A Multi-Modal Gait Database of Natural Everyday-Walk in an Urban Environment

A kinematic dataset of locomotion with gait and sit-to-stand movements of young adults

Kinematic data is a valuable source of movement information that provides insights into the health status, mental state, and motor skills of individuals. Additionally, kinematic data can serve as biometric data, enabling the identification of personal characteristics such as height, weight, and sex. In CeTI-Locomotion, four types of walking tasks and the 5 times sit-to-stand test (5RSTST) were recorded from 50 young adults wearing motion capture (mocap) suits equipped with Inertia-Measurement-Units (IMU). Our dataset is unique in that it allows the study of both intra- and inter-participant variability with high quality kinematic motion data for different motion tasks. Along with the raw kinematic data, we provide the source code for phase segmentation and the processed data, which has been segmented into a total of 4672 individual motion repetitions. To validate the data, we conducted visual inspection as well as machine-learning based identity and action recognition tests, achieving 97% and 84% accuracy, respectively. The data can serve as a normative reference of gait and sit-to-stand movements in healthy young adults and as training data for biometric recognition.

A Novel Gait Event Detection Algorithm Using a Thigh-Worn Inertial Measurement Unit and Joint Angle Information

This paper describes the development and evaluation of a novel, threshold-based gait event detection algorithm utilizing only one thigh inertial measurement unit (IMU) and unilateral, sagittal plane hip and knee joint angles. The algorithm was designed to detect heel strike (HS) and toe off (TO) gait events, with the eventual goal of detection in a real-time exoskeletal control system. The data used in the development and evaluation of the algorithm were obtained from two gait databases, each containing synchronized IMU and ground reaction force (GRF) data. All database subjects were healthy individuals walking in either a level-ground, urban environment or a treadmill lab environment. Inertial measurements used were three-dimensional thigh accelerations and three-dimensional thigh angular velocities. Parameters for the TO algorithm were identified on a per-subject basis. The GRF data were utilized to validate the algorithm's timing accuracy and quantify the fidelity of the algorithm, measured by the F1-Score. Across all participants, the algorithm reported a mean timing error of -41±20 ms with an F1-Score of 0.988 for HS. For TO, the algorithm reported a mean timing error of -1.4±21 ms with an F1-Score of 0.991. The results of this evaluation suggest that this algorithm is a promising solution to inertial based gait event detection; however, further refinement and real-time evaluation are required for use in exoskeletal control.

Inertial measurement unit sensor-based gait analysis in adults and older adults: A cross-sectional study

BACKGROUND

Gait assessment has been used in a wide range of clinical applications, and gait velocity is also a leading predictor of disease and physical functional aspects in older adults.

RESEARCH QUESTION

The study aim to examine the changes in IMU-based gait parameters according to age in healthy adults aged 50 and older, to analyze differences between aging patients.

METHODS

A total of 296 healthy adults (65.32 ± 6.74 yrs; 83.10 % female) were recruited. Gait assessment was performed using an IMU sensor-based gait analysis system, and 3D motion information of hip and knee joints was obtained using magnetic sensors. The basic characteristics of the study sample were stratified by age category, and the baseline characteristics between the groups were compared using analysis of variance (ANOVA). Pearson's correlation analysis was used to analyze the relationship between age as the dependent variable and several measures of gait parameters and joint angles as independent variables.

RESULTS

The results of this study found that there were significant differences in gait velocity and both terminal double support in the three groups according to age, and statistically significant differences in the three groups in hip joint angle and knee joints angle. In addition, it was found that the gait velocity and knee/hip joint angle changed with age, and the gait velocity and knee/hip joint angle were also different in the elderly and adult groups.

CONCLUSIONS

We found changes in gait parameters and joint angles according to age in healthy adults and older adults and confirmed the difference in gait velocity and joint angles between adults and older adults.

NONAN GaitPrint: An IMU gait database of healthy young adults

An ongoing thrust of research focused on human gait pertains to identifying individuals based on gait patterns. However, no existing gait database supports modeling efforts to assess gait patterns unique to individuals. Hence, we introduce the Nonlinear Analysis Core (NONAN) GaitPrint database containing whole body kinematics and foot placement during self-paced overground walking on a 200-meter looping indoor track. Noraxon Ultium MotionTM inertial measurement unit (IMU) sensors sampled the motion of 35 healthy young adults (19-35 years old; 18 men and 17 women; mean ± 1 s.d. age: 24.6 ± 2.7 years; height: 1.73 ± 0.78 m; body mass: 72.44 ± 15.04 kg) over 18 4-min trials across two days. Continuous variables include acceleration, velocity, position, and the acceleration, velocity, position, orientation, and rotational velocity of each corresponding body segment, and the angle of each respective joint. The discrete variables include an exhaustive set of gait parameters derived from the spatiotemporal dynamics of foot placement. We technically validate our data using continuous relative phase, Lyapunov exponent, and Hurst exponent-nonlinear metrics quantifying different aspects of healthy human gait.

Human Gait Activity Recognition Using Multimodal Sensors

Human activity recognition is an application of machine learning with the aim of identifying activities from the gathered activity raw data acquired by different sensors. In medicine, human gait is commonly analyzed by doctors to detect abnormalities and determine possible treatments for the patient. Monitoring the patient's activity is paramount in evaluating the treatment's evolution. This type of classification is still not enough precise, which may lead to unfavorable reactions and responses. A novel methodology that reduces the complexity of extracting features from multimodal sensors is proposed to improve human activity classification based on accelerometer data. A sliding window technique is used to demarcate the first dominant spectral amplitude, decreasing dimensionality and improving feature extraction. In this work, we compared several state-of-art machine learning classifiers evaluated on the HuGaDB dataset and validated on our dataset. Several configurations to reduce features and training time were analyzed using multimodal sensors: all-axis spectrum, single-axis spectrum, and sensor reduction.

Challenges and advances in the use of wearable sensors for lower extremity biomechanics

The use of wearable sensors for the collection of lower extremity biomechanical data is increasing in popularity, in part due to the ease of collecting data and the ability to capture movement outside of traditional biomechanics laboratories. Consequently, an increasing number of researchers are facing the challenges that come with utilizing the data captured by wearable sensors. These challenges include identifying/calculating meaningful measures from unfamiliar data types (measures of acceleration and angular velocity instead of positions and joint angles), defining sensor-to-segment alignments for calculating traditional biomechanics metrics, using reduced sensor sets and machine learning to predict unmeasured signals, making decisions about when and how to make algorithms freely available, and developing or replicating methods to perform basic processing tasks such as recognizing activities of interest or identifying gait events. In this perspective article, we present our own approaches to common challenges in lower extremity biomechanics research using wearable sensors and share our perspectives on approaching several of these challenges. We present these perspectives with examples that come mostly from gait research, but many of the concepts also apply to other contexts where researchers may use wearable sensors. Our goal is to introduce common challenges to new users of wearable sensors, and to promote dialogue amongst experienced users towards best practices.

Age and walking conditions differently affect domains of gait

INTRODUCTION

Analysing gait in controlled conditions that resemble daily life walking could overcome the limitations associated with gait analysis in uncontrolled real-world conditions. Such analyses could potentially aid the identification of a walking condition that magnifies age-differences in gait. Therefore, the aim of the current study was to determine the effects of age and walking conditions on gait performance.

METHODS

Trunk accelerations of young (n = 27, age: 21.6) and older adults (n = 26, age: 68.9) were recorded for 3 min in four conditions: walking up and down a university hallway on a track of 10 m; walking on a specified path, including turns, in a university hallway; walking outside on a specified path on a pavement including turns; and walking on a treadmill. Factor analysis was used to reduce 27 computed gait measures to five independent gait domains. A multivariate analysis of variance was used to examine the effects of age and walking condition on these gait domains.

RESULTS

Factor analysis yielded 5 gait domains: variability, pace, stability, time & frequency, complexity, explaining 64% of the variance in 27 gait outcomes. Walking conditions affected all gait domains (p < 0.01) but age only affected the time & frequency domain (p < 0.05). Age and walking conditions differently affected the domains variability, stability, time & frequency. The largest age-differences occurred mainly during straight walking in a hallway (variability: 31% higher in older adults), or during treadmill walking (stability: 224% higher, time&frequency: 120% lower in older adults).

CONCLUSION

Walking conditions affect all domains of gait independent of age. Treadmill walking and walking on a straight path in a hallway, were the most constrained walking conditions in terms of limited possibilities to adjust step characteristics. The age by condition interaction suggests that for the gait domains variability, stability, and time & frequency, the most constrained walking conditions seem to magnify the age-differences in gait.