Lumbar muscle atrophy, diminished strength, stamina, and increased fatigability have been associated with chronic nonspecific low back pain (LBP). When evaluating patients with LBP, trunk or core stability, provided by the performance and coordination of trunk muscles, appears to be essential. Several clinical tests have been developed to identify deficiencies in trunk performance, demonstrating high levels of validity and reproducibility. The most frequently prescribed tests for assessing the core body muscles are the prone plank bridge test (PBT), the side bridge test (SBT), and the supine bridge test (SUBT). However, quantitative assessments of the kinematics of the lumbar spine during their execution have not yet been conducted. The purpose of our study was to provide objective biomechanical data for the assessment of LBP patients. The lumbar spine ranges of motion of 22 healthy subjects (Group A) and 25 patients diagnosed with chronic LBP (Group B) were measured using two inertial measurement units during the execution of the PBT, SUBT, and SBT. Statistically significant differences between the two groups were found in all three tests’ kinematic patterns. This quantitative assessment of lumbar spine motion transforms the three bridge tests into an objective biomechanical diagnostic tool for LPBs that may be used to assess the efficacy of applied rehabilitation programs.

Gait analysis may serve various purposes related to health care, such as the estimation of elderly people’s risk of falling. This paper is devoted to gait analysis based on data from depth sensors which are suitable for use both at healthcare facilities and in monitoring systems dedicated to household environments. This paper is focused on the comparison of three methods for spatiotemporal gait analysis based on data from depth sensors, involving the analysis of the movement trajectories of the knees, feet, and centre of mass. The accuracy of the results obtained using those methods was assessed for different depth sensors’ viewing angles and different types of subject clothing. Data were collected using a Kinect v2 device. Five people took part in the experiments. Data from a Zebris FDM platform were used as a reference. The obtained results indicate that the viewing angle and the subject’s clothing affect the uncertainty of the estimates of spatiotemporal gait parameters, and that the method based on the trajectories of the feet yields the most information, while the method based on the trajectory of the centre of mass is the most robust.

The gait cycle of humans may be influenced by a range of variables, including neurological, orthopedic, and pathological conditions. Thus, gait analysis has a broad variety of applications, including the diagnosis of neurological disorders, the study of disease development, the assessment of the efficacy of a treatment, postural correction, and the evaluation and enhancement of sport performances. While the introduction of new technologies has resulted in substantial advancements, these systems continue to struggle to achieve a right balance between cost, analytical accuracy, speed, and convenience. The target is to provide low-cost support to those with motor impairments in order to improve their quality of life. The article provides a novel automated approach for motion characterization that makes use of artificial intelligence to perform real-time analysis, complete automation, and non-invasive, markerless analysis. This automated procedure enables rapid diagnosis and prevents human mistakes. The gait metrics obtained by the two motion tracking systems were compared to show the effectiveness of the proposed methodology.

Concerning the biomechanics and energy consumption of the lower limbs, a soft exoskeleton for the powered plantar flexion of the ankle, named A-Suit, was developed to improve walking endurance in the lower limbs and reduce metabolic consumption. The method of ergonomics design was used based on the biological structures of the lower limbs. A profile of auxiliary forces was constructed according to the biological force of the Achilles tendon, and an iterative learning control was applied to shadow this auxiliary profile by iteratively modifying the traction displacements of drive units. During the evaluation of the performance experiments, four subjects wore the A-Suit and walked on a treadmill at different speeds and over different inclines. Average heart rate was taken as the evaluation index of metabolic consumption. When subjects walked at a moderate speed of 1.25 m/s, the average heart rate H_av under the Power-ON condition was 7.25 ± 1.32% (mean ± SEM) and 14.40 ± 2.63% less than the condition of No-suit and Power-OFF. Meanwhile, the additional mass of A-Suit led to a maximum H_av increase of 7.83 ± 1.44%. The overall reduction in H_av with Power-ON over the different inclines was 6.93 ± 1.84% and 13.4 ± 1.93% compared with that of the No-Suit and Power-OFF condition. This analysis offers interesting insights into the viability of using this technology for human augmentation and assistance for medical and other purposes.

In recent years, surface electromyogram signals have been increasingly used to operate wearable devices. These devices can aid to help workers or soldiers to lower the load in the task to boost efficiency. However, achieving effective signal prediction has always been a challenge. It is critical to use an appropriate signal preprocessing method and prediction algorithm when developing a controller that can accurately predict and control human movements in real time. For this purpose, this article investigates the effect of various surface electromyogram preprocessing methods and algorithms on prediction results. Walking data (surface electromyogram angle) were collected from 10 adults (5 males and 5 females). To investigate the effect of preprocessing methods on the experimental results, the raw surface electromyogram signals were grouped and subjected to different preprocessing (bandpass/principal component analysis/independent component analysis, respectively). The processed data were then imported into the random forest and support vector regression algorithm for training and prediction. Multiple scenarios were combined to compare the results. The independent component analysis-processed data had the best performance in terms of convergence time and prediction accuracy in the support vector regression algorithm. The prediction accuracy of knee motion with this scheme was 94.54% ± 2.98. Notably, the forecast time was halved in comparison to the other combinations. The independent component analysis algorithm’s “blind source separation” feature effectively separates the original surface electromyogram signal and reduces signal noise, hence increasing prediction efficiency. The main contribution of this work is that the method (independent component analysis + support vector regression) has the potency of best prediction of surface electromyogram signal for knee movement. This work is the first step toward myoelectric control of assisted exoskeleton robots through discrete decoding.

Sit-to-stand and stand-to-sit transfers are fundamental daily motions that enable all other types of ambulation and gait. However, the ability to perform these motions can be severely impaired by different factors, such as the occurrence of a stroke, limiting the ability to engage in other daily activities. This study presents the recording and analysis of a comprehensive database of full body biomechanics and force data captured during sit-to-stand-to-sit movements in subjects who have and have not experienced stroke. These data were then used in conjunction with simple machine learning algorithms to predict vertical motion trajectories that could be further employed for the control of an assistive robot. A total of 30 people (including 6 with stroke) each performed 20 sit-to-stand-to-sit actions at two different seat heights, from which average trajectories were created. Weighted k-nearest neighbours and linear regression models were then used on two different sets of key participant parameters (height and weight, and BMI and age), to produce a predicted trajectory. Resulting trajectories matched the true ones for non-stroke subjects with an average $R^2$ score of $0.864\pm 0.134$ using k = 3 and 100% seat height when using height and weight parameters. Even among a small sample of stroke patients, balance and motion trends were noticed along with a large within-class variation, showing that larger scale trials need to be run to obtain significant results. The full dataset of sit-to-stand-to-sit actions for each user is made publicly available for further research.

Purpose: The walk ratio (WR)—the step-length/cadence relation—is a promising measure for gait control. GPS-running watches deliver clinically relevant outcomes including the WR. The aim of this study was to determine test-retest agreement, reliability and concurrent validity of an outdoor WR assessment using a GPS-running watch.Methods: Healthy adults and moderate—high functioning stroke survivors (≥6 months), performed the 1 km-outdoor walk twice using a GPS-running watch (Garmin Forerunner 35, GFR35) and a Step Activity Monitor (SAM 3). Global cognition was assessed using the Montreal Cognitive Assessment. Test-retest agreement and reliability were assessed using Bland-Altman plots, standard error of measurement (SEM), intraclass correlation coefficients (ICCs) and smallest detectable changes (SDCs). Concurrent validity was determined by the mean difference (MD), standard error (SE), mean absolute percentage errors (MAPEs) and Spearman’s Rho between GFR35 and SAM3. WR values of the two groups were compared by a Welch’s test. A hierarchical multiple regression was performed with the WR as dependent variable and possible predictors as independent variables.Results: Fifty-one healthy adults [median: 60.0 (47.0, 67.0) years) and 20 stroke survivors [mean: 63.1 (12.4) years, median: 76 (30, 146) months post-stroke] were included. Test-retest agreement and reliability were excellent (SEM% ≤ 2.2, ICCs > 0.9, SDC% ≤ 6.1) and concurrent validity was high (MAPE < 5, ρ > 0.7) for those walking ≥ 1 m/s. Walking < 1 m/s impaired accurate step counting and reduced agreement, reliability, and validity. The WR differed between healthy adults and stroke survivors (t = −2.126, p = 0.045). The hierarchical regression model including stroke and global cognition (Montreal Cognitive Assessment, 0—30) explained 25% of the WR variance (ΔR² = 0.246, p < 0.001). Stroke had no effect (β = −0.05, p = 0.682), but global cognition was a predictor for an altered WR (β = 0.44, p = 0.001).Discussion: The outdoor WR assessment using the GFR35 showed excellent test-retest agreement, reliability and concurrent validity in healthy adults and chronic stroke survivors walking at least 1 m/s. As the WR seems relevant in chronic stroke, future studies should further investigate this parameter.

Virtual Reality (VR) therapy is popular in treating children with Cerebral Palsy (CP) as a new technology for rehabilitation. Nevertheless, no substantial evidence supporting VR therapy promotion has been developed to date. This study aimed to investigate the effects of VR therapy on balance in children with CP. We conducted a systematic search in PubMed and Web of Science (updated to December 30, 2021). The systematic review and meta-analysis included all randomized controlled trials that included children with CP. A total of 18 RCT studies were eligible for inclusion in the systematic review, and meta-analysis was performed on 16 of them. Results showed that the VR intervention was beneficial for balance (SMD 0.47 [95% CI, SD 0.28, 0.66]). We concluded that VR therapy interventions for children with CP have positive effects. However, cautious implementation is needed in clinical applications.

Advanced aerial images have led to the development of improved human–object interaction recognition (HOI) methods for usage in surveillance, security, and public monitoring systems. Despite the ever-increasing rate of research being conducted in the field of HOI, the existing challenges of occlusion, scale variation, fast motion, and illumination variation continue to attract more researchers. In particular, accurate identification of human body parts, the involved objects, and robust features is the key to effective HOI recognition systems. However, identifying different human body parts and extracting their features is a tedious and rather ineffective task. Based on the assumption that only a few body parts are usually involved in a particular interaction, this article proposes a novel parts-based model for recognizing complex human–object interactions in videos and images captured using ground and aerial cameras. Gamma correction and non-local means denoising techniques have been used for pre-processing the video frames and Felzenszwalb’s algorithm has been utilized for image segmentation. After segmentation, twelve human body parts have been detected and five of them have been shortlisted based on their involvement in the interactions. Four kinds of features have been extracted and concatenated into a large feature vector, which has been optimized using the t-distributed stochastic neighbor embedding (t-SNE) technique. Finally, the interactions have been classified using a fully convolutional network (FCN). The proposed system has been validated on the ground and aerial videos of the VIRAT Video, YouTube Aerial, and SYSU 3D HOI datasets, achieving average accuracies of 82.55%, 86.63%, and 91.68% on these datasets, respectively.

Background: The recurrence rate of lumbar spine microdiscectomies (rLSMs) is estimated to be 5–15%. Lumbar spine flexion (LSF) of more than 10° is mentioned as the most harmful load to the intervertebral disc that could lead to recurrence during the first six postoperative weeks. The purpose of this study is to quantify LSFs, following LSM, at the period of six weeks postoperatively. Methods: LSFs were recorded during the daily activities of 69 subjects for 24 h twice per week, using Inertial Measurement Units (IMU). Results: The mean number of more than 10 degrees of LSFs per hour were: 41.3/h during the 1st postoperative week (P.W.) (29.9% healthy subjects-H.S.), 2nd P.W. 60.1/h (43.5% H.S.), 3rd P.W. 74.2/h (53.7% H.S.), 4th P.W. 82.9/h (60% H.S.), 5th P.W. 97.3/h (70.4% H.S.) and 6th P.W. 105.5/h (76.4% H.S.). Conclusions: LSFs constitute important risk factors for rLDH. Our study records the lumbar spine kinematic pattern of such patients for the first time during their daily activities. Patients’ data report less sagittal plane movements than healthy subjects. In vitro studies should be carried out, replicating our results to identify if such a kinematic pattern could cause rLDH. Furthermore, IMU biofeedback capabilities could protect patients from such harmful movements.

Swing-phase dorsiflexion assistance with robotic ankle–foot orthosis could improve toe clearance and limb shortening such that compensatory movements are suppressed. However, facilitating voluntary effort under assistance remains a challenge. In our previous study, we examined assistance effects of swing-phase dorsiflexion with different delay times after toe-off on a dorsiflexion-restricted gait with a high-dorsiflexion assistive system. Results showed that later dorsiflexion assistance could lead to an increase in the tibialis anterior’s surface electromyography but could also deteriorate compensatory movement. Thus, we concluded that there is a suitable assistance timing to simultaneously achieve voluntary effort and optimal gait. In the present research, we derived a method to identify a suitable dorsiflexion assistance delay time via a multiple linear regression analysis on ankle data of stroke patients with a pathological gait with insufficient dorsiflexion. With the identification method, an experiment was conducted on six healthy participants with restricted dorsiflexion. Results showed that the identified assistance timing improved the amplitude of the tibialis anterior’s surface electromyography while also suppressing limb shortening during circumduction and hip hiking. Although a practical study of stroke survivors is required, observations from this research indicate the potential to successfully induce voluntary efforts with the identified dorsiflexion assistance timing.

Summary: The knee joint plays a significant role in ground clearness, which is a crucial subtask of normal walking and avoiding falls. While post-stroke survivors are often faced with muscle weakness during walking, which leads to inadequate knee flexion. The lack of ground clearance caused by inadequate knee flexion will severely impede walking, increase metabolic exertion, and increase the risk of falls. A compliant exoskeleton robot possesses more favorable edges than other rigid ones in lightweight, safety, sense of comfort, and so on. We developed a new type of soft exoskeleton robot to assist the knee joint to achieve desired movements with Bowden cable transmitting force and torque. With the agonist–antagonist driving method, like a group of muscles working, we have explored dual-motors structure to realize the knee flexion function. It has built a standard dynamic model to analyze stability and realize the control law. We have conducted simulation and prototype experiments to verify the feasibility and usefulness of our method. The results show that the device can compensate for the lack of the knee joint driving force and realize the reference movement. Finally, we concluded that our method is a desirable way, and the scheme could improve the knee flexion ability and clearing ground.

Human motion analysis provides useful information for the diagnosis and recovery assessment of people suffering from pathologies, such as those affecting the way of walking, i.e., gait. With recent developments in deep learning, state-of-the-art performance can now be achieved using a single 2D-RGB-camera-based gait analysis system, offering an objective assessment of gait-related pathologies. Such systems provide a valuable complement/alternative to the current standard practice of subjective assessment. Most 2D-RGB-camera-based gait analysis approaches rely on compact gait representations, such as the gait energy image, which summarize the characteristics of a walking sequence into one single image. However, such compact representations do not fully capture the temporal information and dependencies between successive gait movements. This limitation is addressed by proposing a spatiotemporal deep learning approach that uses a selection of key frames to represent a gait cycle. Convolutional and recurrent deep neural networks were combined, processing each gait cycle as a collection of silhouette key frames, allowing the system to learn temporal patterns among the spatial features extracted at individual time instants. Trained with gait sequences from the GAIT-IT dataset, the proposed system is able to improve gait pathology classification accuracy, outperforming state-of-the-art solutions and achieving improved generalization on cross-dataset tests.

Wearable robotic devices have been proved to considerably reduce the energy expenditure of human walking. It is not only suitable for healthy people, but also for some patients who require rehabilitation exercises. However, in many cases, the weight of soft exosuits are relatively large, which makes it difficult for the assistant effect of the system to offset the metabolic consumption caused by the extra weight, and the heavy weight will make people uncomfortable. Therefore, reducing the weight of the whole system as much as possible and keeping the soft exosuit output power unchanged, may improve the comfort of users and further reduce the metabolic consumption. In this paper, we show that a novel lightweight soft exosuit which is currently the lightest among all known powered exoskeletons, which assists hip flexion. Indicated from the result of experiment, the novel lightweight soft exosuit reduces the metabolic consumption rate of wearers when walking on the treadmill at 5 km per hour by 11.52% compared with locomotion without the exosuit. Additionally, it can reduce more metabolic consumption than the hip extension assisted (HEA) and hip flexion assisted (HFA) soft exosuit which our team designed previously, which has a large weight. The muscle fatigue experiments show that using the lightweight soft exosuit can also reduce muscle fatigue by about 10.7%, 40.5% and 5.9% for rectus femoris, vastus lateralis and gastrocnemius respectively compared with locomotion without the exosuit. It is demonstrated that decreasing the weight of soft exosuit while maintaining the output almost unchanged can further reduce metabolic consumption and muscle fatigue, and appropriately improve the users’ comfort.

(1) Dynamic knee valgus is a predisposing factor for anterior cruciate ligament rupture and osteoarthritis. The single-leg squat (SLS) test is a widely used movement pattern test in clinical practice that helps to assess the risk of lower-limb injury. We aimed to quantify the SLS test using a marker-less optical system. (2) Kinect validity and accuracy during SLS were established by marker-based OptiTrack and MVN Xsens motion capture systems. Then, 22 individuals with moderate knee symptoms during sports activities (Tegner > 4, Lysholm > 60) performed SLS, and this was recorded and analyzed with a Kinect Azure camera and the Dynaknee software. (3) An optical sensor coupled to an artificial-intelligence-based joint recognition algorithm gave a comparable result to traditional marker-based motion capture devices. The dynamic valgus sign quantified by the Q-angle at the lowest point of the squat is highly dependent on squat depth, which severely limits its comparability among subjects. In contrast, the medio-lateral shift of the knee midpoint at a fixed squat depth, expressed in the percentage of lower limb length, is more suitable to quantify dynamic valgus and compare values among individual patients. (4) The current study identified a new and reliable way of evaluating dynamic valgus of the knee joint by measuring the medial shift of the knee-over-foot at a standardized squat depth. Using a marker-less optical system widens the possibilities of evaluating lower limb functional instabilities for medical professionals.

The key technology of the prosthetic knee is to simulate the torque and angle of the biological knee. In this work, we proposed a novel prosthetic knee operated in semi-active mode. The structure with ball-screw driven by the motor and the passive hydraulic damping cylinder was presented. A four-bar linkage was adapted to track the instantaneous center motion of human knee. The mathematical models of hydraulic cylinder damping and active torque were established to simulate the knee torque and angle. The results show that the knee torque symmetry index is smaller than 10% in the whole gait. The knee angle symmetry index value is 34.7% in stance phase and 11.5% in swing phase. The angle in swing phase is closer to the intact knee. The semi-active prosthetic knee could provide similar torque and angle of the biological knee in the simulation. It has shown good potential in improving the gait symmetry of the transfemoral amputee.

Whether the lower limb prosthesis can better meet the needs of amputees, the biomimetic performance of the knee joint is particularly important. In this paper, Nokov(metric) optical 3D motion capture system was used to collect motion data of normal human lower limbs, and the motion instantaneous center of multi-gait knee joint was obtained. Taking the error of knee joint motion instantaneous center line as the objective function, a set of six-bar mechanism prosthetic knee joint was designed based on a genetic algorithm. The experimental results show that the movement trajectory of the instantaneous center of the knee joint is basically similar to that of the human knee joint, so it can help amputees complete a variety of gaits and has good biomimetic performance. Gait acquisition technology can provide important data for prosthetic designers and it will be widely used in prosthetic design and other fields.