ABSTRACT
In 2019, the Novel Coronavirus Disease (COVID-19) was categorized as a pandemic. This disease can be transmitted via droplets on items or surfaces within several hours. Therefore, the researchers aimed to develop a wirelessly controlled robot arm and platform capable of picking up objects detected via object detection. Robot arm movements are done via the use of inverse kinematics. Meanwhile, a custom object detection model that can detect objects of interest will be trained and implemented in this project. To achieve this, the researchers utilize various open-source libraries, microcontrollers, and readily available materials to construct and program the entire system. At the end of this research, the prototype could reliably detect objects of interest, along with a grab-and-dispose success rate of 88%. Instruction data can be properly sent and received, and dual web cam image transfer reaches up to 1.72 frames per second. © 2023 IEEE.
ABSTRACT
Purpose: Rehabilitation to address modifiable factors associated with chronic hip-related groin pain (CHRGP) may lead to reduced pain and improved function, yet little is known about its effectiveness. We assessed the preliminary effects of two interventions that target two distinct mechanisms, sensory disturbances and abnormal movement patterns. Sensory disturbances such as peripheral and central sensitization may contribute to pain persistence long after initial injury. Joint mobilization (JtMob) may impart a neurophysiological response within the nervous system that results in pain reduction and improved mobility. Abnormal movement patterns may create altered mechanical stresses on hip joint structures, resulting in pain and activity limitations. Movement pattern training (MoveTrain) may improve movement patterns and thus patient function. Method(s): Patients with CHRGP, 18-40, were enrolled. Assessments included self-report questionnaires, clinical exam, and quantitative sensory testing. Outcomes included the Hip disability and Osteoarthritis Outcome Score (HOOS), a patient-reported outcome;frontal plane kinematics of hip, pelvis, and trunk during single leg squat;and pain pressure threshold (PPT) assessed at the anterior groin of the most bothersome hip and dominant thenar eminence (local and generalized pressure hypersensitivity, respectively). Patients were randomized to JtMob or MoveTrain in a 1:1 ratio stratified by sex and HOOS Symptoms. Treatment for both groups included 10 individualized visits over 12 weeks with a trained physical therapist (PT);assessment of patient goals and education which focused on patient-specific tasks reported by the patient to be symptom-producing;instruction in a home exercise program (HEP);and handouts that provided education, description and benefits of assigned treatment and instructions for HEP. The key element of JtMob was PT-provided manual techniques using specific criteria to determine the joint mobilization techniques and parameters used for each patient. The patient's symptom report to each technique was monitored and if indicated, the technique modified according to our outlined procedures. The HEP included flexibility exercises. The key element of MoveTrain was task-specific instruction to correct abnormal movement patterns displayed during daily and patient-specific tasks. For example, hip adduction was minimized during a step descent. The HEP included repeated practice of modified tasks. Task difficulty was progressed based on each patient's performance. Immediately after treatment completion, patients returned for follow up assessment. To assess treatment sustainability after the active treatment phase, we collected HOOS at 6 and 12 months (extended follow-up), and kinematics and PPT at 12 months. Data from patients who provided any data after baseline were analyzed with a repeated measures analysis of variance (RM-ANOVA) with baseline value as a covariate, patient as a random effect, and an autoregressive covariance structure. After adjusting for baseline, the between-group difference in change from post-treatment to each extended follow-up results from pre-planned statistical contrasts in a RM-ANOVA that includes main effects for treatment group, visit and the group by visit interaction. The within-group treatment effect at each extended follow-up was calculated by subtracting the earlier time point from the later follow-up within each treatment group. Dependent samples t-tests were used to assess the degree of within-group change. Result(s): Demographics and outcome data are provided in Tables 1 and 2, respectively. Thirty-three patients with CHRGP were randomized and 29 (88%) provided post-treatment data. Four patients did not complete treatment or post-treatment testing (3 due to COVID pandemic, 1 lost to follow up);6 patients did not complete 12 month laboratory testing (due to pandemic), but did complete 12 month questionnaires. Previously, we reported that both groups reported clinically important improvements in HOOS subscales and MoveTrain group improved hip and pelvis kinematics immediately after treatment compared to baseline. After adjusting for baseline, there were no between-group differences in change in outcomes between post-treatment and extended follow-up when comparing JtMob and MoveTrain, indicating that treatment effects immediately post-treatment were maintained at 12 months after treatment completion. Conclusion(s): Our preliminary findings suggest that 12 weeks of JtMob or MoveTrain, may result in improvements in patient-reported pain and function and these effects may persist 12 months after treatment completion. A future, larger trial to definitively assess the efficacy of JtMob and MoveTrain and identify factors associated with long-term outcomes will improve our ability to develop treatment strategies for people with CHRGP. [Formula presented] [Formula presented]Copyright © 2023
ABSTRACT
The Internet of Drones (IoD) allows drones to collaborate safely while operating in a restricted airspace for numerous applications in Industry 4.0 world. Energy efficiency and sharing sensing data are the main challenges in swarm-drone collaboration for performing complex tasks effectively and efficiently in real-time. Information security of consensus achievement is required for multi-drone collaboration in the presence of Byzantine drones. Byzantine drones may be enough to cause present swarm coordination techniques to collapse, resulting in unpredictable or calamitous results. One or more Byzantine drones may lead to failure in consensus while exploring the environment. Moreover, Blockchain technology is in the early stage for swarm drone collaboration. Therefore, we introduce a novel blockchain-based approach to managing multi-drone collaboration during a swarm operation. Within drone swarms, blockchain technology is utilized as a communication tool to broadcast instructions to the swarm. This paper aims to improve the security of the consensus achievement process of multi-drone collaboration, energy efficiency, and connectivity during the environment's exploration while maintaining consensus achievement effectiveness. Improving the security of consensus achievement among drones will increase the possibility and stability of multi-drone applications by improving connectivity and energy efficiency in the smart world and solving real environmental issues.
ABSTRACT
With the occurrence of pandemics, such as COVID-19, which lead to social isolation, there is a need for home rehabilitation procedures without the direct supervision of health professionals. The great difficulty of treatment at home is the cost of the conventional equipment and the need for specialized labor to operate it. Thus, this paper aimed to develop serious games to assist health professionals in the physiotherapy of patients with spinal pain for clinical and home applications. Serious games integrate serious aspects such as teaching, rehabilitation, and information with the playful and interactive elements of video games. Despite the positive indication and benefits of physiotherapy for cases of chronic spinal pain, the long treatment time, social isolation due to pandemics, and lack of motivation to use traditional methods are some of the main causes of therapeutic failure. Using Unity 3D (version 2019.4.24f1) software and a personal computer with a webcam, we developed aesthetically pleasing, smooth, and attractive games, while maintaining the essence of seriousness that is required for rehabilitation. The serious games, controlled using OpenPose (version v1.0.0alpha-1.5.0) software, were tested with a healthy volunteer. The findings demonstrated that the proposed games can be used as a playful tool to motivate patients during physiotherapy and to reduce cases of treatment abandonment, including at home.
ABSTRACT
With the concept of quality education put forward, students' sports activities have received extensive attention from society. As a result, sports injuries among students during sports have also aroused widespread concern, so it is an irreversible trend to detect sports injuries. The development of multimedia intelligent 3D image technology also provides technical support for sports injury detection, which makes it possible to automatically detect sports injuries. In this paper, an automatic detection system for sports injuries was designed based on multimedia intelligent three-dimensional image technology, and the related content was evaluated. In the investigation of the parts of students' sports injuries, it was concluded that the injury rate of the students' ankle joints was the highest;in the investigation of the types of sports injuries among students, it was concluded that students were more likely to suffer from joint sprains;in the project investigation of students' sports injuries, it was concluded that students were more prone to sports injuries in ball games with a large amount of exercise;in the investigation of the causes of students' sports injuries, it was concluded that the main reasons for students' sports injuries were physical insufficiency and a bad venue environment;in terms of the performance evaluation of the sports injury detection system, it was concluded that the accuracy, effectiveness, authenticity, and efficiency of the sports injury automatic detection system based on multimedia intelligent three-dimensional image processing technology had been improved to different degrees compared with the traditional sports injury detection methods. Therefore, the detection efficiency of the sports injury automatic detection system proposed in this paper was improved by 5.7% compared with the traditional sports injury detection method.
ABSTRACT
The science of robotics is considered one of the most practical sciences in all fields. The application of this science is visible in all kinds of work fields and related fields, from construction activities to activities in the fields of medicine or even social services. One of the social services that are very widely used, is delivering items and orders to customers. This work is the duty of people who are called waiters. This job has very few benefits for people working in this field. Also, things like illness can cause some delay in the employer's work or not complete his work in some cases, also in situations such as when contagious diseases have spread, the direct communication of people within a short distance can cause more spread of the disease. The devices ordered by the customers could increase the speed of work and have a low-risk connection, the costs of the employer could be reduced, perfect service could be given to the customers, and the workforce could be employed for more useful work. This robot is specifically designed to use for reception in the conference hall of the growth center of Kharazmi University to receive the people present in this conference hall, but as mentioned above, these robots can be used in other places such as hospitals for delivering medicines to patients, also can be used in restaurants to deliver customer's orders to them. With this replacement, the speed of catering increases, at the same time, there is no lack of accuracy, and the issue that becomes more important with the spread of the contagious disease Covid-19 is hygiene, which can achieve several important goals in this field with this replacement. Specifically, during the reception, the distance between the host and the guest is less than one meter and is unsafe. Also, there is a possibility that each of the parties is a carrier of contagious diseases, and these problems are solved by this replacement. © 2022 IEEE.
ABSTRACT
The current study aims to investigate and compare the effects of waste plastic oil blended with n-butanol on the characteristics of diesel engines and exhaust gas emissions. Waste plastic oil produced by the pyrolysis process was blended with n-butanol at 5%, 10%, and 15% by volume. Experiments were conducted on a four-stroke, four-cylinder, water-cooled, direct injection diesel engine with a variation of five engine loads, while the engine's speed was fixed at 2500 rpm. The experimental results showed that the main hydrocarbons present in WPO were within the range of diesel fuel (C13–C18, approximately 74.39%), while its specific gravity and flash point were out of the limit prescribed by the diesel fuel specification. The addition of n-butanol to WPO was found to reduce the engine's thermal efficiency and increase HC and CO emissions, especially when the engine operated at low-load conditions. In order to find the suitable ratio of n-butanol blends when the engine operated at the tested engine load, the optimization process was carried out by considering the engine's load and ratio of the n-butanol blend as input factors and the engine's performance and emissions as output factors. It was found that the multi-objective function produced by the general regression neural network (GRNN) can be modeled as the multi-objective function with high predictive performances. The coefficient of determination (R2), mean absolute percentage error (MAPE), and root mean square error (RSME) of the optimization model proposed in the study were 0.999, 2.606%, and 0.663, respectively, when brake thermal efficiency was considered, while nitrogen oxide values were 0.998, 6.915%, and 0.600, respectively. As for the results of the optimization using NSGA-II, a single optimum value may not be attained as with the other methods, but the optimization's boundary was obtained, which was established by making a trade-off between brake thermal efficiency and nitrogen oxide emissions. According to the Pareto frontier, the engine load and ratio of the n-butanol blend that caused the trade-off between maximum brake thermal efficiency and minimum nitrogen oxides are within the approximate range of 37 N.m to 104 N.m and 9% to 14%, respectively.
ABSTRACT
This article develops a stochastic programming framework for multiagent systems, where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with distributed subtasks. Examples include pandemic robotic service coordination, explore and rescue, and delivery systems with heterogeneous vehicles. Owing to their inherent flexibility and robustness, multiagent systems are applied in a growing range of real-world problems that involve heterogeneous tasks and uncertain information. Most previous works assume one fixed way to decompose a task into roles that can later be assigned to the agents. This assumption is not valid for a complex task where the roles can vary and multiple decomposition structures exist. Meanwhile, it is unclear how uncertainties in task requirements and agent capabilities can be systematically quantified and optimized under a multiagent system setting. A representation for complex tasks is proposed: agent capabilities are represented as a vector of random distributions, and task requirements are verified by a generalizable binary function. The conditional value at risk is chosen as a metric in the objective function to generate robust plans. An efficient algorithm is described to solve the model, and the whole framework is evaluated in two different practical test cases: capture-the-flag and robotic service coordination during a pandemic (e.g., COVID-19). Results demonstrate that the framework is generalizable, is scalable up to 140 agents and 40 tasks for the example test cases, and provides low-cost plans that ensure a high probability of success.
ABSTRACT
After the new coronavirus has undergone multiple mutations, its infectivity and severity have greatly increased, which has caused great threats and inconvenience to people's production and life. In order to disinfect the isolated area comprehensively, a control system of disinfection robot for epidemic prevention and control is designed. The robot takes STM32 as the main controller, collects and analyses the environmental information by lidar EKF-SLAM. In addition, Improved Ant Colony Algorithm is used for optimal path planning, and 3-DOF robotic arm is carried out to sanitize the designated area. The system can achieve the functions such as mapping, real-time localization, robot distribution and disinfection. The feasibility and superiority of the 3D reconstruction, path planning algorithm and end-effector pose control method are verified by MATLAB simulation. It can reduce the contact frequency of the crowd and the workload of the disinfection staff, and making contributions to epidemic prevention and control further. © 2022 IEEE.
ABSTRACT
OBJECTIVE: The purpose of this study was to determine the extent to which sensory integration strategies via head sway, derived from a Head-Mounted Display (HMD), change in people with vestibular disorders following vestibular rehabilitation. DESIGN: Randomized Controlled TrialSetting:Vestibular Rehabilitation ClinicParticipants:Thirty participants with vestibular dysfunction and 21 age-matched controls. MAIN OUTCOME MEASURES: Participants experienced two levels of visual surround (static or moving 'stars', front to back at 0.2âHz, 32âmm) and white noise (none or rhythmic) while their head sway was recorded via the HTC Vive. We quantified head sway via Directional Path (DP) and Root Mean Square Velocity (RMSV) in 5 directions: anterior-posterior, medio-lateral, pitch, yaw, and roll and Power Spectral Density in low (PSD 1), medium (PSD 2) and high (PSD 3) frequencies in the anterior-posterior direction. INTERVENTIONS: Participants performed the assessment prior to being randomized into 8-weeks of contextual sensory integration training in virtual reality or traditional vestibular rehabilitation and once again following completion of the intervention. Controls performed the assessment once. Twelve participants dropped out, half due to covid lock-down. We applied an intention to treat analysis. RESULTS: We observed significant increases in AP DP, RMSV and all PSDs with change in visual level. Both intervention groups significantly decreased medio-lateral, pitch and roll DP and RMSV and anterior-posterior PSD 2 with no group differences. Vestibular participants were significantly higher than controls on all outcomes pre rehabilitation. Post rehabilitation they were only significantly higher on PSD 2. Sound was not a significant predictor of head sway in this protocol. CONCLUSIONS: Head sway decreased following vestibular rehabilitation regardless of visual load or type of intervention applied. This change was measured via head kinematics derived from a portable HMD which can serve as a sensitive in-clinic assessment for tracking improvement over time.
Subject(s)
COVID-19 , Vestibular Diseases , Humans , Postural Balance , Communicable Disease Control , Treatment OutcomeABSTRACT
The essential part of robots in the medical services framework is principal limiting individual to individual contact defilement and guaranteeing cleaning disinfection. Robots can be defined as an artificially intelligent physical systems capable of interrelating with the environment. The term robot was coined from the Czech what "robota" which implies serf/worker. Robots are classified as Receptionist robots, Surgical robots, Ambulance robots, Service robots, Telemedicine robots. During this pandemic, these mechanical frameworks can diminish the danger of irresistible illness transmission among forefront medical services laborers and afterward make it a potential advance to assess, accentuate, screen, and treat the patients from a safe distance, accordingly bringing down the responsibility of medical care staff. Robots are all around planned with UV light to sanitize the rooms and even themselves. Teleoperated robots in the medical care framework turn into the laborers' eyes, ears, and bodies in the Isolation Ward, which might be dependable during this COVID-19 pandemic. This mechanical innovation will assume a vital part during this basic stage in certain spaces of medical care framework like estimating pulse, oxygen immersion, observing essential signs. Low-cost, miniature robots can be easily assembled and controlled via remote, and this system includes an active end effector, a passive positioning arm and a detachable swap gripper with integrated force sensing capability. Robot execution in the fight against COVID-19 has received positive criticism from medical services laborers for its potential to obstruct disease and is successful in easing clinical specialists from repeated tasks. Copyright © 2022 Society of Pharmaceutical Sciences and Research. All rights reserved.
ABSTRACT
This article is a new robotic arm for cleaning the floor in the toilet with an increased radius of action of the robotic arm type SCARA. The most common current trends in production include short production cycles, low volumes and a wide variety of orders that can be solved with the help of the SCARA robot. With the advent of the COVID-19 virus in the world, the term "cleaning and disinfection" has become one of the most important tools for preventing the population from becoming infected with the virus. The research focuses on the research and implementation of SCARA-type robots and describes the possibilities of using a SCARA-type robot. This article describes the selection and deployment of a SCARA robot in industrial automation. This research project describes the simulation of a new SCARA-type robotic arm with a long reach and sliding mechanism, we have developed a new multi-joint robotic arm for working in confined spaces with an autonomous toilet floor cleaning system.
ABSTRACT
This work reports the design, construction and deployment of a mechatronic system, which, combined with a computer vision module, provides students and teachers with a tool to experience with concepts of kinematics of a particle throughout the usage of a robot, known as to Cinebot, which can be controlled from any smart device endowed with a stable internet connection. The methodology used for envisioning and developing the system was engineering design. The figure of merits of the prototype was evaluated under a linear motion scheme with constant speed (~0.10 m/s), showing errors between 0.08 and 3.2%. © GKA Ediciones, authors.
ABSTRACT
This article develops a stochastic programming framework for multiagent systems, where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with distributed subtasks. Examples include pandemic robotic service coordination, explore and rescue, and delivery systems with heterogeneous vehicles. Owing to their inherent flexibility and robustness, multiagent systems are applied in a growing range of real-world problems that involve heterogeneous tasks and uncertain information. Most previous works assume one fixed way to decompose a task into roles that can later be assigned to the agents. This assumption is not valid for a complex task where the roles can vary and multiple decomposition structures exist. Meanwhile, it is unclear how uncertainties in task requirements and agent capabilities can be systematically quantified and optimized under a multiagent system setting. A representation for complex tasks is proposed: agent capabilities are represented as a vector of random distributions, and task requirements are verified by a generalizable binary function. The conditional value at risk is chosen as a metric in the objective function to generate robust plans. An efficient algorithm is described to solve the model, and the whole framework is evaluated in two different practical test cases: capture-the-flag and robotic service coordination during a pandemic (e.g., COVID-19). Results demonstrate that the framework is generalizable, is scalable up to 140 agents and 40 tasks for the example test cases, and provides low-cost plans that ensure a high probability of success.
ABSTRACT
Under the remote learning mode due to COVID-19, educational laboratory modules lacking the active data acquisition step tend to lose students' engagement and diminish their eagerness to explore further knowledge. Such shortcomings are more profound in practical fields of study, such as Biomechanics. The goal of this paper is to present a remote laboratory delivery and evaluation method where students can apply principles of kinematic and kinetic biomechanical analysis on their own body motions with a computer vision algorithm to interactively solve a motion analysis problem. In this preliminary study, students were given the freedom to choose a specific body motion to be captured and analyzed, such as elbow, knee, wrist, and neck joint movements. Motion specifications included determination of the motion type, and also the starting and ending angular or linear positions. Readily available labels were utilized as passive joint markers. Students were then instructed to video record their joint motions using their laptop cameras. A custom video tracking algorithm specifically designed to track spatial locations was then employed to capture relative positions of the recorded motions. Laboratory instructions asked the students to perform kinematic calculations on the algorithm's generated positional data to determine joint velocities and accelerations, and then perform kinetic analyses to estimate the associated muscle forces. Laboratory requirements were concluded with a reflection prompt to evaluate the activity's workload and effort perceived by the students. These activities were delivered twice in two different academic terms. Samples of the produced kinematic data using our methods were verified in comparison with a standard physical motion capture system, where similar joint motion descriptive results were observed. Results show that the completion rate of laboratory requirements was 97% in the first term of delivery, and 100% in the second term, as supported by the full technical reports submissions that included critical data analysis and reflections of the laboratory experience. Student reflections were very positive and expressed how the lab activity was interesting as it kept a high level of engagement and provided a way to make connections between practice and theory. In conclusion, the proposed approach may improve the students' laboratory experience in learning biomechanics through a motion analysis scenario, and allow them to remotely be fully engaged, active, and passionate learners. © American Society for Engineering Education, 2022.
ABSTRACT
The present work is focused on the development of a Virtual Environment as a test system for new advanced control algorithms for an Unmanned Aerial Vehicles. The virtualized environment allows us to visualize the behavior of the UAV by including the mathematical model of it. The mathematical structure of the kinematic and dynamic models is represented in a matrix form in order to be used in different control algorithms proposals. For the dynamic model, the constants are obtained experimentally, using a DJI Matrice 600 Pro UAV. All of this is conducted with the purpose of using the virtualized environment in educational processes in which, due to the excessive cost of the materials, it is not possible to acquire physical equipment;moreover, is it desired to avoid damaging them. Finally, the stability and robustness of the proposed controllers are determined to ensure analytically the compliance with the control criteria and its correct operation.
ABSTRACT
This study aims to see the effectiveness of using motion diagram-based module to improve students’ conceptual understanding of 1D Kinematics. We have integrated module in online learning during the COVID-19 pandemic. This research was an experimental research with one group pretest-posttest design. The research was conducted on 36 first year Physics undergraduate students. The research instrument consisted of 14 reasoned multiple choice questions. Data analysis was performed using paired sample t-test, N-gain, and d-effect size. The results showed that t = -47.81 [df = 35;sig.(2-tailed) = 0.000] so it can be concluded that students’ understanding of concepts is significantly different. The results of N-gain = 0.543 indicate that the increase is in the upper medium category and the d-effect size = 2.189 indicates that the influence of learning has a strong effect on increasing students’ conceptual understanding. The results of this study indicate that the use of motion diagram-based module can improve students’ conceptual understanding of 1D Kinematics. The students’ conceptual understanding that increased the most significantly was related to compare the velocity of two objects moving in opposite directions. But, many students still have difficulty in determining the instantaneous velocity from the x-t table.
ABSTRACT
Due to the challenges of the IR 4.0 era and the Covid-19 pandemic at the same time, this paper provides a brief review of the published studies predominantly on biodiesel storage tank materials and followed by the Internet of Things (IoT) system as an alternative monitoring method in biodiesel industries. The suitability of storage material for a longer storage duration due to lower oil demands amidst this pandemic becomes a major concern. In this paper, two important parameters: kinematic viscosity and flashpoint in consideration of storage tank materials relating to surrounding conditions and biofuel blends were discussed. It was found that the degradation of fuel in plastic and glass storage tanks is significant for outdoor storage. Over time, the kinematic viscosity of biodiesel shows an increasing trend meanwhile the flashpoint is in decreasing trend or almost constant. However, these physical properties show very limited changes when stored at an ambient temperature. On another note, IoT systems to date are mostly used to detect fuel theft, fuel consumption, fuel impurities, and fuel tank level but are yet to be used to observe the fuel quality under a longer storage period, more than 6 months. IoT solution with suitable embedded sensors has potential to become the advance solution for remote biodiesel quality monitoring, reducing the need for manpower and interaction. This review paper provides necessary information for further investigations on biodiesel stability, storage material, and monitoring advancement systems. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
The physical therapy generally requires direct assistance from therapists continuously, however, the time is very limited. Moreover, the social distancing policy in the COVID-19 pandemic period made the patient could not come to rehabilitation center for physical therapy. Remote physical therapy is suggested to reduce dependency of therapist for conducting the physical therapy. However, there is few information about the necessary parameters in lower limb monitoring of post-stroke patient. Therefore, in this paper, a review for designing a low-cost online homecare physical therapy monitoring system is proposed. Article finding had been done using online search engine Google Scholars to conclude the design of the online monitoring system. Several keywords had been used, such as “online stroke rehabilitation monitoring,” “stroke rehabilitation parameters,” “stroke monitoring Internet of Things,” and “lower limb stroke monitoring.” The results show that the necessary monitor parameters are lower limb kinematics and dynamics, which can be complimented by bio-signal data, such as EMG. The lower limb monitoring system can use IMU, muscle sensor, and footswitches to measure the necessary parameters. IMU measures the lower limb kinematics because it provides wide range of measurement. Muscle sensor, which compatible to microcontroller, measures the EMG. Lastly, the footswitches detect the gait phases, which classify the measured data for more in-depth analysis. The mentioned sensors are cheap and available in the online market of Indonesia, which is suitable to realize a low-cost lower limb monitoring system. The research finding also suggests quick and accurate feedback mechanism for improving the training quality, which the feedback is combination of therapist opinion and artificial intelligence prediction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.