Continuous plantar pressure modeling using sparse sensors

Abstract

The foot complications constitute a tremendous challenge for diabetic patients, caregivers, and the healthcare system. With current technology, in-shoe monitoring systems can be implemented to continuously monitor foot's at-risk ulceration sites and send feedback to patients and physicians. The few available high resolution in-shoe pressure measuring systems are extremely expensive and targeting clinical use only. The more affordable price ranges can be reached by limiting the number of sensors in the shoe. Precise subject-specific sensor placement is still a challenge in such platforms. Moreover, there is no good way to estimate pressure on other points of the foot. In this paper, we address these technical challenges by proposing SCPM algorithm that reconstructs a continuous foot plantar pressure image from a sparse set of sensor readings. Using our technique, sensor placement can be the same in every electronic insole. However, the SCPM's trained parameters are unique for every subject and foot.

A Portable Insole Pressure Mapping System

“…This cycle will repeat in every normal gait. The distributions of pressure acting on the foot is similar to [11], whereby at heel strike phase, the lateral heel, medial heel and back heel are involved; at loading response phase the great toe, 1st metatarsal, 5th metatarsal, lateral heel, medial heel and back heel are involved; at mid-stance phase the involvement is the same as loading response phase; at heel off phase the great toe, 1st metatarsal and 5th metatarsal are involved and lastly the toe off phase that has the same involvement as heel off phase. Figure 11.…”

Insole Systems for Disease Diagnosis and Rehabilitation: A Review

“…Compressive Sensing [43] Gaussian Mixture Model (GMM) is used to reconstruct PSD map. Least Squares Model is used to estimate the value of pressure.…”

“…Based on these principles, three current frequently used methods have been proposed and classified [ 37 ]: compressed sensing (CS), machine learning (ML), and fitting [ 37 ]. Table 1 [ 19 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 ] provides a brief detail of each example in Section 3 .…”

“…Based on these principles, three current frequently used methods have been proposed and classified [37]: compressed sensing (CS), machine learning (ML), and fitting [37]. Table 1 [19,[38][39][40][41][42][43][44][45][46] provides a brief detail of each example in Section 3. The reconstruction of PSD can be succinctly described as converting analog signals into digital signals for further computer-based processing methods.…”

“…Table 1. Brief information of pressure reconstruction research in Section 3 [19,[38][39][40][41][42][43][44][45][46].…”