Gait Estimation from Anatomical Foot Parameters Measured by a Foot Feature Measurement System using a Deep Neural Network Model

Mun, Kyung-Ryoul; Song, Gyuwon; Chun, Sung; Kim, Jin Wook

doi:10.1038/s41598-018-28222-2

Cited by 33 publications

(12 citation statements)

References 26 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a similar approach, Mun et al [104] used a deep ANN to estimate and quantify spatiotemporal gait parameters from foot characteristics. This was achieved with a footstep feature measurement system that scans the foot while a subject performs various motion tasks, and a set of IMU sensors integrated in a commercial motion-capture system (Xsens MVN, Enschede, The Netherlands), to detect heel strike and toe-off off events during gait cycle.…”

Section: Multi-modality Gait Sensor Fusionmentioning

confidence: 99%

Deep Learning for Monitoring of Human Gait: A Review

2019

View full text Add to dashboard Cite

The essential human gait parameters are briefly reviewed, followed by a detailed review of the state of the art in deep learning for the human gait analysis. The modalities for capturing the gait data are grouped according to the sensing technology: video sequences, wearable sensors, and floor sensors, as well as the publicly available datasets. The established artificial neural network architectures for deep learning are reviewed for each group, and their performance are compared with particular emphasis on the spatiotemporal character of gait data and the motivation for multi-sensor, multi-modality fusion. It is shown that by most of the essential metrics, deep learning convolutional neural networks typically outperform shallow learning models. In the light of the discussed character of gait data, this is attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted gait features.

show abstract

Section: Multi-modality Gait Sensor Fusionmentioning

confidence: 99%

Deep Learning for Monitoring of Human Gait: A Review

2019

View full text Add to dashboard Cite

show abstract

“…Gaits are important to know any developmental progress during some diseases or after some surgeries. Some important health and medical-related terminologies that can be addressed by gait characteristics are patients with cerebral palsy, cerebellar ataxia, knee arthroplasty, hip arthroplasty, Charcot-Marie-Tooth disease, idiopathic arthritis, idiopathic Parkinson's disease, atypical Parkinson's disease, bipolar disorder, dementia, Pick's disease, idiopathic normal pressure hydrocephalus, ankle osteoarthritis, Alzheimer's disease, postural instability, and gait difficulty, and to improve the life-quality of patients and elderly people who are suffering due to gait-related or walking pattern-related problems [13,21,22].…”

Section: Related Workmentioning

confidence: 99%

“…Effect of treadmill walking on upper trunk and gait are studied in [40] where they engaged eight subjects. Mun et al [21] introduced a CNN-based model to analyze gait estimation from various foot parameters. They employed multiple inertial sensors as well as a commercialized motion capture system to evaluate on 42 subjects.…”

Section: Related Workmentioning

confidence: 99%

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Ahad

Ngo

Antar

et al. 2020

Sensors

View full text Add to dashboard Cite

Wearable sensor-based systems and devices have been expanded in different application domains, especially in the healthcare arena. Automatic age and gender estimation has several important applications. Gait has been demonstrated as a profound motion cue for various applications. A gait-based age and gender estimation challenge was launched in the 12th IAPR International Conference on Biometrics (ICB), 2019. In this competition, 18 teams initially registered from 14 countries. The goal of this challenge was to find some smart approaches to deal with age and gender estimation from sensor-based gait data. For this purpose, we employed a large wearable sensor-based gait dataset, which has 745 subjects (357 females and 388 males), from 2 to 78 years old in the training dataset; and 58 subjects (19 females and 39 males) in the test dataset. It has several walking patterns. The gait data sequences were collected from three IMUZ sensors, which were placed on waist-belt or at the top of a backpack. There were 67 solutions from ten teams—for age and gender estimation. This paper extensively analyzes the methods and achieved-results from various approaches. Based on analysis, we found that deep learning-based solutions lead the competitions compared with conventional handcrafted methods. We found that the best result achieved 24.23% prediction error for gender estimation, and 5.39 mean absolute error for age estimation by employing angle embedded gait dynamic image and temporal convolution network.

show abstract

“…A recent work on gait estimation using a deep neural network was demonstrated in Ref. 34, where the algorithm could estimate and quantify the gait temporospatial parameters from foot characteristics.…”

Section: Processing Control Telemetry and Powermentioning

confidence: 99%

Smart Lower Limb Prostheses with a Fiber Optic Sensing Sole: A Multicomponent Design Approach

Butt¹,

Qureshi²

2019

Sensors and Materials

View full text Add to dashboard Cite

A review on a multicomponent design is presented for the development of a lower limb smart prosthetic system based on fiber optic sensing. The key component of this system is the smart sole consisting of a group of fiber optic sensors called the fiber Bragg grating (FBG). Such a group of sensors allow the human sense of touch to be mimicked through strategic sensor placement while identifying minute changes in contact conditions. Gait control through plantar pressure measurements is an important feature of lower limb prosthetics and allows for the identification of terrain through ground reaction forces (GRFs). Current smart lower limb prosthetics consist of a powered ankle equipped with torque sensors and a motorized assembly to enable proper gait control. Adding a smart sensing sole, which incorporates the sense of touch in addition to GRF identification, will enable patients with neurological disorders or amputation to relive the experience of a normal human being. Prosthetic technologies that will assist in developing a smart lower limb prosthetic system with a multicomponent design are presented on the basis of review, and a complete integrated system that will include sensing, processing, and control is suggested. The control can come through two approaches: (a) a trained system based on artificial intelligence or (b) a direct intervention of the subject. The intervention in the latter approach is based on sensing the signals from the smart foot and receiving them in the brain through a brain-machine interface (BMI).

show abstract

Gait Estimation from Anatomical Foot Parameters Measured by a Foot Feature Measurement System using a Deep Neural Network Model

Cited by 33 publications

References 26 publications

Deep Learning for Monitoring of Human Gait: A Review

Deep Learning for Monitoring of Human Gait: A Review

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Smart Lower Limb Prostheses with a Fiber Optic Sensing Sole: A Multicomponent Design Approach

Contact Info

Product

Resources

About