Journal Articles
Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915
Browse
3 results
Search Results
Item Efficient Limb Range of Motion Analysis from a Monocular Camera for Edge Devices.(MDPI (Basel, Switzerland), 2025-01-22) Yan X; Zhang L; Liu B; Qu G; Amerini I; Russo P; Di Ciaccio FTraditional limb kinematic analysis relies on manual goniometer measurements. With computer vision advancements, integrating RGB cameras can minimize manual labor. Although deep learning-based cameras aim to offer the same ease as manual goniometers, previous approaches have prioritized accuracy over efficiency and cost on PC-based devices. Nevertheless, healthcare providers require a high-performance, low-cost, camera-based tool for assessing upper and lower limb range of motion (ROM). To address this, we propose a lightweight, fast, deep learning model to estimate a human pose and utilize predicted joints for limb ROM measurement. Furthermore, the proposed model is optimized for deployment on resource-constrained edge devices, balancing accuracy and the benefits of edge computing like cost-effectiveness and localized data processing. Our model uses a compact neural network architecture with 8-bit quantized parameters for enhanced memory efficiency and reduced latency. Evaluated on various upper and lower limb tasks, it runs 4.1 times faster and is 15.5 times smaller than a state-of-the-art model, achieving satisfactory ROM measurement accuracy and agreement with a goniometer. We also conduct an experiment on a Raspberry Pi, illustrating that the method can maintain accuracy while reducing equipment and energy costs. This result indicates the potential for deployment on other edge devices and provides the flexibility to adapt to various hardware environments, depending on diverse needs and resources.Item Reinventing the wheel for a manual wheelchair.(Taylor and Francis Group, 2023-11-02) Flemmer CL; Flemmer RCPurpose Standard manual wheelchairs (MWCs) are inefficient and pushrim propulsion may cause progressive damage and pain to the user’s arms. We describe a wheel for a MWC with a novel propulsion mechanism. Methods The wheel has two modes of operation called “Standard” mode and “Run” mode. In Run mode, the wheelchair is propelled forward by pushing a compliant handle forward and then pulling it back, both strokes contributing to forward propulsion. We report the propulsive force and preliminary testing on a rough outdoor circuit by three able-bodied participants. Results In Run mode, the peak applied force is reduced to 30% and the maximum force gradient is reduced to 10% of that for standard pushrim propulsion, for the same work output. The travel time for the 1.06 km outdoor circuit is about 60% of that for a brisk walk and about 40% of that for pushrim propulsion. At a propulsion speed of 1 m/s, the cardiovascular effort in Run mode is 56% of that for pushrim propulsion. Automatic hill-hold in Run mode improves safety when ascending slopes. The mechanism has three gears so that it can be used by people with widely varying strength and fitness. Folding the handle away converts the operation to Standard mode with the conventional pushrim propulsion, supplemented by three gears. Conclusions Despite the increased weight, width and friction, the bimodal geared wheels facilitate wheelchair travel on challenging paths. This may bring significant improvement to the quality of life of MWC users.Item Biomechanical comparison of titanium alloy additively manufactured and conventionally manufactured plate-screw constructs.(Taylor and Francis Group, 2023-12-10) Polak S; Beever L; Wade A; Fukuoka M; Worth AJAIM: To biomechanically compare the bending stiffness, strength, and cyclic fatigue of titanium additively manufactured (AM) and conventionally manufactured (CM) limited contact plates (LCP) of equivalent dimensions using plate-screw constructs. METHODS: Twenty-four 1.5/2.0-mm plate constructs (CM: n = 12; AM: n = 12) were placed under 4-point bending conditions. Data were collected during quasi-static single cycle to failure and cyclic fatigue testing until implants plastically deformed or failed. Bending stiffness, bending structural stiffness, and bending strength were determined from load-displacement curves. Fatigue life was determined as number of cycles to failure. Median test variables for each method were compared using the Wilcoxon rank sum test within each group. Fatigue data was also analysed by the Kaplan-Meier estimator of survival function. RESULTS: There was no evidence for a difference in bending stiffness and bending structural stiffness between AM and CM constructs. However, AM constructs exhibited greater bending strength (median 3.07 (min 3.0, max 3.4) Nm) under quasi-static 4-point bending than the CM constructs (median 2.57 (min 2.5, max 2.6) Nm, p = 0.006). Number of cycles to failure under dynamic 4-point bending was higher for the CM constructs (median 164,272 (min 73,557, max 250,000) cycles) than the AM constructs (median 18,704 (min 14,427, max 33,228) cycles; p = 0.02). Survival analysis showed that 50% of AM plates failed by 18,842 cycles, while 50% CM plates failed by 78,543 cycles. CONCLUSION AND CLINICAL RELEVANCE: Additively manufactured titanium implants, printed to replicate a conventional titanium orthopaedic plate, were more prone to failure in a shorter fatigue period despite being stronger in single cycle to failure. Patient-specific implants made using this process may be brittle and therefore not comparable to CM orthopaedic implants. Careful selection of their use on a case/patient-specific basis is recommended.