Resistance bands are widely used nowadays to enhance muscle strength due to their high portability, but the relationship between resistance band workouts and conventional dumbbell weight training is still unclear. Thus, this study suggests a convolutional neural network model that identifies the type of band workout and counts the number of repetitions and a regression model that deduces the band force that corresponds to the one-repetition maximum. Thirty subjects performed five different exercises using resistance bands and dumbbells. Joint movements during each exercise were collected using a camera and an inertial measurement unit. By using different types of input data, several models were created and compared. As a result, the accuracy of the convolutional neural network model using inertial measurement units and joint position is 98.83%. The mean absolute error of the repetition counting algorithm ranges from 0.88 (seated row) to 3.21 (overhead triceps extension). Lastly, the values of adjusted r-square for the 5 exercises are 0.8415 (chest press), 0.9202 (shoulder press), 0.8429 (seated row), 0.8778 (biceps curl), and 0.9232 (overhead triceps extension). In conclusion, the model using 10-channel inertial measurement unit data and joint position data has the best accuracy. However, the model needs to improve the inaccuracies resulting from non-linear movements and one-time performance.
This study departs from the conventional research on horizontal plane reach movements by examining human motor control strategies in vertical plane elastic load reach movements conducted without visual feedback. Here, participants performed shoulder presses with elastic resistances at low, moderate, and high intensities without access to visual information about their hand position, relying exclusively on proprioceptive feedback and synchronizing their movements with a metronome set at a 3 s interval. The results revealed consistent performance symmetry across different intensities in terms of the reach speed (p = 0.254–0.736), return speed (p = 0.205–0.882), and movement distance (p = 0.480–0.919). This discovery underscores the human capacity to uphold bilateral symmetry in movement execution when relying solely on proprioception. Furthermore, this study observed an asymmetric velocity profile where the reach duration remained consistent irrespective of the load (1.15 s), whereas the return duration increased with higher loads (1.39 s–1.45 s). These findings suggest that, in the absence of visual feedback, the asymmetric velocity profile does not result from the execution of the action but rather represents a deliberate deceleration post-reach aimed at achieving the target position as generated by the brain’s internal model. These findings hold significant implications for interpreting rehabilitation approaches under settings devoid of visual feedback.