Search Results (5,946)

To address the uncertainty of the measurement noise covariance matrix in vehicle state estimation, this paper proposes a symmetry-aware extended Kalman filter optimized by a chaotic-gradient strategy. The symmetry-aware concept is introduced from the approximate mirror symmetry of vehicle lateral dynamics under left and right steering excitations. Under identical road adhesion and vehicle operating conditions, the yaw-rate and sideslip-angle responses should exhibit balanced statistical characteristics for positive and negative lateral motions. However, a fixed measurement noise covariance matrix may break this balance and lead to direction-dependent estimation bias or delayed convergence. To improve the statistical consistency of the estimation process, the proposed method adaptively tunes the measurement noise covariance matrix according to the innovation covariance mismatch. A chaotic search mechanism is first used to enhance global exploration, and a variable-step gradient method is then applied to refine the local optimal solution. Through the iterative combination of chaotic traversal and gradient-based refinement, the proposed observer improves the balance between model prediction and measurement correction under stochastic disturbances. The effectiveness of the proposed method is verified through CarSim and MATLAB/Simulink co-simulation. The results show that, compared with EKF, UKF, and AEKF benchmark observers, the proposed CG_EKF provides more accurate estimation of vehicle yaw rate and sideslip angle. Full article

To satisfy the requirements of channel-type ultra-low penetration air (ULPA) filters for high filtration efficiency, low pressure drop, and good corrugation processability, a three-layer composite filter medium with a bast-fiber surface layer/glass wool–lyocell blended core layer/bast-fiber surface layer structure was designed and prepared. The effects of surface-layer material, core-layer fiber composition, surface-layer basis weight, and processing conditions on the overall performance of the medium were systematically investigated. Bast-fiber paper exhibited the best corrugation processability and mechanical performance and was selected as the surface layer. The optimal core-layer composition was 25 wt.% 475-79 glass wool fibers, 30 wt.% 475-59 glass wool fibers, and 45 wt.% lyocell fibers, yielding an original-sheet filtration efficiency of 99.9996% and a pressure drop of 381 Pa. Further optimization showed that a bast-fiber surface layer with a basis weight of 15 g/m² provided the best balance among pleat retention, structural stability, and low-resistance characteristics. Under optimized corrugation conditions of 120 °C roller temperature, 10 m/min roller speed, and 0.480 mm roller gap, a desirable pleat morphology suitable for channel-type structures was obtained. The resulting channel-type ULPA filter maintained a filtration efficiency of 99.99954%, while increasing the effective filtration area by 51.6% and reducing the pressure drop by 26.1% compared with a conventional pleated filter with the same dimensions. These results provide a useful reference for the design and application of low-resistance, high-efficiency filter media for channel-type ULPA filters. Full article

Scene graph generation (SGG) provides a structured representation for visual understanding. However, most existing methods are designed to optimize global triplet recall rather than retrieve relation instances specified by a user query. In query-driven visual relation retrieval, two major challenges arise: the target relation must compete with a highly redundant candidate space, and query semantics are not incorporated before relation classification. To address these challenges, we propose a Query-Driven Candidate Relation Screening (QCRS) module, which injects query semantics into the candidate screening process. Specifically, QCRS encodes the query and candidate visual relation features, and then filters query-relevant candidates through relevance scoring. By reducing interference from irrelevant candidates and avoiding redundant computation, QCRS improves the final exact triplet hit performance and enhances the interpretability of query-specific relations, thereby facilitating query-driven visual relation retrieval. Built upon the strong EGTR baseline, QCRS learns query relevance to prioritize relation instances matching the target query, enabling precise triplet retrieval. Extensive ablation studies and analyses on the VG150 benchmark validate the effectiveness of the proposed approach: when integrated with EGTR, QCRS improves PairR@50 from 61.52% to 80.06% and ETR@50 from 30.54% to 47.07%, achieving absolute gains of over 16 percentage points in both correct object pair retention and end-to-end target relation retrieval performance. Full article

Nonlinear state estimation plays an important role in aerospace sensing applications, where estimation accuracy must be balanced against computational efficiency. In this paper, a sparse-grid Gaussian kernel quadrature Kalman filter (SGKQKF) is proposed for discrete-time nonlinear state estimation by combining Gaussian kernel quadrature (GKQ) weighting with a Smolyak sparse-grid construction. The univariate GKQ rule is constructed on scaled Gauss–Hermite nodes through a truncated Mercer eigendecomposition of the Gaussian kernel and is then extended to multivariate cases via the Smolyak construction to alleviate the curse of dimensionality associated with tensor-product rules. The proposed method is positioned within the established sparse-grid filtering framework, with the specific contribution of integrating kernel-adapted quadrature weights into sparse-grid structures for discrete-time nonlinear Gaussian filtering. For fixed nodes, the exact kernel-quadrature weights minimize the worst-case integration error in the reproducing kernel Hilbert space (RKHS) induced by the Gaussian kernel, whereas the closed-form weights used in the implementation are interpreted as a Mercer-based practical approximation to this exact rule, with the approximation error characterized through the Mercer spectral-tail expression of the Gaussian kernel. For sparse grids, where a closed-form RKHS optimality result is not available, numerical maximum mean discrepancy (MMD) evaluations are presented as empirical diagnostics in the tested configurations. Numerical experiments demonstrate that the proposed filter achieves a favorable accuracy–efficiency trade-off compared with conventional deterministic Gaussian filters. Full article

Stochastic policy reinforcement learning (RL) algorithms are widely used in industrial control due to their strong exploration ability and high sample efficiency. However, these algorithms often produce large action fluctuations and noise, making them unsuitable for steady-state chemical processes. To solve this problem, this study uses a thermal regeneration column (TRC) as the research object and selects the Soft Actor-Critic (SAC) algorithm as the baseline. Three strategies are introduced to improve the SAC algorithm: an action-amplitude-constrained reward function, a low-pass filter, and a Kalman filter. Experimental results show that the combination of the action-amplitude-constrained reward function and the Kalman filter achieves the best performance. Compared with the traditional SAC algorithm, the fluctuation amplitudes of steam consumption, cooling water consumption, sulfur concentration and methanol makeup rate are reduced by 85.50%, 82.81%, 90.84% and 85.49%, respectively. In addition, the fluctuation amplitude of the reward function decreases by 90.68%. This method not only optimizes operating costs but also ensures the stable operation of the TRC. Full article

The precise and timely diagnosis of grapevine diseases is paramount for ensuring food security and mitigating economic losses within the viticulture sector. While existing deep learning models offer high accuracy, their computational intensity and hardware requirements often hinder their use in portable or low-power field systems. This study addresses this gap by proposing GrapeLeafNet, a lightweight convolutional neural network optimized for efficient feature extraction. GrapeLeafNet introduces a strategic hybrid approach that combines the low parameter efficiency of models like SqueezeNet with the rapid feature propagation advantages offered by shallow architectures such as AlexNet. By eliminating the sequential processing latency caused by SqueezeNet’s 18-layer deep structure and the excessive 61-million-parameter memory burden of AlexNet, this model establishes a critical balance between low latency and high accuracy through its optimized 7-layer architecture. Characterized by an original integration of standard convolutional layers, batch normalization, and max pooling, GrapeLeafNet achieves high computational efficiency with only 1.6 million parameters and a 6.26 MB memory footprint. This structural optimization enhances deep feature hierarchies, enabling the model to focus on distinctive pathological signs within complex leaf patterns and maximize classification sensitivity by filtering out irrelevant features. The evaluation was conducted using the Niphad Grape Leaf Disease (NGLD) dataset, incorporating data augmentation to mitigate inherent class imbalances. Additionally, data augmentation techniques were employed to mitigate inherent class imbalances within the dataset. Experimental results demonstrate that GrapeLeafNet achieved 97.06% accuracy and a 94.77% F1-score on the original dataset, outperforming recent benchmarks by 2.46%. Following augmentation, performance reached 98.29% accuracy and a 98.16% F1-score, representing a 6.16% higher F1-score than contemporary models. GrapeLeafNet exhibits high robustness against asymmetric class distributions and establishes a significant performance margin over existing architectures. Its lightweight nature, combined with superior accuracy and F1-score metrics, makes it an ideal candidate for integration into mobile devices and real-time agricultural monitoring systems. Full article

Rooftop photovoltaic (PV) potential assessments have advanced significantly through high-resolution geospatial methods. However, most studies remain focused on well-planned urban environments and primarily consider geometric or radiative factors, often neglecting material constraints and deployment realism in heterogeneous cities of the Global South. This study addresses these gaps by developing an automated LiDAR- and GIS-based methodology to estimate rooftop PV potential in Cartagena, Colombia, explicitly integrating cadastral constraints, geometric feasibility, and roof material exclusion. The workflow combines LiDAR-derived elevation data, parcel-based segmentation, slope and aspect filtering, and post-processing techniques to identify PV-suitable rooftops, validated against 482 manually delineated polygons. The optimal configuration (45° slope threshold; 0.25 m buffer) achieved RMSE values of 6.79° (slope) and 20.95° (aspect). A geometry-constrained panel fitting algorithm estimated 3,599,631 panels across 146,091 rooftops, representing 7.06 km² of suitable area. Compared to simple area-based methods, this approach reduced capacity estimates by approximately 15.3%, demonstrating the importance of geometric realism. A key contribution is the integration of asbestos-cement (AC) roof exclusion, which reduced suitable rooftop area by ~65%, resulting in a final capacity of 1,281,202 panels. Estimated annual generation decreased from 1891.9 GWh/year to 673.4 GWh/year, equivalent to supplying 53.4–126.8% of Cartagena’s households. The proposed methodology provides a scalable framework for realistic urban PV assessment and introduces a dual-purpose planning tool that enables authorities to both prioritize solar deployment and identify areas requiring roof remediation, supporting safer and more controlled energy transitions in developing-country cities. Full article

Background: Neurological disorders are a leading cause of disability worldwide, placing increasing strain on healthcare systems. In Eastern Europe, and specifically Bulgaria, there is a significant lack of granular data regarding how ambulatory neurology services are utilized and how clinical workloads are distributed across different diagnostic groups. Objective: In this study, we aimed to analyze the clinical workload, demographic patterns, and diagnostic distribution within a single-center ambulatory neurology setting in Bulgaria, while identifying the primary determinants of patient age stratification. Methods: We conducted a retrospective observational study of 518 consecutive clinical encounters recorded over a one-year period in a specialized outpatient neurology clinic. Data on age, gender, visit type (ambulatory vs. dispensary), and ICD-10 diagnostic groups were analyzed. Inferential analyses included a one-way ANOVA for age differences and multivariable linear regression to identify independent predictors of age patterns, with age modeled as a continuous variable. Results: The clinical workload was highly concentrated, with spine-related disorders accounting for over 40% of all visits, and primary consultative examinations were the predominant service type (65.4%). Statistical analysis revealed significant age differences across diagnostic categories (p < 0.001), with neurodegenerative and cerebrovascular diseases associated with the highest mean age, while spine and headache syndromes involved significantly younger populations. Multivariable modeling confirmed that diagnostic category is the sole independent determinant of age distribution (p < 0.001), whereas gender and visit type showed no significant independent associations. Conclusions: Ambulatory neurology utilization in this setting is characterized by a high-turnover primary consultation model and a heavy concentration of musculoskeletal neurological conditions. These findings suggest that outpatient neurology functions as a critical diagnostic filter and pain management hub. The study underscores the need for diagnosis-specific clinical pathways and targeted resource allocation to optimize service efficiency and improve long-term management of chronic neurological morbidity in a public insurance-driven framework. Full article

Electroencephalogram (EEG) signals, as a direct measure of the brain’s cortical electrophysiological activity, can objectively capture emotion-induced neural changes. Phase space reconstruction is an effective method for processing nonlinear time series. It maps time series to a high-dimensional phase space, thereby better preserving subtle dynamic information in the signal. This paper proposes a method for emotion recognition in EEG signals based on phase space reconstruction. First, the macro-topological features of the trajectories are constructed via phase space reconstruction. The time delay and embedding dimension are then optimized using the minimum cross-prediction error and the G-P method, followed by dimensionality reduction to a two-dimensional plane via local linear embedding. Building on this foundation, and in response to the limitations of manually designed features, we further propose a deep learning-based method for extracting multiscale dynamic features from trajectory images. The designed GN-MVXXS framework, which utilizes a granularity-adaptive module to adaptively switch the receptive field and a noise-filtering module to suppress isolated noise points, thereby effectively uncovers microscopic evolutionary features at the image level. Finally, to leverage the complementary strengths of macro- and micro-level information, we propose a fusion method based on dynamic attention. This approach aligns the dual representational dimensions through global average pooling and nonlinear dimension expansion, and utilizes a dynamic attention mechanism to adaptively assign feature weights, enabling the model to collaboratively enhance both overall dynamic patterns and local details based on sample characteristics. The experimental results show that the model achieved an accuracy of 96.11% in the three-class classification task on the SEED, 86.33% in the four-class classification task on the HIED, and 83.67% in classification across normal-hearing and hearing-impaired individuals, significantly outperforming single-feature models and traditional fusion methods. Full article

We present a hybrid algorithm for 3D obstacle-avoidance path planning of a six-axis robotic arm in cable inspection environments. It improves on traditional RRT, which suffers from blind sampling and low efficiency, and APF, which tends to become stuck in local optima and has unstable potential fields. For the bidirectional RRT, we introduce target-biased sampling and a dynamic step-size expansion strategy driven by target attraction to enhance sampling directionality. For the APF, we optimize the potential field function by incorporating shape and size factors, use simulated annealing to overcome local optima, and apply Gaussian filtering to smooth the potential field. A triangular inequality pruning strategy with a target chain is then used to optimize the initial path, combined with cubic B-spline curves for path smoothing, and we design a simplified collision detection method to reduce computational cost. Simulation experiments are carried out in 2D and 3D spaces, as well as in a robotic arm setup that mimics cable inspection. Compared with basic RRT, bidirectional RRT, and the RRT-APF fusion algorithm, our method achieves significant improvements in average iteration count, planning time, path length, and number of generated nodes. The resulting trajectories are shorter and smoother, effectively boosting the efficiency and quality of 3D obstacle-avoidance path planning for six-axis robotic arms, and offering a practical solution for engineering scenarios such as power line inspection. Full article

This paper proposes an adaptive residual extended Kalman filter method optimized by a multi-strategy improved parrot optimization algorithm (MIPO-ARKEKF) to improve the kinematic parameter calibration accuracy and efficiency of robotic polishing systems. To address the limitations of the standard extended Kalman filter (EKF), such as truncation-error accumulation during repeated linearization and sensitivity to manually selected noise parameters, an integrated improvement framework is developed. Specifically, a gradient stabilizer based on state-estimation increments is introduced to alleviate estimation degradation caused by accumulated truncation errors, while the proposed MIPO algorithm is employed to adaptively optimize the process and measurement noise covariance matrices, thereby improving the robustness of parameter identification under practical measurement uncertainty. The calibration process is established on the basis of high-precision external measurement data obtained from the robotic polishing system. In benchmark-function tests, MIPO demonstrates superior convergence performance. In physical experiments based on a KUKA KR210 R2700 robot, the proposed MIPO-ARKEKF method reduces the root mean square positioning error from 0.8927 mm to 0.4858 mm, corresponding to a 45.58% improvement in accuracy. Compared with representative hybrid calibration methods, the proposed method achieves comparable compensation accuracy while reducing computation time by 34.88% to 65.08%. Practical polishing experiments on ultra-low-expansion glass lenses further verify that the proposed method effectively improves end-effector trajectory tracking accuracy and polishing quality, providing an efficient solution for high-precision robotic polishing. Full article

Medication recommendation, a crucial application of artificial intelligence in healthcare, has garnered widespread attention due to its research and practical value. However, existing methods often struggle to address three key challenges: misleading co-occurrence correlations, insufficient medication representation, and the balance between recommendation accuracy and drug–drug interaction (DDI). To overcome these challenges, we propose CDMed, a medication recommendation framework based on causal inference and dual-granularity information enhancement. First, the framework applies causal inference to identify and quantify the real therapeutic pathways among diseases, procedures, and medications in electronic health record (EHR), effectively filtering out spurious correlations commonly found in co-occurrence statistics. Second, by integrating coarse-grained medical entity relationships with fine-grained molecular structural information, it achieves effective multi-scale information fusion and enhances medication representation. Additionally, CDMed jointly models the 2D and 3D molecular structures of medications, serving as the foundation for subsequent molecular feature extraction. Finally, to achieve a balance between recommendation accuracy and safety, we applied a DDI-Constrained Bias Correction at the output stage, which enhances recommendation accuracy while controlling clinical risks. Extensive experiments on two public datasets demonstrate that CDMed improves recommendation accuracy by 2.2%, while maintaining a low DDI rate of 0.0661 alongside high inference efficiency. This result proves that CDMed achieves an optimal balance among recommendation accuracy, safety, and computational efficiency. Full article

This paper proposes a novel neural network model that integrates a modified Volterra digital filter with a feedforward neural network for time-series modeling. In the proposed architecture, all input signals in the conventional Volterra filter are replaced by corresponding output signals, since time-series problems typically consist of observable output sequences over time without explicit external inputs. These output signals, together with their cross-product terms, are constructed as input vectors for the feedforward neural network. To optimize the network parameters, including weights and thresholds, the well-known particle swarm optimization (PSO) algorithm is employed. Based on the proposed PSO-trained neural network model, two types of time series are investigated: chaotic time series and financial time series involving exchange rates. For each case, multiple independent runs with different initial conditions are conducted to ensure the robustness of the proposed method. Furthermore, the effects of varying filter orders and population sizes on modeling performance are also examined. Full article

Accurate navigation line recognition in mature soybean fields presents significant challenges due to complex backgrounds. To address this issue, we developed an enhanced YOLOv10n-based model for robust visual navigation, and the assessment was conducted in the experimental fields of the laboratory. The dataset comprised 1363 original images collected at this site and was expanded to 5452 images through data augmentation. The study utilized an innovative data annotation approach focusing on inter-ridge navigation areas to minimize background noise from mature soybean rows. The model was optimized by integrating the CSP Multi-Scale Edge Information Enhancement (CSP-MEIE) module and a lightweight detection head. This architecture significantly improves efficiency, achieving a model size of just 4.5 MB and a parameter count of 2.137 M, while delivering a rapid detection speed of 204.1 FPS. Crucially, the model expands the effective receptive field to 96.6% (t = 99%), far exceeding the 73.0% of the baseline YOLOv10n, ensuring robust feature capture without compromising accuracy (92.6% mAP50-95). For path planning, path points were extracted and predicted using a combination of Kalman filtering and adaptive segmentation. Field experiments demonstrated the system’s effectiveness, achieving an average distance error of 4.53 pixels and an average angle error of 3.57°, a processing speed of 28.17 ms per frame, and a navigation line recognition accuracy of 98.05%. These findings highlight the method’s capability to meet real-time agricultural requirements, offering a reliable visual perception and decision-making basis for autonomous navigation in complex field environments. Full article

A novel double-criterion early stopping pruning strategy is introduced in this study. The proposed approach enables the structural optimization of a hybrid filtering framework that integrates FeedForward Neural Networks with an adaptive Extended Kalman Filter, by simultaneously monitoring the validation error and the trace of the error covariance matrix. Unlike classical pruning methods, which are applied after the completion of the training process and aggressively remove network neurons, the proposed scheme exploits the learning procedure, achieving a more selective reduction of 2% to 13%, balancing effectively between strong generalization performance and computationally efficient training. The proposed framework is evaluated on wind speed forecasts obtained from a numerical weather prediction model, within a time-varying window scheme, demonstrating promising improvements. Key statistical indices, such as the Mean Absolute Error and the Root Mean Square Error, were significantly reduced, with reductions ranging from approximately 65% to 80% and 60% to 78%, respectively. These findings suggest that the proposed methodology offers a robust and accurate framework for time series forecasting in operational settings. Full article