Data-Driven Approach for Upper Limb Fatigue Estimation Based on Wearable Sensors.

Muscle fatigue is defined as a reduced ability to maintain maximal strength during voluntary contraction. It is associated with musculoskeletal disorders that affect workers performing repetitive activities, affecting their performance and well-being. Although electromyography remains the gold standard for measuring muscle fatigue, its limitations in long-term work motivate the use of wearable devices. This article proposes a computational model for estimating muscle fatigue using wearable and non-invasive devices, such as Optical Fiber Sensors (OFSs) and Inertial Measurement Units (IMUs) along the subjective Borg scale. Electromyography (EMG) sensors are used to observe their importance in estimating muscle fatigue and comparing performance in different sensor combinations. This study involves 30 subjects performing a repetitive lifting activity with their dominant arm until reaching muscle fatigue. Muscle activity, elbow angles, and angular and linear velocities, among others, are measured to extract multiple features. Different machine learning algorithms obtain a model that estimates three fatigue states (low, moderate and high). Results showed that between the machine learning classifiers, the LightGBM presented an accuracy of 96.2% in the classification task using all of the sensors with 33 features and 95.4% using only OFS and IMU sensors with 13 features. This demonstrates that elbow angles, wrist velocities, acceleration variations, and compensatory neck movements are essential for estimating muscle fatigue. In conclusion, the resulting model can be used to estimate fatigue during heavy lifting in work environments, having the potential to monitor and prevent muscle fatigue during long working shifts.

Development of a 3D Relative Motion Method for Human-Robot Interaction Assessment.

Exoskeletons have been assessed by qualitative and quantitative features known as performance indicators. Within these, the ergonomic indicators have been isolated, creating a lack of methodologies to analyze and assess physical interfaces. In this sense, this work presents a three-dimensional relative motion assessment method. This method quantifies the difference of orientation between the user's limb and the exoskeleton link, providing a deeper understanding of the Human-Robot interaction. To this end, the AGoRA exoskeleton was configured in a resistive mode and assessed using an optoelectronic system. The interaction quantified a difference of orientation considerably at a maximum value of 41.1 degrees along the sagittal plane. It extended the understanding of the Human-Robot Interaction throughout the three principal human planes. Furthermore, the proposed method establishes a performance indicator of the physical interfaces of an exoskeleton.

Predicting Perceived Exhaustion in Rehabilitation Exercises Using Facial Action Units.

Physical exercise has become an essential tool for treating various non-communicable diseases (also known as chronic diseases). Due to this, physical exercise allows to counter different symptoms and reduce some risk of death factors without medication. A solution to support people in doing exercises is to use artificial systems that monitor their exercise progress. While one crucial aspect is to monitor the correct physical motions for rehabilitative exercise, another essential element is to give encouraging feedback during workouts. A coaching system can track a user's exhaustion and give motivating feedback accordingly to boost exercise adherence. For this purpose, this research investigates whether it is possible to predict the subjective exhaustion level based on non-invasive and non-wearable technology. A novel data set was recorded with the facial record as the primary predictor and individual exhaustion levels as the predicted variable. 60 participants (30 male, 30 female) took part in the data recording. 17 facial action units (AU) were extracted as predictor variables for the perceived subjective exhaustion measured using the BORG scale. Using the predictor and the target variables, several regression and classification methods were evaluated aiming to predict exhaustion. The results showed that the decision tree and support vector methods provide reasonable prediction results. The limitation of the results, depending on participants being in the training data set and subjective variables (e.g., participants smiling during the exercises) were further discussed.

Biomechanical Assessment of Post-Stroke Patients' Upper Limb before and after Rehabilitation Therapy Based on FES and VR.

Stroke is a medical condition characterized by the rapid loss of focal brain function. Post-stroke patients attend rehabilitation training to prevent the degeneration of physical function and improve upper limb movements and functional status after stroke. Promising rehabilitation therapies include functional electrical stimulation (FES), exergaming, and virtual reality (VR). This work presents a biomechanical assessment of 13 post-stroke patients with hemiparesis before and after rehabilitation therapy for two months with these three methods. Patients performed two tests (Maximum Forward Reach and Apley Scratching) where maximum angles, range of motion, angular velocities, and execution times were measured. A Wilcoxon test was performed (p = 0.05) to compare the variables before and after the therapy for paretic and non-paretic limbs. Significant differences were found in range of motion in flexion-extension, adduction-abduction, and internal-external rotation of the shoulder. Increases were found in flexion-extension, 17.98%, and internal-external rotation, 18.12%, after therapy in the Maximum Forward Reach Test. For shoulder adduction-abduction, the increase found was 20.23% in the Apley Scratching Test, supporting the benefits of rehabilitation therapy that combines FES, exergaming, and VR in the literature.

A Data-Driven Approach to Physical Fatigue Management Using Wearable Sensors to Classify Four Diagnostic Fatigue States.

Physical exercise contributes to the success of rehabilitation programs and rehabilitation processes assisted through social robots. However, the amount and intensity of exercise needed to obtain positive results are unknown. Several considerations must be kept in mind for its implementation in rehabilitation, as monitoring of patients' intensity, which is essential to avoid extreme fatigue conditions, may cause physical and physiological complications. The use of machine learning models has been implemented in fatigue management, but is limited in practice due to the lack of understanding of how an individual's performance deteriorates with fatigue; this can vary based on physical exercise, environment, and the individual's characteristics. As a first step, this paper lays the foundation for a data analytic approach to managing fatigue in walking tasks. The proposed framework establishes the criteria for a feature and machine learning algorithm selection for fatigue management, classifying four fatigue diagnoses states. Based on the proposed framework and the classifier implemented, the random forest model presented the best performance with an average accuracy of ≥98% and F-score of ≥93%. This model was comprised of ≤16 features. In addition, the prediction performance was analyzed by limiting the sensors used from four IMUs to two or even one IMU with an overall performance of ≥88%.

Evaluation of Physical Interaction during Walker-Assisted Gait with the AGoRA Walker: Strategies Based on Virtual Mechanical Stiffness.

Smart walkers are commonly used as potential gait assistance devices, to provide physical and cognitive assistance within rehabilitation and clinical scenarios. To understand such rehabilitation processes, several biomechanical studies have been conducted to assess human gait with passive and active walkers. Several sessions were conducted with 11 healthy volunteers to assess three interaction strategies based on passive, low and high mechanical stiffness values on the AGoRA Smart Walker. The trials were carried out in a motion analysis laboratory. Kinematic data were also collected from the smart walker sensory interface. The interaction force between users and the device was recorded. The force required under passive and low stiffness modes was 56.66% and 67.48% smaller than the high stiffness mode, respectively. An increase of 17.03% for the hip range of motion, as well as the highest trunk's inclination, were obtained under the resistive mode, suggesting a compensating motion to exert a higher impulse force on the device. Kinematic and physical interaction data suggested that the high stiffness mode significantly affected the users' gait pattern. Results suggested that users compensated their kinematics, tilting their trunk and lower limbs to exert higher impulse forces on the device.

Machine Learning Approach for Fatigue Estimation in Sit-to-Stand Exercise.

Physical exercise (PE) has become an essential tool for different rehabilitation programs. High-intensity exercises (HIEs) have been demonstrated to provide better results in general health conditions, compared with low and moderate-intensity exercises. In this context, monitoring of a patients' condition is essential to avoid extreme fatigue conditions, which may cause physical and physiological complications. Different methods have been proposed for fatigue estimation, such as: monitoring the subject's physiological parameters and subjective scales. However, there is still a need for practical procedures that provide an objective estimation, especially for HIEs. In this work, considering that the sit-to-stand (STS) exercise is one of the most implemented in physical rehabilitation, a computational model for estimating fatigue during this exercise is proposed. A study with 60 healthy volunteers was carried out to obtain a data set to develop and evaluate the proposed model. According to the literature, this model estimates three fatigue conditions (low, moderate, and high) by monitoring 32 STS kinematic features and the heart rate from a set of ambulatory sensors (Kinect and Zephyr sensors). Results show that a random forest model composed of 60 sub-classifiers presented an accuracy of 82.5% in the classification task. Moreover, results suggest that the movement of the upper body part is the most relevant feature for fatigue estimation. Movements of the lower body and the heart rate also contribute to essential information for identifying the fatigue condition. This work presents a promising tool for physical rehabilitation.

BCI-Based Control for Ankle Exoskeleton T-FLEX: Comparison of Visual and Haptic Stimuli with Stroke Survivors.

Brain-computer interface (BCI) remains an emerging tool that seeks to improve the patient interaction with the therapeutic mechanisms and to generate neuroplasticity progressively through neuromotor abilities. Motor imagery (MI) analysis is the most used paradigm based on the motor cortex's electrical activity to detect movement intention. It has been shown that motor imagery mental practice with movement-associated stimuli may offer an effective strategy to facilitate motor recovery in brain injury patients. In this sense, this study aims to present the BCI associated with visual and haptic stimuli to facilitate MI generation and control the T-FLEX ankle exoskeleton. To achieve this, five post-stroke patients (55-63 years) were subjected to three different strategies using T-FLEX: stationary therapy (ST) without motor imagination, motor imagination with visual stimulation (MIV), and motor imagination with visual-haptic inducement (MIVH). The quantitative characterization of both BCI stimuli strategies was made through the motor imagery accuracy rate, the electroencephalographic (EEG) analysis during the MI active periods, the statistical analysis, and a subjective patient's perception. The preliminary results demonstrated the viability of the BCI-controlled ankle exoskeleton system with the beta rebound, in terms of patient's performance during MI active periods and satisfaction outcomes. Accuracy differences employing haptic stimulus were detected with an average of 68% compared with the 50.7% over only visual stimulus. However, the power spectral density (PSD) did not present changes in prominent activation of the MI band but presented significant variations in terms of laterality. In this way, visual and haptic stimuli improved the subject's MI accuracy but did not generate differential brain activity over the affected hemisphere. Hence, long-term sessions with a more extensive sample and a more robust algorithm should be carried out to evaluate the impact of the proposed system on neuronal and motor evolution after stroke.

Semi-Remote Gait Assistance Interface: A Joystick with Visual Feedback Capabilities for Therapists.

The constant growth of pathologies affecting human mobility has led to developing of different assistive devices to provide physical and cognitive assistance. Smart walkers are a particular type of these devices since they integrate navigation systems, path-following algorithms, and user interaction modules to ensure natural and intuitive interaction. Although these functionalities are often implemented in rehabilitation scenarios, there is a need to actively involve the healthcare professionals in the interaction loop while guaranteeing safety for them and patients. This work presents the validation of two visual feedback strategies for the teleoperation of a simulated robotic walker during an assisted navigation task. For this purpose, a group of 14 clinicians from the rehabilitation area formed the validation group. A simple path-following task was proposed, and the feedback strategies were assessed through the kinematic estimation error (KTE) and a usability survey. A KTE of 0.28 m was obtained for the feedback strategy on the joystick. Additionally, significant differences were found through a Mann-Whitney-Wilcoxon test for the perception of behavior and confidence towards the joystick according to the modes of interaction (p-values of 0.04 and 0.01, respectively). The use of visual feedback with this tool contributes to research areas such as remote management of therapies and monitoring rehabilitation of people's mobility.

Evaluation of biomechanical gait parameters of patients with Cerebral Palsy at three different levels of gait assistance using the CPWalker.

BACKGROUND: Cerebral Palsy (CP) is the most common cause of permanent serious physical disability in childhood. Although many platforms have been developed, so far there are still not precise guidelines for the rehabilitation of the population with CP. The CPWalker is a robotic platform for the rehabilitation of children with CP, through which they can start experiencing autonomous locomotion in the rehabilitation environment. It allows the possibility of free movement and includes physical and cognitive interfaces into the therapy. The main objective of this work is to evaluate the effects of the CPWalker-based rehabilitation intervention in children with CP by comparing different gait parameters before, during and after the use of the platform. FINDINGS: The evaluation was divided in three stages where the gait parameters and symmetry indexes of eight subjects with CP were evaluated. In the first stage patients walked only with the help they receive normally in daily life. During the second stage they walked with the CPWalker and finally, in the third stage, they repeated their gait without the platform. In all stages they wore an inertial G-Sensor Ⓡ while walking through the hospital facilities. The results showed statistical significant differences in several spatio-temporal parameters, pelvic angles and general gait cycle parameters, with and without the use of the robotic device. For the eight patients: cadence, speed and stride length presented similar values when comparing before and after the therapy. However, they decreased during the intervention (both means and standard deviations). No significant differences were found in the symmetry indexes with the use of the platform. In spite of this, a reduction in the pelvic angles ranges and propulsion was observed. CONCLUSIONS: The effect of using the device was analyzed for spatio-temporal parameters, pelvic girdle angles and general gait cycle parameters. Among the eighteen initial parameters, seven presented a statistical significant difference when comparing stage 2 of the intervention with stages 1 and 3. Those changes showed the potential of the CPWalker to improve muscular strength and gait patterns of the patients with CP in the long term and to provide useful information for the design of the future generations of rehabilitation robotic devices.

Human-Robot-Environment Interaction Interface for Smart Walker Assisted Gait: AGoRA Walker.

The constant growth of the population with mobility impairments has led to the development of several gait assistance devices. Among these, smart walkers have emerged to provide physical and cognitive interactions during rehabilitation and assistance therapies, by means of robotic and electronic technologies. In this sense, this paper presents the development and implementation of a human-robot-environment interface on a robotic platform that emulates a smart walker, the AGoRA Walker. The interface includes modules such as a navigation system, a human detection system, a safety rules system, a user interaction system, a social interaction system and a set of autonomous and shared control strategies. The interface was validated through several tests on healthy volunteers with no gait impairments. The platform performance and usability was assessed, finding natural and intuitive interaction over the implemented control strategies.

Gait Phase Detection for Lower-Limb Exoskeletons using Foot Motion Data from a Single Inertial Measurement Unit in Hemiparetic Individuals.

Due to the recent rise in the use of lower-limb exoskeletons as an alternative for gait rehabilitation, gait phase detection has become an increasingly important feature in the control of these devices. In addition, highly functional, low-cost recovery devices are needed in developing countries, since limited budgets are allocated specifically for biomedical advances. To achieve this goal, this paper presents two gait phase partitioning algorithms that use motion data from a single inertial measurement unit (IMU) placed on the foot instep. For these data, sagittal angular velocity and linear acceleration signals were extracted from nine healthy subjects and nine pathological subjects. Pressure patterns from force sensitive resistors (FSR) instrumented on a custom insole were used as reference values. The performance of a threshold-based (TB) algorithm and a hidden Markov model (HMM) based algorithm, trained by means of subject-specific and standardized parameters approaches, were compared during treadmill walking tasks in terms of timing errors and the goodness index. The findings indicate that HMM outperforms TB for this hardware configuration. In addition, the HMM-based classifier trained by an intra-subject approach showed excellent reliability for the evaluation of mean time, i.e., its intra-class correlation coefficient (ICC) was greater than 0 . 75 . In conclusion, the HMM-based method proposed here can be implemented for gait phase recognition, such as to evaluate gait variability in patients and to control robotic orthoses for lower-limb rehabilitation.

Analysis of muscular activity and dynamic response of the lower limb adding vibration to cycling.

Vibration in cycling has been proved to have undesirable effects over health, comfort and performance of the rider. In this study, 15 participants performed eight 6-min sub-maximal pedalling exercises at a constant power output (150W) and pedalling cadence (80 RPM) being exposed to vibration at different frequencies (20, 30, 40, 50, 60, 70 Hz) or without vibration. Oxygen uptake (VO2), heart rate (HR), surface EMG activity of seven lower limb muscles (GMax, RF, BF, VM, GAS, SOL and TA) and 3-dimentional accelerations at ankle, knee and hip were measured during the exercises. To analyse the dynamic response, the influence of the pedalling movement was taken into account. The results show that there was not significant influence of vibrations on HR and VO2 during this pedalling exercise. However, muscular activity presents a significant increase with the presence of vibration that is influenced by the frequency, but this increase was very low (< 1%). Also, the dynamic response shows an influence of the frequency as well as an influence of the different parts of the pedalling cycle. Those results help to explain the effects of vibration on the human body and the influence of the rider/bike interaction in those effects.

A Freirean liberatory perspective of community colleges education: critical consciousness and social justice science issues in the biology curriculum.

This paper discusses the value of a Freirean liberatory perspective in community colleges, countering the traditional "second chance" or "social reproduction" viewpoints attributed by scholars to the education offered in these institutions, emphasizing its vital need in science and healthcare careers education. I explore the potential of this perspective by providing illustrative examples from a biology course incorporating social justice science issues in the curriculum to examine their relationship in cultivating students' critical consciousness at a community college with a programmatic emphasis on healthcare professions.

Effects of stance control via hidden Markov model-based gait phase detection on healthy users of an active hip-knee exoskeleton.

Introduction: In the past years, robotic lower-limb exoskeletons have become a powerful tool to help clinicians improve the rehabilitation process of patients who have suffered from neurological disorders, such as stroke, by applying intensive and repetitive training. However, active subject participation is considered to be an important feature to promote neuroplasticity during gait training. To this end, the present study presents the performance assessment of the AGoRA exoskeleton, a stance-controlled wearable device designed to assist overground walking by unilaterally actuating the knee and hip joints. Methods: The exoskeleton's control approach relies on an admittance controller, that varies the system impedance according to the gait phase detected through an adaptive method based on a hidden Markov model. This strategy seeks to comply with the assistance-as-needed rationale, i.e., an assistive device should only intervene when the patient is in need by applying Human-Robot interaction (HRI). As a proof of concept of such a control strategy, a pilot study comparing three experimental conditions (i.e., unassisted, transparent mode, and stance control mode) was carried out to evaluate the exoskeleton's short-term effects on the overground gait pattern of healthy subjects. Gait spatiotemporal parameters and lower-limb kinematics were captured using a 3D-motion analysis system Vicon during the walking trials. Results and Discussion: By having found only significant differences between the actuated conditions and the unassisted condition in terms of gait velocity (ρ = 0.048) and knee flexion (ρ ≤ 0.001), the performance of the AGoRA exoskeleton seems to be comparable to those identified in previous studies found in the literature. This outcome also suggests that future efforts should focus on the improvement of the fastening system in pursuit of kinematic compatibility and enhanced compliance.

Mechanical assessment of novel compliant mechanisms for underactuated prosthetic hands.

This paper proposes novel compliant mechanisms for constructing hand prostheses based on soft robotics. Two models of prosthetic hands are developed in this work. Three mechanical evaluations are performed to determine the suitability of the two designs for carrying out activities of daily living (ADLs). The first test measures the grip force that the prosthesis can generate on objects. The second determines the energy required and dissipated from the prosthesis to operate. The third test identifies the maximum traction force that the prosthesis can support. The tests showed that the PrHand1 prosthesis has a maximum grip force of 23.38 ± 1.5 N, the required energy is 0.76 ± 0.13 J, and the dissipated energy is 0.21 ± 0.17 J. It supports a traction force of 173.31 ± 5.7 N. The PrHand2 prosthesis has a maximum grip force of 36.13 ± 2.3 N, the required energy is 1.28 ± 0.13 J, the dissipated energy is 0.96 ± 0.12 J, and it supports a traction force of 78.48 ± 0 N. In conclusion, the PrHand1 prosthesis has a better performance in terms of energy and tensile force supported. The difference between the energy and traction force results is related to two design features of the PrHand2: fully silicone-coated fingers and a unifying mechanism that requires more force on the tendons to close the prosthesis. The grip force of the PrHand2 prosthesis was more robust than the PrHand1 due to its silicone coating, which allowed for an improved grip.

Neuro-Rehabilitation Therapy with T-FLEX Ankle Exoskeleton and Serious Games: A Case Study.

Acquired Brain Injury (ABI) causes permanent disabilities, such as foot drop. This condition affects the gait pattern, increasing the metabolic cost and risk of falling. Robotics with serious games has shown promising results in the gait rehabilitation context. This paper aims to analyze the effects of using the T-FLEX exoskeleton with (1) Automated Therapy (AT) and (2) Serious Game Therapy (SGT) in two ABI patients. Each participant completed six assisted sessions for each strategy. Results showed that AT increases the user-robot interaction torque by 10% for the first patient and 70% for the second patient, and SGT decreases by 5% for both patients. This way, SGT required the patient to generate torque to execute the ankle movement, while AT did the opposite, resulting in greater device assistance. In the functional assessment, SGT induced variations greater than 50% for the paretic ankle and knee's range of motion (ROM), indicating a potential for motor recovery. Thus, SGT led to improved ankle control and increased gait speed compared to AT. These findings suggest that SGT may be an effective rehabilitation strategy for ABI-related foot drop patients.

Personalised socially assistive robot for cardiac rehabilitation: Critical reflections on long-term interactions in the real world.

Lack of motivation and low adherence rates are critical concerns of long-term rehabilitation programmes, such as cardiac rehabilitation. Socially assistive robots are known to be effective in improving motivation in therapy. However, over longer durations, generic and repetitive behaviours by the robot often result in a decrease in motivation and engagement, which can be overcome by personalising the interaction, such as recognising users, addressing them with their name, and providing feedback on their progress and adherence. We carried out a real-world clinical study, lasting 2.5 years with 43 patients to evaluate the effects of using a robot and personalisation in cardiac rehabilitation. Due to dropouts and other factors, 26 patients completed the programme. The results derived from these patients suggest that robots facilitate motivation and adherence, enable prompt detection of critical conditions by clinicians, and improve the cardiovascular functioning of the patients. Personalisation is further beneficial when providing high-intensity training, eliciting and maintaining engagement (as measured through gaze and social interactions) and motivation throughout the programme. However, relying on full autonomy for personalisation in a real-world environment resulted in sensor and user recognition failures, which caused negative user perceptions and lowered the perceived utility of the robot. Nonetheless, personalisation was positively perceived, suggesting that potential drawbacks need to be weighed against various benefits of the personalised interaction.

A fabric-based soft hand exoskeleton for assistance: the ExHand Exoskeleton.

Introduction: The rise of soft robotics has driven the development of devices for assistance in activities of daily living (ADL). Likewise, different types of actuation have been developed for safer human interaction. Recently, textile-based pneumatic actuation has been introduced in hand exoskeletons for features such as biocompatibility, flexibility, and durability. These devices have demonstrated their potential use in assisting ADLs, such as the degrees of freedom assisted, the force exerted, or the inclusion of sensors. However, performing ADLs requires the use of different objects, so exoskeletons must provide the ability to grasp and maintain stable contact with a variety of objects to lead to the successful development of ADLs. Although textile-based exoskeletons have demonstrated significant advancements, the ability of these devices to maintain stable contact with a variety of objects commonly used in ADLs has yet to be fully evaluated. Materials and methods: This paper presents the development and experimental validation in healthy users of a fabric-based soft hand exoskeleton through a grasping performance test using The Anthropomorphic Hand Assessment Protocol (AHAP), which assesses eight types of grasping with 24 objects of different shapes, sizes, textures, weights, and rigidities, and two standardized tests used in the rehabilitation processes of post- stroke patients. Results and discussion: A total of 10 healthy users (45.50 ± 14.93 years old) participated in this study. The results indicate that the device can assist in developing ADLs by evaluating the eight types of grasps of the AHAP. A score of 95.76 ± 2.90% out of 100% was obtained for the Maintaining Score, indicating that the ExHand Exoskeleton can maintain stable contact with various daily living objects. In addition, the results of the user satisfaction questionnaire indicated a positive mean score of 4.27 ± 0.34 on a Likert scale ranging from 1 to 5.

Do different robot appearances change emotion recognition in children with ASD?

Introduction: Socially Assistive Robotics has emerged as a potential tool for rehabilitating cognitive and developmental disorders in children with autism. Social robots found in the literature are often able to teach critical social skills, such as emotion recognition and physical interaction. Even though there are promising results in clinical studies, there is a lack of guidelines on selecting the appropriate robot and how to design and implement the child-robot interaction. Methods: This work aims to evaluate the impacts of a social robot designed with three different appearances according to the results of a participatory design (PD) process with the community. A validation study in the emotion recognition task was carried out with 21 children with autism. Results: Spectrum disorder results showed that robot-like appearances reached a higher percentage of children's attention and that participants performed better when recognizing simple emotions, such as happiness and sadness. Discussion: This study offers empirical support for continuing research on using SAR to promote social interaction with children with ASD. Further long-term research will help to identify the differences between high and low-functioning children.