AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
This paper presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data

Physical Human Activity Recognition Using Wearable Sensors

SENSORS, no. 12.0 (2015): 31314.0-31338

Cited by: 130|Views259
EI

Abstract

This paper presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data. Three inertial sensor units were used in this study and were worn by healthy subjects at key points of upper/lower body limbs (chest, right thigh and left ankle). Three main steps describe the activity...More

Code:

Data:

0
Introduction
  • The aging population is constantly increasing around the world. In the last decade, the active involvement and participation of the elderly in society became an important challenge from a social and economic point of view.
  • Activity recognition based on new wearable technologies is one of these important challenges.
  • Sensors 2015, 15, 31314–31338 alone, physically or mentally disabled people, and children.
  • These populations need continuous monitoring of their activities to detect abnormal situations or prevent unpredictable events such as falls [1].
  • The new technologies of health monitoring devices range from on-body wearable sensors to in vivo sensors.
  • Bio-sensors are generally used to monitor vital signs such as
Highlights
  • The aging population is constantly increasing around the world
  • This paper in organized as follows: in Section 2, background on wearable sensor’s placement, pre-processing data including feature extraction/selection and classification techniques used in the field of human activity recognition, are addressed
  • We briefly describe the classification techniques used in this study (GMMs, k-Nearest Neighbors (k-NN), Support Vector Machines, Random Forests (RFs), K-means and Hidden Markov Model), as well as other techniques that are widely used in human activity recognition such as multilayer perceptron, naive Bayes, hierarchical classification, etc
  • The k-Nearest Neighbor algorithm gives the best results in terms of global correct classification rate, F-measure, recall, and precision, followed by Random Forest, Support Vector Machines and at the Supervised Learning Gaussian Mixture Models algorithm gives relatively the worst results
  • We have presented a review of different classification techniques that were used to recognize human activities from wearable inertial sensor data
  • This paper describes the whole structure of the recognition detection process, from data acquisition to classification
Methods
  • 3.InMtheitshosdecstion, the authors present the proposed methodology including data acquisition, the used classifierIsn atnhdis tsheectipoenr,fowrme apnrceeseenvtatlhueatipornopuossiendg mtheeth1o0d-foololdgycrionscsluvdailnidgadtiaotna maceqtuhiosdit.ioFni,guthre u3sed sumcmlaassrifizesrsthaendiftfhereenptersftoeprms oanf ctheeeavdaolupatetidonapupsrionagchth. e 10-fold cross validation method.
  • 3.InMtheitshosdecstion, the authors present the proposed methodology including data acquisition, the used classifierIsn atnhdis tsheectipoenr,fowrme apnrceeseenvtatlhueatipornopuossiendg mtheeth1o0d-foololdgycrionscsluvdailnidgadtiaotna maceqtuhiosdit.ioFni,guthre u3sed sumcmlaassrifizesrsthaendiftfhereenptersftoeprms oanf ctheeeavdaolupatetidonapupsrionagchth.
  • E 10-fold cross validation method.
  • Figure 3 summarizes the different steps of the adopted approach.
  • Data Acquisition 3.1.
  • Data Acquisition In this study, human activities are estimated using the Xbus Kit from Xsens (Enschede, NetherlaInndsth) iws hsitcuhdeyn, abhluems aamn baucltaivtoitriyesmaeraesuersetmimeantteodf tuhseinhgumthaen mXboutisonK.
  • IItt cforonmsistXs soefnasprwpohriacthesenaanbXlebsuasmMbualsatetorraynmd etahsruereeMmeTnxt ionfetrhtiealhuunmitasntmhaottaiorne .pIltaccoendsiosntstohfeacphoesrtt,able the sryigsthetmththigaht ianncodrpthoeralteefst aannkXlbeuosfMthasetesruabnjedctthsreeee FMigTuxriene4r.tiEaalcuhniMtsTthxaut narite ipslaecqeudipopnetdhewcihtehsta, the tri-arxigiahlt athccigehleraonmdettheer lteoft manekalseuoref tthhees3uDbjeacctcseeleerFaitgiounre, a4.
  • Rmesapneucatlilvyelvye. rIinfiethdisbosttuhdqyuaannteitxiteesrnal prioorpteoraeatocrhheaxspmeraimnueanltlaytivoenritfieesdt. both quantities prior to each experimentation test
Results
  • The authors review and compare the performances of the standard supervised and unsupervised machine learning approaches to recognize the daily living activities presented in the previous section.
  • This comparison highlights the different algorithm performances in terms of average accuracy rate (R) and its standard deviation, F-measure, recall, precision and specificity.
  • The k-NN algorithm gives the best results in terms of global correct classification rate, F-measure, recall, and precision, followed by RF, SVM and at the SLGMM algorithm gives relatively the worst results
Conclusion
  • It is clear that comparing algorithm performance across different studies is a difficult task for many reasons
  • This difficulty is mainly related to: (i) the variability in the experimental protocols; the applicative objectives behind the human activity recognition; the type of sensors used thaant dcomthpaeriirngaatltgaocrhithmmepnetrfotromatnhcee abcroodssydif;.
  • The authors have presented a review of different classification techniques that were used to recognize human activities from wearable inertial sensor data.
  • The different classification approaches are compared in terms of the recognition of twelve activities using data from three MTx inertial IMUs placed at the chest, the right thigh and the left ankle
Tables
  • Table1: Review of studies on accelerometer placement for human activity recognition
  • Table2: Table 2
  • Table3: Performances of the supervised algorithms using raw data
  • Table4: Performance results of the unsupervised algorithms using raw data
  • Table5: Global confusion matrix obtained with k-NN using raw data
  • Table6: Global confusion matrix obtained with HMM using raw data
  • Table7: Performances of the supervised algorithms using extracted features
  • Table8: Performances of the unsupervised algorithms using extracted features
  • Table9: Global confusion matrix obtained with k-NN using selected features
  • Table10: Global confusion matrix obtained with HMM using selected features
Download tables as Excel
Funding
  • Presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data
Reference
  • Karantonis et al., 2006 [15]
    Google ScholarFindings
  • Mathie, 2004 [18]
    Google ScholarFindings
  • Yang et al., 2008
    Google ScholarFindings
  • [20] Pirttikangas, 2006
    Google ScholarFindings
  • [21] Parkka, 2006 [17] Olguın, 2006 [22]
    Google ScholarFindings
  • Bonomi, 2009 [14]
    Google ScholarFindings
  • [19] Lyons, 2005 [23] Salarian et al., 2007 [24]
    Google ScholarLocate open access versionFindings
  • Gjoreski, 2011 [25]
    Google ScholarFindings
  • Chamroukhi, 2013 [7]
    Google ScholarFindings
  • Bayat et al., 2014 [26]
    Google ScholarFindings
  • Moncada-Torres, 2014 [27]
    Google ScholarFindings
  • Gupta et al. 2014 [28]
    Google ScholarFindings
  • Garcia-Ceja et al., 2014 [29]
    Google ScholarFindings
  • Gao et al., 2014 [8]
    Google ScholarFindings
  • Sensors 2015, 15, 31314–31338 Sensors 2015, 15, page–page
    Google ScholarLocate open access versionFindings
  • [63] Foerster and Fahrenberg combined k-NN with a hierarchical decision approach to recognize nine activities using frequency-domain features. This approach has shown to be more efficient, in terms of classification accuracy, compared to the k-NN. Other studies based on k-NN for human activity recognition have also shown a high level of accuracy and satisfactory segmentation results [7,64].
    Google ScholarFindings
  • 4. Experimental Results
    Google ScholarFindings
  • 5. Conclusions and Future Work
    Google ScholarFindings
  • 1. Chan, M.; Estève, D.; Fourniols, J.-Y.; Escriba, C.; Campo, E. Smart wearable systems: Current status and future challenges. Artif. Intel. Med. 2012, 56, 137–156. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 2. Teng, X.-F.; Zhang, Y.-T.; Poon, C.C.; Bonato, P. Wearable medical systems for p-health. IEEE Rev. Biomed. Eng. 2008, 1, 62–74. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 3. Preece, S.J.; Goulermas, J.Y.; Kenney, L.P.; Howard, D.; Meijer, K.; Crompton, R. Activity identification using body-mounted sensors—A review of classification techniques. Physiol. Meas. 2009, 30. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 4. Patel, S.; Park, H.; Bonato, P.; Chan, L.; Rodgers, M. A review of wearable sensors and systems with application in rehabilitation. J. Neuroeng. Rehabil. 2012, 9. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 5. Altun, K.; Barshan, B.; Tunçel, O. Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recognit. 2010, 43, 3605–3620. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 6. Gill, T.; Keller, J.M.; Anderson, D.T.; Luke, R. A system for change detection and human recognition in voxel space using the Microsoft Kinect sensor. In Proceedings of the Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA, 11–13 October 2011.
    Google ScholarLocate open access versionFindings
  • 7. Chamroukhi, F.; Mohammed, S.; Trabelsi, D.; Oukhellou, L.; Amirat, Y. Joint segmentation of multivariate time series with hidden process regression for human activity recognition. Neurocomputing 2013, 120, 633–644. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 8. Gao, L.; Bourke, A.; Nelson, J. Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems. Med. Eng. Phys. 2014, 36, 779–785. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 9. Chernbumroong, S.; Cang, S.; Atkins, A.; Yu, H. Elderly activities recognition and classification for applications in assisted living. Exp. Syst. Appl. 2013, 40, 1662–1674. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 10. Altun, K.; Barshan, B. Human Activity Recognition Using Inertial/Magnetic Sensor Units. In Human Behavior Understanding; Springer: Berlin, Germany, 2010; pp. 38–51.
    Google ScholarFindings
  • 11. McAdams, E.T.; Gehin, C.; Noury, N.; Ramon, C.; Nocua, R.; Massot, B.; Oliveira, A.; Dittmar, A.; Nugent, C.D.; McLaughlin, J. Biomedical Sensors for Ambient Assisted Living. In Advances in Biomedical Sensing, Measurements, Instrumentation and Systems; Springer: Berlin, Germany, 2010; pp. 240–262.
    Google ScholarLocate open access versionFindings
  • 12. Cleland, I.; Kikhia, B.; Nugent, C.; Boytsov, A.; Hallberg, J.; Synnes, K.; McClean, S.; Finlay, D. Optimal Placement of Accelerometers for the Detection of Everyday Activities. Sensors 2013, 13, 9183–9200. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 13. Najafi, B.; Aminian, K.; Paraschiv-Ionescu, A.; Loew, F.; Bula, C.J.; Robert, P. Ambulatory system for human motion analysis using a kinematic sensor: Monitoring of daily physical activity in the elderly. IEEE Trans. Biomed. Eng. 2003, 50, 711–723. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 14. Bonomi, A.G.; Goris, A.; Yin, B.; Westerterp, K.R. Detection of type, duration, and intensity of physical activity using an accelerometer. Med. Sci. Sports Exerc. 2009, 41, 1770–1777. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 15. Karantonis, D.M.; Narayanan, M.R.; Mathie, M.; Lovell, N.H.; Celler, B.G. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans. Inf. Technol. Biomed. 2006, 10, 156–167. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 16. Yang, C.-C.; Hsu, Y.-L. A review of accelerometry-based wearable motion detectors for physical activity monitoring. Sensors 2010, 10, 7772–7788. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 17. Parkka, J.; Ermes, M.; Korpipaa, P.; Mantyjarvi, J.; Peltola, J.; Korhonen, I. Activity classification using realistic data from wearable sensors. IEEE Trans. Inf. Technol. Biomed. 2006, 10, 119–128. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 18. Mathie, M.; Celler, B.G.; Lovell, N.H.; Coster, A. Classification of basic daily movements using a triaxial accelerometer. Med. Biol. Eng. Comput. 2004, 42, 679–687. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 19. Yeoh, W.-S.; Pek, I.; Yong, Y.-H.; Chen, X.; Waluyo, A.B. Ambulatory monitoring of human posture and walking speed using wearable accelerometer sensors. In Proceedings of the Engineering in Medicine and Biology Society, 2008 EMBS 30th Annual International Conference of the IEEE, Vancouver, BC, USA, 20–25 August 2008; pp. 5184–5187.
    Google ScholarLocate open access versionFindings
  • 20. Yang, J.-Y.; Wang, J.-S.; Chen, Y.-P. Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers. Pattern Recog. Lett. 2008, 29, 2213–2220. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 21. Pirttikangas, S.; Fujinami, K.; Nakajima, T. Feature Selection and Activity Recognition from Wearable Sensors. In Ubiquitous Computing Systems; Springer: Berlin, Germany, 2006; pp. 516–527.
    Google ScholarFindings
  • 22. Olguın, D.O.; Pentland, A.S. Human activity recognition: Accuracy across common locations for wearable sensors. In Proceedings of 2006 10th IEEE International Symposium on Wearable Computers, Montreux, Switzerland, 11–14 October 2006.
    Google ScholarLocate open access versionFindings
  • 23. Lyons, G.; Culhane, K.; Hilton, D.; Grace, P.; Lyons, D. A description of an accelerometer-based mobility monitoring technique. Med. Eng. Phys. 2005, 27, 497–504. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 24. Salarian, A.; Russmann, H.; Vingerhoets, F.J.; Burkhard, P.R.; Aminian, K. Ambulatory monitoring of physical activities in patients with Parkinson's disease. IEEE Trans. Biomed. Eng. 2007, 54, 2296–2299. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 25. Gjoreski, H.; Lustrek, M.; Gams, M. Accelerometer placement for posture recognition and fall detection. In Proceedings of the 2011 7th International Conference on Intelligent Environments (IE), Nottingham, UK, 25–28 July 2011; pp. 47–54.
    Google ScholarLocate open access versionFindings
  • 26. Bayat, A.; Pomplun, M.; Tran, D.A. A Study on Human Activity Recognition Using Accelerometer Data from Smartphones. Proced. Comput. Sci. 2014, 34, 450–457. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 27. Moncada-Torres, A.; Leuenberger, K.; Gonzenbach, R.; Luft, A.; Gassert, R. Activity classification based on inertial and barometric pressure sensors at different anatomical locations. Physiol. Meas. 2014, 35. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 28. Gupta, P.; Dallas, T. Feature Selection and Activity Recognition System using a Single Tri-axial Accelerometer. IEEE Trans. Biomed. Eng. 2014, 61, 1780–1786. [CrossRef] [PubMed]
    Google ScholarFindings
  • 29. Garcia-Ceja, E.; Brena, R.F.; Carrasco-Jimenez, J.C.; Garrido, L. Long-Term Activity Recognition from Wristwatch Accelerometer Data. Sensors 2014, 14, 22500–22524. [CrossRef] [PubMed]
    Google ScholarFindings
  • 30. Massé, F.; Gonzenbach, R.R.; Arami, A.; Paraschiv-Ionescu, A.; Luft, A.R.; Aminian, K. Improving activity recognition using a wearable barometric pressure sensor in mobility-impaired stroke patients. J. Neuroeng. Rehabil. 2015, 12. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 31. Raj, A.; Subramanya, A.; Fox, D.; Bilmes, J. Rao-Blackwellized Particle Filters for Recognizing Activities and Spatial Context from Wearable Sensors. In Experimental Robotics; Springer: Berlin, Germany, 2008; pp. 211–221.
    Google ScholarFindings
  • 32. Morillo, D.S.; Ojeda, J.L.R.; Foix, L.F.C.; Jiménez, A.L. An accelerometer-based device for sleep apnea screening. IEEE Trans. Inf. Technol. Biomed. 2010, 14, 491–499. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 33. Kuo, Y.-L.; Culhane, K.M.; Thomason, P.; Tirosh, O.; Baker, R. Measuring distance walked and step count in children with cerebral palsy: An evaluation of two portable activity monitors. Gait Posture 2009, 29, 304–310. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 34. Menz, H.B.; Lord, S.R.; Fitzpatrick, R.C. Age-related differences in walking stability. Age Ageing 2003, 32, 137–142. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 35. Park, J.-H.; Kim, H.J.; Kang, S.-J. Validation of the AMP331 monitor for assessing energy expenditure of free-living physical activity. Res. Quart. Exerc. Sport 2006, 77, A40.
    Google ScholarLocate open access versionFindings
  • 36. Ronao, C.A.; Cho, S.-B. Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models. In Proceedings of the 2014 10th International Conference on Natural Computation (ICNC), Xiamen, China, 19–21 August 2014; pp. 681–686.
    Google ScholarLocate open access versionFindings
  • 37. Peetoom, K.K.; Lexis, M.A.; Joore, M.; Dirksen, C.D.; De Witte, L.P. Literature review on monitoring technologies and their outcomes in independently living elderly people. Disabil. Rehabil. Assist. Technol. 2014, 10, 271–294. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 38. Farringdon, J.; Moore, A.J.; Tilbury, N.; Church, J.; Biemond, P.D. Wearable sensor badge and sensor jacket for context awareness. In Proceedings of the Third International Symposium on Wearable Computers, 1999 Digest of Papers, San Francisco, CA, USA, 18–19 October 1999; pp. 107–113.
    Google ScholarLocate open access versionFindings
  • 39. Bouten, C.V.; Koekkoek, K.T.; Verduin, M.; Kodde, R.; Janssen, J.D. A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Trans. Biomed. Eng. 1997, 44, 136–147. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 40. Figo, D.; Diniz, P.C.; Ferreira, D.R.; Cardoso, J.M. Preprocessing techniques for context recognition from accelerometer data. Pers. Ubiquitous Comput. 2010, 14, 645–662. [CrossRef]
    Google ScholarLocate open access versionFindings
  • 41. Oppenheim, A.V.; Schafer, R.W.; Buck, J.R. Discrete-Time Signal Processing; Prentice-hall: Upper Saddle River, NJ, USA, 1989.
    Google ScholarFindings
  • 42. Nham, B.; Siangliulue, K.; Yeung, S. Predicting Mode of Transport from Iphone Accelerometer Data; Technical Report; Standford University: Stanford, CA, USA, 2008.
    Google ScholarFindings
  • 43. Ho, J.J.C. Interruptions: Using Activity Transitions to Trigger Proactive Messages. Master’s Thesis, Massachusetts Institute of Technology, Cambridge, MA, USA, August 2004.
    Google ScholarFindings
  • 44. Bao, L.; Intille, S.S. Activity Recognition from User-Annotated Acceleration Data. In Pervasive Computing; Springer: Berlin, Germany, 2004; pp. 1–17.
    Google ScholarFindings
  • 45. Preece, S.J.; Goulermas, J.Y.; Kenney, L.P.; Howard, D. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans. Biomed. Eng. 2009, 56, 871–879. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 46. Guyon, I.; Elisseeff, A. An introduction to variable and feature selection. J. Mach. Learn. Res. 2003, 3, 1157–1182.
    Google ScholarLocate open access versionFindings
  • 47. Liu, H.; Yu, L. Toward integrating feature selection algorithms for classification and clustering. IEEE Trans. Knowl. Data Eng. 2005, 17, 491–502.
    Google ScholarLocate open access versionFindings
  • 48. Kohavi, R.; John, G.H. Wrappers for feature subset selection. Artif. Intel. 1997, 97, 273–324. [CrossRef] 49. Das, S. Filters, wrappers and a boosting-based hybrid for feature selection. In Proceedings of the Eighteenth
    Google ScholarLocate open access versionFindings
  • International Conference on Machine Learning (ICML 2001), Williamstown, MA, USA, 28 June–1 July 2001; pp. 74–81.
    Google ScholarLocate open access versionFindings
  • 50. Zhang, M.; Sawchuk, A.A. A feature selection-based framework for human activity recognition using wearable multimodal sensors. In Proceedings of the 6th International Conference on Body Area Networks: ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), Beijing, China, 7–8 November 2011; pp. 92–98.
    Google ScholarLocate open access versionFindings
  • 51. Fish, B.; Khan, A.; Chehade, N.H.; Chien, C.; Pottie, G. Feature selection based on mutual information for human activity recognition. In Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 25–30 March 2012; pp. 1729–1732.
    Google ScholarLocate open access versionFindings
  • 52. Chau, T. A review of analytical techniques for gait data. Part 1: Fuzzy, statistical and fractal methods. Gait Posture 2001, 13, 49–66. [CrossRef] 53. Martínez, A.M.; Kak, A.C. Pca versus lda. IEEE Trans. Pattern Anal. Mach. Intel. 2001, 23, 228–233. [CrossRef] 54.
    Google ScholarLocate open access versionFindings
  • Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification; John Wiley & Sons: Malden, MA, USA, 1999.
    Google ScholarFindings
  • 55. Krause, A.; Siewiorek, D.P.; Smailagic, A.; Farringdon, J. Unsupervised, dynamic identification of physiological and activity context in wearable computing. In Proceedings of the 2012 16th International Symposium on Wearable Computers: IEEE Computer Society, White Plains, NY, USA, 21–23 October 2003; p. 88.
    Google ScholarLocate open access versionFindings
  • 56. Huynh, T.; Schiele, B. Unsupervised Discovery of Structure in Activity Data Using Multiple Eigenspaces. In Location-and Context-Awareness; Springer: Berlin, Germany, 2006; pp. 151–167.
    Google ScholarFindings
  • 57. Webb, A.R. Statistical Pattern Recognition; John Wiley & Sons: Malden, MA, USA, 2003.
    Google ScholarFindings
  • 58. Theodoridis, S.; Pikrakis, A.; Koutroumbas, K.; Cavouras, D. Introduction to Pattern Recognition: A Matlab Approach; Academic Press: Waltham, NA, USA, 2010.
    Google ScholarFindings
  • 59. Vapnik, V. The Nature of Statistical Learning Theory; Springer: Berlin, Germany, 2000.
    Google ScholarFindings
  • 60. Rabiner, L. A tutorial on hidden Markov models and selected applications in speech recognition. IEEE Proc. 1989, 77, 257–286. [CrossRef] 61.
    Google ScholarLocate open access versionFindings
  • Trabelsi, D.; Mohammed, S.; Chamroukhi, F.; Oukhellou, L.; Amirat, Y. An unsupervised approach for automatic activity recognition based on hidden Markov model regression. IEEE Trans. Autom. Sci. Eng. 2013, 10, 829–835. [CrossRef] 62.
    Google ScholarLocate open access versionFindings
  • Foerster, F.; Smeja, M.; Fahrenberg, J. Detection of posture and motion by accelerometry: A validation study in ambulatory monitoring. Comput. Hum. Behav. 1999, 15, 571–583. [CrossRef] 63.
    Google ScholarLocate open access versionFindings
  • Foerster, F.; Fahrenberg, J. Motion pattern and posture: Correctly assessed by calibrated accelerometers. Behav. Res. Method. Instrum. Comput. 2000, 32, 450–457. [CrossRef] 64.
    Google ScholarLocate open access versionFindings
  • Zhang, T.; Wang, J.; Xu, L.; Liu, P. Using Wearable Sensor and NMF Algorithm to Realize Ambulatory Fall Detection. In Advances in Natural Computation; Springer: Berlin, Germany, 2006; pp. 488–491.
    Google ScholarLocate open access versionFindings
  • 65. Scholkopf, B.; Smola, A.J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond; MIT Press: Cambridge, MA, USA, 2001.
    Google ScholarFindings
  • 66. Cover, T.M. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electron. Comput. 1965, EC-14, 326–334. [CrossRef] 67. Huynh, T.; Schiele, B. Towards less supervision in activity recognition from wearable sensors. In Proceedings of the 2006 10th IEEE International Symposium on Wearable Computers, Montreux, Switzerland, 11–14 October 2006; pp. 3–10.
    Google ScholarLocate open access versionFindings
  • 68. Krause, A.; Ihmig, M.; Rankin, E.; Leong, D.; Gupta, S.; Siewiorek, D.; Smailagic, A.; Deisher, M.; Sengupta, U. Trading off prediction accuracy and power consumption for context-aware wearable computing. In Proceedings of the 2005 Ninth IEEE International Symposium on Wearable Computers, Osaka, Japan, 18–21 October 2005; pp. 20–26.
    Google ScholarLocate open access versionFindings
  • 69. Doukas, C.; Maglogiannis, I. Advanced patient or elder fall detection based on movement and sound data. In Proceedings of the 2008 Second International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth, Tampere, Filand, 30 January–1 February 2008; pp. 103–107.
    Google ScholarLocate open access versionFindings
  • 70. Breiman, L.; Friedman, J.; Stone, C.J.; Olshen, R.A. Classification and Regression Trees; CRC press: Boca Raton, FL, USA, 1984.
    Google ScholarFindings
  • 71. Bedogni, L.; Di Felice, M.; Bononi, L. By train or by car? Detecting the user's motion type through smartphone sensors data. In Proceedings of the 2012 IFIP Wireless Days (WD), Dublin, Ireland, 21–23 November 2012; pp. 1–6.
    Google ScholarLocate open access versionFindings
  • 72. Dempster, A.P.; Laird, N.M.; Rubin, D.B. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. Ser. B (Methodol.) 1977, 39, 1–38.
    Google ScholarLocate open access versionFindings
  • 73. Mannini, A.; Sabatini, A.M. Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors 2010, 10, 1154–1175. [CrossRef] [PubMed] 74. Ong, W.-H.; Koseki, T.; Palafox, L. An Unsupervised Approach for Human Activity Detection and Recognition. Int. J. Simul. Syst. Sci. Technol. 2013, 14. [CrossRef] 75.
    Google ScholarLocate open access versionFindings
  • Cottone, P.; Re, G.L.; Maida, G.; Morana, M. Motion sensors for activity recognition in an ambient-intelligence scenario. In Proceedings of the 2013 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), San Diego, CA, USA, 18–22 March 2013; pp. 646–651.
    Google ScholarLocate open access versionFindings
  • 76. Forney, G.D., Jr. The viterbi algorithm. IEEE Proc. 1973, 61, 268–278. [CrossRef] 77. Lester, J.; Choudhury, T.; Kern, N.; Borriello, G.; Hannaford, B. A Hybrid Discriminative/ Generative Approach for Modeling Human Activities. In Proceedings of the IJCAI'05 19th international joint conference on Artificial intelligence, Edinburgh, UK, 30 July–5 August 2005; pp. 766–772.
    Google ScholarLocate open access versionFindings
  • 78. Laerhoven, K.V.; Gellersen, H.-W.; Malliaris, Y.G. Long term activity monitoring with a wearable sensor node. In Proceedings of the 2006 BSN 2006 International Workshop on Wearable and Implantable Body Sensor Networks, Cambridge, MA, USA, 3–5 April 2006.
    Google ScholarLocate open access versionFindings
  • 79. Lukowicz, P.; Ward, J.A.; Junker, H.; Stäger, M.; Tröster, G.; Atrash, A.; Starner, T. Recognizing Workshop Activity Using Body Worn Microphones and Accelerometers. In Pervasive Computing; Springer: Berlin, Germany, 2004; pp. 18–32.
    Google ScholarLocate open access versionFindings
  • 80. Ward, J.A.; Lukowicz, P.; Troster, G.; Starner, T.E. Activity recognition of assembly tasks using body-worn microphones and accelerometers. IEEE Trans. Pattern Anal. Mach. Intel. 2006, 28, 1553–1567. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 81. Hidden markov model (hmm) toolbox for matlab. Available online: http://www ai mit edu/~murphyk/ Software/HMM/hmm html (accessed on 9 December 2015).
    Locate open access versionFindings
  • 82. Boyle, J.; Karunanithi, M.; Wark, T.; Chan, W.; Colavitti, C. Quantifying functional mobility progress for chronic disease management. In Proceedings of the 2006 28th Annual International Conference of the Engineering in Medicine and Biology Society (EMBS'06), New York, NY, USA, 30 August–3 September 2006; pp. 5916–5919.
    Google ScholarLocate open access versionFindings
  • 83. Culhane, K.; Lyons, G.; Hilton, D.; Grace, P.; Lyons, D. Long-term mobility monitoring of older adults using accelerometers in a clinical environment. Clin. Rehabil. 2004, 18, 335–343. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 84. Najafi, B.; Aminian, K.; Loew, F.; Blanc, Y.; Robert, P.A. Measurement of stand-sit and sit-stand transitions using a miniature gyroscope and its application in fall risk evaluation in the elderly. IEEE Trans. Biomed. Eng. 2002, 49, 843–851. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 85. Bourke, A.; O’donovan, K.; Olaighin, G. The identification of vertical velocity profiles using an inertial sensor to investigate pre-impact detection of falls. Med. Eng. Phys. 2008, 30, 937–946. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 86. Marin-Perianu, M.; Lombriser, C.; Amft, O.; Havinga, P.; Tröster, G. Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks. In Distributed Computing in Sensor Systems; Springer: Berlin, Germany, 2008; pp. 296–313.
    Google ScholarLocate open access versionFindings
  • 87. McClelland, J.L.; Rumelhart, D.E.; Group, P.R. Parallel Distributed Processing: Explorations in the Microstructures of Cognition; MIT Press: Cambridge, MA, USA, 1986; Volume 2.
    Google ScholarFindings
  • 88. Maurer, U.; Rowe, A.; Smailagic, A.; Siewiorek, D. Location and Activity Recognition Using eWatch: A Wearable Sensor Platform. In Ambient Intelligence in Everyday Life; Springer: Berlin, Germany, 2006; pp. 86–102.
    Google ScholarLocate open access versionFindings
  • 89. Ravi, N.; Dandekar, N.; Mysore, P.; Littman, M.L. Activity recognition from accelerometer data. In Proceedings of the IAAI'05 17th conference on Innovative applications of artificial intelligence, Pittsburgh, MA, USA, 9–13 July 2005; pp. 1541–1546.
    Google ScholarLocate open access versionFindings
  • 90. Fahrenberg, J.; Muller, W.; Foerster, F.; Smeja, M. A multi-channel investigation of physical activity. J. Psychophysiol. 1996, 10, 209–217.
    Google ScholarLocate open access versionFindings
  • 91. Lee, S.; Park, H.; Hong, S.; Lee, K.; Kim, Y. A study on the activity classification using a triaxial accelerometer. In Proceedings of the 25th Annual International Conference of the Engineering in Medicine and Biology Society, Cancun, Mexico, 17–21 September 2003; pp. 2941–2943.
    Google ScholarLocate open access versionFindings
  • 92. Ermes, M.; Parkka, J.; Mantyjarvi, J.; Korhonen, I. Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans. Inf. Technol. Biomed. 2008, 12, 20–26. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 93. Liu, K.; Liu, T.; Shibata, K.; Inoue, Y. Ambulatory measurement and analysis of the lower limb 3D posture using wearable sensor system. In Proceedings of the 2009 ICMA International Conference on Mechatronics and Automation, Changchun, China, 9–12 August 2009; pp. 3065–3069.
    Google ScholarLocate open access versionFindings
  • 94. Favre, J.; Luthi, F.; Jolles, B.; Siegrist, O.; Najafi, B.; Aminian, K. A new ambulatory system for comparative evaluation of the three-dimensional knee kinematics, applied to anterior cruciate ligament injuries. Knee Surg. Sports Traumatol. Arthrosc. 2006, 14, 592–604. [CrossRef] [PubMed]
    Google ScholarLocate open access versionFindings
  • 95. Chang, C.-C.; Lin, C.-J. LIBSVM: A library for support vector machines. ACM Trans. Intel. Syst. Technol. (TIST) 2011, 2. [CrossRef]
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科