Human Gait Research Articles

BAHGRF3: Human gait recognition in the indoor environment using deep learning features fusion assisted framework and posterior probability moth flame optimisation

AbstractBiometric characteristics are playing a vital role in security for the last few years. Human gait classification in video sequences is an important biometrics attribute and is used for security purposes. A new framework for human gait classification in video sequences using deep learning (DL) fusion assisted and posterior probability‐based moth flames optimization (MFO) is proposed. In the first step, the video frames are resized and fine‐tuned by two pre‐trained lightweight DL models, EfficientNetB0 and MobileNetV2. Both models are selected based on the top‐5 accuracy and less number of parameters. Later, both models are trained through deep transfer learning and extracted deep features fused using a voting scheme. In the last step, the authors develop a posterior probability‐based MFO feature selection algorithm to select the best features. The selected features are classified using several supervised learning methods. The CASIA‐B publicly available dataset has been employed for the experimental process. On this dataset, the authors selected six angles such as 0°, 18°, 90°, 108°, 162°, and 180° and obtained an average accuracy of 96.9%, 95.7%, 86.8%, 90.0%, 95.1%, and 99.7%. Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state‐of‐the‐art techniques.

Modelling Human-Structure Interaction in Pedestrian Bridges Using a Three-Dimensional Biomechanical Approach

Pedestrian bridges, which are essential in urban and rural infrastructures, are vulnerable to vibrations induced by pedestrian traffic owing to their low mass, stiffness, and damping. This paper presents a novel predictive model of Human-Structure Interaction (HSI) that integrates a three-dimensional biomechanical model of the human body, and a pedestrian bridge represented as a simply supported Euler-Bernoulli beam. Using inverse dynamics, the human model accurately captures three-dimensional gait and its interaction with structural vibrations. The results show that this approach provides precise estimates of human gait kinematics and kinetics, as well as the bridge response under pedestrian loads. The incorporation of a three-dimensional human gait model reflects the changes induced by bridge vibrations, providing a robust tool for evaluating and improving the effect of structural vibrations on the properties and gait patterns.

Ankle Moment Estimation Based on A Novel Distributed Plantar Pressure Sensing System.

Ankle moment plays an important role in human gait analysis, patients' rehabilitation process monitoring, and the human-machine interaction control of exoskeleton robots. However, current ankle moment estimation methods mainly rely on inverse dynamics (ID) based on optical motion capture system (OMC) and force plate. These methods rely on fixed instruments in the laboratory, which are difficult to be applied to the control of exoskeleton robots. To solve this problem, this paper developed a new distributed plantar pressure system and proposed an ankle plantar flexion moment estimation method using the plantar pressure system. We integrated eight pressure sensors in each insole to collect the pressure data of the key area of the foot and then used the plantar pressure data to train four neural networks to obtain the ankle moment. The performance of the models was evaluated using normalized root mean square error (NRMSE) and cross-correlation coefficient (ρ). During experiments, eight subjects were recruited for the overground walking tests, and OMC and force plate were used as the gold standard. The results indicate that the Genetic algorithm - Gated recurrent unit estimation algorithm (GA-GRU) was the best estimation model which achieved the highest accuracy in generalized ankle moment estimation (NRMSE = 7.23%, ρ = 0.85) compared with the other models. The designed novel distributed plantar pressure system and the proposed method could serve as a joint moment estimation approach in wearable robot control and human motion state monitoring.

Walking on Virtual Surface Patterns Leads to Changed Control Strategies.

Inclusive design does not stop at removing physical obstacles such as staircases. It also involves identifying architectural features that impose sensory burdens, such as repetitive visual patterns that are known to potentially cause dizziness or visual discomfort. In order to assess their influence on human gait and its stability, three repetitive patterns-random dots, repetitive stripes, and repetitive waves (Lisbon pattern)-were displayed in a coloured and greyscale variant in a virtual reality (VR) environment. The movements of eight participants were recorded using a motion capture system and electromyography (EMG). During all test conditions, a significant increase in the muscular activity of leg flexor muscles was identified just before touchdown. Further, an increase in the activity of laterally stabilising muscles during the swing phase was observed for all of the test conditions. The lateral and vertical centre of mass (CoM) deviation was statistically evaluated using a linear mixed model (LMM). The patterns did cause a significant increase in the CoM excursion in the vertical direction but not in the lateral direction. These findings are indicative of an inhibited and more cautious gait style and a change in control strategy. Furthermore, we quantified the induced discomfort by using both algorithmic estimates and self-reports. The Fourier-based methods favoured the greyscaled random dots over repetitive stripes. The colour metric favoured the striped pattern over the random dots. The participants reported that the wavey Lisbon pattern was the most disruptive. For architectural and structural design, this study indicates (1) that highly repetitive patterns should be used with care in consideration of their impact on the human visuomotor system and its behavioural effects and (2) that coloured patterns should be used with greater caution than greyscale patterns.

Auto-Correlation and Channel Attention Enhanced Deep Graph Convolution Networks for Gait Phase Prediction Based on Multi-IMU System

Gait phase prediction is important in controlling assistive robotic devices such as exoskeletons, where the control unit must differentiate between gait phases to provide the necessary assistance when the user is wearing the exoskeleton. To achieve the objective of precisely identifying the gait phase of users for the accurate control of the exoskeleton, this study proposes Auto-Correlation and Channel Attention enhanced Deep Graph Convolutional Networks (ACCA-DGCN) for gait phase prediction, and a gait phase prediction model based on multiple inertial measurement units (IMUs) and skeleton graph was established, in order to fully utilize the dependency among joints, and enhance accuracy and reliability of gait phase prediction. First, a human lower limb gait data acquisition equipment was developed, and the gait data of human walking were collected. The skeleton graph of the human lower limb was constructed through the natural connection relationship of joints in the human skeleton. After that, the ACCA-DGCN-based gait phase prediction model was constructed by using the gait data of human walking. Auto-Correlation (AC) and Efficient Channel Attention (ECA) were introduced to effectively capture periodic features of gait data and focus on the channels with high contributions to gait phase prediction. Finally, the effect of the window size on the performance of the ACCA-DGCN model was explored, and the proposed algorithm was compared with the other five deep learning algorithms: CNN, RNN, TCN, LSTM, and DGCN. The experimental results show that the average accuracy of gait phase prediction model based on ACCA-DGCN reaches up to 92.26% and 97.21% in user-independent and user-dependent experiments, respectively, which is superior to the other five algorithms. This study provides a new method for gait phase prediction, which is useful for improving the control of exoskeleton robots.

Self-Powered Wearable Pressure Sensor System for Smart Healthcare Applications

Wearable sensors mark a groundbreaking advancement in the realm of health monitoring technology. However, traditional wearable devices lack comprehensive solutions for tracking sports exercise behaviors and providing feedback on rehabilitation for those undergoing home-based recovery. To bridge this gap, a self-powered triboelectric nanogenerator (TENG)-based wearable sensing system has been developed with in-house monitoring capabilities. The wearable sensor system is composed of triboelectric pressure sensors with an electro-conductive silicone sheet and patterned Ecoflex film as the contact layers. Highly sensitive TENG sensors have been successfully embedded into a bicycle saddle and human shoe insole for real-time pressure monitoring. Experimental results demonstrate that biomechanical energy, originating from both the pelvic-saddle interactions on bicycle and human gait movements, has been successfully converted into electrical energy. The generated sensor voltage remains stable under frequency variations and external environmental conditions, such as temperature and humidity variations. Utilizing distinctive information contained in individual body mass imbalances and gait characteristics, a smart healthcare monitoring system is envisioned to extract essential biomechanical insights via artificial intelligence, facilitating a pivotal role in in-house monitoring and tracking of sports rehabilitation exercises. The as-designed low-cost, highly scalable self-powered wearable sensor system offers an accessible, user-friendly point-of-care solution for gait detection and rehabilitation monitoring for individuals with various physical impairments, with considerable potential for commercialization. Figure 1

A porous elastomer with a cavity array for three-dimensional plantar force sensing

Human gait is an important indicator for diagnosis of various movement-related disorders. Three-dimensional (3D) plantar force monitoring enables real-time recording of contact forces in both the normal and tangential directions in each step, providing useful clues for identification of irregular gait patterns or gait-related health issues. Most flexible sensors for gait monitoring focus on contact forces in the normal direction, being limited to detect forces in the tangential direction. Herein we have developed a porous elastomer with a cavity array (PECA) to measure 3D contact forces for gait analysis. The sensor consists of two fabric electrodes and a dielectric layer of porous Ecoflex elastomer containing a 5 × 5 cavity array, forming four parallel-plate capacitor units in a soft construction. Therefore, a 3D force in any arbitrary direction generates four unique capacitive electrical signals. Importantly, the PECA includes a well-designed combination of micrometer-scale pores and millimeter-sized cavities, dramatically improving the detection sensitivity and linear elasticity range. We have demonstrated high sensitivities of 0.41 N−1 and 0.23 N−1 in the normal and tangential directions, respectively. The flexible PECA-based sensors have been tested to sensitively distinguish various standing postures and different stride lengths for gait analysis, promising reliable translation into areas such as healthcare monitoring, sports training, and rehabilitation engineering.

Harvesting energy from a soldier's gait using the piezoelectric effect

Abstract There is an increasing dependence on electronic devices in the battlefield, including equipment for communications, positioning and navigation, and combat situation awareness. These devices are usually powered by batteries because they are reliable and have good power density (energy per kilogram). Nevertheless, batteries are heavy and bulky, which reduces agility and increases fatigue of the ground troops. An alternative is to extract energy from renewable sources (like the sun and the wind) or harvest energy from the human body itself (like temperature gradients and walking). This article studies the feasibility of a piezoelectric generator, stimulated by human gait, to power electronic devices on the battlefield. Tests were carried out to measure the energy harvested from several piezoelectric ceramics placed under the sole of a soldier’s boot. Different materials and arrangements were tried to maximize the power, leading to the development of a prototype. The prototype was able to harvest 875 μ J {\rm{\mu }}{\rm{J}} on each step, on average. Walking 1 h, at a pace of 40 steps/min, leads to 2.1 J of energy, enough to supply a 3.3 V device consuming 10 mA for around a minute. These results are interesting for any situation that requires emergency power on the battlefield (e.g., trigger a device, call for rescue, acquire localization).

Human Gait phases recognition based on multi-source data fusion and BILSTM attention neural network

A human gait recognition algorithm with deep learning based on multi-source data fusion is proposed to assist exoskeleton realizing complex human-exoskeleton cooperative motion. A lightweight gait acquisition device simultaneously acquires three different types of sensor signals, i.e., thigh surface electromyography (sEMG), ground reaction force (GRF) of human feet and two joints motion information. The sample data is obtained by many multi-scene gait experiments involving stand still, walk up/down stairs, and walk up/down slope, etc. The proposed algorithm recognizes multiple gait phases (27 classes) in different motion patterns by using short-time gait data, which has two typical advantages: (1) Based on multi-source sensor distributed in human body, this wearable device is constructed for ease of use to address several Subjects (different weights and heights) with low cost and light weight. (2) The critical features of gait data are identified by Bi-directional Long Short-Term Memory (BILSTM) attention neural network with higher recognition accuracy than other state-of-art recognition methods, especially in arbitrary gait switching durations.

Microchannel pressure sensor for continuous and real-time wearable gait monitoring

A highly sensitive and multi-functional pressure sensor capable of continuous pressure readings is greatly needed, particularly for precise gait pattern analysis. Here, we fabricate a sensitive and reliable pressure sensor by employing eutectic gallium indium (EGaIn) liquid metal as the sensing material and EcoFlex 00-30 silicone as the substrate, via a low-cost process. The device architecture features a microchannel, creating two independent sensing devices, and the mechanical properties of the substrate and sensing material contribute to high stretchability and flexibility, resulting in a sensitivity of 66.07 MPa−1 and a low measurement resolution of 0.056 kPa. The sensor detects applied pressure accurately and can distinguish pressure distribution across a wide area. We demonstrate high efficiency for monitoring human walking gait at various speeds when a single sensor is attached to the foot, and can differentiate between walking postures. This device has strong potential for clinical and rehabilitation applications in gait analysis.

Recent Advances in Self-Powered Wearable Flexible Sensors for Human Gaits Analysis.

The rapid progress of flexible electronics has met the growing need for detecting human movement information in exoskeleton auxiliary equipment. This study provides a review of recent advancements in the design and fabrication of flexible electronics used for human motion detection. Firstly, a comprehensive introduction is provided on various self-powered wearable flexible sensors employed in detecting human movement information. Subsequently, the algorithms utilized to provide feedback on human movement are presented, followed by a thorough discussion of their methods and effectiveness. Finally, the review concludes with perspectives on the current challenges and opportunities in implementing self-powered wearable flexible sensors in exoskeleton technology.

Uncertainty-aware ensemble model for stride length estimation in gait analysis

Deep neural network (DNN) models have become highly effective tools for function estimation in regression tasks, with applications in various domains, including human gait stride length estimation. Several studies have developed DNN models that use gait cycle data from wearable devices equipped with inertial measurement units to accurately predict stride lengths within a cycle. However, many of these deep learning approaches do not quantify predictive uncertainty and fail to consider individual gait characteristics. To address these limitations, we introduced an ensemble model based on a heteroscedastic neural network that quantifies the uncertainty in stride length predictions. Additionally, we proposed a novel stride training strategy that uses the average stride instead of individual strides to optimize the training process and improve model efficiency. Our extensive performance evaluations demonstrate the robustness and adaptability of our model, accurately predicting both the uncertainty of individual stride lengths and the specific stride lengths for each gait cycle. Our study represents a significant advancement in stride length estimation, addressing the challenges of uncertainty quantification and capturing the unique aspects of human gait. The proposed model has considerable potential for practical applications in gait analysis and related fields.

Quantifying Human Gait Symmetry During Blindfolded Treadmill Walking.

Bilateral gait symmetry is an essential requirement for normal walking since asymmetric gait patterns increase the risk of falls and injuries. While human gait control heavily relies on the contribution of sensory inputs, the role of sensory systems in producing symmetric gait has remained unclear. This study evaluated the influence of vision as a dominant sensory system on symmetric gait production. Ten healthy adults performed treadmill walking with and without vision. Twenty-two gait parameters including ground reaction forces, joint range of motion, and other spatial-temporal gait variables were evaluated to quantify gait symmetry and compared between both visual conditions. Visual block caused increased asymmetry in most parameters of ground reaction force, however mainly in the vertical direction. When vision was blocked, symmetry of the ankle and knee joint range of motion decreased, but this change did not occur in the hip joint. Stance and swing time symmetry decreased during no-vision walking while no significant difference was found for step length symmetry between the two conditions. This study provides a comprehensive analysis to reveal how the visual system influences bilateral gait symmetry and highlights the important role of vision in gait control. This approach could be applied to investigate how vision alters gait symmetry in patients with disorders to help better understand the role of vision in pathological gaits.

A gait phase recognition method for obstacle crossing based on multi-sensor fusion

The analysis of human motion patterns and gait phase detection holds significant importance for both human motion analysis and precise control of exoskeleton devices. Presently, research on gait during obstacle crossing primarily focuses on the medical rehabilitation domain, with limited studies concerning gait phase analysis during obstacle crossing. This study conducts a detailed analysis of gait data during obstacle crossing and proposes a CNN-PCA-LSTM algorithm that fuses multi-sensor data to accurately identify gait phases when crossing obstacles in the horizontal direction. A wearable multi-sensor data acquisition system was designed, utilizing flexible capacitive pressure sensors to collect pressure data from the soles of both feet and IMUs to gather foot motion data. Kinematic simulation analyses of human obstacle-crossing motions were performed using Anybody software to determine various gait phases, validating the efficacy of the simulation model. Subsequently, one-dimensional and two-dimensional convolutional neural networks were separately employed to extract features from sole pressure data and foot motion data. Principal Component Analysis (PCA) was utilized to reduce the dimensionality of these feature datasets, which were then inputted into LSTM networks. Finally, the Softmax function was employed for the classification and recognition of gait phases when crossing obstacles in the horizontal direction. The experimental results indicate that employing the CNN-PCA-LSTM algorithm integrating multiple sensor data achieves a recognition accuracy of 97.91 % for identifying gait phases during horizontal obstacle crossing.

An Enhanced Human Gait Recognition System using UALNN Classifier

Human gait recognition is a biometric identification method that uses a person’s gait patterns to identify them. Gait Recognition (GR) is the steps to follow in recognizing walking style of an individual. It identifies a person as of a longer distance with higher precision owing to its unique characteristics; thus, it is mostly utilized for tracking purposes. In computer vision software, specifically, to track the same individual across multiple scenarios, the individual recognition across numerous cameras is a significant task. However, owing to the position of caught image or video, human identification by means of GR could be limited. Therefore, for person re-identification, a novel GR methodology has been proposed here. Five phases were undergone by the proposed methodology. Initially, from an openly accessible dataset, the input video is collected, which is then transmuted into a number of frames. To eliminate the noise from the frames, the Mean Modified Filter (MMF) is utilized after frame conversion. The Gaussian Taxicab Mixture Model (GTMM) is employed to get rid of the background from the frames. After that, Similarity Histogram Silhouette Segmentation (SHSS) model is utilized to segment the humans’ silhouette as of the background removed frames; thus, generating the energy image. The features are extracted from this energy image. The Uniform Alex Neural Network classifier (UALNN) uses these features to identify the human gait. Improved recognition performance is attained from the experiential outcomes. The overall recognition outcomes obtained concluded that the proposed methodology is highly promising.

Enhanced Euler–Lagrange Formulation for Analyzing Human Gait With Moving Base Reference

Abstract Euler–Lagrange's formulation is known for its systematic and simplified approach to deriving dynamics of complex systems. In order to apply the existing formulation to human gait dynamics, the base reference frame must be assumed as an inertial reference frame. Conventionally, the ankle joints or the hip joints are regarded as base reference frames during the stance and swing phases of human walking. As these joints are non-inertial in nature during actual locomotion, this assumption could result in inaccurate calculation of lower-limb joint torques and forces. Therefore, in this paper, an existing Euler–Lagrange-based formulation originally developed for fixed-base robotic manipulators is considered and modified to accommodate the movement of the base reference frame with respect to an inertial frame of reference defined outside the human body. The applicability of the modified formulation is studied, implemented, and validated using three standard and publicly available gait datasets covering the phases of walking and running. The joint torques obtained using the proposed dynamic model are compared with reference torques by calculating the mean absolute error values and visually through Bland–Altman plots. The obtained joint torque values and plots indicate a close agreement with published torques, thereby validating the accuracy of the proposed dynamic model. The robust formulation implementation makes it a valuable resource for researchers in this field, offering a reliable framework for gait analysis and the design of lower-limb prosthetics or exoskeletons.

Unobtrusive measurement of gait parameters using seismographs: An observational study

Analyzing irregularities in walking patterns helps detect human locomotion abnormalities that can signal health changes. Traditional observation-based assessments have limitations due to subjective biases and capture only a single time point. Ambient and wearable sensor technologies allow continuous and objective locomotion monitoring but face challenges due to the need for specialized expertise and user compliance. This work proposes a seismograph-based algorithm for quantifying human gait, incorporating a step extraction algorithm derived from mathematical morphologies, with the goal of achieving the accuracy of clinical reference systems. To evaluate our method, we compared the gait parameters of 50 healthy participants, as recorded by seismographs, and those obtained from reference systems (a pressure-sensitive walkway and a camera system). Participants performed four walking tests, including traversing a walkway and completing the timed up-and-go (TUG) test. In our findings, we observed linear relationships with strong positive correlations (R2 > 0.9) and tight 95% confidence intervals for all gait parameters (step time, cycle time, ambulation time, and cadence). We demonstrated that clinical gait parameters and TUG mobility test timings can be accurately derived from seismographic signals, with our method exhibiting no significant differences from established clinical reference systems.

A dynamic foot model for predictive simulations of human gait reveals causal relations between foot structure and whole-body mechanics.

The unique structure of the human foot is seen as a crucial adaptation for bipedalism. The foot's arched shape enables stiffening the foot to withstand high loads when pushing off, without compromising foot flexibility. Experimental studies demonstrated that manipulating foot stiffness has considerable effects on gait. In clinical practice, altered foot structure is associated with pathological gait. Yet, experimentally manipulating individual foot properties (e.g. arch height or tendon and ligament stiffness) is hard and therefore our understanding of how foot structure influences gait mechanics is still limited. Predictive simulations are a powerful tool to explore causal relationships between musculoskeletal properties and whole-body gait. However, musculoskeletal models used in three-dimensional predictive simulations assume a rigid foot arch, limiting their use for studying how foot structure influences three-dimensional gait mechanics. Here, we developed a four-segment foot model with a longitudinal arch for use in predictive simulations. We identified three properties of the ankle-foot complex that are important to capture ankle and knee kinematics, soleus activation, and ankle power of healthy adults: (1) compliant Achilles tendon, (2) stiff heel pad, (3) the ability to stiffen the foot. The latter requires sufficient arch height and contributions of plantar fascia, and intrinsic and extrinsic foot muscles. A reduced ability to stiffen the foot results in walking patterns with reduced push-off power. Simulations based on our model also captured the effects of walking with anaesthetised intrinsic foot muscles or an insole limiting arch compression. The ability to reproduce these different experiments indicates that our foot model captures the main mechanical properties of the foot. The presented four-segment foot model is a potentially powerful tool to study the relationship between foot properties and gait mechanics and energetics in health and disease.

Lateralized modulation of cortical beta power during human gait is related to arm swing

Human gait is a complex behavior requiring dynamic control of upper and lower extremities that is accompanied by cortical activity in multiple brain areas. We investigated the contribution of beta (15-30Hz) and gamma (30-50Hz) band electroencephalography (EEG) activity during specific phases of the gait cycle, comparing treadmill walking with and without arm swing. Modulations of spectral power in the beta band during early double support and swing phases source-localized to the sensorimotor cortex ipsilateral, but not contralateral, to the leading leg. The lateralization disappeared in the condition with constrained arms, together with an increase of activity in bilateral supplementary motor areas. By contrast, gamma band modulations that localized to the presumed leg area of sensorimotor cortex around the heel-strike events were unaffected by arm movement. Our findings demonstrate that arm swing is accompanied by considerable cortical activation that should not be neglected in gait-related neuroimaging studies.

A Novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication.

The need for non-interactive human recognition systems to ensure safe isolation between users and biometric equipment has been exposed by the COVID-19 pandemic. This study introduces a novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication (MSDCS-PHGA). The proposed MSDCS-PHGA involves segmenting, preprocessing, and resizing silhouette images into three scales. Gait features are extracted from these multi-scale images using custom convolutional layers and fused to form an integrated feature set. This multi-scaled deep convolutional approach demonstrates its efficacy in gait recognition by significantly enhancing accuracy. The proposed convolutional neural network (CNN) architecture is assessed using three benchmark datasets: CASIA, OU-ISIR, and OU-MVLP. Moreover, the proposed model is evaluated against other pre-trained models using key performance metrics such as precision, accuracy, sensitivity, specificity, and training time. The results indicate that the proposed deep CNN model outperforms existing models focused on human gait. Notably, it achieves an accuracy of approximately 99.9% for both the CASIA and OU-ISIR datasets and 99.8% for the OU-MVLP dataset while maintaining a minimal training time of around 3 min.