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.

Biomechanical Effects of Adding an Ankle Soft Actuation in a Unilateral Exoskeleton.

Stroke disease leads to a partial or complete disability affecting muscle strength and functional mobility. Early rehabilitation sessions might induce neuroplasticity and restore the affected function or structure of the patients. Robotic rehabilitation minimizes the burden on therapists by providing repetitive and regularly monitored therapies. Commercial exoskeletons have been found to assist hip and knee motion. For instance, unilateral exoskeletons have the potential to become an effective training system for patients with hemiparesis. However, these robotic devices leave the ankle joint unassisted, essential in gait for body propulsion and weight-bearing. This article evaluates the effects of the robotic ankle orthosis T-FLEX during cooperative assistance with the AGoRA unilateral lower-limb exoskeleton (hip and knee actuation). This study involves nine subjects, measuring muscle activity and gait parameters such as stance and swing times. The results showed a reduction in muscle activity in the Biceps Femoris of 50%, Lateral Gastrocnemius of 59% and Tibialis Anterior of 35% when adding T-FLEX to the AGoRA unilateral lower-limb exoskeleton. No differences were found in gait parameters. Nevertheless, stability is preserved when comparing the two legs. Future works should focus on evaluating the devices in ground tests in healthy subjects and pathological patients.

Assessment of a Robotic Walker in Older Adults With Parkinson's Disease in Daily Living Activities.

The constant growth of the population with mobility impairments, such as older adults and people suffering from neurological pathologies like Parkinson's disease (PD), has encouraged the development of multiple devices for gait assistance. Robotic walkers have emerged, improving physical stability and balance and providing cognitive aid in rehabilitation scenarios. Different studies evaluated human gait behavior with passive and active walkers to understand such rehabilitation processes. However, there is no evidence in the literature of studies with robotic walkers in daily living scenarios with older adults with Parkinson's disease. This study presents the assessment of the AGoRA Smart Walker using Ramps Tests and Timed Up and Go Test (TUGT). Ten older adults participated in the study, four had PD, and the remaining six had underlying conditions and fractures. Each of them underwent a physical assessment (i.e., Senior Fitness, hip, and knee strength tests) and then interacted with the AGoRA SW. Kinematic and physical interaction data were collected through the AGoRA walker's sensory interface. It was found that for lower limb strength tests, older adults with PD had increases of at least 15% in all parameters assessed. For the Sit to Stand Test, the Parkinson's group evidenced an increase of 23%, while for the Chair Sit and Reach Test (CSRT), this same group was only 0.04 m away from reaching the target. For the Ramp Up Test (RUT), the subjects had to make a greater effort, and significant differences (p-value = 0.04) were evidenced in the force they applied to the device. For the Ramp Down Test (RDT), the Parkinson's group exhibited a decrease in torque, and there were statistically significant differences (p-value = 0.01) due to the increase in the complexity of the task. In the Timed Up and Go Test (TUGT), the subjects presented significant differences in torque (p-value of 0.05) but not in force (p-value of 0.22) due to the effect of the admittance controller implemented in the study. Finally, the results suggested that the walker, represents a valuable tool for assisting people with gait motor deficits in tasks that demanded more physical effort adapting its behavior to the specific needs of each user.