The spine is an important part of the human body. Thus, its curvature and shape are closely monitored, and treatment is required if abnormalities are detected. However, the current method of spinal examination mostly relies on two-dimensional static imaging, which does not provide real-time information on dynamic spinal behaviour. Therefore, this study explored an easier and more efficient method based on machine learning and sensors to determine the curvature of the spine. Fifteen participants were recruited and performed tests to generate data for training a neural network. This estimated the spinal curvature from the readings of three inertial measurement units and had an average absolute error of 0.261161 cm.

The measurement and prediction of breast skin deformation are key research directions in health-related research areas, such as cosmetic and reconstructive surgery and sports biomechanics. However, few studies have provided a systematic analysis on the deformations of aging breasts. Thus, this study has developed a model order reduction approach to predict the real-time strain of the breast skin of seniors during movement. Twenty-two women who are on average 62 years old participated in motion capture experiments, in which eight body variables were first extracted by using the gray relational method. Then, backpropagation artificial neural networks were built to predict the strain of the breast skin. After optimization, the R-value for the neural network model reached 0.99, which is within acceptable accuracy. The computer-aided system of this study is validated as a robust simulation approach for conducting biomechanical analyses and predicting breast deformation.