Real-time Gait Event Detection Research Articles

Detecting Toe-Off and Initial Contact in Real-Time With Self-Adapting Thresholds.

This research introduces an adaptive control algorithm designed to determine gait phase in real-time using an inertial measurement unit (IMU) affixed to the shank. Focusing on detecting specific gait events, primarily initial contact (IC) and toe-off (TO), the algorithm utilizes dynamic thresholds and ratios that facilitate accurate event determination adaptively across a range of walking speeds. Built-in safety checks further ensure precision and minimize false detections. We validated the algorithm with eight participants walking at varying speeds. The algorithm demonstrated promising results in detecting IC and TO events with mean lead of 8.95 ms and 4.42 ms and detection success rate of 100% and 99.72%, respectively. These results are consistent with benchmarks from established algorithms (Hanlon and Anderson, 2009, "Real-Time Gait Event Detection Using Wearable Sensors," Gait Posture, 30(4), pp. 523-527; Maqbool et al., 2017, "A Real-Time Gait Event Detection for Lower Limb Prosthesis Control and Evaluation," IEEE Trans. Neural Syst. Rehabil. Eng.: Publ. IEEE Eng. Med. Biol. Soc., 25(9), pp. 1500-1509). Moreover, the algorithm's self-adaptive nature ensures it can be used in scenarios of varying movement, offering a promising solution for real-time gait phase detection.

Robust and adaptive terrain classification and gait event detection system

Real-time gait event detection (GED) system can be utilized for gait analysis and tracking fitness activities. GED for various types of terrains (e.g., stair-walk, uneven surfaces, etc.) is still an open research problem. This study presents an inertial sensor-based approach for real-time GED system that works for diverse terrains in an uncontrolled environment. The GED system classifies three types of terrains, i.e., flat-walk, stair-ascend and stair-descend, with an average classification accuracy of 99%. It also accurately detects various gait events, including, toe-strike, heel-rise, toe-off, and heel-strike. It is computationally efficient, implemented on a low-cost microcontroller, works in real-time and can be used in portable rehabilitation devices for use in dynamic environments.

Real-Time Gait Event Detection with Adaptive Frequency Oscillators From a Single Head-Mounted IMU

Accurate real-time gait event detection is the basis for the development of new gait rehabilitation techniques, especially when utilizing robotics or virtual reality (VR). The recent emergence of affordable wearable technologies, especially inertial measurement units (IMUs), has brought forth various new methods and algorithms for gait analysis. In this paper, we highlight some advantages of using adaptive frequency oscillators (AFOs) over traditional gait event detection algorithms, implemented a real-time AFO-based algorithm that estimates the gait phase from a single head-mounted IMU, and validated our method on a group of healthy subjects. Gait event detection was accurate at two different walking speeds. The method was reliable for symmetric, but not asymmetric gait patterns. Our method could prove especially useful in VR applications since a head-mounted IMU is already an integral part of commercial VR products.

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.

Real-Time Gait Event Detection for a Lower Extremity Exoskeleton Robot by Infrared Distance Sensors

Gait event detection is a crucial part in the motion control and performance evaluation of exoskeleton robots. To detect the whole gait events conveniently and effectively, a wearable system based on infrared distance sensors is proposed. The heel and toe clearances were used for the first time for the online detection of all six gait events in one gait cycle. Smart shoes integrated with three infrared distance sensors were designed to obtain stable distance signals, which were then converted into effective foot posture information. Moreover, an online detection algorithm was proposed using local search windows and fixed thresholds, resulting in a minimal time delay and a small computational burden. By comparing the system with the motion capture system at different walking speeds, the average detection error of gait events is within 34ms, and the average detection rate of the system is 99.62%. When applied to a lower extremity exoskeleton robot, the system successfully detects all gait events of the human-robot synchronous walk. The results show that the system has good real-time performance and high detection rate. This study provides a convenient and reliable detection method for gait research of human body and exoskeleton robots.

Foot angular kinematics measured with inertial measurement units: A reliable criterion for real-time gait event detection

Accurate and reliable real-time detection of gait events using inertial measurement units (IMUs) is crucial for (1) developing clinically meaningful gait parameters to differentiate normal and impaired gait or (2) creating patient-tailored gait rehabilitation strategies or control of prosthetic devices using feedback from gait phases. However, most previous studies focused only on algorithms with high temporal accuracy and neglected the importance of (1) high reliability, i.e., detecting only and all true gait events, and (2) real-time implementation. Thus, in this study, we presented a novel approach for initial contact (IC) and terminal contact (TC) detection in real-time based on the measurement of the foot orientation. Unlike foot/shank angular velocity and acceleration, foot orientation provides physiologically meaningful kinematic features corresponding to our observational recognition of IC and TC, regardless of the walking modality. We conducted an experimental study to validate our algorithm, including seven participants performing four walking/running activities. By analyzing 5,555 ICs/TCs recorded during the tests, only our algorithm achieved a sensitivity and precision of 100%. Our obtained temporal accuracy (mean ± standard deviation of errors ranging from 0 ± 3 to 6 ± 5 time samples; sampling frequency: 100 Hz) was better than or comparable to those reported in the literature. Our algorithm’s performance does not depend on thresholds and gait speed/modality, and it can be used for feedback-based therapeutic gait training or real-time control of assistive or prosthetic technologies. Nevertheless, its performance for pathological gait must be validated in the future. Finally, we shared the codes and sample data on https://www.ncbl.ualberta.ca/codes.

Knee Exoskeleton Assistive Torque Control Based on Real-Time Gait Event Detection

In this paper, an assistive torque control strategy is proposed for the control of a bionic knee exoskeleton based on real-time gait event detection. Real-time gait event detection is executed with an inertial measurement unit based on an onboard trained model. Two models are trained based on the collected data from the knee exoskeleton at normal walking speed under zero torque and assistive torque control modes, respectively. We conduct two experiments: 1) real-time detection experiments under zero torque control at different speeds and 2) real-time detection and assistive torque control experiments based on real-time detection results at different speeds. Five able-bodied subjects participated in the experiments. The recognition accuracy and assistive torque performances based on real-time detection are evaluated. The experimental results show that all the critical gait events are detected rightly and the delay of gait event detection does not lead to damage to the overall system of knee exoskeleton. In addition, in real-time detection and assistive torque control experiments, parameters of the controller are refreshed for the current cycle based on the previous gait cycle, which is reasonable according to the detection result. The tracking performance of the torque could meet the requirement. This paper provides a feasible and applicable method for knee exoskeleton control based on real-time gait event detection.

Automatic real-time gait event detection in children using deep neural networks.

Annotation of foot-contact and foot-off events is the initial step in post-processing for most quantitative gait analysis workflows. If clean force plate strikes are present, the events can be automatically detected. Otherwise, annotation of gait events is performed manually, since reliable automatic tools are not available. Automatic annotation methods have been proposed for normal gait, but are usually based on heuristics of the coordinates and velocities of motion capture markers placed on the feet. These heuristics do not generalize to pathological gait due to greater variability in kinematics and anatomy of patients, as well as the presence of assistive devices. In this paper, we use a data-driven approach to predict foot-contact and foot-off events from kinematic and marker time series in children with normal and pathological gait. Through analysis of 9092 gait cycle measurements we build a predictive model using Long Short-Term Memory (LSTM) artificial neural networks. The best-performing model identifies foot-contact and foot-off events with an average error of 10 and 13 milliseconds respectively, outperforming popular heuristic-based approaches. We conclude that the accuracy of our approach is sufficient for most clinical and research applications in the pediatric population. Moreover, the LSTM architecture enables real-time predictions, enabling applications for real-time control of active assistive devices, orthoses, or prostheses. We provide the model, usage examples, and the training code in an open-source package.

Change in the walking speed induced by sound intervention using real-time gait event detection

In recent years, people who lack exercise have been increasing. However, it is reported that a lack of exercise leads to chronic diseases. Therefore, if not having a habit of exercising, getting rid of the lack of exercise is hopeful by increasing the exercise intensity of daily behavior. As one of the fundamental daily behavior, walking is considered. It is desired to promote this exercise strength at walking in everyday life by natural intervention. This study focused on the change in walking speed induced by the sound intervention using real-time gait event detection. Experiments were conducted on three healthy males. The following methods were employed for the sound interventions: generating a beep sound in constant tempo (Constant Tempo) and generating a sound in adapted tempo based on the initial contact (Adapted Tempo). Among two interventions, the significant increase in walking speed by entrainment was observed in the latter method which generated the beep sound synchronously with the gait event by detecting the initial contact.

Real-time gait event detection in a real-world environment using a laser-ranging sensor and gyroscope fusion method

Objective: Wearable gait event detection (GED) techniques have great potential for clinical applications by aiding the rehabilitation of individuals in their daily living environment. Unlike previous wearable GED techniques, which have been proposed for offline detection or laboratory settings, we aimed to develop a real-time GED system adapted for utilization in the daily living environment. Approach: This study presents a novel GED system in which foot clearance and sagittal angular velocity were incorporated to realize real-time GED in a real-world environment. The accuracy and robustness of the proposed system were validated in a real-world scenario that consisted of complex ground surfaces, i.e. varying inclinations. Forty-three subjects (23–83 years) were included in this study, and a total of 8866 gait cycles were recorded for analysis. Main results: The proposed system demonstrated consistently high performance in detecting toe off (TO) and heel strike (HS) events in indoor and outdoor walking data which was supported by high performance scores. The detection accuracy of the walking data reached 2.59 ± 13.26 ms (indoor) and 3.31 ± 14.78 ms (outdoor) for TO events, 3.36 ± 15.92 ms (indoor) and 3.77 ± 16.99 ms (outdoor) for HS events. The proposed system showed better performance in detection precision than state-of-the-art real-time GED methods. Significance: The proposed system will benefit the development of long-term analysis and intervention techniques for use in clinics and daily living environments.

Real-Time Gait Event Detection Based on Kinematic Data Coupled to a Biomechanical Model.

Real-time detection of multiple stance events, more specifically initial contact (IC), foot flat (FF), heel off (HO), and toe off (TO), could greatly benefit neurorobotic (NR) and neuroprosthetic (NP) control. Three real-time threshold-based algorithms have been developed, detecting the aforementioned events based on kinematic data in combination with a biomechanical model. Data from seven subjects walking at three speeds on an instrumented treadmill were used to validate the presented algorithms, accumulating to a total of 558 steps. The reference for the gait events was obtained using marker and force plate data. All algorithms had excellent precision and no false positives were observed. Timing delays of the presented algorithms were similar to current state-of-the-art algorithms for the detection of IC and TO, whereas smaller delays were achieved for the detection of FF. Our results indicate that, based on their high precision and low delays, these algorithms can be used for the control of an NR/NP, with the exception of the HO event. Kinematic data is used in most NR/NP control schemes and is thus available at no additional cost, resulting in a minimal computational burden. The presented methods can also be applied for screening pathological gait or gait analysis in general in/outside of the laboratory.

A Real-Time Gait Event Detection for Lower Limb Prosthesis Control and Evaluation

Lower extremity amputees suffer from mobility limitations which will result in a degradation of their quality of life. Wearable sensors are frequently used to assess spatio-temporal, kinematic and kinetic parameters providing the means to establish an interactive control of the amputee-prosthesis-environment system. Gait events and the gait phase detection of an amputee's locomotion are vital for controlling lower limb prosthetic devices. The paper presents an approach to real-time gait event detection for lower limb amputees using a wireless gyroscope attached to the shank when performing level ground and ramp activities. The results were validated using both healthy and amputee subjects and showed that the time differences in identifying Initial Contact (IC) and Toe Off (TO) events were larger in a transfemoral amputee when compared to the control subjects and a transtibial amputee (TTA). Overall, the time difference latency lies within a range of ±50 ms while the detection rate was 100% for all activities. Based on the validated results, the IC and TO events can be accurately detected using the proposed system in both control subjects and amputees when performing activities of daily living and can also be utilized in the clinical setup for rehabilitation and assessing the performance of lower limb prosthesis users.

Real-time gait event detection for lower limb amputees using a single wearable sensor.

This paper presents a rule-based real-time gait event/phase detection system (R-GEDS) using a shank mounted inertial measurement unit (IMU) for lower limb amputees during the level ground walking. Development of the algorithm is based on the shank angular velocity in the sagittal plane and linear acceleration signal in the shank longitudinal direction. System performance was evaluated with four control subjects (CS) and one transfemoral amputee (TFA) and the results were validated with four FlexiForce footswitches (FSW). The results showed a data latency for initial contact (IC) and toe off (TO) within a range of ± 40 ms for both CS and TFA. A delay of about 3.7 ± 62 ms for a foot-flat start (FFS) and an early detection of -9.4 ± 66 ms for heel-off (HO) was found for CS. Prosthetic side showed an early detection of -105 ± 95 ms for FFS whereas intact side showed a delay of 141 ±73 ms for HO. The difference in the kinematics of the TFA and CS is one of the potential reasons for high variations in the time difference. Overall, detection accuracy was 99.78% for all the events in both groups. Based on the validated results, the proposed system can be used to accurately detect the temporal gait events in real-time that leads to the detection of gait phase system and therefore, can be utilized in gait analysis applications and the control of lower limb prostheses.

Real-time gait event detection for transfemoral amputees during ramp ascending and descending.

Events and phases detection of the human gait are vital for controlling prosthesis, orthosis and functional electrical stimulation (FES) systems. Wearable sensors are inexpensive, portable and have fast processing capability. They are frequently used to assess spatio-temporal, kinematic and kinetic parameters of the human gait which in turn provide more details about the human voluntary control and ampute-eprosthesis interaction. This paper presents a reliable real-time gait event detection algorithm based on simple heuristics approach, applicable to signals from tri-axial gyroscope for lower limb amputees during ramp ascending and descending. Experimental validation is done by comparing the results of gyroscope signal with footswitches. For healthy subjects, the mean difference between events detected by gyroscope and footswitches is 14 ms and 10.5 ms for initial contact (IC) whereas for toe off (TO) it is -5 ms and -25 ms for ramp up and down respectively. For transfemoral amputee, the error is slightly higher either due to the placement of footswitches underneath the foot or the lack of proper knee flexion and ankle plantarflexion/dorsiflexion during ramp up and down. Finally, repeatability tests showed promising results.

A robust real-time gait event detection using wireless gyroscope and its application on normal and altered gaits

Gait events detection allows clinicians and biomechanics researchers to determine timing of gait events, to estimate duration of stance phase and swing phase and to segment gait data. It also aids biomedical engineers to improve the design of orthoses and FES (functional electrical stimulation) systems. In recent years, researchers have resorted to using gyroscopes to determine heel-strike (HS) and toe-off (TO) events in gait cycles. However, these methods are subjected to significant delays when implemented in real-time gait monitoring devices, orthoses, and FES systems. Therefore, the work presented in this paper proposes a method that addresses these delays, to ensure real-time gait event detection. The proposed algorithm combines the use of heuristics and zero-crossing method to identify HS and TO. Experiments involving: (1) normal walking; (2) walking with knee brace; and (3) walking with ankle brace for overground walking and treadmill walking were designed to verify and validate the identified HS and TO. The performance of the proposed method was compared against the established gait detection algorithms. It was observed that the proposed method produced detection rate that was comparable to earlier reported methods and recorded reduced time delays, at an average of 100 ms.

Quasi real-time gait event detection using shank-attached gyroscopes

This article describes an ambulatory gait event detection method for long-term monitoring of walking. Aminian et al. [2] have developed an automatic gait event detection algorithm based on shank-attached gyroscope signals. However, this algorithm has a drawback in that it is post-processed. We propose a modified algorithm which detects foot initial and end contact timings using the same concept as in [2], but in quasi real-time. The utilization of the knowledge on gait sequence and peak angular acceleration realizes the quasi real-time detection. Furthermore, to be practical, the algorithm has been developed to ensure the robustness of detection (i.e., without missing the gait events in various speed conditions). Validation of the algorithm using footswitches shows that the algorithm detected the end contacts earlier (-8 ms) and the initial contacts later (19 ms) than the footswitch-based method.

Real-time gait event detection for normal subjects from lower trunk accelerations

In this paper we report on a novel algorithm for the real-time detection and timing of initial (IC) and final contact (FC) gait events. We process the vertical and antero-posterior accelerations registered at the lower trunk (L3 vertebra). The algorithm is based on a set of heuristic rules extracted from a set of 1719 steps. An independent experiment was conducted to compare the results of our algorithms with those obtained from a Digimax force platform. The results show small deviations from times of occurrence of events recorded from the platform (13 ± 35 ms for IC and 9 ± 54 ms for FC). Results for the FC timing are especially relevant in this field, as no previous work has addressed its temporal location through the processing of lower trunk accelerations. The delay in the real-time detection of the IC is 117 ± 39 ms and 34 ± 72 ms for the FC, improving previously reported results for real-time detection of events from lower trunk accelerations.

Real-time gait event detection using wearable sensors

Real-time gait event detection is a requirement for functional electrical stimulation and gait biofeedback. This gait event detection should ideally be achieved using an ambulatory system of durable, lightweight, low-cost sensors. Previous research has reported issues with durability in footswitch systems. Therefore, this study describes the development and assessment of novel detection algorithms using footswitch and accelerometer sensors on 12 healthy individuals. Subjects were equipped with one force sensitive resistor on the heel, one accelerometer at the foot, and one accelerometer at the knee. Subjects performed 10, 8-m walking trials in each of three conditions: normal, slow, and altered (reduced knee ROM) walking. Data from a subset of four subjects were used to develop prediction algorithms for initial contact (IC). Subsequently, these algorithms were tested on the remaining eight subjects against standard forceplate IC data (threshold of 5 N on a rising edge). The footswitch force threshold algorithm was most accurate for IC detection (mean absolute error of 2.4 ± 2.1 ms) and was significantly more accurate ( p < 0.001) than the optimal accelerometer algorithm (mean absolute error of 9.5 ± 9.0 ms). The optimal accelerometer algorithm used data from both accelerometers, with IC determined from the second derivative of foot fore-aft acceleration. The error results for footswitch and accelerometer algorithms are lower (∼60%) than in previous research on ambulatory real-time gait event detection systems. Currently, footswitch systems must be recommended over accelerometer systems for accurate detection of IC, however, further research into accelerometer algorithms is merited due to its advantages as a durable, low-cost sensor.

Real-time gait event detection using wearable sensors

Real-time gait event detection using wearable sensors

Real-time gait event detection for paraplegic FES walking.

A real-time method for the detection of gait events that occur during the electrically stimulated locomotion of paraplegic subjects is described. It consists of a two-level algorithm for the processing of sensor signals and the determination of gait event times. Sensor signals and information about the progression of the stimulator though its pre-specified stimulation "pattern" are processed by a machine intelligence (fuzzy logic) algorithm to determine an initial estimate of the patient's current phase of gait. This is then reviewed and modified by a second algorithm that removes spurious gait estimates, and determines gait event times. These gait event times are known to the system within approximately one-half of a gait cycle. The resulting gait event detection system was successfully evaluated on three subjects. Detection accuracy is not adversely affected by day-to-day gait variability. This work resolved technical and practical issues that previously limited the real time application of these methods. In particular, cosmetically acceptable insole force transducers were used. This gait event detector is designed for use in a real time controller for the automatic adjustment of the intensity and timing of stimulation while the subject is walking using functional electrical stimulation (FES).