Search Results (2,151)

As an electric multiple unit (EMU) train passes through an extreme tunnel characterized by high altitude, steep gradient, and extended lengths, the pressure waves generated by the train–tunnel aerodynamic coupling combine with the baseline pressure variations within the tunnel. This interaction results in rapid fluctuations and extreme external pressure with higher amplitudes, which are transmitted into the carriage, causing pressure fluctuations that can adversely affect passenger comfort. These waves interact with multiple factors within the carriage, such as air ducts, airtight gaps, carbody deformation, oxygen supply systems, and temperature, creating a highly nonlinear internal pressure transmission system. This study first establishes a single-factor internal pressure fluctuation model. Subsequently, a multi-factor coupled internal pressure fluctuation model is constructed based on the ideal gas polytropic process assumption and the law of mass conservation. The model parameters are corrected and the model’s effectiveness and accuracy are validated using experimental data to predict and summarize the internal pressure variation patterns of the EMU train during dynamic operation in such tunnels, ensuring safe train operation and meeting the pressure comfort requirements of passengers. Finally, to address the challenges of maintaining and regulating multi-physical variable comfort under extreme tunnel conditions, this study investigates the impact of partial oxygen pressure and temperature on pressure fluctuations and comfort. The study finds that higher oxygen pressure and temperature significantly increase internal pressure fluctuation amplitude, with the oxygen supply system contributing 18.11% and temperature 5.74% of total variation. Thus, setting appropriate standards for oxygen supply, temperature, and valve operation is crucial for mitigating internal pressure fluctuations and enhancing safety and comfort. This research provides a theoretical foundation for developing a comprehensive comfort evaluation and regulation system under harsh environments. Full article

In recent years, advanced controllers, including Model Predictive Control (MPC), have emerged as promising solutions to improve the efficiency of building energy systems. This paper explores the capabilities of MPC in handling multiple control objectives and constraints. A first MPC controller focuses on the task of ensuring thermal comfort in a residential house served by a heat pump while minimizing the operating costs when subject to different pricing schedules. A second MPC controller working on the same system tests the ability of MPC to deal with demand response events by enforcing a time-varying maximum power usage limitation signal from the electric grid. Furthermore, multiple combinations of the control parameters are tested in order to assess their influence on the controller performance. The controllers are tested on the BOPTEST framework, which offers standardized test cases in high-fidelity emulation models, and pre-defined baseline control strategies to allow fair comparisons also across different studies. Results show that MPC is able to handle multi-objective optimal control problems, reducing thermal comfort violations by between 66.9% and 82% and operational costs between 15.8% up to 20.1%, depending on the specific scenario analyzed. Moreover, MPC proves its capability to exploit the building thermal mass to shift heating power consumption, allowing the latter to adapt its time profile to time-varying constraints. The proposed methodology is based on technologically feasible steps that are intended to be easily transferred to large scale, in-field applications. Full article

Vehicle logo detection plays a crucial role in various computer vision applications, such as vehicle classification and detection. In this research, we propose an improved vehicle logo detection method leveraging the self-attention mechanism. Our feature-sampling structure integrates multiple attention mechanisms and bidirectional feature aggregation to enhance the discriminative power of the detection model. Specifically, we introduce the multi-head attention for multi-scale feature fusion module to capture multi-scale contextual information effectively. Moreover, we incorporate the bidirectional aggregation mechanism to facilitate information exchange between different layers of the detection network. Experimental results on a benchmark dataset (VLD-45 dataset) demonstrate that our proposed method outperforms baseline models in terms of both detection accuracy and efficiency. Our experimental evaluation using the VLD-45 dataset achieves a state-of-the-art result of 90.3% mAP. Our method has also improved AP by 10% for difficult samples, such as HAVAL and LAND ROVER. Our method provides a new detection framework for small-size objects, with potential applications in various fields. Full article

In fields such as manufacturing and aerospace, remaining useful life (RUL) prediction estimates the failure time of high-value assets like industrial equipment and aircraft engines by analyzing time series data collected from various sensors, enabling more effective predictive maintenance. However, significant temporal diversity and operational complexity during equipment operation make it difficult for traditional single-scale, single-dimensional feature extraction methods to effectively capture complex temporal dependencies and multi-dimensional feature interactions. To address this issue, we propose a Dual-Path Interaction Network, integrating the Multiscale Temporal-Feature Convolution Fusion Module (MTF-CFM) and the Dynamic Weight Adaptation Module (DWAM). This approach adaptively extracts information across different temporal and feature scales, enabling effective interaction of multi-dimensional information. Using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset for comprehensive performance evaluation, our method achieved RMSE values of 0.0969, 0.1316, 0.086, and 0.1148; MAPE values of 9.72%, 14.51%, 8.04%, and 11.27%; and Score results of 59.93, 209.39, 67.56, and 215.35 across four different data categories. Furthermore, the MTF-CFM module demonstrated an average improvement of 7.12%, 10.62%, and 7.21% in RMSE, MAPE, and Score across multiple baseline models. These results validate the effectiveness and potential of the proposed model in improving the accuracy and robustness of RUL prediction. Full article

Short-term origin–destination (OD) passenger flow forecasting is crucial for urban rail transit enterprises aiming to optimise transportation products and increase operating income. As there are large-scale OD pairs in an urban rail transit system, OD passenger flow cannot be obtained in real time (temporal hysteresis). Additionally, the distribution characteristics are also complex. Previous studies mainly focus on passenger flow prediction at metro stations, while few methods solve the OD passenger flow prediction problems of an urban rail transit system. In view of this, we propose a novel deep learning method fusing high-dimensional features (HDF-DL) with multi-source data. The HDF-DL method is combined with three modules. The temporal module incorporates the time-varying, trend, and cyclic characteristics of OD passenger flow, while the latest OD passenger flow time sequence (within 1 h) is excluded from the time-varying characteristics. In the spatial module, the K-means and K-shape algorithms are used to classify OD pairs from multiple perspectives and capture the spatial features, reducing the difficulty of OD passenger flow predictions with large-scale and complex characteristics. Weather factors are considered in the external feature module. The HDF-DL method is tested on a large-scale metro system in China, in which eight baseline models are designed. The results show that the HDF-DL method achieves high prediction accuracy across multiple time granularities, with a mean absolute percentage error of about 10%. OD passenger flow in every departure time interval can be predicted with high and stable accuracy, effectively capturing temporal characteristics. The modular design of HDF-DL, which fuses high-dimensional features and employs appropriate neural networks for different data types, significantly reduces prediction errors and outperforms baseline models. Full article

Wheelchair basketball players often develop shoulder pain due to repetitive wheelchair propulsion motion. Wheelchair propulsion involves two phases, push and recovery, with several different muscles simultaneously active in each phase. Although differences in the coordinated activity of multiple muscles may influence the mechanism of injury occurrence, there have been no studies investigating muscle synergy in wheelchair propulsion motion. Twelve healthy adult males with no previous wheelchair driving experience were included. The surface electromyography data of 10 muscles involved in shoulder joint movements were measured during a 20 m wheelchair propulsion motion. Muscle synergies were extracted using non-negative matrix factorization analysis of the electromyography data. Four muscle synergies were identified during wheelchair propulsion. Synergy 1 reflects propulsion through shoulder flexion and elbow flexion, while Synergy 2 involves shoulder flexion and elbow extension. Synergy 3 describes shoulder extension returning the upper limb, which has moved forward during the push, back to its original position, and Synergy 4 relates to stabilize the shoulder girdle during the recovery phase. This study is the first to explore muscle synergy during wheelchair propulsion, and the data from healthy participants without disabilities or pain will provide a baseline for future comparisons with data from wheelchair basketball players. Full article

Introduction: As the COVID-19 pandemic becomes an endemic state, still many questions remain regarding the risks and impact of SARS-CoV-2 infection and vaccination in patients with immune-mediated inflammatory diseases (IMIDs) who were excluded from the phase 3 COVID-19 vaccination trials. Methods: The BELCOMID study collected patient data and serological samples from a large, multicentric IMID patient cohort that was prospectively followed during sequential stages of the pandemic. Patients were stratified according to vaccination status into five groups across three sampling periods. Interactions between SARS-CoV-2 infection, COVID-19 vaccination status, IMID-treatment modalities and IMID course were explored. Results: In total, 2165 patients with IBD, a dermatological or rheumatological IMID participated. SARS-CoV-2 infection rates increased over the course of the pandemic and were highest in IMID patients that had refused every vaccine. After baseline COVID-19 vaccination, serologic spike (S)-antibody responses were attenuated by particular types of immune-modulating treatment: anti-TNF, rituximab, JAKi, systemic steroids, combined biologic/immunomodulator treatment. Nonetheless, S-antibody concentration increased progressively in patients who received a booster vaccination, reaching 100% seroconversion rate in patients who had received two booster vaccines. Previous SARS-CoV-2 infection was found as a predictor of higher S-antibody response. Patients who had refused every vaccine showed the lowest rates of S-seroconversion (53.8%). Multiple logistic regression did not identify previous SARS-CoV-2 infection as a risk factor for IMID flare-up. Furthermore, no increased risk of IMID flare-up was found with booster vaccination. Conclusions: Altogether, the BELCOMID study provides evidence for the efficacy and safety of COVID-19 vaccination and confirms the importance of repeated booster vaccination in IMID patients. Full article

The commonly used baseline-free Lamb wave damage identification methods often require a large amount of sensor data to eliminate the dependence on baseline signals. To improve the efficiency of damage localization, this paper proposes a new Lamb wave damage location method, namely the probabilistic exchanging-element time-reversal method (PEX-TRM), which is based on the exchanging-element time-reversal method (EX-TRM) and the probabilistic damage identification method. In this method, the influence of the damage wave packet migration on the correlation coefficient between the reconstructed signals of each sensing path and the initial excitation signal is analyzed, and the structure is divided into multiple regional units corresponding to the damage to locate damage. In addition, the influence of the number of sensing paths on the location accuracy is also analyzed. A method of damage probability imaging based on structural symmetry is proposed to enhance location accuracy in the case of sparse sensing paths. The experimental and simulation results verify that the method can achieve damage location with fewer excitation times. Moreover, this method can avoid the problem that the damage wave packet is difficult to extract, improve the efficiency of damage location, and promote the engineering application of the Lamb wave damage location method. Full article

The interseismic behavior of faults (whether they are locked or creeping) and their quantitative kinematic constraints are critical for assessing the seismic hazards of faults and their surrounding areas. Currently, the creep of the eastern segment of the Laohushan Fault in the Haiyuan Fault Zone at the northeastern margin of the Tibetan Plateau, as revealed by InSAR observations, lacks confirmation from other observational methods, particularly high-precision GNSS studies. In this study, we utilized nearly seven years of observation data from a dense GNSS continuous monitoring profile (with a minimum station spacing of 2 km) that crosses the eastern segment of the Laohushan Fault. This dataset was integrated with GNSS data from regional continuous stations, such as those from the Crustal Movement Observation Network of China, and multiple campaign measurements to calculate GNSS baseline change time series across the Laohushan Fault and to obtain a high spatial resolution horizontal crustal velocity field for the region. A comprehensive analysis of this primary dataset indicates that the Laohushan Fault is currently experiencing left-lateral creep, characterized by a partially locked shallow segment and a deeper locked segment. The fault creep is predominantly concentrated in the shallow crustal region, within a depth range of 0–5.7 ± 3.4 km, exhibiting a creep rate of 1.5 ± 0.7 mm/yr. Conversely, at depths of 5.7 ± 3.4 km to 16.8 ± 4.2 km, the fault remains locked, with a loading rate of 3.9 ± 1.1 mm/yr. The shallow creep is primarily confined within 3 km on either side of the fault. Over the nearly seven-year observation period, the creep movement within approximately 5 km of the fault’s near field has shown no significant time-dependent variation, instead demonstrating a steady-state behavior. This steady-state creep appears unaffected by postseismic effects from historical large earthquakes in the adjacent region, although the deeper (far-field) tectonic deformation of the Laohushan Fault may have been influenced by the postseismic effects of the 1920 Haiyuan M8.5 earthquake. Full article

Background: Acute Kidney Injury (AKI) is a condition that affects a significant proportion of acutely unwell patients and is associated with a high mortality rate. Patients undergoing haemopoietic stem cell transplantation (HSCT) are in an extremely high group for AKI. Identifying a biomarker or panel of markers that can reliably identify at-risk individuals undergoing HSCT can potentially impact management and outcomes. Early identification of AKI can reduce its severity and improve prognosis. We evaluated the urinary Liver type fatty acid binding protein (L-FABP), a tubular stress and injury biomarker both as an ELISA and a point of care (POC) assay for AKI detection in HSCT. Methods: 85 patients that had undergone autologous and allogenic HSCT (35 and 50, respectively) had urinary L-FABP (uL-FABP) measured by means of a quantitative ELISA and a semi-quantitative POC at baseline, day 0 and 7 post-transplantation. Serum creatinine (SCr) was also measured at the same time. Patients were followed up for 30 days for the occurrence of AKI and up to 18 months for mortality. The sensitivity and specificity of uL-FABP as an AKI biomarker were evaluated and compared to the performance of sCr using ROC curve analysis and logistic regression. Results: 39% of participants developed AKI within 1 month of their transplantation. The incidence of AKI was higher in the allogenic group than in the autologous HTSC group (57% vs. 26%, p = 0.008) with the median time to AKI being 25 [range 9-30] days. This group was younger (median age 59 vs. 63, p < 0.001) with a lower percentage of multiple myeloma as the primary diagnosis (6% vs. 88%, p < 0.001). The median time to AKI diagnosis was 25 [range 9–30] days. uL-FABP (mcg/gCr) at baseline, day of transplant and on the 7th day post-transplant were 1.61, 5.39 and 10.27, respectively, for the allogenic group and 0.58, 4.36 and 5.14 for the autologous group. Both SCr and uL-FABP levels rose from baseline to day 7 post-transplantation, while the AUC for predicting AKI for baseline, day 0 and day 7 post-transplant was 0.54, 0.59 and 0.62 for SCr and for 0.49, 0.43 and 0.49 uL-FABP, respectively. Univariate logistic regression showed the risk of AKI to be increased in patients with allogenic HSCT (p = 0.004, 95%CI [0.1; 0.65]) and in those with impaired renal function at baseline (p = 0.01, 95%CI [0.02, 0.54]). The risk of AKI was also significantly associated with SCr levels on day 7 post-transplant (p = 0.03, 95%CI [1; 1.03]). Multivariate logistic regression showed the type of HSCT to be the strongest predictor of AKI at all time points, while SCr levels at days 0 and 7 also correlated with increased risk in the model that included uL-FABP levels at the corresponding time points. The POC device for uL-FABP measurement correlated with ELISA (p < 0.001, Spearman ‘correlation’ = 0.54) Conclusions: The urinary biomarker uL-FABP did not demonstrate an independent predictive value in the detection of AKI at all stages. The most powerful risk predictor of AKI in this setting appears to be allograft recipients and baseline renal impairment, highlighting the importance of clinical risk stratification. Urinary L-FAPB as a POC biomarker was comparable to ELISA, which provides an opportunity for simple and rapid testing. However, the utility of LFABP in AKI is unclear and needs further exploration. Whether screening through rapid testing of uL-FABP can prevent or reduce AKI severity is unknown and merits further studies. Full article

Background/Objectives: This study aims to evaluate the performance of various classification algorithms and resampling methods across multiple diagnostic and prognostic cancer datasets, addressing the challenges of class imbalance. Methods: A total of five datasets were analyzed, including three diagnostic datasets (Wisconsin Breast Cancer Database, Cancer Prediction Dataset, Lung Cancer Detection Dataset) and two prognostic datasets (Seer Breast Cancer Dataset, Differentiated Thyroid Cancer Recurrence Dataset). Nineteen resampling methods from three categories were employed, and ten classifiers from four distinct categories were utilized for comparison. Results: The results demonstrated that hybrid sampling methods, particularly SMOTEENN, achieved the highest mean performance at 98.19%, followed by IHT (97.20%) and RENN (96.48%). In terms of classifiers, Random Forest showed the best performance with a mean value of 94.69%, with Balanced Random Forest and XGBoost following closely. The baseline method (no resampling) yielded a significantly lower performance of 91.33%, highlighting the effectiveness of resampling techniques in improving model outcomes. Conclusions: This research underscores the importance of resampling methods in enhancing classification performance on imbalanced datasets, providing valuable insights for researchers and healthcare professionals. The findings serve as a foundation for future studies aimed at integrating machine learning techniques in cancer diagnosis and prognosis, with recommendations for further research on hybrid models and clinical applications. Full article

Background: kidney transplant recipients are exposed to multiple pathogenic pathways that may alter short and long-term allograft survival. Metabolomic profiling is useful for detecting potential biomarkers of kidney disease with a predictive capacity. This field is still under development in kidney transplantation and metabolome analysis is faced with analytical challenges. We performed a cross-sectional study including stable kidney transplant patients and aimed to search for relevant associations between baseline plasmatic and urinary metabolites and relevant outcomes over a follow-up period of 3 years. Methods: we performed a cross-sectional study including 72 stable kidney transplant patients with stored plasmatic and urinary samples at the baseline evaluation which were there analyzed by nuclear magnetic resonance in order to quantify and describe metabolites. We performed a 3-year follow-up and searched for relevant associations between renal failure outcomes and baseline metabolites. Between-group comparisons were made after classification by observed estimated glomerular filtration rate slope during the follow-up: positive slope and negative slope. Results: The mean estimated GFR (glomerular filtration rate) was higher at baseline in the patients who exhibited a negative slope during the follow-up (63.4 mL/min/1.73 m² vs. 55.8 mL/min/1.73 m², p = 0,019). After log transformation and division by urinary creatinine, urinary dimethylamine (3.63 vs. 3.16, p = 0.027), hippuric acid (7.33 vs. 6.29, p = 0.041), and acetone (1.88 vs. 1, p = 0.023) exhibited higher concentrations in patients with a negative GFR slope when compared to patients with a positive GFR slope. By computing a linear regression, a significant low-strength regression equation between the log 2 transformed plasmatic level of glycine and the estimated glomerular filtration rate was found (F (1,70) = 5.15, p = 0.026), with an R² of 0.069. Several metabolites were correlated positively with hand grip strength (plasmatic tyrosine with r = 0.336 and p = 0.005 and plasmatic leucine with r = 0.371 and p = 0.002). Other urinary metabolites were found to be correlated negatively with hand grip strength (dimethylamine with r = −0.250 and p = 0.04, citric acid with r = −0.296 and p = 0.014, formic acid with r = −0.349 and p = 0.004, and glycine with r = −0.306 and p = 0.01). Conclusions: some metabolites had different concentrations compared to kidney transplant patients with negative and positive slopes, and significant correlations were found between hand grip strength and urinary and plasmatic metabolites. Full article

The logistics demands of industries represented by e-commerce have experienced explosive growth in recent years. Vehicle path-planning plays a crucial role in optimization systems for logistics and distribution. A path-planning scheme suitable for an actual scenario is the key to reducing costs and improving service efficiency in logistics industries. In complex application scenarios, however, it is difficult for conventional heuristic algorithms to ensure the quality of solutions for vehicle routing problems. This study proposes a joint approach based on the genetic algorithm and graph convolutional network for solving the capacitated vehicle routing problem with multiple distribution centers. First, we use the heuristic method to modularize the complex environment and encode each module based on the constraint conditions. Next, the graph convolutional network is adopted for feature embedding for the graph representation of the vehicle routing problem, and multiple decoders are used to increase the diversity of the solution space. Meanwhile, the REINFORCE algorithm with a baseline is employed to train the model, ensuring quick returns of high-quality solutions. Moreover, the fitness function is calculated based on the solution to each module, and the genetic algorithm is employed to seek the optimal solution on a global scale. Finally, the effectiveness of the proposed framework is validated through experiments at different scales and comparisons with other algorithms. The experimental results show that, compared to the single decoder GCN-based solving method, the method proposed in this paper improves the solving success rate to 100% across 15 generated instances. The average path length obtained is only 11% of the optimal solution produced by the GCN-based multi-decoder method. Full article

Ship welding is a crucial part of ship building, requiring higher levels of robot coordination and working efficiency than ever before. To this end, this paper studies the coordinated ship-welding task, which involves multi-robot welding of multiple weld lines consisting of synchronous ones to be executed by a pair of robots and normal ones that can be executed by one robot. To evaluate working efficiency, the objectives of optimal lazy robot ratio and energy consumption were considered, which are tackled by the proposed dynamic Kuhn–Munkres-based model-free policy gradient (DKM-MFPG) reinforcement learning algorithm. In DKM-MFPG, a dynamic Kuhn–Munkres (DKM) dispatcher is designed based on weld line and co-welding robot position information obtained by the wireless sensors, such that robots always have dispatched weld lines in real-time and the lazy robot ratio is 0. Simultaneously, a model-free policy gradient (MFPG) based on reinforcement learning is designed to achieve the energy-optimal motion control for all robots. The optimal lazy robot ratio of the DKM dispatcher and the network convergence of MFPG are theoretically analyzed. Furthermore, the performance of DKM-MFPG is simulated with variant settings of welding scenarios and compared with baseline optimization methods. Compared to the four baselines, DKM-MFPG owns a slight performance advantage within 1% on energy consumption and reduces the average lazy robot ratio by 11.30%, 10.99%, 8.27%, and 10.39%. Full article

Behavior Skills Training (BST) was used remotely to teach four special education teachers who lived in China to conduct free-operant preference assessments. A multiple baseline across participant design demonstrated a functional relationship between remote BST and the percentage of assessment steps completed correctly. Additionally, two of the four participants demonstrated generalization. Limitations and future research directions are discussed. Full article