Brain-computer interface (BCI) is a technology used in various fields to analyze electroencephalography (EEG) signals to recognize an individual"s intention or state and control a computer or machine. However, most of the research on BCI is on motor imagery, and research on active movement is concentrated on upper limb movement. In the case of lower limb movement, most of the research is on the static state or single movements. Therefore, in this research, we developed a deep-learning model for classifying walking behavior(1: walking, 2: upstairs, 3: downstairs) based on EEG signals in a dynamic environment to verify the possibility of classifying EEG signals in a dynamic state. We developed a model that combined a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM). The model obtained an average recognition performance of 82.01%, with an average accuracy of 93.77% for walking, 76.52% for upstairs, and 75.75% for downstairs. It is anticipated that various robotic devices aimed at assisting people with disabilities and the elderly could be designed in the future with multiple features, such as human-robot interaction, object manipulation, and path-planning utilizing BCI for control.
Climbing stairs places a greater load on lower limb joints compared to walking on level ground. Variations in anatomical structures and muscle characteristics between genders suggest potential differences in the distribution of required mechanical work among the three lower limb joints. This study aimed to identify gender disparities in the allocation of mechanical work to lower limb joints during stair climbing. A total of thirty-six adults (equally divided between men and women) participated in the study. Participants ascended stairs equipped with force plates at their comfortable speeds, while motion was captured using nine cameras. Inverse dynamics analysis was employed to calculate the mechanical work performed by each joint during four phases of stance: weight acceptance, pull-up, forward continuation, and push-up. Male participants exhibited significantly higher mechanical work than females at the hip and ankle joints (p < 0.05) from the 1st- 3rd phases and the 2nd phase, respectively. Conversely, female subjects displayed greater knee joint work during the 2nd- 3rd phases (p < 0.05). Notably, a pronounced gender difference was observed during the 2nd pull-up phase, where body mass is lifted by a single leg. These findings suggest that men and women employ distinct strategies in distributing mechanical work across lower limb joints.
In this study, the Inertial Measurement Unit (IMU) signals and clinical evaluation scales for Parkinson"s disease were correlated. The study included 16 patients diagnosed with Parkinson"s disease. Each subject was evaluated based on Korean Mini-Mental State Examination (KMMSE), Unified Parkinson"s Disease Rating Scale (UPDRS) part 3, New Freezing of Gait Questionnaire (NFOGQ) parts 2 & 3, and Hoehn & Yahr Scale (H&Y). All subjects performed the Time Up and Go test by attaching IMU sensors to both ankles and torso. Based on the tilting angle of torso and the time of first step, the freezing and non-freezing windows were determined. Seven IMU features involving the ankle signals were calculated in the specific window. Spearman’s correlation analysis of clinical evaluation scales was performed. As a result, the freezing index and power of locomotion band (0.3-3 Hz) were recommended to determine UPDRS part 3. Also, the intensity of the locomotion band facilitated evaluation of NFOGQ part 3 regardless of freezing of gait.
There are no known studies on the changes in walking ability in patients with transfemoral amputations returning to daily activities after prosthetic gait training. The ability to walk after discharge may vary depending on an individual’s physical, psychological, and social factors. This study compared spatiotemporal variables and lower limb coordination ability at the end of training and one year after the end of training in seven unilateral transfemoral amputees and analyzed the factors affecting walking ability. The study results confirmed that there was no significant difference in spatiotemporal parameters such as walking speed and lower limb coordination ability after one year of training, and walking ability was well maintained after training. Five out of seven (71.4%) participants in this study returned to work, and there was a strong correlation between employment and gait improvement (r = 0.806, p < .05). In conclusion, activities such as social participation, employment, and exercise were very important factors in maintaining and improving an individual’s walking ability. The findings are intended to be used as basic data to provide guidelines for maintaining the health of lower limb amputees.
The understanding of impaired neural control of gait after stroke is important to evaluate mobility impairments focused on improving walking function. Previous studies have shown that the central nervous system may control gait via muscle synergies, which modularly organizes multiple muscles. However, there are insufficient studies to evaluate mobility impairments, using muscle synergy during walking in post-stroke patients. Thus, the purpose of this study was to determine if the variability of muscle synergies during gait reflects impaired motor performance. Electromyography (EMG) signals were collected from five persons with post-stroke hemiparesis and five similarly age healthy persons, as they walked on a treadmill at a comfortable speed. EMG signals were decomposed using non-negative matrix factorization and the variability of muscle synergies was calculated using a synergy stability index (SSI). We also investigated correlation between the SSI and Fugl-Meyer assessment and Berg Balance Scale, which are clinical evaluation indicators. Post-stroke patients were found to have variable muscle synergies. We also observed a positive proportional relation, between SSI and clinical motor impair evaluation indicators. These results could yield a quantitative assessment of gait after stroke, and provide a causal relationship between internal neuromuscular mechanisms and functional performance.
In this study, an insole-type ground reaction force (GRF) measurement system using a load cell was manufactured and configured as a system that can measure joint angle and GRF, when walking in conjunction with a commercialized inertial sensor. The data acquisition device was used to acquire synchronized data, between the inertial measurement unit (IMU) sensor and the load cell insole. A three-dimensional motion analysis system comprising six infrared cameras and two ground reaction forces, was used to check the accuracy of the gait measurement system, comprising an inertial sensor and a load cell insole. The motion and force data were acquired while performing five times six-meter walking test by five young adult male subjects (Age: 26.0±1.8, Height: 171.4±6.8 cm, Weight: 62.2±10.8 kg). It was measured and as a result of comparing the calculated sagittal joint angle with the vertical GRF, the sagittal lower extremity joint angle correlation coefficient (Pearson’s r) was 0.40 to 0.94, and the vertical GRF to be 0.98 to 0.99. It is necessary to upgrade the joint angle calculation algorithm through future research. Additionally, the possibility of clinical application for actual stroke patients will be reviewed.
The current method of gait analysis has several limitations for determining gait stability, such as a complicated preparation process, repeated experimental procedures that are time-consuming, and financial burden of experiments. This study investigated whether gait stability could be analyzed using only the COM-COP (Center of Mass-Center of Pressure) inclination angle connecting COM and COP. COM and COP coordinates were obtained from a motion analysis system for a total of 40 elderly and young subjects. The COM-COP inclination angle that changed in real time during level walking was then analyzed to obtain gait stability on each of sagittal and frontal planes using these coordinates. As a result, the gait symmetry index on the sagittal plane did not show a statistically significant difference between young and elderly subjects (First Step, p = 0.189; Second Step, p = 0.711). On the frontal plane, elderly subjects showed 0.39 degrees (p = 0.058) and 0.5 degree (p = 0.03) larger side-to-side sway angles in the first and second steps than young subjects, respectively. Gait stability can be analyzed using a more simplified experimental method with minimum amount of data in future gait analysis.
The purpose of this study was to suggest the method for automated locomotion modes (Level Walking, Stair Ascent, Stair Descent) detection based on the Radial Basis Function Support Vector Machine (RBF-SVM) for the hip gait assist robot. The universal hip gait assist robot had a limit in detection of the walking intention of users because of the limited sensors’ quantity. Through the offline training, using MATLAB, we trained the collected gait data of users wearing the hip gait assist robot and obtained the parameter of the RBF-SVM model. In the online test, using LabVIEW, we developed the algorithm for the locomotion modes decision of individuals using the optimized parameter of the RBF-SVM. Finally, we executed the gait test for three terrains through the walking environment’s test platform. As a result, the locomotion modes decision rate for three terrains was 98.5%, 99%, and 98% respectively. And the decision delay time of algorithm was 0.03 s, 0.03 s, and 0.06 s respectively.
Citations
Citations to this article as recorded by
A fuzzy convolutional attention-based GRU network for human activity recognition Ghazaleh Khodabandelou, Huiseok Moon, Yacine Amirat, Samer Mohammed Engineering Applications of Artificial Intelligence.2023; 118: 105702. CrossRef
Locomotion Mode Recognition Algorithm Based on Gaussian Mixture Model Using IMU Sensors Dongbin Shin, Seungchan Lee, Seunghoon Hwang Sensors.2021; 21(8): 2785. CrossRef
Patients with complete paralysis that only walk with the assistance of exoskeleton robots because they lost their ability to walk. However, robots do not allow the exoskeleton robot to grasp the current state before walking and change the walking pattern. A "Stability Circle Region" was proposed to determine the current state of the exoskeleton robot. The Stability Circle is an area that can determine the possibility of a fall situation before the next walk using the link parameters of the robot and the current center of gravity of the patients. This study verified the validity of "stability circle" by simulating the change in the center of mass. Simulation results can be used to determine the stability of walking depending on whether the position of the center of mass before the walking is included in the circle area.
Citations
Citations to this article as recorded by
Design of Assistive Wearable System for Walking Seong-Dae Choi, Sang-Hun Lee Journal of the Korean Society of Manufacturing Process Engineers.2019; 18(12): 111. CrossRef
Research of different types of powered exoskeleton have been conducted for various purposes. Recently, the exoskeleton has been used in rehabilitation training for patients with walking problems. For the exoskeletons to appropriately assist the user in gait rehabilitation, it is essential to understand user"s intention. The user"s walking intention includes the temporal aspect of timing of movements and the quantitative aspect of how large the movement is. This study, quantitatively identifies the relationship between arm and leg movements during walking, the user"s quantitative intention for gait, and suggests for a control strategy to assist user"s movement accordingly for a 1DoF hip exoskeleton for hemiplegic gait rehabilitation.
Citations
Citations to this article as recorded by
Measurement, Evaluation, and Control of Active Intelligent Gait Training Systems—Analysis of the Current State of the Art Yi Han, Chenhao Liu, Bin Zhang, Ning Zhang, Shuoyu Wang, Meimei Han, João P. Ferreira, Tao Liu, Xiufeng Zhang Electronics.2022; 11(10): 1633. CrossRef
This study presented a mechanism overview of a novel modular knee exoskeleton, ACE-Knee, and the analysis of the design requirements by observing human knee-motion characteristics. The ACE-Knee exoskeleton consists of 1) base frame at waist, 2) a 3-DOF (degrees of freedom) passive spherical hip, and 3) a knee driving mechanism. The passive hip is designed based on a 3R spherical serial chain such that it has RCM (remote center of motion) capability. For designing a compact and efficient knee driving mechanism, it is realized by two crank-slider linkages where two sliders are coupled with a linear spring. The proposed kinematic structure enables the driving concept of the passive support by the linear spring and the active following by an actuator. In order to setup design requirements, gait experiments were performed for level walking and ascending/descending stairs. From the analysis of experimental results, unique motion and quasi-stiffness characteristics of human knee were identified.
Citations
Citations to this article as recorded by
Static and Dynamic Friction Characteristics Analysis of Actuation Module for Friction Compensation of Exoskeleton Robot Byoung Ju Lee, Gwang Tae Kim, Hong Cheol Kim, Young June Shin Journal of the Korean Society for Precision Engineering.2019; 36(10): 929. CrossRef
Gait analysis is the best objective measurement tool for monitoring rehabilitation. However, it has limitations to evaluate gait recovery. Previous studies have evaluated the effect of gait training using continuous relative phase. The objective of this study was to determine the effect of gait recovery by rehabilitation gait training on lower limb coordination. We analyzed spatio-temporal parameters and CRP values of hip and knee joints based on gait analysis data obtained by 3D motion analysis system at 15 days intervals in 24 uni-lateral transfemoral amputees participated in IRP. Our results revealed that walking velocity of uni-lateral transfemoral amputees who participated in the program during a mean of 107.1 days was 49.2% faster than that at initial stage. The walking velocity showed a 46% increase at the end of 30 days after training. In gait coordination, values of CRP-RMS and CRP-SD were increased and maintained in-phase pattern. CRP showed symmetry in both limbs at the end of 90 days after training. Therefore, CRP is a significant factor in the gait recovery process. Effects of various rehabilitation training methods can be determined through CRP analysis.
Citations
Citations to this article as recorded by
A Comparative Study of the Effects of Augmented Reality Application on Movement Accuracy and Subjective Satisfaction in Rehabilitation Training for Individuals with Lower Limb Amputations Yunhee Chang, Jungsun Kang, Hyeonseok Cho, Sehoon Park Applied Sciences.2025; 15(12): 6703. CrossRef
Changes in Gait Characteristics after Completion of Prosthetic Gait Training in Patients with Unilateral Transfemoral Amputation: Follow-Up after 1 Year Bo Ra Jeong, Gyoo Suk Kim, Yun Hee Chang Journal of the Korean Society for Precision Engineering.2022; 39(11): 849. CrossRef
First
Prev
