Inertial Sensor-Based Gait Recognition: A Review

Classification of inertial sensor-based gait patterns of orthopaedic conditions using machine learning: A pilot study

Elderly patients often have more than one disease that affects walking behavior. An objective tool to identify which disease is the main cause of functional limitations may aid clinical decision making. Therefore, we investigated whether gait patterns could be used to identify degenerative diseases using machine learning. Data were extracted from a clinical database that included sagittal joint angles and spatiotemporal parameters measured using seven inertial sensors, and anthropometric data of patients with unilateral knee or hip osteoarthritis, lumbar or cervical spinal stenosis, and healthy controls. Various classification models were explored using the MATLAB Classification Learner app, and the optimizable Support Vector Machine was chosen as the best performing model. The accuracy of discrimination between healthy and pathologic gait was 82.3%, indicating that it is possible to distinguish pathological from healthy gait. The accuracy of discrimination between the different degenerative diseases was 51.4%, indicating the similarities in gait patterns between diseases need to be further explored. Overall, the differences between pathologic and healthy gait are distinct enough to classify using a classical machine learning model; however, routinely recorded gait characteristics and anthropometric data are not sufficient for successful discrimination of the degenerative diseases.

Kinematic Analysis of Human Gait in Healthy Young Adults Using IMU Sensors: Exploring Relevant Machine Learning Features for Clinical Applications

BACKGROUND

Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the treatment or prevention of gait disorders. The aim of the present study was to identify the key features of normal human gait using inertial unit (IMU) recordings in a walking test.

METHODS

Gait analysis was conducted on 32 healthy participants (age range 19-29 years) at speeds of 2 km/h and 4 km/h using a treadmill. Dynamic data were obtained using a microcontroller (Arduino Nano 33 BLE Sense Rev2) with IMU sensors (BMI270). The collected data were processed and analyzed using a custom script (MATLAB 2022b), including the labeling of the four relevant gait phases and events (Stance, Toe-Off, Swing, and Heel Strike), computation of statistical features (64 features), and application of machine learning techniques for classification (8 classifiers).

RESULTS

Spider plot analysis revealed significant differences in the four events created by the most relevant statistical features. Among the different classifiers tested, the Support Vector Machine (SVM) model using a Cubic kernel achieved an accuracy rate of 92.4% when differentiating between gait events using the computed statistical features.

CONCLUSIONS

This study identifies the optimal features of acceleration and gyroscope data during normal gait. The findings suggest potential applications for injury prevention and performance optimization in individuals engaged in activities involving normal gait. The creation of spider plots is proposed to obtain a personalised fingerprint of each patient's gait fingerprint that could be used as a diagnostic tool. A deviation from a normal gait pattern can be used to identify human gait disorders. Moving forward, this information has potential for use in clinical applications in the diagnosis of gait-related disorders and developing novel orthoses and prosthetics to prevent falls and ankle sprains.

A global bibliometric and visualized analysis of gait analysis and artificial intelligence research from 1992 to 2022

Gait is an important basic function of human beings and an integral part of life. Many mental and physical abnormalities can cause noticeable differences in a person's gait. Abnormal gait can lead to serious consequences such as falls, limited mobility and reduced life satisfaction. Gait analysis, which includes joint kinematics, kinetics, and dynamic Electromyography (EMG) data, is now recognized as a clinically useful tool that can provide both quantifiable and qualitative information on performance to aid in treatment planning and evaluate its outcome. With the assistance of new artificial intelligence (AI) technology, the traditional medical environment has undergone great changes. AI has the potential to reshape medicine, making gait analysis more accurate, efficient and accessible. In this study, we analyzed basic information about gait analysis and AI articles that met inclusion criteria in the WoS Core Collection database from 1992-2022, and the VosViewer software was used for web visualization and keyword analysis. Through bibliometric and visual analysis, this article systematically introduces the research status of gait analysis and AI. We introduce the application of artificial intelligence in clinical gait analysis, which affects the identification and management of gait abnormalities found in various diseases. Machine learning (ML) and artificial neural networks (ANNs) are the most often utilized AI methods in gait analysis. By comparing the predictive capability of different AI algorithms in published studies, we evaluate their potential for gait analysis in different situations. Furthermore, the current challenges and future directions of gait analysis and AI research are discussed, which will also provide valuable reference information for investors in this field.

Validity and reliability of the DANU sports system for walking and running gait assessment

Objective. Gait assessments have traditionally been analysed in laboratory settings, but this may not reflect natural gait. Wearable technology may offer an alternative due to its versatility. The purpose of the study was to establish the validity and reliability of temporal gait outcomes calculated by the DANU sports system, against a 3D motion capture reference system.Approach. Forty-one healthy adults (26 M, 15 F, age 36.4 ± 11.8 years) completed a series of overground walking and jogging trials and 60 s treadmill walking and running trials at various speeds (8-14 km hr-1), participants returned for a second testing session to repeat the same testing.Main results. For validity, 1406 steps and 613 trials during overground and across all treadmill trials were analysed respectively. Temporal outcomes generated by the DANU sports system included ground contact time, swing time and stride time all demonstrated excellent agreement compared to the laboratory reference (intraclass correlation coefficient (ICC) > 0.900), aside from ground contact time during overground jogging which had good agreement (ICC = 0.778). For reliability, 666 overground and 511 treadmill trials across all speeds were examined. Test re-test agreement was excellent for all outcomes across treadmill trials (ICC > 0.900), except for swing time during treadmill walking which had good agreement (ICC = 0.886). Overground trials demonstrated moderate to good test re-test agreement (ICC = 0.672-0.750), which may be due to inherent variability of self-selected (rather than treadmill set) pacing between sessions.Significance. Overall, this study showed that temporal gait outcomes from the DANU Sports System had good to excellent validity and moderate to excellent reliability in healthy adults compared to an established laboratory reference.

Adaptive Control Method for Gait Detection and Classification Devices with Inertial Measurement Unit

Cueing and feedback training can be effective in maintaining or improving gait in individuals with Parkinson's disease. We previously designed a rehabilitation assist device that can detect and classify a user's gait at only the swing phase of the gait cycle, for the ease of data processing. In this study, we analyzed the impact of various factors in a gait detection algorithm on the gait detection and classification rate (GDCR). We collected acceleration and angular velocity data from 25 participants (1 male and 24 females with an average age of 62 ± 6 years) using our device and analyzed the data using statistical methods. Based on these results, we developed an adaptive GDCR control algorithm using several equations and functions. We tested the algorithm under various virtual exercise scenarios using two control methods, based on acceleration and angular velocity, and found that the acceleration threshold was more effective in controlling the GDCR (average Spearman correlation -0.9996, p < 0.001) than the gyroscopic threshold. Our adaptive control algorithm was more effective in maintaining the target GDCR than the other algorithms (p < 0.001) with an average error of 0.10, while other tested methods showed average errors of 0.16 and 0.28. This algorithm has good scalability and can be adapted for future gait detection and classification applications.

Smartphone Authentication System Using Personal Gaits and a Deep Learning Model

In a society centered on hyper-connectivity, information sharing is crucial, but it must be ensured that each piece of information is viewed only by legitimate users; for this purpose, the medium that connects information and users must be able to identify illegal users. In this paper, we propose a smartphone authentication system based on human gait, breaking away from the traditional authentication method of using the smartphone as the medium. After learning human gait features with a convolutional neural network deep learning model, it is mounted on a smartphone to determine whether the user is a legitimate user by walking for 1.8 s while carrying the smartphone. The accuracy, precision, recall, and F1-score were measured as evaluation indicators of the proposed model. These measures all achieved an average of at least 90%. The analysis results show that the proposed system has high reliability. Therefore, this study demonstrates the possibility of using human gait as a new user authentication method. In addition, compared to our previous studies, the gait data collection time for user authentication of the proposed model was reduced from 7 to 1.8 s. This reduction signifies an approximately four-fold performance enhancement through the implementation of filtering techniques and confirms that gait data collected over a short period of time can be used for user authentication.

Comparison of inertial records during anticipatory postural adjustments obtained with devices of different masses

Background

Step initiation involves anticipatory postural adjustments (APAs) that can be measured using inertial measurement units (IMUs) such as accelerometers. However, previous research has shown heterogeneity in terms of the population studied, sensors used, and methods employed. Validity against gold standard measurements was only found in some studies, and the weight of the sensors varied from 10 to 110 g. The weight of the device is a crucial factor to consider when assessing APAs, as APAs exhibit significantly lower magnitudes and are characterized by discrete oscillations in acceleration paths.

Objective

This study aims to validate the performance of a commercially available ultra-light sensor weighing only 5.6 g compared to a 168-g smartphone for measuring APAs during step initiation, using a video capture kinematics system as the gold standard. The hypothesis is that APA oscillation measurements obtained with the ultra-light sensor will exhibit greater similarity to those acquired using video capture than those obtained using a smartphone.

Materials and Methods

Twenty subjects were evaluated using a commercial lightweight MetaMotionC accelerometer, a smartphone and a system of cameras-kinematics with a reflective marker on lumbar vertebrae. The subjects initiated 10 trials of gait after a randomized command from the experimenter and APA variables were extracted: APAonset, APAamp, PEAKtime. A repeated measures ANOVA with post-hoc test analyzed the effect of device on APA measurements. Bland-Altman plots were used to evaluate agreement between MetaMotionC, smartphone, and kinematics measurements. Pearson's correlation coefficients were used to assess device correlation. Percentage error was calculated for each inertial sensor against kinematics. A paired Student's t-test compared th devices percentage error.

Results

The study found no significant difference in temporal variables APAonset and PEAKtime between MetaMotionC, smartphone, and kinematic instruments, but a significant difference for variable APAamp, with MetaMotionC yielding smaller measurements. The MetaMotionC had a near-perfect correlation with kinematic data in APAonset and APAamp, while the smartphone had a very large correlation in APAamp and a near-perfect correlation in APAonset and PEAKtime. Bland-Altman plots showed non-significant bias between smartphone and kinematics for all variables, while there was a significant bias between MetaMotionC and kinematics for APAamp. The percentage of relative error was not significantly different between the smartphone and MetaMotionC.

Conclusions

The temporal analysis can be assessed using ultralight sensors and smartphones, as MetaMotionC and smartphone-based measurements have been found to be valid compared to kinematics. However, caution should be exercised when using ultralight sensors for amplitude measurements, as additional research is necessary to determine their effectiveness in this regard.

Early postoperative step count and walking time have greater impact on lower limb fracture outcomes than load-bearing metrics

INTRODUCTION

Weight-bearing protocols for rehabilitation of lower extremity fractures are the gold standard despite not being data-driven. Additionally, current protocols are focused on the amount of weight placed on the limb, negating other patient rehabilitation behaviors that may contribute to outcomes. Wearable sensors can provide insight into multiple aspects of patient behavior through longitudinal monitoring. This study aimed to understand the relationship between patient behavior and rehabilitation outcomes using wearable sensors to identify the metrics of patient rehabilitation behavior that have a positive effect on 1-year rehabilitation outcomes.

METHODS

Prospective observational study on 42 closed ankle and tibial fracture patients. Rehabilitation behavior was monitored continuously between 2 and 6 weeks post-operative using a gait monitoring insole. Metrics describing patient rehabilitation behavior, including step count, walking time, cadence, and body weight per step, were compared between patient groups of excellent and average rehabilitation outcomes, as defined by the 1-year Patient Reported Outcome Measure Physical Function t-score (PROMIS PF). A Fuzzy Inference System (FIS) was used to rank metrics based on their impact on patient outcomes. Additionally, correlation coefficients were calculated between patient characteristics and principal components of the behavior metrics.

RESULTS

Twenty-two patients had complete insole data sets, and 17 of which had 1-year PROMIS PF scores (33.7 ± 14.5 years of age, 13 female, 9 in Excellent group, 8 in Average group). Step count had the highest impact ranking (0.817), while body weight per step had a low impact ranking (0.309). No significant correlation coefficients were found between patient or injury characteristics and behavior principal components. General patient rehabilitation behavior was described through cadence (mean of 71.0 steps/min) and step count (logarithmic distribution with only ten days exceeding 5,000 steps/day).

CONCLUSION

Step count and walking time had a greater impact on 1-year outcomes than body weight per step or cadence. The results suggest that increased activity may improve 1-year outcomes for patients with lower extremity fractures. The use of more accessible devices, such as smart watches with step counters combined with patient reported outcome measures may provide more valuable insights into patient rehabilitation behaviors and their effect on rehabilitation outcomes.

Digital manufacturing of personalised footwear with embedded sensors

The strong clinical demand for more accurate and personalized health monitoring technologies has called for the development of additively manufactured wearable devices. While the materials palette for additive manufacturing continues to expand, the integration of materials, designs and digital fabrication methods in a unified workflow remains challenging. In this work, a 3D printing platform is proposed for the integrated fabrication of silicone-based soft wearables with embedded piezoresistive sensors. Silicone-based inks containing cellulose nanocrystals and/or carbon black fillers were thoroughly designed and used for the direct ink writing of a shoe insole demonstrator with encapsulated sensors capable of measuring both normal and shear forces. By fine-tuning the material properties to the expected plantar pressures, the patient-customized shoe insole was fully 3D printed at room temperature to measure in-situ gait forces during physical activity. Moreover, the digitized approach allows for rapid adaptation of the sensor layout to meet specific user needs and thereby fabricate improved insoles in multiple quick iterations. The developed materials and workflow enable a new generation of fully 3D printed soft electronic devices for health monitoring.

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

Nowadays, it becomes of paramount societal importance to support many frail-prone groups in our society (elderly, patients with neurodegenerative diseases, etc.) to remain socially and physically active, maintain their quality of life, and avoid their loss of autonomy. Once older people enter the prefrail stage, they are already likely to experience falls whose consequences may accelerate the deterioration of their quality of life (injuries, fear of falling, reduction of physical activity). In that context, detecting frailty and high risk of fall at an early stage is the first line of defense against the detrimental consequences of fall. The second line of defense would be to develop original protocols to detect future fallers before any fall occur. This paper briefly summarizes the current advancements and perspectives that may arise from the combination of affordable and easy-to-use non-wearable systems (force platforms, 3D tracking motion systems), wearable systems (accelerometers, gyroscopes, inertial measurement units-IMUs) with appropriate machine learning analytics, as well as the efforts to address these challenges.

A New Post-Processing Proposal for Improving Biometric Gait Recognition Using Wearable Devices

In this work, a novel Window Score Fusion post-processing technique for biometric gait recognition is proposed and successfully tested. We show that the use of this technique allows recognition rates to be greatly improved, independently of the configuration for the previous stages of the system. For this, a strict biometric evaluation protocol has been followed, using a biometric database composed of data acquired from 38 subjects by means of a commercial smartwatch in two different sessions. A cross-session test (where training and testing data were acquired in different days) was performed. Following the state of the art, the proposal was tested with different configurations in the acquisition, pre-processing, feature extraction and classification stages, achieving improvements in all of the scenarios; improvements of 100% (0% error) were even reached in some cases. This shows the advantages of including the proposed technique, whatever the system.

Human Gait Activity Recognition Machine Learning Methods

Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject's quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm's robustness was also verified with the successful detection of freezing gait episodes in a Parkinson's disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization.

Adaptive Inertial Sensor-Based Step Length Estimation Model

Pedestrian dead reckoning (PDR) using inertial sensors has paved the way for developing several approaches to step length estimation. In particular, emerging step length estimation models are readily available to be utilized on smartphones, yet they are seldom formulated considering the kinematics of the human body during walking in combination with measured step lengths. We present a new step length estimation model based on the acceleration magnitude and step frequency inputs herein. Spatial positions of anatomical landmarks on the human body during walking, tracked by an optical measurement system, were utilized in the derivation process. We evaluated the performance of the proposed model using our publicly available dataset that includes measurements collected for two types of walking modes, i.e., walking on a treadmill and rectangular-shaped test polygon. The proposed model achieved an overall mean absolute error (MAE) of 5.64 cm on the treadmill and an overall mean walked distance error of 4.55% on the test polygon, outperforming all the models selected for the comparison. The proposed model was also least affected by walking speed and is unaffected by smartphone orientation. Due to its promising results and favorable characteristics, it could present an appealing alternative for step length estimation in PDR-based approaches.

Rules-Based Real-Time Gait Event Detection Algorithm for Lower-Limb Prosthesis Users during Level-Ground and Ramp Walking

Real-time gait event detection (GED) using inertial sensors is important for applications such as remote gait assessments, intelligent assistive devices including microprocessor-based prostheses or exoskeletons, and gait training systems. GED algorithms using acceleration and/or angular velocity signals achieve reasonable performance; however, most are not suited for real-time applications involving clinical populations walking in free-living environments. The aim of this study was to develop and evaluate a real-time rules-based GED algorithm with low latency and high accuracy and sensitivity across different walking states and participant groups. The algorithm was evaluated using gait data collected from seven able-bodied (AB) and seven lower-limb prosthesis user (LLPU) participants for three walking states (level-ground walking (LGW), ramp ascent (RA), ramp descent (RD)). The performance (sensitivity and temporal error) was compared to a validated motion capture system. The overall sensitivity was 98.87% for AB and 97.05% and 93.51% for LLPU intact and prosthetic sides, respectively, across all walking states (LGW, RA, RD). The overall temporal error (in milliseconds) for both FS and FO was 10 (0, 20) for AB and 10 (0, 25) and 10 (0, 20) for the LLPU intact and prosthetic sides, respectively, across all walking states. Finally, the overall error (as a percentage of gait cycle) was 0.96 (0, 1.92) for AB and 0.83 (0, 2.08) and 0.83 (0, 1.66) for the LLPU intact and prosthetic sides, respectively, across all walking states. Compared to other studies and algorithms, the herein-developed algorithm concurrently achieves high sensitivity and low temporal error with near real-time detection of gait in both typical and clinical populations walking over a variety of terrains.

Gait Trajectory Prediction on an Embedded Microcontroller Using Deep Learning

Achieving a normal gait trajectory for an amputee's active prosthesis is challenging due to its kinematic complexity. Accordingly, lower limb gait trajectory kinematics and gait phase segmentation are essential parameters in controlling an active prosthesis. Recently, the most practiced algorithm in gait trajectory generation is the neural network. Deploying such a complex Artificial Neural Network (ANN) algorithm on an embedded system requires performing the calculations on an external computational device; however, this approach lacks mobility and reliability. In this paper, more simple and reliable ANNs are investigated to be deployed on a single low-cost Microcontroller (MC) and hence provide system mobility. Two neural network configurations were studied: Multi-Layered Perceptron (MLP) and Convolutional Neural Network (CNN); the models were trained on shank and foot IMU data. The data were collected from four subjects and tested on a fifth to predict the trajectory of 200 ms ahead. The prediction was made for two cases: with and without providing the current phase of the gait. Then, the models were deployed on a low-cost microcontroller (ESP32). It was found that with fewer data (excluding the current gait phase), CNN achieved a better correlation coefficient of 0.973 when compared to 0.945 for MLP; when including the current phase, both network configurations achieved better correlation coefficients of nearly 0.98. However, when comparing the execution time required for the prediction on the intended MC, MLP was much faster than CNN, with an execution time of 2.4 ms and 142 ms, respectively. In summary, it was found that when training data are scarce, CNN is more efficient within the acceptable execution time, while MLP achieves relative accuracy with low execution time with enough data.

Progress in Data Acquisition of Wearable Sensors

Wearable sensors have demonstrated wide applications from medical treatment, health monitoring to real-time tracking, human-machine interface, smart home, and motion capture because of the capability of in situ and online monitoring. Data acquisition is extremely important for wearable sensors, including modules of probes, signal conditioning, and analog-to-digital conversion. However, signal conditioning, analog-to-digital conversion, and data transmission have received less attention than probes, especially flexible sensing materials, in research on wearable sensors. Here, as a supplement, this paper systematically reviews the recent progress of characteristics, applications, and optimizations of transistor amplifiers and typical filters in signal conditioning, and mainstream analog-to-digital conversion strategies. Moreover, possible research directions on the data acquisition of wearable sensors are discussed at the end of the paper.

Integrating wearables and modelling for monitoring rehabilitation following total knee joint replacement

BACKGROUND AND OBJECTIVE

Wearable inertial devices integrated with modelling and cloud computing have been widely adopted in the sports sector, however, their use in the health and medical field has yet to be fully realised. To date, there have been no reported studies concerning the use of wearables as a surrogate tool to monitor knee joint loading during recovery following a total knee joint replacement. The objective of this study is to firstly evaluate if peak tibial acceleration from wearables during gait is a good surrogate metric for computer modelling predicted functional knee loading; and secondly evaluate if traditional clinical patient related outcomes measures are consistent with wearable predictions.

METHODS

Following ethical approval, four healthy participants were used to establish the relationship between computer modelling predicted knee joint loading and wearable measured tibial acceleration. Following this, ten patients who had total knee joint replacements were then followed during their 6-week rehabilitation. Gait analysis, wearable acceleration, computer models of knee joint loading, and patient related outcomes measures including the Oxford knee score and range of motion were recorded.

RESULTS

A linear correlation (R² of 0.7-0.97) was observed between peak tibial acceleration (from wearables) and musculoskeletal model predicted knee joint loading during gait in healthy participants first. Whilst patient related outcome measures (Oxford knee score and patient range of motion) were observed to improve consistently during rehabilitation, this was not consistent with all patient's tibial acceleration. Only those patients that exhibited increasing peak tibial acceleration over 6-weeks rehabilitation were positively correlated with the Oxford knee score (R² of 0.51 to 0.97). Wearable predicted tibial acceleration revealed three patients with a consistent knee loading, five patients with improving knee loading, and two patients with declining knee loading during recovery. Hence, 20% of patients did not present with satisfactory joint loading following total knee joint replacement and this was not detected with current patient related outcome measures.

CONCLUSIONS

The use of inertial measurement units or wearables in this study provided additional insight into patients who were not exhibiting functional improvements in joint loading, and offers clinicians an 'off-site' early warning metric to identify potential complications during recovery and provide the opportunity for early intervention. This study has important implications for improving patient outcomes, equity, and for those who live in rural regions.

A multi-sensor human gait dataset captured through an optical system and inertial measurement units

Different technologies can acquire data for gait analysis, such as optical systems and inertial measurement units (IMUs). Each technology has its drawbacks and advantages, fitting best to particular applications. The presented multi-sensor human gait dataset comprises synchronized inertial and optical motion data from 25 participants free of lower-limb injuries, aged between 18 and 47 years. A smartphone and a custom micro-controlled device with an IMU were attached to one of the participant’s legs to capture accelerometer and gyroscope data, and 42 reflexive markers were taped over the whole body to record three-dimensional trajectories. The trajectories and inertial measurements were simultaneously recorded and synchronized. Participants were instructed to walk on a straight-level walkway at their normal pace. Ten trials for each participant were recorded and pre-processed in each of two sessions, performed on different days. This dataset supports the comparison of gait parameters and properties of inertial and optical capture systems, whereas allows the study of gait characteristics specific for each system.

Measurement(s)	G Force • Spatial Orientation
Technology Type(s)	Accelerometer • Optical Instrument

A case study on the value of in-socket force measurements in gait monitoring of lower-limb prosthesis users

Wearable sensors have the potential to drastically improve gait rehabilitation and assessments. This is especially the case for lower limb prosthesis users as small wearables can provide useful information about in-socket conditions. Through a simple case study, we investigated the value of measuring in-socket forces in addition to gait parameters in gauging the effectiveness of a training intervention. The results showed that the additional objective information obtained through in-socket measurements can enhance our understanding of how a particular intervention affects both gait and socket comfort.

A Unified Local–Global Feature Extraction Network for Human Gait Recognition Using Smartphone Sensors

Smartphone-based gait recognition has been considered a unique and promising technique for biometric-based identification. It is integrated with multiple sensors to collect inertial data while a person walks. However, captured data may be affected by several covariate factors due to variations of gait sequences such as holding loads, wearing types, shoe types, etc. Recent gait recognition approaches either work on global or local features, causing failure to handle these covariate-based features. To address these issues, a novel weighted multi-scale CNN (WMsCNN) architecture is designed to extract local to global features for boosting recognition accuracy. Specifically, a weight update sub-network (Ws) is proposed to increase or reduce the weights of features concerning their contribution to the final classification task. Thus, the sensitivity of these features toward the covariate factors decreases using the weight updated technique. Later, these features are fed to a fusion module used to produce global features for the overall classification. Extensive experiments have been conducted on four different benchmark datasets, and the demonstrated results of the proposed model are superior to other state-of-the-art deep learning approaches.

Reliability and generalization of gait biometrics using 3D inertial sensor data and 3D optical system trajectories

Particularities in the individuals’ style of walking have been explored for at least three decades as a biometric trait, empowering the automatic gait recognition field. Whereas gait recognition works usually focus on improving end-to-end performance measures, this work aims at understanding which individuals’ traces are more relevant to improve subjects’ separability. For such, a manifold projection technique and a multi-sensor gait dataset were adopted to investigate the impact of each data source characteristics on this separability. Assessments have shown it is hard to distinguish individuals based only on their walking patterns in a subject-based identification scenario. In this setup, the subjects’ separability is more related to their physical characteristics than their movements related to gait cycles and biomechanical events. However, this study’s results also points to the feasibility of learning identity characteristics from individuals’ walking patterns learned from similarities and differences between subjects in a verification setup. The explorations concluded that periodic components occurring in frequencies between 6 and 10 Hz are more significant for learning these patterns than events and other biomechanical movements related to the gait cycle, as usually explored in the literature.

Tracking of Gymnast's Limb Movement Trajectory Based on MEMS Inertial Sensor

In order to track the limb movement trajectory of gymnasts, a method based on MEMS inertial sensor is proposed. The system mainly collects the acceleration and angular velocity data of 11 positions during gymnastics by constructing sensor network. Based on the two kinds of preprocessed data, the parameters such as sample mean, standard deviation, information entropy, and mean square error are calculated as classification features, the support vector machine (SVM) classification model is established, and the movements of six kinds of gymnastics are effectively recognized. The experimental results show that when the human body is doing gymnastics, the measured three-axis acceleration values are between -0.5 g~2.2 g, -1 g~2.8 g, and -1.8 g~1 g, respectively, and the static error range accounts for only 1.6%~2% of the actual measured data range. Therefore, it is considered that such static error has little effect on the accuracy of data feature extraction and action recognition, which can be ignored. It is proved that MEMS inertial sensor can effectively track the movement trajectory of gymnasts' limbs.

Recent Trends and Practices Toward Assessment and Rehabilitation of Neurodegenerative Disorders: Insights From Human Gait

The study of human movement and biomechanics forms an integral part of various clinical assessments and provides valuable information toward diagnosing neurodegenerative disorders where the motor symptoms predominate. Conventional gait and postural balance analysis techniques like force platforms, motion cameras, etc., are complex, expensive equipment requiring specialist operators, thereby posing a significant challenge toward translation to the clinics. The current manuscript presents an overview and relevant literature summarizing the umbrella of factors associated with neurodegenerative disorder management: from the pathogenesis and motor symptoms of commonly occurring disorders to current alternate practices toward its quantification and mitigation. This article reviews recent advances in technologies and methodologies for managing important neurodegenerative gait and balance disorders, emphasizing assessment and rehabilitation/assistance. The review predominantly focuses on the application of inertial sensors toward various facets of gait analysis, including event detection, spatiotemporal gait parameter measurement, estimation of joint kinematics, and postural balance analysis. In addition, the use of other sensing principles such as foot-force interaction measurement, electromyography techniques, electrogoniometers, force-myography, ultrasonic, piezoelectric, and microphone sensors has also been explored. The review also examined the commercially available wearable gait analysis systems. Additionally, a summary of recent progress in therapeutic approaches, viz., wearables, virtual reality (VR), and phytochemical compounds, has also been presented, explicitly targeting the neuro-motor and functional impairments associated with these disorders. Efforts toward therapeutic and functional rehabilitation through VR, wearables, and different phytochemical compounds are presented using recent examples of research across the commonly occurring neurodegenerative conditions [viz., Parkinson's disease (PD), Alzheimer's disease (AD), multiple sclerosis, Huntington's disease (HD), and amyotrophic lateral sclerosis (ALS)]. Studies exploring the potential role of Phyto compounds in mitigating commonly associated neurodegenerative pathologies such as mitochondrial dysfunction, α-synuclein accumulation, imbalance of free radicals, etc., are also discussed in breadth. Parameters such as joint angles, plantar pressure, and muscle force can be measured using portable and wearable sensors like accelerometers, gyroscopes, footswitches, force sensors, etc. Kinetic foot insoles and inertial measurement tools are widely explored for studying kinematic and kinetic parameters associated with gait. With advanced correlation algorithms and extensive RCTs, such measurement techniques can be an effective clinical and home-based monitoring and rehabilitation tool for neuro-impaired gait. As evident from the present literature, although the vast majority of works reported are not clinically and extensively validated to derive a firm conclusion about the effectiveness of such techniques, wearable sensors present a promising impact toward dealing with neurodegenerative motor disorders.

Exploring Artificial Neural Networks Efficiency in Tiny Wearable Devices for Human Activity Recognition

The increasing diffusion of tiny wearable devices and, at the same time, the advent of machine learning techniques that can perform sophisticated inference, represent a valuable opportunity for the development of pervasive computing applications. Moreover, pushing inference on edge devices can in principle improve application responsiveness, reduce energy consumption and mitigate privacy and security issues. However, devices with small size and low-power consumption and factor form, like those dedicated to wearable platforms, pose strict computational, memory, and energy requirements which result in challenging issues to be addressed by designers. The main purpose of this study is to empirically explore this trade-off through the characterization of memory usage, energy consumption, and execution time needed by different types of neural networks (namely multilayer and convolutional neural networks) trained for human activity recognition on board of a typical low-power wearable device.Through extensive experimental results, obtained on a public human activity recognition dataset, we derive Pareto curves that demonstrate the possibility of achieving a 4× reduction in memory usage and a 36× reduction in energy consumption, at fixed accuracy levels, for a multilayer Perceptron network with respect to more sophisticated convolution network models.

Recognizing Solo Jazz Dance Moves Using a Single Leg-Attached Inertial Wearable Device

We present here a method for recognising dance moves in sequences using 3D accelerometer and gyroscope signals, acquired by a single wearable device, attached to the dancer's leg. The recognition entails dance tempo estimation, temporal scaling, a wearable device orientation-invariant coordinate system transformation, and, finally, sliding correlation-based template matching. The recognition is independent of the orientation of the wearable device and the tempo of dancing, which promotes the usability of the method in a wide range of everyday application scenarios. For experimental validation, we considered the versatile repertoire of solo jazz dance moves. We created a database of 15 authentic solo jazz template moves using the performances of a professional dancer dancing at 120 bpm. We analysed 36 new dance sequences, performed by the professional and five recreational dancers, following six dance tempos, ranging from 120 bpm to 220 bpm with 20 bpm increment steps. The recognition F1 scores, obtained cumulatively for all moves for different tempos, ranged from 0.87 to 0.98. The results indicate that the presented method can be used to recognise repeated dance moves and to assess the dancer's consistency in performance. In addition, the results confirm the potential of using the presented method to recognise imitated dance moves, supporting the learning process.

Shock Response Spectrum Analysis of Fatigued Runners

The purpose of this study was to determine the effect of fatigue on impact shock wave attenuation and assess how human biomechanics relate to shock attenuation during running. In this paper, we propose a new methodology for the analysis of shock events occurring during the proposed experimental procedure. Our approach is based on the Shock Response Spectrum (SRS), which is a frequency-based function that is used to indicate the magnitude of vibration due to a shock or a transient event. Five high level CrossFit athletes who ran at least three times per week and who were free from musculoskeletal injury volunteered to take part in this study. Two Micromachined Microelectromechanical Systems (MEMS) accelerometers (RunScribe®, San Francisco, CA, USA) were used for this experiment. The two RunScribe pods were mounted on top of the foot in the shoelaces. All five athletes performed three maximum intensity runs: the 1st run was performed after a brief warmup with no prior exercise, then the 2nd and the 3rd run were performed in a fatigued state. Prior to the 2nd and the 3rd run, the athletes were asked to perform at maximum intensity for two minutes on an Assault AirBike to tire them. For all five athletes, there was a direct correlation between fatigue and an increase in the aggressiveness of the SRS. We noticed that for all five athletes for the 3rd run the average SRS peaks were significantly higher than for the 1st run and 2nd run (p < 0.01) at the same natural frequency of the athlete. This confirms our hypothesis that fatigue causes a decrease in the shock attenuation capacity of the musculoskeletal system thus potentially involving a higher risk of overuse injury.

Gait metrics analysis utilizing single-point inertial measurement units: a systematic review

BACKGROUND

Wearable sensors, particularly accelerometers alone or combined with gyroscopes and magnetometers in an inertial measurement unit (IMU), are a logical alternative for gait analysis. While issues with intrusive and complex sensor placement limit practicality of multi-point IMU systems, single-point IMUs could potentially maximize patient compliance and allow inconspicuous monitoring in daily-living. Therefore, this review aimed to examine the validity of single-point IMUs for gait metrics analysis and identify studies employing them for clinical applications.

METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses Guidelines (PRISMA) were followed utilizing the following databases: PubMed; MEDLINE; EMBASE and Cochrane. Four databases were systematically searched to obtain relevant journal articles focusing on the measurement of gait metrics using single-point IMU sensors.

RESULTS

A total of 90 articles were selected for inclusion. Critical analysis of studies was conducted, and data collected included: sensor type(s); sensor placement; study aim(s); study conclusion(s); gait metrics and methods; and clinical application. Validation research primarily focuses on lower trunk sensors in healthy cohorts. Clinical applications focus on diagnosis and severity assessment, rehabilitation and intervention efficacy and delineating pathological subjects from healthy controls.

DISCUSSION

This review has demonstrated the validity of single-point IMUs for gait metrics analysis and their ability to assist in clinical scenarios. Further validation for continuous monitoring in daily living scenarios and performance in pathological cohorts is required before commercial and clinical uptake can be expected.

WildGait: Learning Gait Representations from Raw Surveillance Streams

Simple Summary

In this work, we explore self-supervised pretraining for gait recognition. We gather the largest dataset to date of real-world gait sequences automatically annotated through pose tracking (UWG), which offers realistic confounding factors as opposed to current datasets. Results highlight the great performance in scenarios with low amounts of training data, and state-of-the-art accuracy on skeleton-based gait recognition when utilizing all available training data.

Abstract

The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a self-supervised learning framework, WildGait, which consists of pre-training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world surveillance streams to learn useful gait signatures. We collected and compiled the largest pretraining dataset to date of anonymized walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We make the dataset available to the research community. Our results surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data.

Dance Tempo Estimation Using a Single Leg-Attached 3D Accelerometer

We present a methodology that enables dance tempo estimation through the acquisition of 3D accelerometer signals using a single wearable inertial device positioned on the dancer’s leg. Our tempo estimation method is based on enhanced multiple resonators, implemented with comb feedback filters. To validate the methodology, we focus on the versatile solo jazz dance style. Including a variety of dance moves, with different leg activation patterns and rhythmical variations, solo jazz provides for a highly critical validation environment. We consider 15 different solo jazz dance moves, with different leg activation patterns, assembled in a sequence of 5 repetitions of each, giving 65 moves altogether. A professional and a recreational dancer performed this assembly in a controlled environment, following eight dancing tempos, dictated by a metronome, and ranging from 80 bpm to 220 bpm with 20 bpm increment steps. We show that with appropriate enhancements and using single leg signals, the comb filter bank provides for accurate dance tempo estimates for all moves and rhythmical variations considered. Dance tempo estimates for the overall assembles match strongly the dictated tempo—the difference being at most 1 bpm for all measurement instances is within the limits of the established beat onset stability of the used metronome. Results further show that this accuracy is achievable for shorter dancing excerpts, comprising four dance moves, corresponding to one music phrase, and as such enables real-time feedback. By providing for a dancer’s tempo quality and consistency assessment, the presented methodology has the potential of supporting the learning process, classifying individual level of experience, and assessing overall performance. It is extendable to other dance styles and sport motion in general where cyclical patterns occur.

Feature Identification with a Heuristic Algorithm and an Unsupervised Machine Learning Algorithm for Prior Knowledge of Gait Events

The purpose of this study was to compare a heuristic feature identification algorithm with output from the Beta Process Auto Regressive Hidden Markov Model (BP-AR-HMM) utilizing minimally sampled (≤ 100 Hz) human locomotion data for identification of gait events prior to their occurrence. Data were collected from 16 participants (21-64 years) using a single gyroscopic sensor in an inertial measurement unit on the dorsum of the foot, across multiple locomotion modes, including level ground walking and running (across speeds 0.8 m s-1 - 3.0 m s-1), ramps and stairs. Identification of gait events, initial contact (IC) and toe off (TO) with the heuristic algorithm, was 94% across locomotion modes. The features identified prior to initial contact had a lead time of 186.32 ± 86.70 ms, while TO had a lead time of 63.96 ± 46.30 ms. The BP-AR-HMM identified features that indicated an impending IC and TO with 99% accuracy, with a lead time of 59.41 ± 54.41 ms for IC and 90.79 ± 35.51 ms for TO. These approaches are consistent in their identification of gait events and have the potential to be utilized for classification and prediction of locomotion mode.

Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing

Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails, and storing and accessing personal data at any time and from any location. Nowadays, smartphones are used to store a multitude of private and sensitive data including bank account information, personal identifiers, account passwords and credit card information. Many users remain permanently signed in and, as a result, their mobile devices are vulnerable to security and privacy risks through assaults by criminals. Passcodes, PINs, pattern locks, facial verification, and fingerprint scans are all susceptible to various assaults including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To solve these issues, this research introduces a new continuous authentication framework called DeepAuthen, which identifies smartphone users based on their physical activity patterns as measured by the accelerometer, gyroscope, and magnetometer sensors on their smartphone. We conducted a series of tests on user authentication using several deep learning classifiers, including our proposed deep learning network termed DeepConvLSTM on the three benchmark datasets UCI-HAR, WISDM-HARB and HMOG. Results demonstrated that combining various motion sensor data obtained the highest accuracy and energy efficiency ratio (EER) values for binary classification. We also conducted a thorough examination of the continuous authentication outcomes, and the results supported the efficacy of our framework.

Effective detection of abnormal gait patterns in Parkinson's disease patients using kinematics, nonlinear, and stability gait features

BACKGROUND AND OBJECTIVES

Parkinson's disease (PD) is a neurodegenerative disease that produces movement disorders and it is the second most common neurodegenerative disease after Alzheimer's. Among other symptoms, PD affects gait patterns and produces bradykinesia, abnormal changes in posture, and shortened strides. In this study we present a comprehensive analysis of three different feature sets to model those abnormal gait patterns. The proposed approach is evaluated upon three groups of subjects: PD patients, young healthy controls (YHC), and elderly healthy controls (EHC).

METHODS

Three feature sets are created: (1) kinematic measures including those that allow modeling time, distance and velocity of the strides, (2) nonlinear dynamics including different measures extracted from embedded attractors resulting from the time-series of the gait signals, and (3) different stability measures extracted in the time and frequency-domains. Support Vector Machine, Random Forest and XGBoost classifiers are trained to automatically discriminate between PD patients and healthy subjects.

RESULTS

Among the considered feature sets, three individual measures emerge as the ones that yield accurate detection of PD and could potentially be used in clinical practice. Accuracies of up to 87.0% and 90.0% are found for the classification between PD vs. YHC and PD vs. EHC, respectively, considering individual measures.

CONCLUSIONS

This study contributes to a better understanding of abnormal gait patterns observed in PD patients. Particularly the introduced approach shows good results that could be potentially used in clinical practice as a tool to support the diagnosis and follow-up of the patients.

Gait-based Human Identification through Minimum Gait-phases and Sensors

The incredible pace at which the world's elderly population is growing will put severe burdens on current healthcare systems and resources. To alleviate this concern the health care systems must rely on the transformation of eldercare and old homes to use Ambient Assisted Living (AAL). Human identification is one of the most common and critical tasks for condition monitoring, human-machine interaction, and providing assistive services in such environments. Recently, human gait has gained new attention as a biometric for identification to achieve contactless identification from a distance robust to physical appearances. However, an important aspect of gait identification through wearables and image-based systems alike is accurate identification when limited information is available for example, when only a fraction of the whole gait cycle or only a part of the subject's body is visible. In this paper, we present a gait identification technique based on temporal and descriptive statistic parameters of different gait phases as the features and we investigate the performance of using only single gait phases for the identification task using a minimum number of sensors. Gait data were collected from 60 individuals through pelvis and foot sensors. Six different machine learning algorithms were used for identification. It was shown that it is possible to achieve high accuracy of over 95.5% by monitoring a single phase of the whole gait cycle through only a single sensor. It was also shown that the proposed methodology could be used to achieve 100% identification accuracy when the whole gait cycle was monitored through pelvis and foot sensors combined. The ANN was found to be more robust to less number of data features compared to SVM and was concluded as the best machine algorithm for the purpose.

Isolating the Unique and Generic Movement Characteristics of Highly Trained Runners

Human movement patterns were shown to be as unique to individuals as their fingerprints. However, some movement characteristics are more important than other characteristics for machine learning algorithms to distinguish between individuals. Here, we explored the idea that movement patterns contain unique characteristics that differentiate between individuals and generic characteristics that do not differentiate between individuals. Layer-wise relevance propagation was applied to an artificial neural network that was trained to recognize 20 male triathletes based on their respective movement patterns to derive characteristics of high/low importance for human recognition. The similarity between movement patterns that were defined exclusively through characteristics of high/low importance was then evaluated for all participants in a pairwise fashion. We found that movement patterns of triathletes overlapped minimally when they were defined by variables that were very important for a neural network to distinguish between individuals. The movement patterns overlapped substantially when defined through less important characteristics. We concluded that the unique movement characteristics of elite runners were predominantly sagittal plane movements of the spine and lower extremities during mid-stance and mid-swing, while the generic movement characteristics were sagittal plane movements of the spine during early and late stance.

A Low-Cost, Portable, and Wireless In-Shoe System Based on a Flexible Porous Graphene Pressure Sensor

Monitoring gait patterns in daily life will provide a lot of biological information related to human health. At present, common gait pressure analysis systems, such as pressure platforms and in-shoe systems, adopt rigid sensors and are wired and uncomfortable. In this paper, a biomimetic porous graphene–SBR (styrene-butadiene rubber) pressure sensor (PGSPS) with high flexibility, sensitivity (1.05 kPa⁻¹), and a wide measuring range (0–150 kPa) is designed and integrated into an insole system to collect, process, transmit, and display plantar pressure data for gait analysis in real-time via a smartphone. The system consists of 16 PGSPSs that were used to analyze different gait signals, including walking, running, and jumping, to verify its daily application range. After comparing the test results with a high-precision digital multimeter, the system is proven to be more portable and suitable for daily use, and the accuracy of the waveform meets the judgment requirements. The system can play an important role in monitoring the safety of the elderly, which is very helpful in today’s society with an increasingly aging population. Furthermore, an intelligent gait diagnosis algorithm can be added to realize a smart gait monitoring system.

Applying deep neural networks and inertial measurement unit in recognizing irregular walking differences in the real world

Falling injuries pose serious health risks to people of all ages, and knowing the extent of exposure to irregular surfaces will increase the ability to measure fall risk. Current gait analysis methods require overly complicated instrumentation and have not been tested for external factors such as walking surfaces that are encountered in the real-world, thus the results are difficult to extrapolate to real-world situations. Artificial intelligence approaches (in particular deep learning networks of varied architectures) to analyze data collected from wearable sensors were used to identify irregular surface exposure in a real-world setting. Thirty young adults wore six Inertial Measurement Unit (IMU) sensors placed on their body (right wrist, trunks at the L5/S1 level, left and right thigh, left and right shank) while walking over eight different surfaces commonly encountered in the living community as well as occupational settings. Three variations of deep learning models were trained to solve this walking surface recognition problem: 1) convolution neural network (CNN); 2) long short term memory (LSTM) network and 3) LSTM structure with an extra global pooling layer (Global-LSTM) which learns the coordination between different data streams (e.g. different channels of the same sensor as well as different sensors). Results indicated that all three deep learning models can recognize walking surfaces with above 0.90 accuracy, with the Global-LSTM yielding the best performance at 0.92 accuracy. In terms of individual sensors, the right thigh based Global-LSTM model reported the highest accuracy (0.90 accuracy). Results from this study provide further evidence that deep learning and wearable sensors can be utilized to recognize irregular walking surfaces induced motion alteration and applied to prevent falling injuries.

Plantar Pressure Detection System Based on Flexible Hydrogel Sensor Array and WT-RF

This paper presents a hydrogel-based flexible sensor array to detect plantar pressure distribution and recognize the gait patterns to assist those who suffer from gait disorders to rehabilitate better. The traditional pressure detection array is composed of rigid metal sensors, which have poor biocompatibility and expensive manufacturing costs. To solve the above problems, we have designed and fabricated a novel flexible sensor array based on AAM/NaCl (Acrylamide/Sodium chloride) hydrogel and PI (Polyimide) membrane. The proposed array exhibits excellent structural flexibility (209 KPa) and high sensitivity (12.3 mV·N-1), which allows it to be in full contact with the sole of the foot to collect pressure signals accurately. The Wavelet Transform-Random Forest (WT-RF) algorithm is introduced to recognize the gaits based on the plantar pressure signals. Wavelet transform realizes the signal filtering and normalization, and random forest is responsible for the classification of the processed signals. The classification accuracy of the WT-RF algorithm reaches 91.9%, which ensures the precise recognition of gaits.

Technological advancements in the analysis of human motion and posture management through digital devices

Technological development of motion and posture analyses is rapidly progressing, especially in rehabilitation settings and sport biomechanics. Consequently, clear discrimination among different measurement systems is required to diversify their use as needed. This review aims to resume the currently used motion and posture analysis systems, clarify and suggest the appropriate approaches suitable for specific cases or contexts. The currently gold standard systems of motion analysis, widely used in clinical settings, present several limitations related to marker placement or long procedure time. Fully automated and markerless systems are overcoming these drawbacks for conducting biomechanical studies, especially outside laboratories. Similarly, new posture analysis techniques are emerging, often driven by the need for fast and non-invasive methods to obtain high-precision results. These new technologies have also become effective for children or adolescents with non-specific back pain and postural insufficiencies. The evolutions of these methods aim to standardize measurements and provide manageable tools in clinical practice for the early diagnosis of musculoskeletal pathologies and to monitor daily improvements of each patient. Herein, these devices and their uses are described, providing researchers, clinicians, orthopedics, physical therapists, and sports coaches an effective guide to use new technologies in their practice as instruments of diagnosis, therapy, and prevention.

Measuring Spatiotemporal Parameters on Treadmill Walking Using Wearable Inertial System

This study aims to measure and compare spatiotemporal gait parameters in nineteen subjects using a full wearable inertial mocap system Xsens (MVN Awinda, Netherlands) and a photoelectronic system one-meter OptoGaitTM (Microgait, Italy) on a treadmill imposing a walking speed of 5 km/h. A total of eleven steps were considered for each subject constituting a dataset of 209 samples from which spatiotemporal parameters (SPT) were calculated. The step length measurement was determined using two methods. The first one considers the calculation of step length based on the inverted pendulum model, while the second considers an anthropometric approach that correlates the stature with an anthropometric coefficient. Although the absolute agreement and consistency were found for the calculation of the stance phase, cadence and gait cycle, from our study, differences in SPT were found between the two systems. Mean square error (MSE) calculation of their speed (m/s) with respect to the imposed speed on a treadmill reveals a smaller error (MSE = 0.0008) using the OptoGaitTM. Overall, our results indicate that the accurate detection of heel strike and toe-off have an influence on phases and sub-phases for the entire acquisition. Future study in this domain should investigate how to design and integrate better products and algorithms aiming to solve the problematic issues already identified in this study without limiting the user's need and performance in a different environment.

Asymmetric Gait Analysis Using a DTW Algorithm with Combined Gyroscope and Pressure Sensor

Walking is one of the most basic human activities. Various diseases may be caused by abnormal walking, and abnormal walking is mostly caused by disease. There are various characteristics of abnormal walking, but in general, it can be judged as asymmetric walking. Generally, spatiotemporal parameters can be used to determine asymmetric walking. The spatiotemporal parameter has the disadvantage that it does not consider the influence of the diversity of patterns and the walking speed. Therefore, in this paper, we propose a method to analyze asymmetric walking using Dynamic Time Warping (DTW) distance, a time series analysis method. The DTW distance was obtained by combining gyroscope data and pressure data. The experiment was carried out by performing symmetrical walking and asymmetrical walking, and asymmetric walking was performed as a simulation of hemiplegic walking by fixing one ankle using an auxiliary device. The proposed method was compared with the existing asymmetric gait analysis method. As a result of the experiment, a p-value lower than 0.05 was obtained, which proved that there was a statistically significant difference.

User Independent Estimations of Gait Events With Minimal Sensor Data

GOAL

The purpose of this study was to provide an initial examination of the utility of the Beta Process - Auto Regressive - Hidden Markov Model (BP-AR-HMM) for the prior identification of gait events. A secondary objective was to determine whether the output of the model could be used for classification and prediction of locomotion states.

METHODS

In this study we utilized the output of the BP-AR-HMM to develop user-independent identification of gait events and gait classification from an idealized three-dimensional acceleration signal. The input acceleration data were collected from two walking (1.4 and 1.6 ms^-1) and two running (2.6 and 3.0 ms^-1) steady state speeds, and during two dynamic walk to run and run to walk transitions (1.8-2.4 and 2.4-1.8 ms^-1) on an instrumented force treadmill.

RESULTS

The BP-AR-HMM identified 9 unique states. Of these, two states, 4 and 1, were utilized to estimate initial contact and toe off, respectively. The lead time from the first instance of state 4 to initial contact was 0.13 ± 0.02 s. Similarly, the first instance of state 1 occurred 0.14 ± 0.03 s before toe off. Two other states (3 and 7) were examined for possible utilization in a probabilistic model for the prediction of pending locomotion state transitions.

CONCLUSION

The identification of gait events prior to their occurrence by the BP-AR-HMM appears to be an approach that can minimize the quantity of sensor data in an offline approach. Furthermore, there is evidence it could also be used as a basis to build a probabilistic model to estimate locomotion transitions.

Evaluation of Physical Interaction during Walker-Assisted Gait with the AGoRA Walker: Strategies Based on Virtual Mechanical Stiffness

Smart walkers are commonly used as potential gait assistance devices, to provide physical and cognitive assistance within rehabilitation and clinical scenarios. To understand such rehabilitation processes, several biomechanical studies have been conducted to assess human gait with passive and active walkers. Several sessions were conducted with 11 healthy volunteers to assess three interaction strategies based on passive, low and high mechanical stiffness values on the AGoRA Smart Walker. The trials were carried out in a motion analysis laboratory. Kinematic data were also collected from the smart walker sensory interface. The interaction force between users and the device was recorded. The force required under passive and low stiffness modes was 56.66% and 67.48% smaller than the high stiffness mode, respectively. An increase of 17.03% for the hip range of motion, as well as the highest trunk’s inclination, were obtained under the resistive mode, suggesting a compensating motion to exert a higher impulse force on the device. Kinematic and physical interaction data suggested that the high stiffness mode significantly affected the users’ gait pattern. Results suggested that users compensated their kinematics, tilting their trunk and lower limbs to exert higher impulse forces on the device.

Perceptual-motor styles

Even for a stereotyped task, sensorimotor behavior is generally variable due to noise, redundancy, adaptability, learning or plasticity. The sources and significance of different kinds of behavioral variability have attracted considerable attention in recent years. However, the idea that part of this variability depends on unique individual strategies has been explored to a lesser extent. In particular, the notion of style recurs infrequently in the literature on sensorimotor behavior. In general use, style refers to a distinctive manner or custom of behaving oneself or of doing something, especially one that is typical of a person, group of people, place, context, or period. The application of the term to the domain of perceptual and motor phenomenology opens new perspectives on the nature of behavioral variability, perspectives that are complementary to those typically considered in the studies of sensorimotor variability. In particular, the concept of style may help toward the development of personalised physiology and medicine by providing markers of individual behaviour and response to different stimuli or treatments. Here, we cover some potential applications of the concept of perceptual-motor style to different areas of neuroscience, both in the healthy and the diseased. We prefer to be as general as possible in the types of applications we consider, even at the expense of running the risk of encompassing loosely related studies, given the relative novelty of the introduction of the term perceptual-motor style in neurosciences.

Human Posture Detection Method Based on Wearable Devices

The dynamic detection of human motion is important, which is widely applied in the fields of motion state capture and rehabilitation engineering. In this study, based on multimodal information of surface electromyography (sEMG) signals of upper limb and triaxial acceleration and plantar pressure signals of lower limb, the effective virtual driving control and gait recognition methods were proposed. The effective way of wearable human posture detection was also constructed. Firstly, the moving average window and threshold comparison were used to segment the sEMG signals of the upper limb. The standard deviation and singular values of wavelet coefficients were extracted as the features. After the training and classification by optimized support vector machine (SVM) algorithm, the real-time detection and analysis of three virtual driving actions were performed. The average identification accuracy was 90.90%. Secondly, the mean, standard deviation, variance, and wavelet energy spectrum of triaxial acceleration were extracted, and these parameters were combined with plantar pressure as the gait features. The optimized SVM was selected for the gait identification, and the average accuracy was 90.48%. The experimental results showed that, through different combinations of wearable sensors on the upper and lower limbs, the motion posture information could be dynamically detected, which could be used in the design of virtual rehabilitation system and walking auxiliary system.

Understanding LSTM Network Behaviour of IMU-Based Locomotion Mode Recognition for Applications in Prostheses and Wearables

Human Locomotion Mode Recognition (LMR) has the potential to be used as a control mechanism for lower-limb active prostheses. Active prostheses can assist and restore a more natural gait for amputees, but as a medical device it must minimize user risks, such as falls and trips. As such, any control system must have high accuracy and robustness, with a detailed understanding of its internal operation. Long Short-Term Memory (LSTM) machine-learning networks can perform LMR with high accuracy levels. However, the internal behavior during classification is unknown, and they struggle to generalize when presented with novel users. The target problem addressed in this paper is understanding the LSTM classification behavior for LMR. A dataset of six locomotive activities (walking, stopped, stairs and ramps) from 22 non-amputee subjects is collected, capturing both steady-state and transitions between activities in natural environments. Non-amputees are used as a substitute for amputees to provide a larger dataset. The dataset is used to analyze the internal behavior of a reduced complexity LSTM network. This analysis identifies that the model primarily classifies activity type based on data around early stance. Evaluation of generalization for unseen subjects reveals low sensitivity to hyper-parameters and over-fitting to individuals’ gait traits. Investigating the differences between individual subjects showed that gait variations between users primarily occur in early stance, potentially explaining the poor generalization. Adjustment of hyper-parameters alone could not solve this, demonstrating the need for individual personalization of models. The main achievements of the paper are (i) the better understanding of LSTM for LMR, (ii) demonstration of its low sensitivity to learning hyper-parameters when evaluating novel user generalization, and (iii) demonstration of the need for personalization of ML models to achieve acceptable accuracy.

Locomotion in virtual environments predicts cardiovascular responsiveness to subsequent stressful challenges

Individuals differ in their physiological responsiveness to stressful challenges, and stress potentiates the development of many diseases. Heart rate variability (HRV), a measure of cardiac vagal break, is emerging as a strong index of physiological stress vulnerability. Thus, it is important to develop tools that identify predictive markers of individual differences in HRV responsiveness without exposing subjects to high stress. Here, using machine learning approaches, we show the strong predictive power of high-dimensional locomotor responses during novelty exploration to predict HRV responsiveness during stress exposure. Locomotor responses are collected in two ecologically valid virtual reality scenarios inspired by the animal literature and stress is elicited and measured in a third threatening virtual scenario. Our model's predictions generalize to other stressful challenges and outperforms other stress prediction instruments, such as anxiety questionnaires. Our study paves the way for the development of behavioral digital phenotyping tools for early detection of stress-vulnerable individuals.