Plantar Pressure Detection System Based on Flexible Hydrogel Sensor Array and WT-RF

Abstract

This paper presents a hydrogel-based flexible sensor array to detect plantar pressure distribution and recognize the gait patterns to assist those who suffer from gait disorders to rehabilitate better. The traditional pressure detection array is composed of rigid metal sensors, which have poor biocompatibility and expensive manufacturing costs. To solve the above problems, we have designed and fabricated a novel flexible sensor array based on AAM/NaCl (Acrylamide/Sodium chloride) hydrogel and PI (Polyimide) membrane. The proposed array exhibits excellent structural flexibility (209 KPa) and high sensitivity (12.3 mV·N−1), which allows it to be in full contact with the sole of the foot to collect pressure signals accurately. The Wavelet Transform-Random Forest (WT-RF) algorithm is introduced to recognize the gaits based on the plantar pressure signals. Wavelet transform realizes the signal filtering and normalization, and random forest is responsible for the classification of the processed signals. The classification accuracy of the WT-RF algorithm reaches 91.9%, which ensures the precise recognition of gaits.

Recent Advances in Machine Learning Assisted Hydrogel Flexible Sensing

“…Liu et al proposed a hydrogel flexible sensor based on Wavelet Transform-Random Forest(WT-RF) algorithm to detect foot pressure and gait pattern. [81] The accuracy of gait recognition is 91.9 % based on foot pressure signals. This work can assist doctors to make targeted correction plans for patients according to their walking gait.…”

“…However, they require large computing resources and time for training, and also have overfitting problems. RF and GBDT algorithms are often used in financial prediction, text and image classification, system and product recommendation, object recognition, medical diagnosis and other scenarios [79–84] . In addition, RF can be used for feature selection and importance assessment to help select features that have a significant impact on model predictions [85–86] .…”

“…Liu et al. proposed a hydrogel flexible sensor based on Wavelet Transform‐Random Forest(WT‐RF) algorithm to detect foot pressure and gait pattern [81] . The accuracy of gait recognition is 91.9 % based on foot pressure signals.…”

“…RF and GBDT algorithms are often used in financial prediction, text and image classification, system and product recommendation, object recognition, medical diagnosis and other scenarios. [79][80][81][82][83][84] In addition, RF can be used for feature selection and importance assessment to help select features that have a significant impact on model predictions. [85][86] SVM is a small sample learning method, which uses inner product kernel function instead of nonlinear mapping to high-dimensional space, and can handle highdimensional data without dimensionality reduction.…”

A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images

“…One-dimensional plantar pressure signals [ 29 , 30 ] and two-dimensional plantar pressure images [ 31 ] are two methods to capture information on pressure patterns. In addition, the pressure patterns provide detailed information about foot movement [ 32 , 33 ]. Moreover, two-dimensional plantar pressure images can be used to reliably determine the long axis of the foot during walking [ 34 ].…”