Sarcopenia is a progressive and generalized skeletal muscle disorder associated with poor health outcomes in older adults. However, its association with the risk of fracture risk is yet to be clarified. Therefore, this study aimed to assess the incidence and consequence of osteoporosis-related fractures among patients with sarcopenia in Taiwan. A retrospective, population-based study on 616 patients with sarcopenia, aged >40 years, and 1232 individuals without sarcopenia was conducted to evaluate claims data from Taiwan’s National Health Insurance Research Database collected in the period January 2000–December 2013. The incidence rate of osteoporosis-related fracture was 18.13 and 14.61 per 1000 person years in the patients with sarcopenia and comparison cohort, respectively. Patients with sarcopenia had a greater osteoporotic fracture risk (adjusted hazard ratio [HR] 2.11; 95% confidence interval [CI] 1.47–3.04) after correcting for possible confounding. Additionally, females showed statistically significant correlations of sarcopenia with osteoporosis-related fracture risk (HR 1.53; CI 0.83–2.8 for males and HR 2.40, CI 1.51–3.81 for females). During this retrospective study on the fracture risk in Taiwan, an adverse impact of sarcopenia was observed, which substantiates the need to work toward sarcopenia prevention and interventions to reverse fracture susceptibility in patients with sarcopenia.

Muscle dysfunction, skeletal muscle fibrosis, and disability are associated with weakness in patients with end-stage renal disease. The main purpose of this study was to validate the effectiveness of a proposed system for gait monitoring on short-distance 1.5 m walkways in a dialysis center. Gaits with reduced speed and stride length, long sit-to-stand time (SST), two forward angles, and two unbalanced gait regions are defined in the proposed Kinect v3 gait measurement and analysis system (K3S) and have been considered clinical features in end-stage renal disease (ESRD) associated with poor dialysis outcomes. The stride and pace calibrations of the Kinect v3 system are based on the Zeno Walkway. Its single rating intraclass correlation (ICC) for the stride is 0.990, and its single rating ICC for the pace is 0.920. The SST calibration of Kinect v3 is based on a pressure insole; its single rating ICC for the SST is 0.871. A total of 75 patients on chronic dialysis underwent gait measurement and analysis during walking and weighing actions. After dialysis, patients demonstrated a smaller stride (p < 0.001) and longer SST (p < 0.001). The results demonstrate that patients’ physical fitness was greatly reduced after dialysis. This study ensures patients’ adequate physical gait strength to cope with the dialysis-associated physical exhaustion risk by tracing gait outliers. As decreased stride and pace are associated with an increased risk of falls, further studies are warranted to evaluate the clinical benefits of monitoring gait with the proposed reliable and valid system in order to reduce fall risk in hemodialysis patients.

This paper proposes an adaptive control scheme for nonlinear systems with significant nonminimum phase dynamics. The scheme is composed of an inner-level adaptive fuzzy PD control law and an outer-level supervisory control law. Importantly, the inner-level controller of the two-level scheme is designed based on a fuzzy model, which takes nonminimum phase phenomenon and modeling error explicitly into account. The scheme is both much simpler in design and more applicable to general nonlinear systems when compared with most existing nonlinear controllers. Effectiveness of the proposed control strategy is demonstrated by numerical simulation of the control of a five-degree-of-freedom aircraft system in the face of bursting disturbances.

A tracking problem, time-delay, uncertainty and stability analysis of a predictive control system are considered. The predictive control design is based on the input and output of neural plant model (NPM), and a recursive fuzzy predictive tracker has scaling factors which limit the value zone of measured data and cause the tuned parameters to converge to obtain a robust control performance. To improve the further control performance, the proposed random-local-optimization design (RLO) for a model/controller uses offline initialization to obtain a near global optimal model/controller. Other issues are the considerations of modeling error, input-delay, sampling distortion, cost, greater flexibility, and highly reliable digital products of the model-based controller for the continuous-time (CT) nonlinear system. They are solved by a recommended two-stage control design with the first-stage (offline) RLO and second-stage (online) adaptive steps. A theorizing method is then put forward to replace the sensitivity calculation, which reduces the calculation of Jacobin matrices of the back-propagation (BP) method. Finally, the feedforward input of reference signals helps the digital fuzzy controller improve the control performance, and the technique works to control the CT systems precisely.

Robust vehicle detection in real-world traffic surveillance remains challenging due to degraded imagery caused by motion blur, adverse weather, and low illumination, which significantly increases detector sensitivity to hyperparameter configurations. This study proposes a “Frugal AI” distributed multi-GPU framework that optimizes hyperparameters via a stochastic simplex-based search coupled with five-fold cross-validation. Utilizing three low-cost NVIDIA GTX 1050 Ti GPUs, the framework performs parallel candidate exploration with an asynchronous model-level exchange mechanism to escape local optima without the overhead of gradient synchronization. Seven CNN backbones—VGG16, VGG19, GoogLeNet, MobileNetV2, ResNet18, ResNet50, and ResNet101—were evaluated within YOLOv2 and Faster R-CNN detectors. To address memory constraints (4 GB VRAM), YOLOv2 was selected for extensive benchmarking. Performance was measured using a harmonic precision–recall-based cost metric to strictly penalize imbalanced outcomes. Experimental results demonstrate that under identical wall-clock time budgets, the proposed framework achieves an average 1.38% reduction in aggregated cost across all models, with the highly sensitive VGG19 backbone showing a 4.00% improvement. Benchmarking against Bayesian optimization, genetic algorithms, and random search confirms that our method achieves superior optimization quality with statistical significance ($p < 0.05$). Under a rigorous IoU = 0.75 threshold, the optimized models consistently yielded F1-scores 0.8444 $\pm$ 0.0346. Ablation studies further validate that the collaborative model exchange is essential for accelerating convergence in rugged loss landscapes. This research offers a practical, scalable, and cost-efficient solution for deploying robust AI surveillance in resource-constrained smart city infrastructure.