Deep Neural Network for the Detections of Fall and Physical Activities Using Foot Pressures and Inertial Sensing

Abstract

Fall detection and physical activity (PA) classification are important health maintenance issues for the elderly and people with mobility dysfunctions. The literature review showed that most studies concerning fall detection and PA classification addressed these issues individually, and many were based on inertial sensing from the trunk and upper extremities. While shoes are common footwear in daily off-bed activities, most of the aforementioned studies did not focus much on shoe-based measurements. In this paper, we propose a novel footwear approach to detect falls and classify various types of PAs based on a convolutional neural network and recurrent neural network hybrid. The footwear-based detections using deep-learning technology were demonstrated to be efficient based on the data collected from 32 participants, each performing simulated falls and various types of PAs: fall detection with inertial measures had a higher F1-score than detection using foot pressures; the detections of dynamic PAs (jump, jog, walks) had higher F1-scores while using inertial measures, whereas the detections of static PAs (sit, stand) had higher F1-scores while using foot pressures; the combination of foot pressures and inertial measures was most efficient in detecting fall, static, and dynamic PAs.

Laser-light cueing shoes with integrated foot pressure and inertial sensing for investigating the impact of visual cueing on gait characteristics in Parkinson’s disease individuals

“…These FSRs were manufactured using processing and printing-based micromachining technology, employing a resistance-type piezo-resistive polymer composite. Each FSR had a sensing range of 1–5 kg/cm 2 and was individually calibrated using elastic-film pressurization to minimize resistance variance among the sensors ( Chan et al, 2023 ). The custom insole had dimensions of 260 mm in height, 85 mm in metatarsus width, 55 mm in heel width, and a thickness of 0.63 mm.…”

Machine Learning Classification for a Second Opinion System in the Selection of Assistive Technology in Post-Stroke Patients

“…The future of research in the area of assistive technologies design lies in the increased use of robotic devices, personalised by 3D printing; Internet of Things wearable sensors for personalised training of limb use, gait and balance, and activities of daily living and health monitoring [17][18][19][20][21]; and even novel brain-computer interfaces [22,23] and associated computational models [24]. Further, more advanced studies may additionally use data from postural and gait analysis [25,26]. We will also draw inspiration as to the direction of further research from the work of [27][28][29].…”

Daily Activities of Elder Adults Using Optimized Deep Learning Model in China

“…In order to detect falls and categorise different kinds of physical activity (PA), Chan et al [24] offer a novel footwear strategy based on a CNN hybrid. Based on data from 32 subjects who individually performed PAs, it was shown that the detections employing deep-learning knowledge were effective: The F1-score for detecting falls with inertial measures was higher than for detection with foot pressures; the F1-score for detecting dynamic PAs (jump, jog, walks) was higher for inertial measures than for foot pressures; and the F1-score for detecting static PAs (sit, stand) was highest when using a combination of foot measures.…”