The objective of the research presented in this paper was to provide a novel open-source strain gauge system that shall enable the measurement of the pressure of a runner’s feet on the ground and the presentation of the results of that measurement to the user. The system based on electronic shoe inserts with 16 built-in pressure sensors laminated in a transparent film was created, consisting of two parts: a mobile application and a wearable device. The developed system provides a number of advantages in comparison with existing solutions, including no need for calibration, an accurate and frequent measurement of pressure distribution, placement of electronics on the outside of a shoe, low cost, and an open-source approach to encourage enhancements and open collaboration.

/pdf/open-source-strain-gauge-system-for-monitoring-pressure-3om7g7oz.pdf

Open-Source Strain Gauge System for Monitoring Pressure Distribution of Runner’s Feet

Foot placement prediction can be important for exoskeleton and prosthesis controllers, human-robot interaction, or body-worn systems to prevent slips or trips. Previous studies investigating foot placement prediction have been limited to predicting foot placement during the swing phase, and do not fully consider contextual information such as the preceding step or the stance phase before push-off. In this study, we propose a deep learning-based foot placement prediction approach, sequentially processing data from three IMU sensors mounted on the pelvis and feet. The raw sensor data are pre-processed to generate multi-variable time-series data for training two deep learning models, where the first model estimates the gait progression and the second model subsequently predicts the next foot placement. The ground truth gait phase data and foot placement data are acquired from a motion capture system. Ten healthy subjects were invited to walk naturally at different speeds on a treadmill. In cross-subject learning, the trained models had a mean distance error of 5.93 cm for foot placement prediction. In single-subject learning, the prediction accuracy improved with additional training data, and a mean distance error of 2.60 cm was achieved by fine-tuning the cross-subject validated models with the target subject data. Even from 25–81% in the gait cycle, mean distance errors were only 6.99 cm and 3.22 cm for cross-subject learning and single-subject learning, respectively.

A Deep Learning-Based Approach for Foot Placement Prediction

In both athletics and daily life, shoes are crucial. Recently, smart sneakers have also taken on a certain trend among both sportsmen and the general public. Therefore, it has actually become crucial to classify shoes in a way that enables industry specialists to do so in accordance with customer demands keeping medical and health point of view. Each shoe product has four distinct perspectives, front, left, right, and rear, but only a few of these views have the product information that allows researchers to create innovative transfer learning models to understand its qualities with precision. Selection, prediction, and categorization of the specific perspective from the provided dataset from many viewpoints are all made possible via the development of machine learning models and the explanation of the artificial intelligence method. In order to create a sound and useful framework for shoe categorization, several efforts have been made over the past few decades. The suggested model in this research exhibits an accuracy of 88.8% on the Adam optimizer utilizing the EfficientNetB3 model and illustrates the accurate classification of the shoe class as utilized in the dataset. 

Smart Shoe Classification Using Artificial Intelligence on EfficientnetB3 Model

In both athletics and daily life, shoes are crucial. Recently, smart sneakers have also taken on a certain trend among both sportsmen and the general public. Therefore, it has actually become crucial to classify shoes in a way that enables industry specialists to do so in accordance with customer demands keeping medical and health point of view. Each shoe product has four distinct perspectives, front, left, right, and rear, but only a few of these views have the product information that allows researchers to create innovative transfer learning models to understand its qualities with precision. Selection, prediction, and categorization of the specific perspective from the provided dataset from many viewpoints are all made possible via the development of machine learning models and the explanation of the artificial intelligence method. In order to create a sound and useful framework for shoe categorization, several efforts have been made over the past few decades. The suggested model in this research exhibits an accuracy of 88.8% on the Adam optimizer utilizing the EfficientNetB3 model and illustrates the accurate classification of the shoe class as utilized in the dataset.

The analysis of gait patterns and plantar pressure distributions via insoles is increasingly used to monitor patients and treatment progress, such as recovery after surgeries. Despite the popularity of pedography, also known as baropodography, characteristic effects of anthropometric and other individual parameters on the trajectory of the stance phase curve of the gait cycle have not been previously reported. We hypothesized characteristic changes of age, body height, body weight, body mass index and handgrip strength on the plantar pressure curve trajectory during gait in healthy participants. Thirty-seven healthy women and men with an average age of 43.65 ± 17.59 years were fitted with Moticon OpenGO insoles equipped with 16 pressure sensors each. Data were recorded at a frequency of 100 Hz during walking at 4 km/h on a level treadmill for 1 minute. Data were processed via a custom-made step detection algorithm. The loading and unloading slopes as well as force extrema-based parameters were computed and characteristic correlations with the targeted parameters were identified via multiple linear regression analysis. Age showed a negative correlation with the mean loading slope. Body height correlated with Fmeanload and the loading slope. Body weight and the body mass index correlated with all analyzed parameters, except the loading slope. In addition, handgrip strength correlated with changes in the second half of the stance phase and did not affect the first half, which is likely due to stronger kick-off. However, only up to 46% of the variability can be explained by age, body weight, height, body mass index and hand grip strength. Thus, further factors must affect the trajectory of the gait cycle curve that were not considered in the present analysis. In conclusion, all analyzed measures affect the trajectory of the stance phase curve. When analyzing insole data, it might be useful to correct for the factors that were identified by using the regression coefficients presented in this paper.

/pdf/effects-of-age-body-height-body-weight-body-mass-index-and-1byhrel0.pdf

Effects of age, body height, body weight, body mass index and handgrip strength on the trajectory of the plantar pressure stance-phase curve of the gait cycle

This paper presents a plantar pressure sensor system (P2S2) integrated in the insoles of shoes to detect thirteen commonly used human movements including walking, stooping left and right, pulling a cart backward, squatting, descending, ascending stairs, running, and falling (front, back, right, left). Six force sensitive resistors (FSR) sensors were positioned on critical pressure points on the insoles to capture the electrical signature of pressure change in the various movements. A total of 34 adult participants were tested with the P2S2. The pressure data were collected and processed using a Principal Component Analysis (PCA) for input to the multiple machine learning (ML) algorithms, including k-NN, neural network and Support-Vector Machine (SVM) algorithms. The ML models were trained using four-fold cross-validation. Each fold kept subject data independent from other folds. The model proved effective with an accuracy of 86%, showing a promising result in predicting human movements using the P2S2 integrated in shoes.

/pdf/empirical-study-on-human-movement-classification-using-nil8xvrs.pdf

Empirical Study on Human Movement Classification Using Insole Footwear Sensor System and Machine Learning

Extreme angles in lower body joints may adversely increase the risk of injury to joints. These injuries are common in the workplace and cause persistent pain and significant financial losses to people and companies. The purpose of this study was to predict lower body joint angles from the ankle to the lumbosacral joint (L5S1) by measuring plantar pressures in shoes. Joint angle prediction was aided by a designed footwear sensor consisting of six force-sensing resistors (FSR) and a microcontroller fitted with Bluetooth LE sensors. An Xsens motion capture system was utilized as a ground truth validation measuring 3D joint angles. Thirty-seven human subjects were tested squatting in an IRB-approved study. The Gaussian Process Regression (GPR) linear regression algorithm was used to create a progressive model that predicted the angles of ankle, knee, hip, and L5S1. The footwear sensor showed a promising root mean square error (RMSE) for each joint. The L5S1 angle was predicted to be RMSE of 0.21° for the X-axis and 0.22° for the Y-axis, respectively. This result confirmed that the proposed plantar sensor system had the capability to predict and monitor lower body joint angles for potential injury prevention and training of occupational workers.

https://www.mdpi.com/1424-8220/23/1/228/pdf?version=1672043859

Seongcheol Jeong

Papers

Empirical Study on Human Movement Classification Using Insole Footwear Sensor System and Machine Learning

Lower Body Joint Angle Prediction Using Machine Learning and Applied Biomechanical Inverse Dynamics