scholar 

  9. Banos O, Galvez JM, Damas M, Pomares H, Rojas I (2014) Window size impact in human activity recognition. Sensors 14(4):6474–6499

    Article  Google Scholar 

  10. Banos O, Toth MA, Damas M, Pomares H, Rojas I (2014) Dealing with the effects of sensor displacement in wearable activity recognition. Sensors 14(6):9995–10023

  11. Bao L, Intille SS (2004) Activity recognition from user-annotated acceleration data. Perv Comput 23:1–17

    Article  Google Scholar 

  12. Bouten C, Koekkoek K, Verduin M, Kodde R, Janssen J (1997) A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Trans Biomed Eng 44(3):136–147

    Article  MATH  Google Scholar 

  13. Breiman L, Spector P (1992) Submodel selection and evaluation in regression. the x-random case. Int Statist Rev 60(3):291–319

    Article  Google Scholar 

  14. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theor 13(1):21–27

    Article  MATH  Google Scholar 

  15. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines: and other kernel-based learning methods. Cambridge University Press, New York

    Book  Google Scholar 

  16. Dietterich TG (2000) Ensemble methods in machine learning. In: Proceedings of the first international workshop on multiple classifier systems, pp 1–15. Springer, London

  17. Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley-Interscience, New York

    Google Scholar 

  18. Fitbit\(^{\textregistered }\) (2013) Fitbit products. http://www.fitbit.com/es/store

  19. He Z, Jin L (2009) Activity recognition from acceleration data based on discrete consine transform and svm. In: IEEE international conference on systems, man and cybernetics, pp 5041–5044

  20. Hidalgo\(^{\textregistered }\) (2012) Equivital eq02. http://www.equivital.co.uk/products/tnr/sense-and-transmit

  21. Huynh T, Blanke U, Schiele B (2007) Scalable recognition of daily activities with wearable sensors. In: Location-and context-awareness. Springer, Berlin, pp 50–67

  22. Jawbone\(^{\textregistered }\) (2013) Jawbone up. https://jawbone.com/up/international

  23. Jiang M, Shang H, Wang Z, Li H, Wang Y (2011) A method to deal with installation errors of wearable accelerometers for human activity recognition. Physiol Measure 32(3):347

    Article  Google Scholar 

  24. Kailas A (2012) Capturing basic movements for mobile platforms embedded with motion sensors. In: International conference of the IEEE engineering in medicine and biology society, pp 2480–2483

  25. Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, pp 1137–1143. San Francisco, CA, USA

  26. Kusserow M, Amft O, Gubelmann H, Troester G (2010) Arousal pattern analysis of an olympic champion in ski jumping. Sports Technol 3(3):192–203

    Google Scholar 

  27. Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SigKDD Explor 12(2):74–82

  28. Lara O, Labrador M (2012) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 99:1–18

    Google Scholar 

  29. Lester J, Choudhury T, Kern N, Borriello G, Hannaford B (2005) A hybrid discriminative/generative approach for modeling human activities. In: Proceedings of the 19th international joint conference on artificial intelligence, pp 766–772. San Francisco, CA, USA

  30. Mannini A, Intille SS, Rosenberger M, Sabatini AM, Haskell W (2013) Activity recognition using a single accelerometer placed at the wrist or ankle. Med Sci Sports Exer 45(11):2193–2203

    Article  MATH  Google Scholar 

  31. Mäntyjärvi J, Himberg J, Seppanen T (2001) Recognizing human motion with multiple acceleration sensors. In: Proceedings of the international IEEE conference on systems, man and cybernetics, pp 747–752

  32. Mathie MJ, Coster ACF, Lovell NH, Celler BG (2004) Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement. Physiol Measure 25(2):1–20

    Article  Google Scholar 

  33. Maurer U, Smailagic A, Siewiorek D, Deisher M (2006) Activity recognition and monitoring using multiple sensors on different body positions. In: International workshop on wearable and implantable body sensor networks, pp 113–116

  34. Maurtua I, Kirisci PT, Stiefmeier T, Sbodio ML, Witt H (2007) A wearable computing prototype for supporting training activities in automative production. In: 4th international forum on applied wearable computing

  35. Najafi B, Aminian K, Paraschiv-Ionescu A, Loew F, Bula CJ, Robert P (2003) Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly. IEEE Trans Biomed Eng 50(6):711–723

    Article  Google Scholar 

  36. Nike\(^{\textregistered }\) (2013) Nike \(+\) running. http://nikeplus.nike.com/plus/products/gps_app/

  37. Nike\(^{\textregistered }\) (2013) Nike \(+\) sportwatch. http://nikeplus.nike.com/plus/products/sport_watch/

  38. Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J, Korhonen I (2006) Activity classification using realistic data from wearable sensors. IEEE Trans Inf Technol Biomed 10(1):119–128

    Article  Google Scholar 

  39. Pirttikangas S, Fujinami K, Seppanen T (2006) Feature selection and activity recognition from wearable sensors. In: Third international symposium ubiquitous computing systems. LNCS vol 4239, pp 516–527. Springer, Berlin

  40. Preece SJ, Goulermas JY, Kenney LPJ, Howard D, Meijer K, Crompton R (2009) Activity identification using body-mounted sensors—a review of classification techniques. Physiol Measure 30(4):1–33

    Article  Google Scholar 

  41. Ravi N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data. In: Proceedings of the seventeenth conference on innovative applications of artificial intelligence, pp 1541–1546

  42. Roggen D, Calatroni A, Rossi M, Holleczek T, Förster K, Tröster G, Lukowicz P, Bannach D, Pirkl G, Ferscha A, Doppler J, Holzmann C, Kurz M, Holl G, Chavarriaga R, Creatura M, del Millán JR (2010) Collecting complex activity data sets in highly rich networked sensor environments. In: 7th international conference on networked sensing systems, pp 233–240

  43. Roggen D, Magnenat S, Waibel M, Tröster G (2011) Wearable computing: designing and sharing activity-recognition systems across platforms. IEEE Robot Automat Mag 18(2):83–95

  44. Sagha H, Bayati H, del Millan JR, Chavarriaga R (2013) On-line anomaly detection and resilience in classifier ensembles. Pattern Recognit Lett 34(15):1916–1927

  45. Sazonov E, Fulk G, Sazonova N, Schuckers S (2009) Automatic recognition of postures and activities in stroke patients. In: International conference of the IEEE engineering in medicine and biology society, pp 2200–2203

  46. Selles R, Formanoy M, Bussmann J, Janssens P, Stam H (2005) Automated estimation of initial and terminal contact timing using accelerometers; development and validation in transtibial amputees and controls. IEEE Trans Neural Syst Rehab Eng 13(1):81–88

    Article  Google Scholar 

  47. Stiefmeier T, Roggen D, Ogris G, Lukowicz P, Tröster G (2008) Wearable activity tracking in car manufacturing. IEEE Perv Comput Mag 7(2):42–50

    Article  Google Scholar 

  48. Stone M (1977) Asymptotics for and against cross-validation. Biometrika 64(1):29–35

  49. Sun L, Zhang D, Li B, Guo B, Li S (2010) Activity recognition on an accelerometer embedded mobile phone with varying positions and orientations. In: Yu Z, Liscano R, Chen G, Zhang D, Zhou X (eds) Ubiquitous intelligence and computing. Proceedings of the 7th international conference, UIC 2010, Xi’an, China, October 2010. LNCS pp. 548–562. Springer, Berlin

  50. Theodoridis S, Koutroumbas K (2008) Pattern recognition, 4th edn. Academic, San Diego

    Google Scholar 

  51. UnderArmour\(^{\textregistered }\) (2014) Armour39. http://www.underarmour.com/shop/us/en/armour39

  52. Ward JA, Lukowicz P, Gellersen HW (2011) Performance metrics for activity recognition. ACM Trans Intell Syst Technol 2(1):6:1–6:23

  53. Zwartjes D, Heida T, van Vugt J, Geelen J, Veltink P (2010) Ambulatory monitoring of activities and motor symptoms in Parkinson’s disease. IEEE Trans Biomed Eng 57(11):2778–2786

    Article  Google Scholar 

Download references

Acknowledgments

This work was partially supported by the HPC-Europa2 project (no. 228398), the Spanish CICYT Project SAF2010-20558, Junta de Andalucia Project P09-TIC-175476 and the FPU Spanish Grant AP2009-2244.

Author information

Authors and Affiliations

  1. Department of Computer Architecture and Computer Technology, Research Center for Information and Communication Technologies of the University of Granada (CITIC-UGR), C/Periodista Rafael Gomez Montero 2, 18071, Granada, Spain

    Oresti Banos, Miguel Damas, Alberto Guillen, Luis-Javier Herrera, Hector Pomares, Ignacio Rojas & Claudia Villalonga

Authors
  1. Oresti Banos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miguel Damas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alberto Guillen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Luis-Javier Herrera
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hector Pomares
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ignacio Rojas
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Claudia Villalonga
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Oresti Banos.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Banos, O., Damas, M., Guillen, A. et al. Multi-sensor Fusion Based on Asymmetric Decision Weighting for Robust Activity Recognition. Neural Process Lett 42, 5–26 (2015). https://doi.org/10.1007/s11063-014-9395-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-014-9395-0

Keywords

Search

Navigation