Recognition of Pes Cavus Foot Using Smart Insole: A Pilot Study

The presence of pes cavus, a high-arched foot, is a potential reason for some neuromuscular problems. Active research efforts are being made to devise portable systems for monitoring and early detection of foot deviations. In line with that, we have developed instrumented insoles that incorporate force and inertial sensors and used them to capture data from sixty-four subjects; among them, there were forty-four subjects with normal feet arches and twenty subjects exhibiting pes cavus. We applied a 1D convolutional neural network to extract features and classify data. The trained model allowed for a recognition rate of more than 96%. The presented use case could inspire further research on using smart footwear for pes cavus screening and progression monitoring.

[1]  Yubo Fan,et al.  Natural Gaits of the Non-Pathological Flat Foot and High-Arched Foot , 2010, PloS one.

[2]  Mohsen Razeghi,et al.  Foot type classification: a critical review of current methods. , 2002, Gait & posture.

[3]  P. Wicart,et al.  Cavus foot, from neonates to adolescents. , 2012, Orthopaedics & traumatology, surgery & research : OTSR.

[4]  Jonathan T Deland,et al.  Foot type biomechanics part 1: structure and function of the asymptomatic foot. , 2013, Gait & posture.

[5]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[6]  Sung-Bae Cho,et al.  Human activity recognition with smartphone sensors using deep learning neural networks , 2016, Expert Syst. Appl..

[7]  Jack Crosbie,et al.  The effect of pes cavus on foot pain and plantar pressure. , 2005, Clinical biomechanics.

[8]  D. De Clercq,et al.  A functional foot type classification with cluster analysis based on plantar pressure distribution during jogging. , 2006, Gait & posture.

[9]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[10]  Karon E. MacLean,et al.  Real-time gait classification for persuasive smartphone apps: structuring the literature and pushing the limits , 2013, IUI '13.

[11]  Matjaz B. Juric,et al.  Inertial Sensor-Based Gait Recognition: A Review , 2015, Sensors.

[12]  Hylton B. Menz,et al.  Centre of pressure characteristics in normal, planus and cavus feet , 2018, Journal of Foot and Ankle Research.

[13]  B. Yamini,et al.  Evaluating the Cavus Foot. , 2016, Pediatric annals.

[14]  Alfred Gatt,et al.  Shock attenuation properties at heel strike: Implications for the clinical management of the cavus foot. , 2016, Journal of orthopaedics.

[15]  C. Saltzman,et al.  Does Arch Height Affect Impact Loading at the Lower Back Level in Running? , 1999, Foot & ankle international.

[16]  H J Hillstrom,et al.  Acceleration of the calcaneus at heel strike in neutrally aligned and pes planus feet. , 2001, Clinical biomechanics.

[17]  J. G. Barton,et al.  Development of a connectionist expert system to identify foot problems based on under-foot pressure patterns. , 1995, Clinical biomechanics.

[18]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[19]  Yubo Fan,et al.  Why Do Woodpeckers Resist Head Impact Injury: A Biomechanical Investigation , 2011, PloS one.

[20]  Xu Zhou,et al.  A novel gait analysis system based on adaptive neuro-fuzzy inference system , 2010, Expert Syst. Appl..

[21]  Xiang Li,et al.  Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Hylton B Menz,et al.  Foot posture is associated with plantar pressure during gait: A comparison of normal, planus and cavus feet. , 2018, Gait & posture.