Inadequate sitting posture can cause imbalanced loading on the spine and result in abnormal spinal pressure, which serves as the main risk factor contributing to irreversible and chronic spinal deformity. Therefore, sitting posture recognition is important for understanding people’s sitting behaviors and for correcting inadequate postures. Recently, wearable devices embedded with microelectromechanical systems (MEMs) sensors, such as inertial measurement units (IMUs), have received increased attention in human activity recognition. In this study, a wearable device embedded with IMUs and a machine learning algorithm were developed to classify seven static sitting postures: upright, slump, lean, right and left bending, and right and left twisting. Four 9-axis IMUs were uniformly distributed between thoracic and lumbar regions (T1-L5) and aligned on a sagittal plane to acquire kinematic information about subjects’ backs during static-dynamic alternating motions. Time-domain features served as inputs to a signal-based classification model that was developed using long short-term memory-based recurrent neural network (LSTM-RNN) architecture, and the model’s classification performance was used to evaluate the relevance between sensor signals and sitting postures. Overall results from performance evaluation tests indicate that this IMU-based measurement and LSTM-RNN structural scheme was appropriate for sitting posture recognition.

A suture anchor is a medical device commonly used in rotator cuff repair surgery to attach tendons to the greater tuberosity of the humerus. Patient- and device-related factors, such as structural designs and poor bone density, can cause unsatisfactory clinical results. In this study, a new suture anchor design with four distinctive parameters was proposed, and the structural performance was optimized in a full factorial experimental design using finite element analysis. Two types of bone blocks—normal and osteoporotic bone—which received screw implants, were simulated to investigate the parametrical effects on various bone qualities. The prescribed motion at a constant removal velocity was used to evaluate the pullout strength. The von Mises criterion was employed in a force control simulation for topology optimization. Moreover, mechanical tests guided by ASTM-F543-17 were conducted for validation. This paper demonstrates the comprehensive process for developing a suture anchor with sufficient mechanical integrity for clinical use and clarifies the contributions of each distinctive design parameter in this application.