Smart insoles detect elderly activity and prevent falls
Smart Insole Human Activity Recognition for Continuous Monitoring in Elderly Care
Machine Learning
Summary
Falls in older people often happen after changes in how they move or balance. The authors created smart shoe insoles that measure pressure and movement to tell if someone is sitting, standing, walking, or walking unstably. They tested these insoles on healthy adults and used machine learning to accurately recognize these activities even for people the system hadn’t seen before. This work helps track how elderly people move to reduce fall risks.
What this means in practice
- •For elderly care providers: Use smart insoles to continuously monitor elderly patients for changes in activity and unstable walking to improve fall prevention efforts.
- •For wearable device manufacturers: Integrate combined pressure and inertial sensing with machine learning models into footwear products to offer real-time activity recognition and safety alerts.$Commercial implications: Enables development of advanced fall prevention smart shoes marketed to elderly individuals and healthcare organizations.
Authors
Edwin Rios, Antony Garcia, Fengpei Yuan, Xinming Huang
Abstract
Falls in older adults are often preceded by changes in mobility, balance, and postural transitions. This paper presents a wireless smart insole platform and machine-learning workflow for recognizing sitting, standing, walking, and unstable walking from plantar-pressure and inertial signals. Each insole integrates 16 active pressure-sensing locations and a six-dimensional IMU stream consisting of tri-axial acceleration and angular velocity. Data were collected from 15 healthy adults at 80~Hz and segmented into overlapping windows. Window length and candidate model families were first screened with stratified 10-fold cross-validation; the primary performance estimate was then obtained with participant-independent 5-fold Stratified Group cross-validation, ensuring that all windows from a participant remained in a single fold. Under this protocol, Histogram-Based Gradient Boosting (HGB) achieved macro-F1 scores of 0.954 and 0.959 for the left and right feet, respectively, and 0.980 with bilateral sensing. A compact 1D-CNN evaluated with the same participant-independent folds did not significantly outperform HGB ($p=0.0625$). The results show that low-profile footwear sensing can infer activity state from pressure and IMU measurements for participants unseen during training, establishing a basis for activity monitoring and fall prevention in elderly care.