Search Results (12,691)

The expansion of tunnel scale has led to a massive demand for inspections. Light Detection And Ranging (LiDAR) has been widely applied in tunnel structure inspections due to its fast data acquisition speed and strong environmental adaptability. However, raw tunnel point-cloud data contain noise point clouds, such as non-structural facilities, which affect the detection of tunnel lining structures. Methods such as point-cloud filtering and machine learning have been applied to tunnel point-cloud denoising, but these methods usually require a lot of manual data preprocessing. In order to directly denoise the tunnel point cloud without preprocessing, this study proposes a comprehensive processing method for cross-section fitting and point-cloud denoising in subway shield tunnels based on the Huber loss function. The proposed method is compared with classical fitting denoising methods such as the least-squares method and random sample consensus (RANSAC). This study is experimentally verified with 40 m long shield-tunnel point-cloud data. Experimental results show that the method proposed in this study can more accurately fit the geometric parameters of the tunnel lining structure and denoise the point-cloud data, achieving a better denoising effect. Meanwhile, since coordinate system transformations are required during the point-cloud denoising process to handle the data, manual rotations of the coordinate system can introduce errors. This study simultaneously combines the Huber loss function with principal component analysis (PCA) and proposes a three-dimensional spatial coordinate system transformation method for tunnel point-cloud data based on the characteristics of data distribution. Full article

Coaxial rotor helicopters have a wide range of civilian and military applications; however, the collision risk of the upper and lower blades that comes with the coaxial rotor system remains. This paper introduces a blade-tip distance measurement method based on coded ultrasonic ranging to tackle this challenge. Coded ultrasonic ranging with phase modulation was adopted to improve the measurement rate. In this paper, seven-bit M-sequences and Gold codes are chosen with four periods of 200 kHz sine wave carriers as the excitation signals, and the received signals are filtered by a bandpass filter and decoded by a matching filter. The coding performance is evaluated by the distinguishability and energy level of the received signals. The experimental results show that the measurement rate can reach 3060 Hz for a distance of one meter. They also give the potential solution for other high-speed measurement problems. Full article

This study explores smoothing techniques to refine financial risk tolerance (FRT) data for the improved prediction of financial market indicators, including the Volatility Index and S&P 500 ETF. Raw FRT data often contain noise and volatility, obscuring their relationship with market dynamics. Seven smoothing methods were applied to derive smoothed mean and standard deviation values, including exponential smoothing, ARIMA, and Kalman filter. Machine learning models, including support vector machines and neural networks, were used to assess predictive performance. The results demonstrate that smoothed FRT data significantly enhance prediction accuracy, with the smoothed standard deviation offering a more explicit representation of investor risk tolerance fluctuations. These findings highlight the value of smoothing techniques in behavioral finance, providing more reliable insights into market volatility and investor behavior. Smoothed FRT data hold potential for portfolio optimization, risk assessment, and financial decision-making, paving the way for more robust applications in financial modeling. Full article

Background: Surgical site infections (SSIs) lead to higher hospital readmission rates and healthcare costs, representing a significant global healthcare burden. Machine learning (ML) has demonstrated potential in predicting SSIs; however, the challenge of addressing imbalanced class ratios remains. Objectives: The aim of this study is to evaluate and enhance the predictive capabilities of machine learning models for SSIs by assessing the effects of feature selection, resampling techniques, and hyperparameter optimization. Methods: Using routine SSI surveillance data from multiple hospitals in Saudi Arabia, we analyzed a dataset of 64,793 surgical patients, of whom 1632 developed SSI. Seven machine learning algorithms were created and tested: Decision Tree (DT), Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Stochastic Gradient Boosting (SGB), and K-Nearest Neighbors (KNN). We also improved several resampling strategies, such as undersampling and oversampling. Grid search five-fold cross-validation was employed for comprehensive hyperparameter optimization, in conjunction with balanced sampling techniques. Features were selected using a filter method based on their relationships with the target variable. Results: Our findings revealed that RF achieves the highest performance, with an MCC of 0.72. The synthetic minority oversampling technique (SMOTE) is the best-performing resampling technique, consistently enhancing the performance of most machine learning models, except for LR and GNB. LR struggles with class imbalance due to its linear assumptions and bias toward the majority class, while GNB’s reliance on feature independence and Gaussian distribution make it unreliable for under-represented minority classes. For computational efficiency, the Instance Hardness Threshold (IHT) offers a viable alternative undersampling technique, though it may compromise performance to some extent. Conclusions: This study underscores the potential of ML models as effective tools for assessing SSI risk, warranting further clinical exploration to improve patient outcomes. By employing advanced ML techniques and robust validation methods, these models demonstrate promising accuracy and reliability in predicting SSI events, even in the face of significant class imbalances. In addition, using MCC in this study ensures a more reliable and robust evaluation of the model’s predictive performance, particularly in the presence of an imbalanced dataset, where other metrics may fail to provide an accurate evaluation. Full article

In order to deeply absorb the power generation of new energy, coal-fired circulating fluidized bed units are widely required to participate in power grid dispatching. However, the combustion system of the units faces problems such as decreased control performance, strong coupling of controlled signals, and multiple interferences in measurement signals during flexible operation. To this end, this paper proposes a model predictive control (MPC) scheme based on the extended state Kalman filter (ESKF). This scheme optimizes the MPC control framework. The ESKF is used to filter the collected output signals and jointly estimate the state and disturbance quantities in real time, thus promptly establishing a prediction model that reflects the true state of the system. Subsequently, taking the minimum output signal deviation of the main steam pressure and bed temperature and the control signal increment as objectives, a coordinated receding horizon optimization is carried out to obtain the optimal control signal of the control system within each control cycle. Tracking, anti-interference, and robustness experiments were designed to compare the control effects of ESKF-MPC, ID-PI, ID-LADRC, and MPC. The research results show that, when the system parameters had a ±30% perturbation, the adjustment time range of the main steam pressure and bed temperature loops of this method were 770~1600 s and 460~1100 s, respectively, and the ITAE indicator ranges were 0.615 × 10⁵~1.74 × 10⁵ and 3.9 × 10⁶~6.75 × 10⁶, respectively. The overall indicator values were smaller and more concentrated, and the robustness was stronger. In addition, the test results of the actual continuous variable condition process of the unit show that, compared with the PI strategy, after adopting the ESKF-MPC strategy, the overshoot of the main steam pressure loop of the combustion system was small, and the output signal was stable; the fluctuation range of the bed temperature loop was small, and the signal tracking was smooth; the overall control performance of the system was significantly improved. Full article

This paper deals with developing a comparative study of the principal time-domain system identification methods suitable for performing an experimental modal analysis of structural systems. To this end, this work focuses first on analyzing and reviewing the mathematical background concerning the analytical methods and the computational algorithms of interest for this study. The methods considered in the paper are referred to as the AutoRegressive eXogenous (ARX) method, the State-Space ESTimation (SSEST) method, the Numerical Algorithm for Subspace State-Space System Identification (N4SID), the Eigensystem Realization Algorithm (ERA) combined with the Observer/Kalman Filter Identification (OKID) method, and the Transfer Function ESTimation (TFEST) method. Starting from the identified models estimated through the methodologies reported in the paper, a set of second-order configuration-space dynamical models of the structural system of interest can also be determined by employing an estimation method for the Mass, Stiffness, and Damping (MSD) matrices. Furthermore, in practical applications, the correct estimation of the damping matrix is severely hampered by noise that corrupts the input and output measurements. To address this problem, in this paper, the identification of the damping matrix is improved by employing the Proportional Damping Coefficient (PDC) identification method, which is based on the use of the identified set of natural frequencies and damping ratios found for the case study analyzed in the paper. This work also revisits the critical aspects and pitfalls related to using the Model Order Reduction (MOR) approach combined with the Balanced Truncation Method (BTM) to reduce the dimensions of the identified state-space models. Finally, this work analyzes the performance of all the fundamental system identification methods mentioned before when applied to the experimental modal analysis of flexible structures. This is achieved by carrying out an experimental campaign based on the use of a vibrating test rig, which serves as a demonstrative example of a typical structural system. The complete set of experimental results found in this investigation is reported in the appendix of the paper. Full article

This study investigates the spatiotemporal density aggregation and pattern distribution of vessel traffic amidst bustling maritime logistics scenarios. Firstly, a relatively new spatiotemporal segmentation and reconstruction method is proposed for ship AIS trajectories to address trajectory disruptions caused by berthing, anchorage, and other factors. Subsequently, a trajectory filtering algorithm utilizing time window panning is introduced to mitigate position jumps and deviation errors in trajectory points, ensuring that the dynamic trajectory adheres to the spatiotemporal correlations of ship motion. Secondly, to establish a geographical spatial mapping of dynamic trajectories, spatial gridding is applied to maritime traffic areas. By associating the geographical space of traffic activities with the temporal attributes of dynamic trajectories, a dynamic trajectory temporal density model is constructed. Finally, a case study is conducted to evaluate the effectiveness and applicability of the proposed method in identifying spatiotemporal patterns of maritime traffic and spatiotemporal density aggregation states. The results show that the proposed method can identify dynamic trajectory traffic patterns after the application of compression algorithms, providing a novel approach to studying the spatiotemporal aggregation of maritime traffic in the era of big data. Full article

Battery degradation is a critical challenge in the operation and longevity of low-Earth-orbit (LEO) satellites because of its direct impact on mission reliability and power system performance. This study proposes a data-driven approach to accurately estimating the degradation of satellite batteries by integrating a transformer network model for voltage prediction and unscented Kalman filter (UKF) techniques for online state estimation. By utilizing on-orbit telemetry data and machine-learning-based modeling, the proposed method provides processing-time improvements by addressing the limitations of traditional methods imposed by their reliance on predefined conditions and user expertise. The proposed framework is validated using real satellite telemetry data from KOMPSAT-5, demonstrating its ability to predict battery degradation trends over time and under varying operational conditions. This approach minimizes manual data processing requirements and enables the consistent and precise monitoring of battery health. Full article

This study assessed the effect of filter parameters on gait characteristics and the performance of machine-learning models. Overground walking trials (n = 99) with and without perturbations (slips, trips) were collected for 33 healthy older adults. Kinematics were collected by a motion capture system. Different Butterworth low-pass parameters were applied to the raw data, including three orders (2–6) and nine cutoffs (4–20 Hz). Spatiotemporal gait outcomes were then calculated to develop classification models to automatically identify the trial type (gait, gait–slip, or gait–trip) using Logistic Regression, Support Vector Classification, and Random Forest Classification. A 3 × 9 ANOVA showed main effects of order and cutoff (p < 0.01 for all) on gait characteristics during both perturbed and regular walking trials. However, the gait characteristics were different between them. The filter parameters significantly affected the performance of classification models using different classifiers, with significant main effects of the filter order (p < 0.05) and cutoff (p < 0.01) on AUC and overall accuracy for all of the models. Our results suggest that the standard Butterworth filter (fourth-order, cutoff: 6 Hz) is suitable for the development of classification models with low–medium complexity, while for models with high complexity (i.e., ensemble models), a filter with a higher order and cutoff (sixth-order, cutoff 10–12 Hz) might yield better performance. Full article

Aiming at the irreversible demagnetization of permanent magnet synchronous motors (PMSMs) under extreme working conditions, a fault diagnosis method for permanent magnet demagnetization based on multi-parameter estimation is proposed in this paper. This scheme aims to provide technical support for enhancing the safety and reliability of permanent magnet motor drive systems. In the proposed scheme, multiple operating states of the motor are acquired by injecting sinusoidal current signals into the d-axis, ensuring that the parameter estimation equation satisfies the full rank condition. Furthermore, the accurate dq-axis inductance parameters are obtained based on a recursive least square method. Subsequently, a dual extended Kalman filter is employed to acquire real-time permanent magnet flux linkage data of PMSMs, and the estimation data between the two algorithms are transferred to each other to eliminate the bias of permanent magnet flux estimation caused by a parameter mismatch. Finally, accurate evaluation of the remanence level of the rotor permanent magnet and demagnetization fault diagnosis can be achieved based on the obtained permanent magnet flux linkage parameters. The experimental results show that the relative estimation errors of the dq-axis inductance and permanent magnet flux linkage are within 5%, which can realize the effective diagnosis of demagnetization fault and high-precision condition monitoring of a permanent magnet health. Full article

This paper introduces a self-consistent field-null optimization algorithm of a poloidal magnetic field that precisely accounts for the influence of vacuum vessel eddy currents. Building on existing poloidal field (PF) coil currents, the algorithm can refine these waveforms to achieve various target field-null configurations. Firstly, based on the TokSys toolbox, a response model, including the PF coils and vacuum vessel circuits for the HL-3 tokamak, is developed under the MATLAB^® and Simulink^™ framework. The resistivity parameters of the model are calibrated using experimental data obtained from single-coil discharge tests. Subsequently, an iterative method was employed to simultaneously solve the dynamic field-null optimization problem within a specified spatial region and precisely account for the effect of passive eddy currents. Typically, $\left|B_{\perp }\right|\le 1 G$ within a large area can be obtained with this iterative scheme, which can be stably sustained for over 15 milliseconds to ensure the robustness of breakdown. Finally, a low-pass filtered PID controller is applied to the model to achieve precise control of the PF coils currents, confirming the feasibility of implementing the proposed algorithm in real experiments. Full article

Objectives: This study focuses on a novel endovascular technique for treating acute ischemic stroke caused by carotid artery occlusion (CAO) related to extracranial atherosclerosis, a condition typically associated with poor outcomes due to extensive brain infarction and high hemorrhagic risk. While stent retriever thrombectomy is effective for large-vessel occlusions, managing atherosclerosis-related CAO presents challenges. Methods: This retrospective analysis involved a cohort of 18 consecutive patients treated at our center using a new approach that employs a balloon guide catheter (BGC) to access the common carotid artery. Stent retrievers are used as distal filters, and angioplasty is performed through the stent pusher. The technique aims to reduce procedural time and prevent distal embolisms, which are common complications in traditional methods. Results: The results indicate that this approach improves intervention times, increases first-pass success rates, and decreases distal embolism occurrences compared to conventional techniques. It also effectively overcomes obstacles like the management of antiplatelet therapy and lengthy procedures. Conclusions: These preliminary findings demonstrate that using stent retrievers as filters with BGCs, without the need for aspiration catheters, may offer a safer and faster treatment option for atherosclerosis-related CAO. However, further research is required to confirm these findings and potentially establish this technique as the standard in clinical practice. Full article

The growing demand for viral vectors as nanoscale therapeutic agents in gene therapy necessitates efficient and scalable purification methods. This study examined the role of nanoscale biomaterials in optimizing viral vector clarification through a model system mimicking real AAV2 crude harvest material. Using lysed HEK293 cells and silica nanoparticles (20 nm) as surrogates for AAV2 crude harvest, we evaluated primary (depth filters) and secondary (membrane-based) filtration processes under different process parameters and solution conditions. These filtration systems were then assessed for their ability to recover nanoscale viral vectors while reducing DNA (without the need for endonuclease treatment), protein, and turbidity. Primary clarification demonstrated that high flux rates (600 LMH) reduced the depth filter’s ability to leverage adsorptive and electrostatic interactions, resulting in a lower DNA removal. Conversely, lower flux rates (150 LMH) enabled >90% DNA reduction by maintaining these interactions. Solution conductivity significantly influenced performance, with high conductivity screening electrostatic interactions, and the model system closely matching real system outcomes under these conditions. Secondary clarification highlighted material-dependent trade-offs. The PES membranes achieved exceptional AAV2 recovery rates exceeding 90%, while RC membranes excelled in DNA reduction (>80%) due to their respective surface charge and hydrophilic properties. The integration of the primary clarification step dramatically improved PES membrane performance, increasing the final flux from ~60 LMH to ~600 LMH. Fouling analysis revealed that real AAV2 systems experienced more severe and complex fouling compared to the model system, transitioning from intermediate blocking to irreversible cake layer formation, which was exacerbated by nanoscale impurities (~10–600 nm). This work bridges nanomaterial science and biomanufacturing, advancing scalable viral vector purification for gene therapy. Full article

High-dimensional survival data, such as microarray datasets, present significant challenges in variable selection and model performance due to their complexity and dimensionality. Identifying important genes and understanding how these genes influence the survival of patients with cancer are of great interest and a major challenge to biomedical scientists, healthcare practitioners, and oncologists. Therefore, this study combined the strengths of two complementary feature selection methodologies: a filtering (correlation-based) approach and a wrapper method based on Iterative Bayesian Model Averaging (IBMA). This new approach, termed Correlation-Based IBMA, offers a highly efficient and effective means of selecting the most important and influential genes for predicting the survival of patients with cancer. The efficiency and consistency of the method were demonstrated using diffuse large B-cell lymphoma cancer data. The results revealed that the 15 most important genes out of 3835 gene features were consistently selected at a threshold p-value of 0.001, with genes with posterior probabilities below 1% being removed. The influence of these 15 genes on patient survival was assessed using the Cox Proportional Hazards (Cox-PH) Model. The results further revealed that eight genes were highly associated with patient survival at a 0.05 level of significance. Finally, these findings underscore the importance of integrating feature selection with robust modeling approaches to enhance accuracy and interpretability in high-dimensional survival data analysis. Full article

Limited intra-session information has constrained the performance of early Graph Neural Network (GNN)-based session-based recommendation (SBR) models. To address this issue, researchers have increasingly incorporated inter-session information to improve next-item prediction. Although such additional information can provide valuable cues, it may also introduce undesirable interference. However, existing approaches often fail to effectively extract relevant information while filtering out extraneous interference, largely owing to incomplete modeling of inter-session dependencies. Specifically, inter-session connections have been examined merely at the item level, overlooking more intricate distinctions and associations between sessions. Moreover, current methods rely exclusively on similarity as the metric for evaluating inter-session dependencies, overlooking their multidimensional complexity. In this work, we propose a GNN-based SBR model that discreetly exploits inter-session information (DEISI). To overcome the first limitation, we introduce factor-level inter-session dependencies using disentangled representation learning, enabling the capture of finer-grained interactions. To address the second limitation, we design a novel metric named “stability” to complement similarity, providing an additional perspective on inter-session relationships. Consequently, DEISI constructs more detailed and reliable inter-session dependencies. Extensive experiments on three benchmark datasets demonstrate the superior performance of DEISI over state-of-the-art models. Full article