Epidemiological, Clinical and Paraclinical Profile of Osteoarthritis of the Lower Limbs in Obese Patients at the Cocody University Teaching Hospital

Objective: To describe the epidemiological, clinical and paraclinical characteristics of osteoarthritis of the lower limbs in obese patients at the Cocody University Teaching Hospital. Methodology: This was an analytical cross-sectional study carried out in the rheumatology department of the Cocody UTH in Abidjan (Ivory Coast) from March 1 to April 30 2023. Patients who came for rheumatology consultation presenting with mechanical arthralgia of the lower limbs, who were obese, had radiographic images were included. All patients without radiographic images were excluded. Obesity was defined as a body mass index (BMI) greater than or equal to 30 kg/m. The Chi2 test was used to compare proportions and determine the existence of associations between osteoarthristis and obesity, obesity severity and radiographic stage of osteoarthritis as well as the functional impact. A p-value below a predefined threshold (p = 0,05) indicates a significant relationship between the variables. Result: Out of 185 patients received for osteoarthritis of the lower limbs during the study period, 136 were obese (74%). There were 115 women (84.6%) with an average age of 56.03 with a standard deviation of 12.72 years (extremes: 22 and 84 years). The main socio-professional category was the informal sector (30%). The majority of patients had a low socio-economic level (80.2%) and lived in urban areas (92.6%). The most common past medical history was hypertension (33.08%) followed by peptic ulcer disease (16.91%). Patients had a body mass index class 1 (81.6%), class 2 (15.40%) and class 3 (2.90%). The average duration of symptom progression until diagnosis was 11 months. Genu varum was the main static disorder (56.10%) and the knee joint was the dominant topography (90.4%) with a bilateral localization (80%). The average Lequesne index was greater than 8 (59.5%). The Kellgren and Lawrence radiographic stages were stage 1 (9.20%), stage 2 (46.90%), stage 3 (29.20%) and stage 4 (6.90%). The Obesity severity was significantly associated with osteoarthritis of the knee (p = 0.042). There was no statistically significant association between obesity severity and radiographic stage of osteoarthritis (p = 0.163) or functional impact (p = 0.180). Conclusion: Osteoarthritis of the lower limbs affected obese women and was dominated by stage 2 osteoarthritis of the knee (Kellgren and Lawrence). There is an association between the severity of obesity and osteoarthritis of the knee.

Neural Network Robust Control Based on Computed Torque for Lower Limb Exoskeleton

The lower limb exoskeletons are used to assist wearers in various scenarios such as medical and industrial settings.Complex modeling errors of the exoskeleton in different application scenarios pose challenges to the robustness and stability of its control algorithm.The Radial Basis Function(RBF)neural network is used widely to compensate for modeling errors.In order to solve the problem that the current RBF neural network controllers cannot guarantee the asymptotic stability,a neural network robust control algorithm based on computed torque method is proposed in this paper,focusing on trajectory tracking.It innovatively incorporates the robust adaptive term while introducing the RBF neural network term,improving the compensation ability for modeling errors.The stability of the algorithm is proved by Lyapunov method,and the effectiveness of the robust adaptive term is verified by the simulation.Experiments wearing the exoskeleton under different walking speeds and scenarios were carried out,and the results show that the absolute value of tracking errors of the hip and knee joints of the exoskeleton are consistently less than 1.5°and 2.5°,respectively.The proposed control algorithm effectively compensates for modeling errors and exhibits high robustness.

Model Parameters Identification and Backstepping Control of Lower Limb Exoskeleton Based on Enhanced Whale Algorithm

Exoskeletons generally require accurate dynamic models to design the model-based controller conveniently under the human-robot interaction condition.However,due to unknown model parameters such as the mass,moment of inertia and mechanical size,the dynamic model of exoskeletons is difficult to construct.Hence,an enhanced whale optimization algorithm(EWOA)is proposed to identify the exoskeleton model parameters.Meanwhile,the periodic excitation trajectories are designed by finite Fourier series to input the desired position demand of exoskeletons with mechanical physical constraints.Then a backstepping controller based on the identified model is adopted to improve the human-robot wearable comfortable performance under cooperative motion.Finally,the proposed Model parameters identification and control are verified by a two-DOF exoskeletons platform.The knee joint motion achieves a steady-state response after 0.5 s.Meanwhile,the position error of hip joint response is less than 0.03 rad after 0.9 s.In addition,the steady-state human-robot interaction torque of the two joints is constrained within 15 N·m.This research proposes a whale optimization algorithm to optimize the excitation trajectory and identify model parameters.Furthermore,an enhanced mutation strategy is adopted to avoid whale evolution’s unsatisfactory local optimal value.

Personalized Lower Limb Gait Reconstruction Modeling Based on RFA-ProMP

Personalized gait curves are generated to enhance patient adaptability to gait trajectories used for passive training in the early stage of rehabilitation for hemiplegic patients.The article utilizes the random forest algorithm to construct a gait parameter model,which maps the relationship between parameters such as height,weight,age,gender,and gait speed,achieving prediction of key points on the gait curve.To enhance prediction accuracy,an attention mechanism is introduced into the algorithm to focus more on the main features.Meanwhile,to ensure high similarity between the reconstructed gait curve and the normal one,probabilistic motion primitives(ProMP)are used to learn the probability distribution of normal gait data and construct a gait trajectorymodel.Finally,using the specified step speed as input,select a reference gait trajectory from the learned trajectory,and reconstruct the curve of the reference trajectoryusing the gait keypoints predictedby the parametermodel toobtain the final curve.Simulation results demonstrate that the method proposed in this paper achieves 98%and 96%curve correlations when generating personalized lower limb gait curves for different patients,respectively,indicating its suitability for such tasks.

Intervention Effect of Lower Limb Rehabilitation Robot with Task-Oriented Training on Stroke Patients and Its Influence on KFAROM Score

Objective: To explore the effect of lower limb rehabilitation robot combined with task-oriented training on stroke patients and its influence on KFAROM score. Methods: 100 stroke patients with hemiplegia admitted to our hospital from January 2023 to December 2023 were randomly divided into two groups, the control group (50 cases) was given task-oriented training assisted by nurses, and the observation group (50 cases) was given lower limb rehabilitation robot with task-oriented training. Lower limb balance, lower limb muscle strength, motor function, ankle function, knee flexion range of motion and walking ability were observed. Results: After treatment, the scores of BBS, quadriceps femoris and hamstrings in the observation group were significantly higher than those in the control group (P Conclusion: In the clinical treatment of stroke patients, the combination of task-oriented training and lower limb rehabilitation robot can effectively improve the lower limb muscle strength, facilitate the recovery of balance function, and have a significant effect on the recovery of motor function, which can improve the walking ability of stroke patients and the range of motion of knee flexion, and achieve more ideal therapeutic effectiveness.

Assistive Devices and Clothing: Exploring Adaptive Clothing Needs for Women with Lower Limb Prostheses Using the FEA Model

This study aimed to comprehensively investigate the essential considerations in designing adaptive clothing for women with lower limb prostheses in Saudi Arabia. Employing a qualitative methodology, the research entailed semi-structured, in-depth interviews with women utilizing lower limb prostheses and prosthetic specialists. This approach was selected to unearth pivotal design prerequisites and comprehend the specific challenges these women encounter within the realm of clothing. The utilization of selective sampling facilitated the collection of intricate and valuable insights. A Functional, Expressive, and Aesthetic (FEA) User Needs model was utilized to scrutinize participant feedback. Functional requisites encompass ease of dressing and undressing, accessibility to the prosthetic limb, comfort, mobility with the prosthesis, and appropriate fit. Additionally, participants highlighted various expressive needs, including privacy preservation, modesty, camouflaging disability appearances, maintaining alignment with non-disabled women’s fashion, and considerations about the aesthetic aspects of garments.

A Clinical Randomized Controlled Study of Low-Frequency rTMS Therapy on Lower Limb Motor Dysfunction after Stroke

Objective:To investigate the efficacy and safety of low-frequency repetitive transcranial magnetic stimulation(rTMS)for the treatment of lower limb motor dysfunction after stroke.Methods:A total of 96 patients with stroke and lower limb motor dysfunction were enrolled in this study,and were randomly divided into the experimental group and the sham stimulation group using the method of calculator-generated random numbers.Both groups received conventional medication and rehabilitation therapy.The experimental group received 4 weeks of 1 Hz rTMS treatment in the primary cortical motor area(M1)of the healthy side,with the treatment coil tangent to the skull surface;the sham stimulation group underwent the same procedures as the experimental group,but the treatment coil was perpendicular to the skull surface instead.Lower-extremity subscale of the Fugl-Meyer Assessment(FMA-LE),Berg Balance Scale(BBS),gait analysis,and lower-extremity surface electromyography(LESEM)were performed in both groups before and after rTMS treatment.Results:All 96 patients completed the test with no shedding and no adverse reactions.After treatment,the FMA-LE score and BBS score of the 2 groups of patients were significantly improved as compared with the pre-treatment(P<0.05),and the TUG test time was reduced as compared with the pre-treatment(P<0.05).The true stimulation group had greater improvement in all assessment indexes than that of the sham stimulation group(P<0.05).After treatment,the electromyographic activity of the tibialis anterior and rectus femoris muscles in the true simulation group improved significantly.The step length,step speed,and step frequency were also significantly improved in both groups after treatment,and the symmetrical ratio of step length and support time was reduced(P<0.05).Comparison between the groups revealed that the true simulation group significantly improved after rTMS treatment as compared to the sham stimulation group(P<0.05).Conclusion:1Hz rTMS treatment safely and effectively improved motor and balance function in patients with post-stroke lower limb motor dysfunction.

Knowledge of Patients and Their Accompanying Persons about Obliterative Arteriopathy of the Lower Limbs at Conakry University Hospital in 2022

Introduction: Obliterative arterial disease of the lower limbs is a marker of advanced atherosclerosis. It is one of the world’s most common cardiovascular diseases, present in one in five people over the age of 60, and carries an increased risk of morbidity and mortality. The aim of this study was to assess the knowledge of patients and their carers about obliterative arteriopathy of the lower limbs at Conakry University Hospital. Material and Methods: We conducted a descriptive cross-sectional study lasting 3 months, from March 12 to June 12, 2022 in the hospitals of the University Hospital of Conakry (Donka and Ignace Deen). Following free and informed consent, they were interviewed on the basis of a pre-established questionnaire. Socio-demographic data (age, gender, level of education) were collected, and knowledge of obliterative arterial disease of the lower limbs. Results: The study involved 159 people, comprising 106 patients (66.66%) and 53 accompanying persons (33.34%) in the hospitals of the University Hospital of Conakry (Donka and Ignace Deen). The 60 to 79 age group was the most represented (44.7%), with an average age of 55.4 ± 15.9 years and extremes of 20 to 84 years. Half (47.8%) had not attended school, and almost all (96.4%) of those who had attended school had a low level of education (primary and secondary). Almost all of them (91.2%) had never heard of AOMI. Only 5% identified at least one risk factor, diabetes, hypertension and smoking. Amputation was the most frequently identified complication. About 98% did not know that AOMI is associated with myocardial infarction and stroke, and 93.7% did not know of any complications. Almost all the participants (99.4%) had poor knowledge of the following complications. Conclusion: Obliterative arterial disease of the lower limbs could be prevented or delayed by screening and controlling risk factors. Our results show a huge deficit in knowledge of this pathology, including risk factors, preventive measures, clinical signs and complications among patients and their relatives. A study conducted outside the hospital environment would provide a better understanding of the extent to which the general population is unaware of this disease.

Adaptive Robust Control for a Lower Limbs Rehabilitation Robot Running Under Passive Training Mode

This paper focuses on the problem of the adaptive robust control of a lower limbs rehabilitation robot(LLRR) that is a nonlinear system running under passive training mode. In reality, uncertainties including modeling error, initial condition deviation, friction force and other unknown external disturbances always exist in a LLRR system. So, it is necessary to consider the uncertainties in the unilateral man-machine dynamical model of the LLRR we described. In the dynamical model, uncertainties are(possibly fast) time-varying and bounded. However, the bounds are unknown. Based on the dynamical model, we design an adaptive robust control with an adaptive law that is leakagetype based and on the framework of Udwadia-Kalaba theory to compensate for the uncertainties and to realize tracking control of the LLRR. Furthermore, the effectiveness of designed control is shown with numerical simulations.

Lower limb amputation rehabilitation status in India: A review

Rehabilitation of lower limb amputation in developing countries is quite challenging.Though there are basic to highly advanced prostheses available in India,the set-up is still facing difficulties in developing countries.Prosthetic management is difficult due to lack of availability of prostheses and reduced affordability among low income populations.In this review we highlighted the lower limb amputation and prosthetic rehabilitation status in India.Currently,India is advancing well in the rehabilitation field,but further studies are required to provide more evidence and recommendation.

Equalisation of Lower Limb Length in Young Adults Using Internal Osteosynthesis: A Case Report of 22 Patients

Introduction: Inequality in the length of the lower limbs has an impact on the stability and function of the musculoskeletal system because of the imbalance it causes in our bodies. Several treatment modalities were used by practitioners. The aim of this study was to evaluate the anatomical and functional results of length equalisation of the lower limbs using internal osteosynthesis in the Orthopaedic and Traumatological Surgery Department of the Amirou Boubacar Diallo National Hospital in Niamey. Patients and method: This was a retrospective, prospective study of 22 patients from January 2010 to November 2015, a period of 5 years. The patients concerned were aged at least 18 years and had undergone a femoral shortening osteotomy not exceeding 5 cm on the contralateral healthy limb with a screw plate as the internal osteosynthesis device. Results: The average age of our patients was 24.18 years (18 to 48 years). The etiologies of these length inequalities were: vascular 54.55% (n = 12), post-traumatic 27.27% (n = 6), post-infectious 13.64% (n = 3) and neuromuscular 4.54% (n = 1). The mean length inequality of our patients was 4.93 cm, with extremes ranging from 4 to 8 cm. At an average follow-up of 6.5 months (6 to 24 months), our functional results were satisfactory overall. Discussion: Despite the significant nature of our initial inequalities, which were moderate and severe, we ended up with slight inequalities or even total correction for some of our patients. Conclusion: Inequality in the length of the lower limbs is a handicap that requires appropriate management.

Deep Venous Thrombosis: Commonly Affected Veins in the Lower Limbs

Aim and Objectives: This study aimed to record the commonly affected veins in the lower limbs, to compare the affected sides and gender and to correlate the Doppler findings and stages of deep venous thrombosis (DVT). Materials and Methods: A descriptive retrospective study of 46 already diagnosed cases of lower limb DVT. Results: Out of 46 cases of DVT, 71.74% were females. The majority of patients (93.47%) were affected in unilateral lower limb with significant predominance (65.22%) to affect the left lower limb (p Conclusion: Lower limb deep venous thrombosis affects left lower limb more than right and females more than males. Superficial femoral vein (SFV) and common femoral vein (CFV) are the most common affected veins. Lower limb DVT predominantly present in acute stage with venous distension and absent blood flow.

The design of exoskeleton lower limbs rehabilitation robot

To achieve human lower limbs rehabilitation training, the exoskeleton lower limbs rehabilitation robot is designed. Through respective motor driving, the retarding mechanism and telescopic adjusting mechanism, the function of human walking is accomplished. After the design of the mechanical structure, the finite element analysis is carried out on the important parts and the control system is achieved by Single Chip Microcomputer.

Risk Factors for Lower Extremity Amputation among Diabetic Patients with Diabetic Foot Gangrene in ATBUTH, Bauchi

Background: Diabetic mellitus was described as an evolving global epidemic of the twenty-first century, due to the exponential rise in the number of people with the condition. Lower extremity amputation is one of the common complications of diabetes. With increase in the number of people with diabetes there will also be increase in the number of diabetics going for lower extremity amputation, increasing both the financial as well as psychologic burden of treatment. Methodology: A prospective cross-sectional study of all diabetic patients going for lower extremity amputation will be done. All the patients with advanced diabetic foot syndrome needing lower extremity amputation are enrolled (Wagener stage IV and V), both through the clinic and emergency center. Informed consent is obtained from the patient after which data are collected using a structured questionnaire. All the investigation results of the patients were also documented. Data collected are analyzed using the SPSS version 29. Chi-square and student t-test were used to measure significant relationship between the variables at 95% confident interval. Results: Within the period of study, which extends from 1st January 2022 to 1st of January 2024, a total of 171 patients were recruited. All diabetic patients with diabetic foot Wagener grade IV and V who presented to the clinic or emergency department were enrolled in the study. We found a significant relationship between gender, previous procedure on the affected limb or amputation of the contralateral limb, knowledge of foot care among diabetics and risk of amputation. There was, however, no statistically significant relationship between. There is no statistically significance relationship between the level of education, occupation, presence of co-morbidity with the risk of amputation among diabetic patients with foot syndrome. Conclusion: Previous lower limb procedure/amputation, male gender, paucity of knowledge on foot care, prolonged duration of the disease and method of treatment are important risk factors for the risk of amputation among diabetic patients with diabetic foot syndrome.

Training and Recommendations on the Lower Limbs Explosive Force of Juvenile Amateur Men Sprinters

Based on the characteristics of physiological development of China's juvenile men sprinters,combined with the training mechanism of explosive force,and taking the track- and- field team of Jianshan High School in Chongqing as experimental object,this article selects the combination of one leg training methods and the combination of two legs training methods to carry out group control experiment. The result shows: each index score of the two groups of athletes is improved after training,but the characteristics of employing forces and the way of muscle work in one leg jumping exercises such as the one leg jump and step are much closer to sprint techniques. And using this kind of methods can effectively develop the special quality of juvenile sprinter.

Effects of Hip Arthroplasties on Bone Adaptation in Lower Limbs: A Computational Study

Gait disorders contribute to the risk of falls and successive injuries, especially to elderly populations. The risk of falls becomes higher for hip osteoarthritis (OA) and hip arthroplasties patients due to poor balancing and gait impairment. Bone adaptation and bone loss are fundamental issues in considering the changes of bone behavior and gait pattern. In this study, computational analysis of the lower limbs was conducted to estimate the bone adaptation after hip arthroplasties procedure. 3D inhomogeneous model of lower limb was developed from computed topography (CT- based) data of 79 years old patient with hip osteoarthritis problem in left limb. Two types of arthroplaties were constructed in the left limb, namely total hip arthroplasty and resurfacing hip arthroplasty using commercial biomedical software, Mechanical Finder v6.1. Prosthesis stem and acetabular cup of THA were modelled as titanium alloy material (E = 114 GPa, v = 0.34), femoral ball and bearing insert as alumina properties (E = 370 GPa, v = 0.22). Meanwhile, RHA implant was assigned as Co-Cr-Mo material (E = 230 GPa, v = 0.30). Contact between both implants and bone were considered to be perfectly bonded at the interface. A load case of quiet standing position was conducted in this analysis with 60 kg of the patients’ body weight. The load was applied at the cross sectional lumbar vertebra and fixed at the distal of femoral shafts. Results show different patterns of stress distribution in right and left (operated) limbs for hip OA, THA and RHA models. An indication of stress alteration on both limbs after arthroplasties suggested that the bone adaptation occurred. The higher percentage of change in the left limb projected that the adaptation was more critical in operated limb.

Epidemiological and Clinical Pattern of Open Fractures of Long Bones of the Lower Limbs in the South-West Region of Cameroon: A 5-Year Review

Background: An open fracture is an injury in which the fracture site and/or hematoma communicates with the external environment. It is associated with significant morbidity and disability and is a challenge to the surgical team. The lower extremities are the most often exposed to traumatic injuries compared to other anatomical parts of the body. Patterns of open fractures differ with different mechanisms of injury and the segment of the long bone affected. The correct and timely management of open fractures is beneficial to the patients and leads to a more favorable outcome. This study aimed at describing the pattern of open fractures of long bones of the lower limb treated in 3 major hospitals of the south west region, Cameroon. Methodology: This was a hospital-based retrospective review of files of patients with open fractures of long bones of the lower limb managed at the surgical units of three secondary health facilities in the South-West region of Cameroon from the 1st of January 2015 to the 31st of December 2019. The socio-demographic characteristics, clinical presentation, treatment modalities, and outcomes were recorded. The data was stored and analyzed using Epi info version 7.0 and SPSS version 23.0 respectively. Results: A total of 195 files of patients aged 8 to 80 years were studied. The main age group affected was between 20 - 40 years. There were 147 (75.4%) males and 48 (24.6%) females giving a sex-ratio of 3.1:1. The most common cause was road traffic crashes 142 (72.8%). In 98 cases (50.3%), the left side was more involved. The tibia was the most common long bone affected in 75 (38.5%) cases. Comminuted fracture was the most common fracture pattern encountered in 126 cases (64.6%). A total of 76 (39%) fractures were graded Gustilo-Anderson IIIA. External fixator was used in 112 cases (57.1%) and internal fixator in 86 cases (42.9%). We recorded 127 (65.1%) cases of wound infection and 143 (73.3%) cases of limb shortening as the most common complications. Other complications include: 20 cases (17.1%) of mal-union, 27 cases (22.5%) of delayed union, 18 cases (15.1%) of non-union and 50 cases (38.5%) chronic osteomyelitis. We recorded a mortality of 2.1%. Gustilo IIIB and IIIC were associated to chronic osteomyelitis (P = 0.02). Conclusion: Open fractures of long bones of the lower limb affect the active age group of the population and road traffic crashes are the most common causes. It tends to affect the left side and the tibia being the most fractured long bone. A reasonable proportion of these fractures subsequently get infected. Comminuted fracture is the common fracture pattern.

Prevention and Treatment of Deep Vein Thrombosis of the Lower Limbs in Patients with Complications after Orthopedic Trauma Surgery

Objective:To explore and analyze on how to prevent and treat deep vein thrombosis of the lower limbs in patients with complications after orthopedic trauma surgery.Methods:The research patients were selected from the cases of surgical treatment of orthopedic trauma in the hospital during the past two years,and a total of 58 patients were selected.The patients were randomly divided into two groups,with 29 patients in the control group treated with conventional clinical methods;and the other 29 patients were assigned to the experimental group,where targeted preventive and therapeutic measures were administered.During the research,the number of complications of postoperative deep vein thrombosis of the lower limbs and the corresponding treatment efficacy were compared between the two groups of patients.Results:According to the results of clinical experiments,the probability of patients in the experimental group suffering from deep vein thrombosis of the lower limbs after surgery was significantly lower than that of the control group(P<0.05);in addition,when complications of deep venous thrombosis of the lower limbs occurred,the treatment efficacy of the patients in the experimental group was 96.55%,and the treatment efficacy of the patients in the control group was 82.76%.There was a significant difference between the two groups(P<0.05).Conclusion:Through clinical experiments to study and analyze the prevention and treatment measures of deep vein thrombosis in patients with complications after orthopedic trauma surgery,this research proves that active and comprehensive preventive and treatment measures can effectively reduce the number of complications and improve surgery treatment efficacy.

A Review on Lower Limb Rehabilitation Exoskeleton Robots

Lower limb rehabilitation exoskeleton robots integrate sensing, control, and other technologies and exhibit the characteristics of bionics, robotics, information and control science, medicine, and other interdisciplinary areas. In this review, the typical products and prototypes of lower limb exoskeleton rehabilitation robots are introduced and stateof-the-art techniques are analyzed and summarized. Because the goal of rehabilitation training is to recover patients’ sporting ability to the normal level, studying the human gait is the foundation of lower limb exoskeleton rehabilitation robot research. Therefore, this review critically evaluates research progress in human gait analysis and systematically summarizes developments in the mechanical design and control of lower limb rehabilitation exoskeleton robots. From the performance of typical prototypes, it can be deduced that these robots can be connected to human limbs as wearable forms;further, it is possible to control robot movement at each joint to simulate normal gait and drive the patient’s limb to realize robot-assisted rehabilitation training. Therefore human–robot integration is one of the most important research directions, and in this context, rigid-flexible-soft hybrid structure design, customized personalized gait generation, and multimodal information fusion are three key technologies.

STGNN-LMR:A Spatial–Temporal Graph Neural Network Approach Based on sEMG Lower Limb Motion Recognition

Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher’s subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial–temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial–temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.