Search Results (5,718)

Addressing key challenges in unstructured environments, including local optimum traps, limited real-time interaction, and convergence difficulties, this research pioneers a hybrid reinforcement learning approach that combines simulated annealing (SA) with proximal policy optimization (PPO) for robotic arm trajectory planning. The framework enables the accurate, collision-free grasping of randomly appearing objects in dynamic obstacles through three key innovations: a probabilistically enhanced simulation environment with a 20% obstacle generation rate; an optimized state-action space featuring 12-dimensional environment coding and 6-DoF joint control; and an SA-PPO algorithm that dynamically adjusts the learning rate to balance exploration and convergence. Experimental results show a 6.52% increase in success rate (98% vs. 92%) and a 7.14% reduction in steps per set compared to the baseline PPO. A real deployment on the AUBO-i5 robotic arm enables real machine grasping, validating a robust transfer from simulation to reality. This work establishes a new paradigm for adaptive robot manipulation in industrial scenarios requiring a real-time response to environmental uncertainty. Full article

(1) Objective: This study is aiming at the key problems, such as insufficient detection accuracy of small targets and complex background interference in remote-sensing image target detection; (2) Methods: by optimizing the YOLOv10x model architecture, the YOLO-KRM model is proposed. Firstly, a new backbone network structure is constructed. By replacing the C2f of the third layer of the backbone network with the Kolmogorov–Arnold network, the approximation ability of the model to complete complex nonlinear functions in high-dimensional space is improved. Then, the C2f of the fifth layer of the backbone network is replaced by the receptive field attention convolution, which enhances the model’s ability to capture the global context information of the features. In addition, the C2f and C2fCIB structures in the upsampling operation in the neck network are replaced by the hybrid local channel attention mechanism module, which significantly improves the feature representation ability of the model. Results: In order to validate the effectiveness of the YOLO-KRM model, detailed experiments were conducted on two remote-sensing datasets, RSOD and NWPU VHR-10. The experimental results show that, compared with the original model YOLOv10x, the mAP@50 of the YOLO-KRM model on the two datasets is increased by 1.77% and 2.75%, respectively, and the mAP @ 50:95 index is increased by 3.82% and 5.23%, respectively; (3) Results: by improving the model, the accuracy of target detection in remote-sensing images is successfully enhanced. The experimental results verify the effectiveness of the model in dealing with complex backgrounds and small targets, especially in high-resolution remote-sensing images. Full article

The complexity of fake information and the inefficiency of parameter optimization in detection models present dual challenges for current detection technologies. Therefore, this paper proposes a hybrid detection model named MIBKA-CNN-BiLSTM, which significantly improves detection accuracy and efficiency through a triple-strategy enhancement of the Black Kite Optimization Algorithm (MIBKA) and an optimized dual-channel deep learning architecture. First, three improvements are introduced in the MIBKA. The population initialization process is restructured using circle chaotic mapping to enhance parameter space coverage. The conventional random perturbation is replaced by a random-to-elite differential mutation strategy (DE/rand-to-best/1) to balance global exploration and local exploitation. Moreover, a logarithmic spiral opposition-based learning (LSOBL) mechanism is integrated to dynamically explore the opposition solution space. Second, a CNN-BiLSTM dual-channel feature extraction network is constructed, with hyperparameters such as the number of convolutional kernels and LSTM units optimized by MIBKA to enable adaptive model structure alignment with task requirements. Finally, a high-quality fake information dataset is created based on social media platforms, including CCTV. The experimental results show that our model achieves the highest accuracy on the self-built dataset, which is 3.11% higher than the optimal hybrid model. Additionally, on the Weibo21 dataset, our model’s accuracy and F1-score increased by 1.52% and 1.71%, respectively, compared to the average values of all baseline models. These findings offer a practical and effective approach for detecting lightweight and robust false information. Full article

In maritime blurred image recognition, ship collision accidents frequently result from three primary blur types: (1) motion blur from vessel movement in complex sea conditions, (2) defocus blur due to water vapor refraction, and (3) scattering blur caused by sea fog interference. This paper proposes a dual-branch recognition method specifically designed for motion blur, which represents the most prevalent blur type in maritime scenarios. Conventional approaches exhibit constrained computational efficiency and limited adaptability across different modalities. To overcome these limitations, we propose a hybrid CNN–Transformer architecture: the CNN branch captures local blur characteristics, while the enhanced Transformer module models long-range dependencies via attention mechanisms. The CNN branch employs a lightweight ResNet variant, in which conventional residual blocks are substituted with Multi-Scale Gradient-Aware Residual Block (MSG-ARB). This architecture employs learnable gradient convolution for explicit local gradient feature extraction and utilizes gradient content gating to strengthen blur-sensitive region representation, significantly improving computational efficiency compared to conventional CNNs. The Transformer branch incorporates a Hierarchical Swin Transformer (HST) framework with Shifted Window-based Multi-head Self-Attention for global context modeling. The proposed method incorporates blur invariant Positional Encoding (PE) to enhance blur spectrum modeling capability, while employing DyT (Dynamic Tanh) module with learnable α parameters to replace traditional normalization layers. This architecture achieves a significant reduction in computational costs while preserving feature representation quality. Moreover, it efficiently computes long-range image dependencies using a compact 16 × 16 window configuration. The proposed feature fusion module synergistically integrates CNN-based local feature extraction with Transformer-enabled global representation learning, achieving comprehensive feature modeling across different scales. To evaluate the model’s performance and generalization ability, we conducted comprehensive experiments on four benchmark datasets: VAIS, GoPro, Mini-ImageNet, and Open Images V4. Experimental results show that our method achieves superior classification accuracy compared to state-of-the-art approaches, while simultaneously enhancing inference speed and reducing GPU memory consumption. Ablation studies confirm that the DyT module effectively suppresses outliers and improves computational efficiency, particularly when processing low-quality input data. Full article

Accurate path-loss characterization in the upper mid-band is critical for 5G/6G outdoor planning, yet classical deterministic expressions lose fidelity at 18 GHz, and purely data-driven regressors offer limited physical insight. We present a physics-guided residual learner that couples a calibrated two-ray model with an XGBoost regressor trained on the deterministic residuals. To enlarge the feature space without promoting overfitting, synthetic samples obtained by perturbing antenna height and ground permittivity within realistic bounds are introduced with a weight of $w=0.3$. The methodology is validated with narrowband measurements collected along two straight 25 m corridors. Under cross-corridor transfer, the hybrid predictor attains $0.59$–$0.62$ dB RMSE and $R^2\ge 0.996$, reducing the error of a pure-ML baseline by half and surpassing deterministic formulas by a factor of four. Small-scale analysis yields decorrelation lengths of 0.23 m and 0.41 m; a cross-correlation peak of unity at Δ = 0.10 m confirms the physical coherence of both corridors. We achieve <1 dB error using a small set of field measurements plus simple synthetic data. The method keeps a clear mathematical core and can be extended to other priors, NLOS cases, and semi-open hotspots. Full article

This paper proposes a novel sound source localization system that combines parametric homomorphic deconvolution with neural network regression to estimate the angle of arrival from a single-channel signal. The system uses an analog adder to sum signals from three spatially arranged microphones, reducing system hardware complexity and requiring the estimation of time delays from a single-channel signal. Time delay features are extracted through parametric homomorphic deconvolution methods—Yule–Walker, Prony, and Steiglitz–McBride—and input to multilayer perceptrons configured with various structures. Simulations confirm that Steiglitz–McBride provides the sharpest and most accurate predictions with reduced model order, while Yule–Walker shows slightly better performance than Prony at higher orders. A hybrid learning strategy that combines synthetic and real-world data improves generalization and robustness across all angles. Experimental validations in an anechoic chamber support the simulation results, showing high correlation and low deviation values, especially with the Steiglitz–McBride method. The proposed sound source localization system demonstrates a compact and scalable design suitable for real-time and resource-constrained applications and provides a promising platform for future extensions in complex environments and broader signal interpretation domains. Full article

Background: Neoadjuvant chemotherapy (NAC) is the important and effective approach to treat locally advanced breast cancer (LABC). The prediction of response to NAC prior to start is an efficient approach to obtaining perspective about the effectiveness of treatment. The objective of this study is to design a machine learning pipeline to predict tumor response to NAC treatment for patients with LABC using the combination of clinical features and radiomics computed tomography (CT) features. Method: A total of 858 clinical and radiomics CT features were determined for 117 patients with LABC to predict the tumor response to NAC treatment. Since the number of features is greater than the number of samples, dimensionality reduction is an indispensable step. To this end, we proposed a novel hybrid feature selection to not only select top features but also optimize the classifier hyperparameters. This hybrid feature selection has two phases. In the first phase, we applied a filter-based strategy feature selection technique using matrix rank theorem to remove all dependent and redundant features. In the second phase, we applied a genetic algorithm which coupled with the SVM classifier. The genetic algorithm determined the optimum number of features and top features. Performance of the proposed technique was assessed by balanced accuracy, accuracy, area under curve (AUC), and F1-score. This is the binary classification task to predict response to NAC. We consider three models for this study including clinical features, radiomics CT features, and a combination of clinical and radiomics CT features. Results: A total of 117 patients with LABC with a mean age of 52 ± 11 were studied in this study. Of these, 82 patients with LABC were the responder group (response to NAC) and 35 were the non-response group to chemotherapy. The best performance was obtained by the combination of clinical and CT radiomics features with Accuracy = 0.88. Conclusion: The results indicate that the combination of clinical features and CT radiomic features is an effective approach to predict response to NAC treatment for patients with LABC. Full article

Ultra-short-term wind power forecasting is challenged by high volatility and complex temporal patterns, with traditional single-model approaches often failing to provide stable and accurate predictions under diverse operational scenarios. To address this issue, a framework based on the TCN-ELM hybrid model with temporal alignment clustering and feature refinement is proposed for ultra-short-term wind power forecasting. First, dynamic time warping (DTW)–K-means is applied to cluster historical power curves in the temporal alignment space, identifying consistent operational patterns and providing prior information for subsequent predictions. Then, a correlation-driven feature refinement method is introduced to weight and select the most representative meteorological and power sequence features within each cluster, optimizing the feature set for improved prediction accuracy. Next, a TCN-ELM hybrid model is constructed, combining the advantages of temporal convolutional networks (TCNs) in capturing sequential features and an extreme learning machine (ELM) in efficient nonlinear modelling. This hybrid approach enhances forecasting performance through their synergistic capabilities. Traditional ultra-short-term forecasting often focuses solely on historical power as input, especially with a 15 min resolution, but this study emphasizes reducing the time scale of meteorological forecasts and power samples to within one hour, aiming to improve the reliability of the forecasting model in handling sudden meteorological changes within the ultra-short-term time horizon. To validate the proposed framework, comparisons are made with several benchmark models, including traditional TCN, ELM, and long short-term memory (LSTM) networks. Experimental results demonstrate that the proposed framework achieves higher prediction accuracy and better robustness across various operational modes, particularly under high-variability scenarios, out-performing conventional models like TCN and ELM. The method provides a reliable technical solution for ultra-short-term wind power forecasting, grid scheduling, and power system stability. Full article

Sensors are widely used in inland waterway buoys to monitor their position, but the collected data are often affected by noise, outliers, and irregular sampling intervals. To address these challenges, a standardized data processing framework is proposed. Outliers are identified using a hybrid approach combining interquartile range filtering and Isolation Forest algorithm. Interpolation methods are adaptively selected based on time intervals. For short-term gaps, cubic spline interpolation is applied, otherwise, a method that combines dominant periodicity estimation with physical constraints based on power spectral density (PSD) is proposed. An adaptive unscented Kalman filter (AUKF), integrated with the Singer motion model, are applied for denoising, dynamically adjusting to local noise statistics and capturing acceleration dynamics. Afterwards, a set of time-frequency features are extracted, including centrality, directional dispersion, and wavelet transform-based features. Taking the lower Yangtze River as a case study, representative buoys are selected based on dynamic time warping similarity. The features analysis result show that the movement of buoys is closely related to the dynamics dominated by the semi-diurnal tide, and is also affected by runoff and accidents. The method improves the quality and interpretability of buoy motion data, facilitating more robust monitoring and hydrodynamic analysis. Full article

The construction sector is particularly prone to financial instability, with insolvencies occurring more frequently among micro- and small-scale firms. The current study explores the application of artificial intelligence (AI) and machine learning (ML) models for predicting insolvency within this sector. The research combined a structured literature review with empirical analysis of construction sector-level insolvency data spanning the recent decade. A critical review of studies highlighted a clear shift from traditional statistical methods to AI/ML-driven approaches, with ensemble learning, neural networks, and hybrid learning models demonstrating superior predictive accuracy and robustness. While current predictive models mostly rely on financial ratio-based inputs, this research complements this foundation by introducing additional sector-specific variables. Empirical analysis reveals persistent patterns of distress, with micro- and small-sized construction businesses accounting for approximately 92% to 96% of insolvency cases each year in the Australian construction sector. Key risk signals such as firm size, cash flow risks, governance breaches and capital adequacy issues were translated into practical features that may enhance the predictive sensitivity of the existing models. The study also emphasises the need for digital self-assessment tools to support micro- and small-scale contractors in evaluating their financial health. By transforming predictive insights into accessible, real-time evaluations, such tools can facilitate early interventions and reduce the risk of insolvency among vulnerable construction firms. The current study combines insights from the review of AI/ML insolvency prediction models with sector-specific feature derivation, potentially providing a foundation for future research and practical adaptation in the construction context. Full article

This project presents the development of an open-source educational platform based on an automotive Electrically Excited Synchronous Machine (EESM) repurposed from a KIA Sportage mild-hybrid vehicle. The introduction provides an overview of hybrid drive systems and the primary configurations employed in automotive applications, including classifications based on power flow and the placement of electric motors. The focus is placed on the parallel hybrid configuration, where a belt-driven starter-generator assists the internal combustion engine (ICE). Due to the proprietary nature of the original control system, the unit was disassembled, and a custom control board was designed using a Texas Instruments C2000 Digital Signal Processor (DSP). The motor features a six-phase dual three-phase stator, offering improved torque smoothness, fault tolerance, and reduced current per phase. A compact Anisotropic Magneto Resistive (AMR) position sensor was implemented for position and speed measurements. Current sensing was achieved using both direct and magnetic field-based methods. The control algorithm was verified on a modified six-phase inverter under simulated vehicle conditions utilizing a dynamometer. Results confirmed reliable operation and validated the control approach. Future work will involve complete hardware testing with the new control board to finalize the platform as a flexible, open-source tool for research and education in hybrid drive technologies. Full article

Accurate and timely detection of islanding events is essential for ensuring the stability and safety of hybrid power systems with high penetration of distributed energy resources. Traditional islanding detection methods often face challenges related to detection speed, false alarms, and robustness under dynamic operating conditions. This paper proposes a Robust Random Vector Functional Link Network (RVFLN)-based detection framework that leverages engineered features extracted from voltage, current, and power signals in a hybrid microgrid. The proposed method integrates statistical, spectral, and spatiotemporal features—including the Dynamic Harmonic Profile (DHP), which tracks rapid harmonic distortions during disconnection, the Sub-band Energy Ratio (SBER), which quantifies the redistribution of signal energy across frequency bands, and the Islanding Anomaly Index (IAI), which measures multivariate deviations in system behavior—capturing both transient and steady-state characteristics. A real-time digital simulator (RTDS) is used to model diverse scenarios including grid-connected operation, islanding at the Point of Common Coupling (PCC), synchronous converter islanding, and fault events. The RVFLN is trained and validated using this high-fidelity data, enabling robust classification of operational states. Results demonstrate that the RVFLN achieves high accuracy (up to 98.5%), low detection latency (average 0.05 s), and superior performance across precision, recall, and F1 score compared to conventional classifiers such as Random Forest, SVM, and k-NN. The proposed approach ensures reliable real-time islanding detection, making it a strong candidate for deployment in intelligent protection and monitoring systems in modern power networks. Full article

This study explores graph-based methods to model and analyze the semantic interplay between editorial taxonomies and user-generated folksonomies on the PornHub platform, using a dataset of over 97,000 videos (2015–2024). We construct and examine a graph of user-assigned tags and platform-defined categories, applying the Leiden community detection algorithm to uncover latent semantic groupings. To enrich the graph structure, we embed textual metadata using state-of-the-art language models (Qwen3-Embedding-4B and all-MiniLM-L6-v2), enabling the integration of natural language processing within graph-based learning. Our analysis reveals that folksonomies partially align with taxonomies through synonymous structures but also diverge by capturing nuanced attributes such as body features and aesthetic styles. These asymmetries highlight how folksonomies introduce higher-resolution semantic layers absent from fixed-category systems. By fusing graph mining, NLP-driven embeddings, and network-based clustering, this work contributes a hybrid methodology for semantic knowledge extraction in large-scale, user-generated content. It offers implications for graph-based recommendation, content moderation, and metadata enrichment—demonstrating the utility of graph-centric AI techniques in real-world multimedia data settings. Full article

The rapid expansion of bike-sharing systems has introduced significant management challenges related to spatial-temporal demand fluctuations and inefficient e-fence capacity allocation. This study proposes a Spatio-Temporal Graph Attention Transformer Network (STGATN), a novel hybrid deep learning framework for dynamic demand forecasting in bike-sharing e-fence systems. The model integrates Graph Convolutional Networks to capture complex spatial dependencies among urban functional zones, Bi-LSTM networks to model temporal patterns with periodic variations, and attention mechanisms to dynamically incorporate weather impacts. By constructing a city-level graph based on POI-derived e-fences and implementing multi-source feature fusion through Transformer architecture, the STGATN effectively addresses the limitations of static capacity allocation strategies. The experimental results from Shenzhen’s Nanshan District demonstrate the performance, with the STGATN model achieving an overall Mean Absolute Error (MAE) of 0.0992 and a Coefficient of Determination (R²) of 0.8426. This significantly outperforms baseline models such as LSTM (R²: 0.6215) and a GCN (R²: 0.5488). Ablation studies confirm the model’s key components are critical; removing the GCN module decreased R² by 12 percentage points to 0.7411, while removing the weather attention mechanism reduced R² by nearly 5 percentage points to 0.8034. The framework provides a scientific basis for dynamic e-fence capacity management, advancing spatio-temporal prediction methodologies for sustainable transportation. Full article

Electricity demand forecasting is essential for smart grid management, yet it presents challenges due to the dynamic nature of consumption trends and regional variability in usage patterns. While federated learning (FL) offers a privacy-preserving solution for handling sensitive, region-specific data, traditional FL approaches struggle when local datasets are limited, often leading models to overfit noisy peak fluctuations. Additionally, many regions exhibit stable, periodic consumption behaviors, further complicating the need for a global model that can effectively capture diverse patterns without overfitting. To address these issues, we propose Federated Hybrid Graph Attention Network with Two-step Optimization for Electricity Consumption Forecasting (FedHMGAT), a hybrid modeling framework designed to balance periodic trends and numerical variations. Specifically, FedHMGAT leverages a numerical structure graph with a Gaussian encoder to model peak fluctuations as dynamic covariance features, mitigating noise-driven overfitting, while a multi-scale attention mechanism captures periodic consumption patterns through hybrid feature representation. These feature components are then fused to produce robust predictions. To enhance global model aggregation, FedHMGAT employs a two-step parameter aggregation strategy: first, a regularization term ensures parameter similarity across local models during training, and second, adaptive dynamic fusion at the server tailors aggregation weights to regional data characteristics, preventing feature dilution. Experimental results verify that FedHMGAT outperforms conventional FL methods, offering a scalable and privacy-aware solution for electricity demand forecasting. Full article