1-repetition maximum (1RM), a representative index for an individual’s weightlifting capacity, provides an organized workout guide, but to measure 1RM needs several repetitive exercises up to one’s limit and has a risk of injury, thus, not adequate for beginners, elders, or disabled people. This study suggests a simpler and safer 1RM measurement method using a hydraulic fitness machine. We asked twenty-five female subjects with less than a month of experience in weight training to repeat chest exercises using a conventional plate-loaded bench press machine and a hydraulic bench press machine and measured 1RMs. Repeated-measures ANOVA and paired t-test reported the difference between the plate and hydraulic 1RMs insignificant (p-value = 0.082) and confirmed the generality of 1RM across the different types of fitness machines. We then derived several 1RM equations in terms of load weight W and lifting speed v during non-1RM exercise and reduced it to a first-order polynomial expression 1RM=−0.3908+0.8251W+0.1054v with adjusted R-square of 0.8849. Goodness-of-fit test and comparison with 1RM equations from reference studies (v=−1.46×W1RM+1.7035, W1RM×100=7.5786v2−75.865v+113.02) verified our formula valid. We finally simplified the 1RM measurement process up to a maximum of three repetitions.

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.