ABSTRACT
Smartphone pedometry offers the possibility of ubiquitous health monitoring, context awareness and indoor location tracking through Pedestrian Dead Reckoning (PDR) systems. However, there is currently no detailed understanding of how well pedometry works when applied to smartphones in typical, unconstrained use.
This paper evaluates common walk detection (WD) and step counting (SC) algorithms applied to smartphone sensor data. Using a large dataset (27 people, 130 walks, 6 smartphone placements) optimal algorithm parameters are provided and applied to the data. The results favour the use of standard deviation thresholding (WD) and windowed peak detection (SC) with error rates of less than 3%. Of the six different placements, only the back trouser pocket is found to degrade the step counting performance significantly, resulting in undercounting for many algorithms.
- H. J. Ailisto, M. Lindholm, J. Mantyjarvi, E. Vildjiounaite, and S. M. Makela. Identifying people from gait pattern with accelerometers. In SPIE, volume 5779, page 7, 2005.Google ScholarCross Ref
- F. Allen, E. Ambikairajah, N. Lovell, and B. Celler. An adapted gaussian mixture model approach to accelerometry-based movement classification using time-domain features. In EMBS '06, pages 3600--3603, 2006.Google ScholarCross Ref
- A. Avci, S. Bosch, M. Marin-Perianu, R. Marin-Perianu, and P. J. M. Havinga. Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey. In ARCS '10, pages 167--176, 2010.Google Scholar
- L. Bao and S. S. Intille. Activity recognition from user-annotated acceleration data. In PERVASIVE '04, pages 1--17, 2004.Google ScholarCross Ref
- P. Barralon, N. Vuillerme, and N. Noury. Walk detection with a kinematic sensor: Frequency and wavelet comparison. In EMBS '06, pages 1711 --1714, 2006.Google ScholarCross Ref
- S. Beauregard. A helmet-mounted pedestrian dead reckoning system. In IFAWC '06, pages 1--11, 2006.Google Scholar
- C. M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, 2007. Google ScholarDigital Library
- S. Chen, J. Lach, O. Amft, M. Altini, and J. Penders. Unsupervised activity clustering to estimate energy expenditure with a single body sensor. In BSN '13, 2013.Google ScholarCross Ref
- B. Choe, J.-K. Min, and S.-B. Cho. Online gesture recognition for user interface on accelerometer built-in mobile phones. In ICONIP '10, pages 650--657, 2010. Google ScholarDigital Library
- W. Dargie. Analysis of time and frequency domain features of accelerometer measurements. In ICCCN '09, pages 1--6, 2009. Google ScholarDigital Library
- J. Demsar. Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7:1--30, 2006. Google ScholarDigital Library
- D. Figo, P. C. Diniz, D. R. Ferreira, and J. M. P. Cardoso. Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing, 14(7):645--662, 2010. Google ScholarDigital Library
- M. Friedman. A comparison of alternative tests of significance for the problem of m rankings. The Annals of Mathematical Statistics, 11:86--92, 1940.Google ScholarCross Ref
- D. Gafurov and E. Snekkenes. Towards understanding the uniqueness of gait biometric. In FG '08, pages 1--8, 2008.Google ScholarCross Ref
- A. R. Golding and N. Lesh. Indoor navigation using a diverse set of cheap, wearable sensors. In ISWC '99, pages 29--36, 1999. Google ScholarDigital Library
- P. Goyal, V. Ribeiro, H. Saran, and A. Kumar. Strap-down pedestrian dead-reckoning system. In IPIN '11, pages 1--7, 2011.Google ScholarCross Ref
- R. Harle. A survey of indoor inertial positioning systems for pedestrians. IEEE Communications Surveys & Tutorials, PP, 2013.Google Scholar
- Harvey WeinBerg. AN-602: Using the ADXL202 in Pedometer and Personal Navigation. Technical report, Analog Devices, 2002.Google Scholar
- Z. He, Z. Liu, L. Jin, L.-X. Zhen, and J.-C. Huang. Weightlessness feature - a novel feature for single tri-axial accelerometer based activity recognition. In ICPR '08, pages 1--4, 2008.Google Scholar
- T. Huynh and B. Schiele. Analyzing features for activity recognition. In sOc-EUSAI '05, pages 159--163, 2005. Google ScholarDigital Library
- R. Ibrahim, E. Ambikairajah, B. Celler, and N. Lovell. Time-frequency based features for classification of walking patterns. In DSP '07, pages 187--190, 2007.Google ScholarCross Ref
- R. Iman and J. Davenport. Approximations of the critical region of the friedman statistic. Communications in Statistics -- Theory and Methods, 9:571--595, 1980.Google Scholar
- T. Iso and K. Yamazaki. Gait analyzer based on a cell phone with a single three-axis accelerometer. In Mobile HCI '06, pages 141--144, 2006. Google ScholarDigital Library
- J. J. Kavanagh and H. B. Menz. Accelerometry: a technique for quantifying movement patterns during walking. Gait & posture, 28(1):1--15, 2008.Google ScholarCross Ref
- J. W. Kim, H. J. Jang, D.-H. Hwang, and C. Park. A Step, Stride and Heading Determination for the Pedestrian Navigation System. Journal of Global Positioning Systems, 3(1--2):273--279, 2004.Google Scholar
- T. Kobayashi, K. Hasida, and N. Otsu. Rotation invariant feature extraction from 3-d acceleration signals. In ICASSP '11, pages 3684--3687, 2011.Google ScholarCross Ref
- A. Krause, D. P. Siewiorek, A. Smailagic, and J. Farringdon. Unsupervised, dynamic identification of physiological and activity context in wearable computing. In ISWC '03, pages 88--97, 2003. Google ScholarDigital Library
- J. B. Kruskal and M. Liberman. The symmetric time-warping problem: from continuous to discrete. In Time Warps, String Edits, and Macromolecules - Theory and Practice of Sequence Comparison, 1983.Google Scholar
- J. Kwapisz, G. Weiss, and S. Moore. Cell phone-based biometric identification. In BTAS '10, pages 1--7, 2010.Google ScholarCross Ref
- J. R. Kwapisz, G. M. Weiss, and S. Moore. Activity recognition using cell phone accelerometers. SIGKDD Explorations, 12(2):74--82, 2010. Google ScholarDigital Library
- S. W. Lee and K. Mase. Activity and Location Recognition Using Wearable Sensors. IEEE Pervasive Computing, 1(3):24--32, 2002. Google ScholarDigital Library
- J. Lester, C. Hartung, L. Pina, R. Libby, G. Borriello, and G. Duncan. Validated caloric expenditure estimation using a single body-worn sensor. In Ubicomp '09, page 225, 2009. Google ScholarDigital Library
- F. Li, C. Zhao, G. Ding, J. Gong, C. Liu, and F. Zhao. A reliable and accurate indoor localization method using phone inertial sensors. In Ubicomp '12, pages 421--430, 2012. Google ScholarDigital Library
- S. Lloyd. Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2):129--137, 1982. Google ScholarDigital Library
- Y. Makihara, T. N. Thanh, H. Nagahara, R. Sagawa, Y. Mukaigawa, and Y. Yagi. Phase registration of a single quasi-periodic signal using self dynamic time warping. In ACCV '10, pages 667--678, 2010. Google ScholarDigital Library
- S. Mallat. A wavelet tour of signal processing. Academic Press, 1999.Google ScholarDigital Library
- A. Mannini and A. Sabatini. A hidden Markov model-based technique for gait segmentation using a foot-mounted gyroscope. In EMBC '11, pages 4369--4373, 2011.Google ScholarCross Ref
- A. Mannini and A. M. Sabatini. Accelerometry-based classification of human activities using markov modeling. Comp. Int. and Neurosc., 2011. Google ScholarDigital Library
- J. Mantyjarvi, J. Himberg, and T. Seppanen. Recognizing human motion with multiple acceleration sensors. In SMC '01, volume 2, pages 747--752 vol.2, 2001.Google ScholarCross Ref
- M. Marschollek, M. Goevercin, K.-H. Wolf, B. Song, M. Gietzelt, R. Haux, and E. Steinhagen-Thiessen. A performance comparison of accelerometry-based step detection algorithms on a large, non-laboratory sample of healthy and mobility-impaired persons. In EMBS '08, volume 2008, pages 1319--22, 2008.Google ScholarCross Ref
- C. Nickel, H. Brandt, and C. Busch. Benchmarking the performance of SVMs and HMMs for accelerometer-based biometric gait recognition. In ISSPIT '11, pages 281--286, 2011. Google ScholarDigital Library
- C. Nickel, H. Brandt, and C. Busch. Classification of acceleration data for biometric gait recognition on mobile devices. In BIOSIG '11, pages 57--66, 2011.Google Scholar
- M. Nyan, F. Tay, K. Seah, and Y. Sitoh. Classification of gait patterns in the time-frequency domain. Journal of Biomechanics, 39(14):2647--2656, 2006.Google ScholarCross Ref
- T. Pfau, M. Ferrari, K. Parsons, and A. Wilson. A hidden markov model-based stride segmentation technique applied to equine inertial sensor trunk movement data. Journal of Biomechanics, 41(1):216--220, 2008.Google ScholarCross Ref
- S. Pirttikangas, K. Fujinami, and T. Nakajima. Feature selection and activity recognition from wearable sensors. In UCS '06, pages 516--527, 2006. Google ScholarDigital Library
- S. J. Preece, J. Y. Goulermas, L. P. J. Kenney, D. Howard, K. Meijer, and R. Crompton. Activity identification using body-mounted sensors -- a review of classification techniques. Physiological Measurement, 30(4):R1, 2009.Google ScholarCross Ref
- A. Rai, K. K. Chintalapudi, V. N. Padmanabhan, and R. Sen. Zee - zero-effort crowdsourcing for indoor localization. In Mobicom '12, page 293, 2012. Google ScholarDigital Library
- C. Randell, C. Djiallis, and H. Muller. Personal position measurement using dead reckoning. In ISWC '03, pages 166--173, 2003. Google ScholarDigital Library
- N. Ravi, N. Dandekar, P. Mysore, and M. L. Littman. Activity recognition from accelerometer data. In AAAI '05, pages 1541--1546, 2005. Google ScholarDigital Library
- L. Rong, D. Zhiguo, Z. Jianzhong, and L. Ming. Identification of individual walking patterns using gait acceleration. In ICBBE '07, pages 543--546, 2007.Google ScholarCross Ref
- B. Santhiranayagam, D. Lai, C. Jiang, A. Shilton, and R. Begg. Automatic detection of different walking conditions using inertial sensor data. In IJCNN '12, pages 1--6, 2012.Google ScholarCross Ref
- P. Siirtola and J. Röning. Recognizing human activities user-independently on smartphones based on accelerometer data. IJIMAI, 1(5):38--45, 2012.Google ScholarCross Ref
- P. (Sundar) Balakrishnan, M. Cooper, V. Jacob, and P. Lewis. A study of the classification capabilities of neural networks using unsupervised learning: A comparison with k-means clustering. Psychometrika, 59(4):509--525, 1994.Google ScholarCross Ref
- C. Torrence and G. P. Compo. A practical guide to wavelet analysis. Bull. Amer. Meteor. Soc., 79(1):61--78, 1998.Google ScholarCross Ref
- M. Vetterli and J. Kovacevic. Wavelets and Subband Coding. Prentice Hall PTR, 1995. Google ScholarDigital Library
- A. Viterbi. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory, 13(2):260--269, 1967. Google ScholarDigital Library
- J.-H. Wang, J.-J. Ding, Y. Chen, and H.-H. Chen. Real time accelerometer-based gait recognition using adaptive windowed wavelet transforms. In APCCAS '12, pages 591--594, 2012.Google ScholarCross Ref
- O. Woodman and R. Harle. Pedestrian Localisation for Indoor Environments. In UbiComp '08, 2008. Google ScholarDigital Library
- A. Ying, Hong, C. A. Silex, A. Schnitzer, A., S. A. Leonhardt, and M. Schiek. Automatic Step Detection in the Accelerometer Signal. In S. Leonhardt, T. Falck, and P. Mähönen, editors, BSN '07, 2007.Google Scholar
Index Terms
- Walk detection and step counting on unconstrained smartphones
Recommendations
GaitTracker: 3D Skeletal Tracking for Gait Analysis Based on Inertial Measurement Units
Gait rehabilitation is a common method of postoperative recovery after the user sustains an injury or disability. However, traditional gait rehabilitations are usually performed under the supervision of rehabilitation specialists, which implies that the ...
Assessing the Accuracy of an Algorithm for the Estimation of Spatial Gait Parameters Using Inertial Measurement Units: Application to Healthy Subject and Hemiparetic Stroke Survivor
MOCO '17: Proceedings of the 4th International Conference on Movement ComputingWe have reviewed and assessed the reliability of a dead reckoning and drift correction algorithm for the estimation of spatial gait parameters using Inertial Measurement Units (IMUs). In particular, we are interested in obtaining accurate stride lengths ...
Estimation of spatial-temporal gait parameters in level walking based on a single accelerometer
This paper investigates the ability of a single wireless inertial sensing device stuck on the lower trunk to provide spatial-temporal parameters during level walking. The 3-axial acceleration signals were filtered and the timing of the main gait events ...
Comments