Gait recognition is an emerging biometric technology applied to the mobile environment. With built-in accelerometers, wearable devices are used to recognize user identity according to gait periodic pattern, which shows strong stability and uniqueness property.
OBJECTIVE:
The purpose of this study is to build analyzing models to find the change of gait normal and pathological function based on gait features.
METHODS:
This work relies on gait recognition methods. In this paper, the performance of different hybrid filter methods is compared by combining four classical filtering methods. The influence of the abnormal pattern of gait cycle is estimated by standard deviation. The effectiveness of feature matching methods is evaluated by six classical distance discrimination function.
RESULTS:
The results highlight the stability and invariance of gait periodic pattern. For analyzing models, the best recognition rate is 96.67% with the combination of MF hybrid filter and Correlation distance function in the small sample, and minimal time consumption is 0.038 s. The effectiveness of analyzing models is further analyzed for different practical applications.
CONCLUSIONS:
This study provides evidence for future scientific teams to make decisions on selecting filter methods and discrimination functions which can more efficiently extract gait features and suggest ways to analyze clinical gait pattern.
MurrayMPDroughtABKoryRC. Walking patterns of normal men. Journal of Bone and Joint Surgery.1964; 46(2): 335-360. doi: 10.2106/00004623-196446020-00009.
2.
MurrayMPKoryRCClarksonBHSepicSB. Comparison of free and fast speed walking patterns of normal men. American Journal of Physical Medicine & Rehabilitation.1966; 45(1): 8-24. doi: 10.1097/00002060-196602000-00002.
3.
BenedettiMGCataniFLeardiniAPignottiEGianniniS. Data management in gait analysis for clinical applications. Clinical Biomechanics.1998; 13(3): 204-215. doi: 10.1016/s0268-0033(97)00041-7.
4.
KhandelwalSWickströmN. Gait event detection in a real-world environment for long-term applications: incorporating domain knowledge into time-frequency Analysis. IEEE Transactions on Neural Systems and Rehabilitation Engineering.2016; 24(12): 1363-1372. doi: 10.1109/tnsre.2016.2536278.
5.
YangCCHsuYLShihKSLuJM. Real-time gait cycle parameter recognition using a wearable accelerometry system. Sensors.2011; 11(8): 7314-7326. doi: 10.3390/s110807314.
6.
RenYZChenYYChuahMCYangJ. User verification leveraging gait recognition for smartphone enabled mobile healthcare systems. IEEE Transactions on Mobile Computing.2015; 14(9): 1961-1974. doi: 10.1109/tmc.2014.2365185.
7.
MäntyjärviJLindholmMVildjiounaiteEMakelaSAilistoHA. Identifying users of portable devices from gait pattern with accelerometers. IEEE International Conference on Acoustics, Speech, and Signal Processing, (Philadelphia, USA). 2005; 973-976. doi: 10.1109/ICASSP.2005.1415569.
8.
GuLHCuiCGaoSWXuH. Gait signal acquisition system based on MPU-6050. Journal of Shenyang University of Technology.2015; 37(2): 176-182. doi: 10.7688/j.issn.1000-1646.2015.02.11.
9.
TongKYGranatMH. A practical gait analysis system using gyroscopes. Medical Engineering & Physics.1999; 21(2): 87-94. doi: 10.1016/s1350-4533(99)00030-2.
MaHLiaoWH. Human gait modeling and analysis using a semi-markov process with ground reaction forces. IEEE Transactions on Neural Systems and Rehabilitation Engineering.2017; 25(6): 597-607. doi: 10.1109/TNSRE.2016.2584923.
12.
GafurovDSnekkenesEBuvarpTE. Robustness of biometric gait authentication against impersonation attack. OTM Workshops Move Meaningful Internet Systemss2006; 71: 479-488. doi: 10.1007/11915034_71.
13.
GafurovDSnekkenesEBoursP. Spoof attacks on gait authentication system. IEEE Transactions on Information Forensics and Security.2007; 2(3): 491-502. doi: 10.1109/TIFS.2007.902030.
14.
LiuRHuangLLiSWLiuY. Gait analysis based on gait acceleration. Chinese Journal sensors and Actuators.2009; 22(6): 893-896. doi: 10.3969/j.issn.1004-1699.2009.06.027.
15.
HausdorffJMLertratanakulACudkowiczMEPetersonALKalitionDGoldbergerAL. Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis. Journal of Applied Physiology.2000; 88(6): 2045-2053. doi: 10.1152/jappl.2000.88.6.2045.
16.
PanGZhangYTWuZ. Accelerometer-based gait recognition via voting by signature points. Electronics Letters.2009; 45(2): 1116-1118. doi: 10.1049/el.2009.2301.
17.
GafurovDSnekkenesEBoursP. Gait authentication and identification using wearable accelerometer sensor. IEEE Workshop on Automatic Identification Advanced Technologies, (Alghero, Italy). 2007; 220-225. doi: 10.1109/autoid.2007.380623.
18.
Arendt-NielsenLGraven-NielsenTSvarrerHSvenssonP. The influence of low back pain on muscle activity and coordination during gait: a clinical and experimental study. Pain.1996; 64(2): 231-240. doi: 10.1016/0304-3959(95)00115-8.
19.
XueYJinLW. A feature extraction and recognition approach for accelerometer-based virtual handwriting digit. Pattern Recognition and Artificial Intelligence.2011; 24(4): 492-500. doi: 10.3969/j.issn.1003-6059.2011.04.006.
20.
FengYYWongCKJanejaVKuberRMentisHM. Comparison of tri-axial accelerometers step-count accuracy in slow walking conditions. Gait & Posture.2017; 53: 11-16. doi: 10.1016/j.gaitpost.2016.12.014.
21.
TuBBGuLHXuH. Quality evaluation method for wavelet de-noising in gait recognition. Journal of Shenyang University of Technology.2017; 39(1): 61-66. doi: 10.7688/j.issn.1000-1646.2017.01.12.
22.
TuBBGuLHChuaiRYXuH. Gait recognition based on MEMS acceleration sensor. Journal of Chinese Inertial Technology.2017; 25(3): 304-308+359. doi: 10.13695/j.cnki.12-1222/o3.2017.03.005.
23.
BakerRMcGinleyJLSchwartzMHBeynonSRozumalskiAGrahamHKTiroshO. The gait profile score and movement analysis profile. Gait & Posture.2009; 30(3): 265-269. doi: 10.1016/j.gaitpost.2009.05.020.
24.
PalMSahaSKonarA. Distance matching based gesture recognition for healthcare using Microsoft’s Kinect sensor. International Conference on Microelectronics, Computing and Communications (MicroCom), (Durgapur, India). 2016; 1-6. doi: 10.1109/MicroCom.2016.7522586.
25.
DehacheISouici-MeslatiL. Immunological classifiers for accelerometer-based gait identification. International Journal of Biometrics.2017; 9(3): 225. doi: 10.1504/IJBM.2017.086646.
26.
XuJFBhagavatulaCJaechAPrasadUSavvidesM. Gait-id on the move: pace independent human identification using cell phone accelerometer dynamics. IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS), (Arlington, USA). 2012; 8-15. doi: 10.1109/btas.2012.6374552.
27.
LyonnetBIoanaCAminMG. Human gait classification using microDoppler time-frequency signal representations. IEEE International Radar Conference, (Arlington, USA). 2010; 915-919. doi: 10.1109/radar.2010.5494489.
28.
KimCMEngJJ. Symmetry in vertical ground reaction force is accompanied by symmetry in temporal but not distance variables of gait in persons with stroke. Gait & Posture.2003; 18(1): 23-28. doi: 10.1016/s0966-6362(02)00122-4.
29.
XueZJMingDSongWWanBJinSJ. Infrared gait recognition based on wavelet transform and support vector machine. Pattern Recognition.2010; 43(8): 2904-2910. doi: 10.1016/j.patcog.2010.03.011.
30.
ZhangYTPanGJiaKLuMWangYMWuZH. Accelerometer-based gait recognition by sparse representation of signature points with clusters. IEEE Transactions on Cybernetics.2015; 45(9): 1864-1875. doi: 10.1109/tcyb.2014.2361287.
31.
BachlinMPlotnikMRoggenD. Wearable assistant for parkinson’s disease patients with the freezing of gait symptom. IEEE Transactions on Information Technology in Biomedicine.2010; 14(2): 436-446. doi: 10.1109/titb.2009.2036165.
