Towards predicting frailty symptoms through a smart walking stick

Abstract

Open Archive Toulouse Archive OuverteOATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible To cite this version: Kessentini, Oussama and Dalcé, Réjane and Megdiche-Bousarsar, Imen and Bastide, Rémi Towards predicting frailty symptoms through a smart walking stick. (Abstract-A warning sign of frailty is imbalance. Psychomotor therapists run tests to evaluate the balance deterioration but not often enough to track the rapidly changing condition of the elderly. The proposed system collects fine-grained data from a smart cane and processes them with Machine Learning (ML) techniques. The originality of our proposition lies in its personalization by the elderly biomarkers in ML algorithms.Our experiments indicate that we can observe the orientation of locomotion through the cane as well as recognize characteristics of specific participants ambulation in the uncontrolled scenario.

Artificial Intelligence-Enabled Caregiving Walking Stick Powered by Ultra-Low-Frequency Human Motion

“…The synchronous kinematic linkage between the walking stick and the human body is generally observed in assisted ambulation; thus the movement patterns of the walking stick also reflect the activity status of the users. Previous research includes structure innovation as a treatment for Parkinsonian freezing episodes, applying inertial sensors to track users’ motion and gait status, , and equipping distance-sensing functions ( e . g ., ultrasonic sensor) to help visually impaired users. − Besides, each strike of the walking stick involves the process of transferring weight from the upper limb to the ground, which contains lots of wasted biomechanical energy that can be scavenged for further use.…”

Imbalance Prediction Among Elderly People Using Deep Learning

“…If we consider fall or imbalance problems their observation rate for elderly people would not be sufficient. That's why we found datasets (Kessentini et al, 2018) (Ojetola et al, 2015) generated by young participants imitating elderly problems.…”

“…In this work, the distance between the center of legs and the cane was investigated in order to classify the subject's activity. The work of (Kessentini et al, 2018) presents a system that contains a smart cane connecting to ChisteraPi gateway. In this study, a dataset was created by letting young adult subjects experience some ADLs and falls.…”