Identification of Gait Motion Patterns Using Wearable Inertial Sensor Network

A comparison of machine learning models' accuracy in predicting lower-limb joints' kinematics, kinetics, and muscle forces from wearable sensors

A combination of wearable sensors' data and Machine Learning (ML) techniques has been used in many studies to predict specific joint angles and moments. The aim of this study was to compare the performance of four different non-linear regression ML models to estimate lower-limb joints' kinematics, kinetics, and muscle forces using Inertial Measurement Units (IMUs) and electromyographys' (EMGs) data. Seventeen healthy volunteers (9F, 28 ± 5 years) were asked to walk over-ground for a minimum of 16 trials. For each trial, marker trajectories and three force-plates data were recorded to calculate pelvis, hip, knee, and ankle kinematics and kinetics, and muscle forces (the targets), as well as 7 IMUs and 16 EMGs. The features from sensors' data were extracted using the Tsfresh python package and fed into 4 ML models; Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine, and Multivariate Adaptive Regression Spline for targets' prediction. The RF and CNN models outperformed the other ML models by providing lower prediction errors in all intended targets with a lower computational cost. This study suggested that a combination of wearable sensors' data with an RF or a CNN model is a promising tool to overcome the limitations of traditional optical motion capture for 3D gait analysis.

Extraction of Lumbar Spine Motion Using a 3-IMU Wearable Cluster

Spine movement is a daily activity that can indicate health status changes, including low back pain (LBP) problems. Repetitious and continuous movement on the spine and incorrect postures during daily functional activities may lead to the potential development and persistence of LBP problems. Therefore, monitoring of posture and movement is essential when designing LBP interventions. Typically, LBP diagnosis is facilitated by monitoring upper body posture and movement impairments, particularly during functional activities using body motion sensors. This study presents a fully wireless multi-sensor cluster system to monitor spine movements. The study suggests an attempt to develop a new method to monitor the lumbopelvic movements of interest selectively. In addition, the research employs a custom-designed robotic lumbar spine simulator to generate the ideal lumbopelvic posture and movements for reference sensor data. The mechanical motion templates provide an automated sensor pattern recognition mechanism for diagnosing the LBP.

Inertial Sensor Estimation of Initial and Terminal Contact during In-Field Running

Given the popularity of running-based sports and the rapid development of Micro-electromechanical systems (MEMS), portable wireless sensors can provide in-field monitoring and analysis of running gait parameters during exercise. This paper proposed an intelligent analysis system from wireless micro–Inertial Measurement Unit (IMU) data to estimate contact time (CT) and flight time (FT) during running based on gyroscope and accelerometer sensors in a single location (ankle). Furthermore, a pre-processing system that detected the running period was introduced to analyse and enhance CT and FT detection accuracy and reduce noise. Results showed pre-processing successfully detected the designated running periods to remove noise of non-running periods. Furthermore, accelerometer and gyroscope algorithms showed good consistency within 95% confidence interval, and average absolute error of 31.53 ms and 24.77 ms, respectively. In turn, the combined system obtained a consistency of 84–100% agreement within tolerance values of 50 ms and 30 ms, respectively. Interestingly, both accuracy and consistency showed a decreasing trend as speed increased (36% at high-speed fore-foot strike). Successful CT and FT detection and output validation with consistency checking algorithms make in-field measurement of running gait possible using ankle-worn IMU sensors. Accordingly, accurate IMU-based gait analysis from gyroscope and accelerometer information can inform future research on in-field gait analysis.

A Novel Walking Activity Recognition Model for Rotation Time Series Collected by a Wearable Sensor in a Free-Living Environment

Solutions to assess walking deficiencies are widespread and largely used in healthcare. Wearable sensors are particularly appealing, as they offer the possibility to monitor gait in everyday life, outside a facility in which the context of evaluation biases the measure. While some wearable sensors are powerful enough to integrate complex walking activity recognition models, non-invasive lightweight sensors do not always have the computing or memory capacity to run them. In this paper, we propose a walking activity recognition model that offers a viable solution to this problem for any wearable sensors that measure rotational motion of body parts. Specifically, the model was trained and tuned using data collected by a motion sensor in the form of a unit quaternion time series recording the hip rotation over time. This time series was then transformed into a real-valued time series of geodesic distances between consecutive quaternions. Moving average and moving standard deviation versions of this time series were fed to standard machine learning classification algorithms. To compare the different models, we used metrics to assess classification performance (precision and accuracy) while maintaining the detection prevalence at the level of the prevalence of walking activities in the data, as well as metrics to assess change point detection capability and computation time. Our results suggest that the walking activity recognition model with a decision tree classifier yields the best compromise in terms of precision and computation time. The sensor that was used had purposely low computing and memory capacity so that reported performances can be thought of as the lower bounds of what can be achieved. Walking activity recognition is performed online, i.e., on-the-fly, which further extends the range of applicability of our model to sensors with very low memory capacity.

Gait phase detection based on inertial measurement unit and force-sensitive resistors embedded in a shoe

This study proposes a system to detect the phases of gait. It consists of an intelligent shoe equipped with an inertial measurement unit (IMU) and force-sensitive resistors (FSRs), and it uses a compound method to recognize gait. The continuous wavelet transform is applied according to accelerations obtained via the IMU to identify heel strike and toe-off events. These events are used to calculate the pressure threshold and proportional factor via the Lopez-Meyer (LM) method by using minimal leave-one-out for training and validation. The LM method can identify the entire sub-phase of the stance of the gait based on ground contact forces measured by using the FSRs and rules of gait event detection. The proposed system was tested on five healthy volunteers who used the intelligent shoe. The results show that it can detect all sub-phases of the gait with an overall accuracy (96%) higher than the LM method. The proportional factor was adaptable to variable body weights, and the reported average errors of competing systems in the literature significantly exceeded the average variation of the proposed system for all phases of gait. The range of errors in the swing phase and sub-phases of stance was also acceptable for application purposes. When the size of the subject's foot was close to that of the intelligent shoe, the error between normative data and phases of gait identified by the detection system was minimal. Furthermore, the proposed system detected abnormalities in the gait circle, and thus, it can be used to monitor the walking activity and measure the motor recovery.

Can Ensemble Deep Learning Identify People by Their Gait Using Data Collected from Multi-Modal Sensors in Their Insole?

Gait is a characteristic that has been utilized for identifying individuals. As human gait information is now able to be captured by several types of devices, many studies have proposed biometric identification methods using gait information. As research continues, the performance of this technology in terms of identification accuracy has been improved by gathering information from multi-modal sensors. However, in past studies, gait information was collected using ancillary devices while the identification accuracy was not high enough for biometric identification. In this study, we propose a deep learning-based biometric model to identify people by their gait information collected through a wearable device, namely an insole. The identification accuracy of the proposed model when utilizing multi-modal sensing is over 99%.