Wyniki wyszukiwania - BazTech

1

A systematic review of artificial neural network techniques for analysis of foot plantar pressure

Wang Chongguang, Evans Kerrie, Hartley Dean, Morrison Scott, Veidt Martin, Wang Gui

Biocybernetics and Biomedical Engineering

|

2024

|

Vol. 44, no. 1

197--208

EN

Plantar pressure distribution offers insights into foot function, gait mechanics, and foot-related issues. This systematic review presents an analysis of the use of artificial neural network techniques in the context of plantar pressure analysis. 60 studies were included in the review. Sample size, pathology, pressure sensor number, data collection device, utilization of other sensor devices, ground-truth methods, pre-processing dataset, neural network type, and evaluation metrics were evaluated. Utilization of customized wearable footwear devices for the acquisition of data was common amongst both healthy participants and patients. Inertial measurement units emerged as an effective compensatory measure to address the limitations associated with the distribution of plantar pressure. Ground truth methods predominantly relied on the usage of both annotations and reference devices. Multilayer perceptron, convolutional neural networks, and recurrent neural networks were identified as the most frequently employed artificial neural network algorithms across the reviewed studies. Finally, the evaluation of performance largely drew upon statistical descriptions and other machine learning methods. This review provides a comprehensive understanding of the use of artificial neural network techniques in plantar pressure analysis, highlighting opportunities for future research.

2

Development and testing of a wearable passive lower-limb support exoskeleton to support industrial workers

Yan Zefeng, Han Bin, Du Zihao, Huang Tiantian, Bai Ou, Peng Ansi

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 1

221--238

EN

A custom-designed, wearable, lightweight, and passive exoskeleton was proposed to provide gravity support for industrial workers to reduce prevalence of musculoskeletal disorders, joint injures, and arthritis caused by repeatedly or persistently squatting task. The designed exoskeleton can act as a wearable chair to allow workers to squat for an extended period when performing prolonged tasks. The exoskeleton employs torsion springs to store energy harvested from the squatting motion, and the stored energy is released to help the workers stand up. Dimensions optimization designs based on the finite element analysis program were implemented for a lightweight of the device. Besides, the exoskeleton effectiveness was investigated by performing an ergonomic assessmenton muscular activity, plantar pressure, endurance time, and comfort. The plantar pressure and electromyography of rectus femoris, biceps femoris, vastus medialis, and vastus laterals were measured in a simulated assembly task with the knee bend for three different angles (60°, 90°, 120°) under two conditions of with and without the exoskeleton. The endurance time was recorded in three different static squatting tasks. The comfort with the exoskeleton was recorded. Under the condition of wearing the exoskeleton, the average reduction of muscle activity was 44.8–71.5%, and the plantar pressure was 58.5–64.2%. The exoskeleton contributed to an increase in endurance time from 2.76 to 13.58 min. Moreover, 70% of the subjects exhibited a comprehensive exoskeleton comfort score of higher than 70. The experimental results demonstrated that this exoskeleton has good potential to reduce physical workload and increase endurance time during industrial assembly tasks.

3

Deep-segmentation of plantar pressure images incorporating fully convolutional neural networks

Wang Dan, Li Zairan, Dey Nilanjan, Ashour Amira S., Moraru Luminita, Simon Sherratt R., Shi Fuqian

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

546--558

EN

Comfort shoe-last design relies on the key points of last curvature. Traditional plantar pressure image segmentation methods are limited to their local and global minimization issues. In this work, an improved fully convolutional networks (FCN) employing SegNet (SegNet+FCN 8 s) is proposed. The algorithm design and operation are performed using the visual geometry group (VGG). The method has high efficiency for the segmentation in positive indices of global accuracy (0.8105), average accuracy (0.8015), and negative indices of average cross-ratio (0.6110) and boundary F1 index (0.6200). The research has potential applications in improving the comfort of shoes.

4

Classification of plantar foot alterations by fuzzy cognitive maps against multi-layer perceptron neural network

Ramirez-Bautista Julian Andres, Huerta-Ruelas Jorge Adalberto, Kóczy László T., Hatwágner Miklós F., Chaparro-Cárdenas Silvia L., Hernández-Zavala Antonio

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

404--414

EN

Load distribution analysis on foot surface allows knowing human mechanical behavior and aids the doctor in the detection of gait disorders like, the risk of foot ulcerations, leg discrepancy, and footprint alterations. Plantar pressure data combined with techniques that use integral reasoning produce easy understanding medical tools for assisting in treatment, early detection, and the development of preventive strategies. The present research compares the classification of human plantar foot alterations using Fuzzy Cognitive Maps (FCM) trained by Genetic Algorithm (GA) against a Multi-Layer Perceptron Neural Network (MLPNN). One hundred and fifty-one subject volunteers (aged 7–77) were classified previously with the flat foot (n = 70) and cavus foot (n = 81) by specialized physicians of the Piédica diagnostic center. The trial walking was conducted using plantar pressure platforms FreeMed®. The foot surface was divided into 14 areas that included toe 1 st to 5th, metatarsal joint 1st to 5th, lateral midfoot, medial midfoot, lateral heel, and medial heel. Pressure data were normalized for each area. Better performance in the classification using small amounts of data were found by using Fuzzy rather than non-Fuzzy approach.

5

Difference of walking plantar loadings in experienced and novice long-distance runners

Gao Zixiang, Mei Qichang, Xiang Liangliang, Gu Yaodong

Acta of Bioengineering and Biomechanics

|

2020

|

Vol. 22, no. 3

85--93

EN

Purpose: Long-distance running has been a global popularity, and differences may be observed in runners of experience. This study was aimed to evaluate the differences in plantar loading between experienced long-distance runners and novice runners during walking. The hypotheses were that smaller load in the middle of the forefoot and the stable foot balance would be observed in experienced runners during walking. Methods: Twenty-five participants were recruited as the experienced runners group (ten: frequency ≥ 4 times/week and distance ≥ 40 km/week, for over 1 year) and the novice group (fifteen: frequency ≤ 2 times/week and distance ≤ 10 km/week, for less than 1 year). Results: The peak Meta loading showed that the novice runners were significantly larger than the experienced runners ( p ≤ .001). The occurring time of peak Meta loading was significantly delayed compared to the experienced runners ( p = .050). Peak Foot balance was higher in the novice runners group ( p ≤ 0.001). Conclusions: This study highlighted the findings of the potential differences of plantar pressures and foot functional parameters during walking in experienced runners and novice runners, specifically the contact duration of phases during stance, toes functions and medial-lateral loading shifting (foot balance) and metatarsals (central forefoot) offloading.

6

Plantar pressure image fusion for comfort fusion in diabetes mellitus using an improved fuzzy hidden Markov model

Li Zairan, Wang Dan, Dey Nilanjan, Ashour Amira S., Sherratt R. Simon, Shi Fuqian

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 3

742--752

EN

Diabetes mellitus is a clinical syndrome caused by the interaction of genetic and environmental factors. The change of plantar pressure in diabetic patients is one of the important reasons for the occurrence of diabetic foot. The abnormal increase of plantar pressure is a predictor of the common occurrence of foot ulcers. The feature extraction of plantar pressure distribution will be beneficial to the design and manufacture of diabetic shoes that will be beneficial for early protection of diabetes mellitus patients. In this research, texture-based features of the angular second moment (ASM), moment of inertia (MI), inverse difference monument (IDM), and entropy (E) have been selected and fused by using the updown algorithm. The fused features are normalized to predict comfort plantar pressure imaging dataset using an improved fuzzy hidden Markov model (FHMM). In FHMM, type-I fuzzy set is proposed and fuzzy Baum–Welch algorithm is also applied to estimate the next features. The results are discussed, and by comparing with other back–forward algorithms and different fusion operations in FHMM. Improved HMMs with up–down fusion using type-I fuzzy definition performs high effectiveness in prediction comfort plantar pressure distribution in an image dataset with an accuracy of 82.2% and the research will be applied to the shoe-last personalized customization in the industry.

7

Do different muscle strength levels affect stability during unplanned gait termination?

Cen Xuanzhen, Jiang Xinyan, Gu Yaodong

Acta of Bioengineering and Biomechanics

|

2019

|

Vol. 21, no. 4

27--35

EN

Unplanned gait termination (UGT) widely occurs in various sports and daily life as a kind of stress response to unexpected stimulus. However, the body stability may be greatly affected when the body completely stops. The purpose of this study was to examine the association between muscle strength levels and body stability during UGT through comparing the plantar pressure. Methods: Twenty healthy participants (10 male and 10 female) with different lower limbs muscle strength and power were asked to perform planned gait termination (PGT) and unplanned gait termination (UGT) on an 8-m walkway. Related plantar pressure data including maximum pressure, maximum force, contact area and center of pressure were recorded with Footscan pressure platform. Results: Two types of gait termination have significant differences in the plantar pressure distribution. Maximum pressure and maximum force in the lateral metatarsal increased significantly during UGT, compared to PGT. At the same time, data from the current study suggested that there might be a correlation between the muscle strength levels of individual and the stability during the gait termination, especially between the muscle power and UGT, which means that the more excellent muscle power an individual has, the more stable the body is when UGT is performed. Conclusions: The findings suggest that different muscle strength levels could affect stability during unplanned gait termination.

8

Plantar pressure analysis of above-knee amputee with a developed microprocessor-controlled prosthetic knee

Cao W., Yu H., Meng Q., Li S.

Acta of Bioengineering and Biomechanics

|

2018

|

Vol. 20, no. 4

33--40

EN

Human gait motion analysis was one useful method for lower limb prosthesis study. The most often measured parameters were plantar pressure, kinetic and kinematic parameters. It was indispensable for prosthetic knee design and performance assessment. The aim of this study was to analysis the plantar pressure in traumatic above-knee amputee equipped with a developed microprocessor-controlled prosthetic knee. Methods: The maximum force of forefoot and rearfoot, the average vertical reaction force and pressure and the centre of pressure (COP) offset trajectories of ten above-knee amputees under different walking speeds were obtained. Results: Both forefoot and rearfoot force were bigger in intact leg than prosthetic leg. As the speed increased, the pressure increased in both sides. Forefoot bore more pressure than rearfoot in both legs. The average vertical pressure and force both increased along with the increase of speed. The force and pressure of intact side were always bigger than the prosthetic side. The trend of COP and gait line of the prosthetic and intact side had no significant difference. The length of the gait line of prosthetic side was greater than the intact side. Conclusions: The results of this study exhibited reduced plantar pressure in the prosthetic side. The typical butterfly diagrams were produced during different walking speeds. It indicated that the stability of the microprocessor-controlled prosthetic knee could be guaranteed.

9

How foot morphology changes influence shoe comfort and plantar pressure before and after long distance running?

Mey Q., Gu Y., Sun D., Fernandez J.

Acta of Bioengineering and Biomechanics

|

2018

|

Vol. 20, no. 2

179--186

EN

Prolonged running has been popularized globally in recent decades. This study was aimed to reveal information about foot morphology, shoe comfort and plantar loading among recreational heel-strike runners. Methods: Twenty-six runners participated in foot morphology, perceived scores and peak pressure tests after 10- and 20-km track running. The foot morphology was measured using a 3D foot scanner, perceived scores were recorded using a visual analogue scale and plantar pressure was measured via insole plantar pressure measurement system. The statistical significance level was set at 0.05. Results: The heel midsole materials properties were measured before and after 20 km. Significant changes were observed in ball width and girth, arch height and foot volume. The perceived scores showed significance in overall, forefoot and heel comfort, arch support and forefoot width. Peak pressure to the heel, medial mid-foot and metatarsal greatly increased. The first metatarsal showed consecutive increase from static to 10 km, and 20 km, while big-toe showed a decrease. Conclusions: The morphology variations and forefoot loading concentration may lead to discomfort and possibly imply dermatological problems and metatarsal bone stress, particularly on the first metatarsal. Combining changes of heel midsole property, knowledge of foot shape, shoe perception and plantar pressure is of great value for recreational long-distance running shoes design and materials selection.

10

Effects of unstable elements with different hardness on lower limb loading

Li F., Mei Q., Gu Y.

Acta of Bioengineering and Biomechanics

|

2015

|

Vol. 17, no. 2

85--92

EN

Purpose: Osteoarthritis of the knee is one of the most common diseases. For this chronic disease, modified footwear structure can effectively prevent and relieve disease of the knee. The aim of this study was to explore the effects of shoe surface elastic modulus on external knee adduction moment and ground reaction force and foot loading characteristics. Methods: Sixteen healthy female volunteers were recruited, and each subject performed five walking trials under two shoes condition. The lower limb loading data was collected using force platform and in-sole pressure measurement system. Results: The results showed that the external knee adduction moment was decreased in all stance phase when wearing SS (unstable shoes with soft unstable elements), compared with HS (unstable shoes with hard unstable elements). The ground reaction force showed no obvious change under two shoes condition. Additionally, compared with HS, plantar pressure transferred from medial foot to lateral foot when wearing SS. Along with changes of contact areas, average pressure and impulse had also presented this tendency. Conclusions: These results can provide some scientific evidence and suggestions for footwear companies, and for the foot plantar medial injury disease has also certain applicability.

11

Analysis of foot load during ballet dancers’ gait

Prochazkova M., Tepla L., Svoboda Z., Janura M., Cieslarová M.

Acta of Bioengineering and Biomechanics

|

2014

|

Vol. 16, no. 2

41--45

EN

Ballet is an art that puts extreme demands on the dancer’s musculoskeletal system and therefore significantly affects motor behavior of the dancers. The aim of our research was to compare plantar pressure distribution during stance phase of gait between a group of professional ballet dancers and non-dancers. Thirteen professional dancers (5 men, 8 women; mean age of 24.1 ± 3.8 years) and 13 nondancers (5 men, 8 women; mean age of 26.1 ± 5.3 years) participated in this study. Foot pressure analysis during gait was collected using a 2 m pressure plate. The participants were instructed to walk across the platform at a self-selected pace barefoot. Three gait cycles were necessary for the data analysis. The results revealed higher ( p < 0.05) pressure peaks in medial edge of forefoot during gait for dancers in comparison with nondancers. Furthermore, differences in total foot loading and foot loading duration of rearfoot was higher ( p < 0.05) in dancers as well. We can attribute these differences to long-term and intensive dancing exercises that can change the dancer’s gait stereotype.

12

A real time plantar pressure feedback device for foot unloading

Femery V., Hespel J.M., Thevenon A., Moretto P.

Journal of Medical Informatics & Technologies

|

2003

|

Vol. 6

IT103--106

EN

The design and development of a plantar pressure control device, adapted to correct plantar pressure distribution patterns, is described. This device is based on the artificial return of information in real time to instantaneously reveal to subject certain events, of which he was unaware and which are difficult to quantify, such as the pressure variation generated by foot-ground contact. An acoustic alarm and visual signals, adjusted to a specific pressure load, alert the user in the case of excessive plantar pressure. So, our feedback device is designed to substitute for loss of feeling in patients who have peripheral neuropathy secondary to diabetes mellitus. The ultimate aim of this project is to prevent the development of neuropathic foot ulceration by providing both visual and auditory extrinsic sensory feedback to compensate for the malfunctioning peripheral nerves and to transmit information to the patient about dangerous conditions on the plantar surface of the feet. A trial of the device in a healthy subject is presented to evaluate whether a new gait pattern can emerge thanks to feedback from plantar pressure measurements.