Search Results (6,814)

Background and Objectives: Hysterectomy is a common non-obstetric procedure. Minimally invasive techniques, such as laparoscopy and robot-assisted surgery, have replaced open surgery for benign gynecologic conditions. Robotic surgery offers reduced blood loss and shorter hospital stays but is limited by high costs. Articulating laparoscopic instruments aim to replicate robotic dexterity cost-effectively. However, comparative data on these two approaches in hysterectomy are limited. Materials and Methods: This multicenter study analyzed the outcomes of hysterectomies for benign gynecological diseases using articulating laparoscopic instruments (prospectively recruited) and robot-assisted surgery (retrospectively reviewed). The surgeries were performed by minimally invasive gynecological surgeons in South Korea, Japan, and Taiwan. The baseline characteristics, operative details, and outcomes, including operative time, blood loss, complications, and hospital stay, were compared. Statistical significance was set at p < 0.05. Results: A total of 151 patients were analyzed, including 67 in the articulating laparoscopy group and 84 in the robot-assisted group. The operating times were comparable (114.9 vs. 119.9 min, p = 0.22). The articulating group primarily underwent dual-port surgery (79.1%), whereas the robot-assisted group required four or more ports in 71.4% of the cases (p < 0.001). Postoperative complications occurred in both groups, without a significant difference (9.0% vs. 3.6%, p = 0.17). No severe complications or significant differences in the 30-day readmission rates were observed. Conclusions: Articulating laparoscopic instruments provide outcomes comparable to robot-assisted surgery in hysterectomy while reducing the number of ports required. Further studies are needed to explore the learning curve and long-term impact on surgical outcomes. Full article

Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems. Full article

Artificial intelligence technologies, particularly machine learning and computer vision, are being increasingly utilized to preserve, restore, and create immersive virtual experiences with cultural artifacts and sites, thus aiding in conserving cultural heritage and making it accessible to a global audience. This paper examines the performance of Generative Adversarial Networks (GAN), especially Style-Based Generator Architecture (StyleGAN), as a deep learning approach for producing realistic images of Egyptian monuments. We used Sigmoid loss for Language–Image Pre-training (SigLIP) as a unique image–text alignment system to guide monument generation through semantic elements. We also studied truncation methods to regulate the generated image noise and identify the most effective parameter settings based on architectural representation versus diverse output creation. An improved discriminator design that combined noise addition with squeeze-and-excitation blocks and a modified MinibatchStdLayer produced 27.5% better Fréchet Inception Distance performance than the original discriminator models. Moreover, differential evolution for latent-space optimization reduced alignment mistakes during specific monument construction tasks by about 15%. We checked a wide range of truncation values from 0.1 to 1.0 and found that somewhere between 0.4 and 0.7 was the best range because it allowed for good accuracy while retaining many different architectural elements. Our findings indicate that specific model optimization strategies produce superior outcomes by creating better-quality and historically correct representations of diverse Egyptian monuments. Thus, the developed technology may be instrumental in generating educational and archaeological visualization assets while adding virtual tourism capabilities. Full article

In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry. Full article

E-Learning is an emerging dominant phenomenon in education, making the development of robust models that can accurately represent the dynamic behavior of learners in MOOCs even more critical. In this article, we propose the Temporal Sparse Attention-Gated Recurrent Unit (TSA-GRU), a novel deep learning framework that combines TSA with a sequential encoder based on the GRU. This hybrid model effectively reconstructs student response times and learning trajectories with high fidelity by leveraging tthe emporal embeddings of instructional and feedback activities. By dynamically filtering noise from student interactions, TSA-GRU generates context-aware representations that seamlessly integrate both short-term fluctuations and long-term learning patterns. Empirical evaluation on the 2009–2010 ASSISTments dataset demonstrates that TSA-GRU achieved a test accuracy of 95.60% and a test loss of 0.0209, outperforming Modular Sparse Attention-Gated Recurrent Unit (MSA-GRU), Bayesian Knowledge Tracing (BKT), Performance Factors Analysis (PFA), and TSA in the same experimental design. TSA-GRU converged in five training epochs; thus, while TSA-GRU is demonstrated to have strong predictive performance for knowledge tracing tasks, these findings are specific to the conducted dataset and should not be implicitly regarded as conclusive for all data. More statistical validation through five-fold cross-validation, confidence intervals, and paired t-tests have confirmed the robustness, consistency, and statistically significant superiority of TSA-GRU over the baseline model MSA-GRU. TSA-GRU’s scalability and capacity to incorporate a temporal dimension of knowledge can make it acceptably well-positioned to analyze complex learner behaviors and plan interventions for adaptive learning in computerized learning systems. Full article

We investigate whether a belief in trend continuation, often associated with the so-called “hot-hand effect,” can be endogenously triggered by personal performance feedback in a controlled financial experiment. Participants allocated funds across assets with randomly generated prices, under conditions of known probabilities and varying levels of risk. In a two-stage setup, participants were first exposed to random price sequences to learn the task and potentially develop perceptions of personal success. They then faced additional price paths under incentivized conditions. Our findings show that participants initially increased purchases following gains—consistent with a feedback-driven belief in momentum—but this pattern faded over time. When facing sustained losses, loss aversion dominated decision-making, overriding early optimism. These results highlight how cognitive heuristics and emotional biases interact dynamically, suggesting that belief in trend continuation is context-sensitive and constrained by the reluctance to realize losses. Full article

Global Navigation Satellite System (GNSS) receivers may produce measurement outliers in real-world applications owing to various circumstances, including poor signal quality, multipath effects, data loss, satellite signal loss, or electromagnetic interference. This can lead to a noise distribution that is non-Gaussian heavy-tailed, affecting the effectiveness of satellite navigation filters. This paper presents a robust Extended Kalman Filter (EKF) based on the Maximum Correntropy Criterion with a Student’s t kernel (STMCCEKF) for GPS navigation under non-Gaussian noise. Unlike traditional EKF and Gaussian-kernel MCCEKF, the proposed method enhances robustness by leveraging the heavy-tailed Student’s t kernel, which effectively suppresses outliers and dynamic observation noise. A fixed-point iterative algorithm is used for state update, and a new posterior error covariance expression is derived. The simulation results demonstrate that STMCCEKF outperforms conventional filters in positioning accuracy and robustness, particularly in environments with impulsive noise and multipath interference. The Student’s t-distribution kernel efficiently mitigates heavy-tailed non-Gaussian noise, while it adaptively adjusts process and measurement noise covariances, leading to improved estimation performance. A detailed explanation of several key concepts along with practical examples are discussed to aid in understanding and applying the Global Positioning System (GPS) navigation filter. By integrating cutting-edge reinforcement learning with robust statistical approaches, this work advances adaptive signal processing and estimation, offering a significant contribution to the field. Full article

While horizontal roughing filters (HRFs) remain widely acclaimed for their exceptional efficiency in water treatment, especially in developing countries, they are inherently susceptible to clogging, which necessitates timely maintenance interventions. Conventional methods for managing clogging in HRFs typically involve evaluating filter head loss coefficients against established water quality standards. This study utilizes artificial neural network (ANN) for the prediction of clogging duration and effluent turbidity in HRF equipment. The ANN was configured with two outputs, the clogging duration and effluent turbidity, which were predicted concurrently. Effluent turbidity was modeled to enhance the network’s learning process and improve the accuracy of clogging prediction. The network steps of the iterative training process of ANN used different types of input parameters, such as influent turbidity, filtration rate, pH, conductivity, and effluent turbidity. The training, in addition, optimized network parameters such as learning rate, momentum, and calibration of neurons in the hidden layer. The quantities of the dataset accounted for up to 70% for training and 30% for testing and validation. The optimized structure of ANN configured in a 4-8-2 topology and trained using the Levenberg–Marquardt (LM) algorithm achieved a mean square error (MSE) of less than 0.001 and R-coefficients exceeding 0.999 across training, validation, testing, and the entire dataset. This ANN surpassed models of scaled conjugate gradient (SCG) and obtained a percentage of average absolute deviation (%AAD) of 9.5. This optimal structure of ANN proved to be a robust tool for tracking the filter clogging duration in HRF equipment. This approach supports proactive maintenance and operational planning in HRFs, including data-driven scheduling of backwashing based on predicted clogging trends. Full article

To address the substantial disparities in operational characteristics between social vehicles and dedicated bus lanes, as well as the sub-optimal coordination control effects, a comprehensive approach is proposed. This approach integrates social vehicle arterial coordination with bus priority control in dedicated bus lanes. Initially, an analysis of the differences in travel time distribution on both types of roads is conducted. The likelihood of buses passing through upstream and downstream intersections without stopping is also assessed. This analysis aids in determining the correlated traffic states and the corresponding signal adjustment strategies for arterial coordination. Subsequently, an incentive mechanism is established by quantitatively analyzing vehicle delay losses and bus priority benefits based on the signal adjustment strategy. Finally, a deep reinforcement learning framework is proposed to solve, in real-time, the optimal signal adjustment strategy. Simulation experiments indicate that, in comparison to the arterial coordination of social vehicles and dedicated bus arterial coordination control, this method significantly reduces the average per capita delay by 38.63% and 27.43%, respectively, under conventional traffic flow scenarios. This is in contrast to the separate arterial coordination for social vehicles and dedicated bus lanes. Furthermore, it leads to a reduction of 52.17% in the number of bus stops at intersections when compared solely with the arterial coordination of social vehicles. In saturated traffic flow scenarios, this method achieves a reduction in average per capita delay by 29.7% and 9.6%, respectively, while also decreasing the number of bus stops at intersections by 39.5% and 8.7%, respectively. Full article

In portfolio optimization, investors often overlook asymmetric preferences for gains and losses. We propose a distributionally robust two-stage portfolio optimization (DR-TSPO) model, which is suitable for scenarios where the loss reference point is adaptively updated based on prior decisions. For analytical convenience, we further reformulate the DR-TSPO model as an equivalent second-order cone programming counterpart. Additionally, we develop a deep learning-based constraint correction algorithm (DL-CCA) trained directly on problem descriptions, which enhances computational efficiency for large-scale non-convex distributionally robust portfolio optimization. Our empirical results obtained using global market data demonstrate that during COVID-19, the DR-TSPO model outperformed traditional two-stage optimization in reducing conservatism and avoiding extreme losses. Full article

Plant disease classification is critical for effective crop management. Recent advances in deep learning, especially Vision Transformers (ViTs), have shown promise due to their strong global feature modeling capabilities. However, ViTs often overlook local features and suffer from feature extraction degradation during patch merging as channels increase. To address these issues, we propose PLTransformer, a hybrid model designed to symmetrically capture both global and local features. We design a symmetric multi-scale convolutional module that combines two different-scale receptive fields to simultaneously extract global and local features so that the model can better perceive multi-scale disease morphologies. Additionally, we propose an overlap-attentive channel downsampler that utilizes inter-channel attention mechanisms during spatial downsampling, effectively preserving local structural information and mitigating semantic loss caused by feature compression. On the PlantVillage dataset, PLTransformer achieves 99.95% accuracy, outperforming DeiT (96.33%), Twins (98.92%), and DilateFormer (98.84%). These results demonstrate its superiority in handling multi-scale disease features. Full article

Motion-capture data provide high accuracy but are difficult to obtain, necessitating dataset augmentation. To our knowledge, no prior study has investigated few-shot generative models for motion-capture data that address both quality and diversity. We tackle the diversity loss that arises with extremely small datasets (n ≤ 10) by applying transfer learning and continual learning to retain the rich variability of a larger pretraining corpus. To assess quality, we introduce MFMMD (Motion Feature-Based Maximum Mean Discrepancy)—a metric well-suited for small samples—and evaluate diversity with the multimodality metric. Our method embeds an Elastic Weight Consolidation (EWC)-based regularization term in the generator’s loss and then fine-tunes the limited motion-capture set. We analyze how the strength of this term influences diversity and uncovers motion-specific characteristics, revealing behavior that differs from that observed in image-generation tasks. The experiments indicate that the transfer learning pipeline improves generative performance in low-data scenarios. Increasing the weight of the regularization term yields higher diversity in the synthesized motions, demonstrating a marked uplift in motion diversity. These findings suggest that the proposed approach can effectively augment small motion-capture datasets with greater variety, a capability expected to benefit applications that rely on diverse human-motion data across modern robotics, animation, and virtual reality. Full article

Various factors influence the formation and adjustment of network freight prices, including transportation costs, cargo characteristics, and policies and regulations. The interaction of these factors increases the difficulty of accurately predicting network freight prices through regressions or other machine learning models, especially when the amount and quality of training data are limited. This paper introduces large language models (LLMs) to predict network freight prices using their inherent prior knowledge. Different data sorting methods and serialization strategies are employed to construct the corpora of LLMs, which are then tested on multiple base models. A few-shot sample dataset is constructed to test the performance of models under insufficient information. The Chain of Thought (CoT) is employed to construct a corpus that demonstrates the reasoning process in freight price prediction. Cross entropy loss with LoRA fine-tuning and cosine annealing learning rate adjustment, and Mean Absolute Error (MAE) loss with full fine-tuning and OneCycle learning rate adjustment to train the models, respectively, are used. The experimental results demonstrate that LLMs are better than or competitive with the best comparison model. Tests on a few-shot dataset demonstrate that LLMs outperform most comparison models in performance. This method provides a new reference for predicting network freight prices. Full article

Unmanned Aerial Vehicles have started to be used more and more due to the benefits they bring. Failure of Unmanned Aerial Vehicle components may result in loss of control, which may cause property damage or personal injury. In order to increase the operational safety of the Unmanned Aerial Vehicle, the implementation of a Predictive Maintenance system using the Internet of Things is required. In this paper, the authors propose a new architecture of Predictive Maintenance system for Unmanned Aerial Vehicles that is able to identify the fault type of Brushless DC electric motor and determine the Remaining Useful Life of the Li-ion batteries. In order to create the Predictive Maintenance system within the Unmanned Aerial Vehicle, an architecture based on Fog Computing was proposed and Machine Learning was used to extract knowledge from the data. The proposed architecture was practically validated. Full article

A global poly-crisis of climate change, biodiversity loss, dwindling natural resources, geopolitical instability, among other complex challenges, is on the rise. Societal transformations are therefore imminent, whether intended or unintended. The key question is how to steward and facilitate such changes where fragmentation and siloed ways of working persist. The concept of synergies and the notion of synergic action could help overcome fragmented efforts to steer transformative changes. However, there exists a critical research gap in understanding the conditions needed to enable synergic action. This paper thus explores how synergic action is currently undertaken and the key essentials needed to deliver synergic action. The study uses a case study of the Yorkshire food system transformation to learn from its exemplar practitioners. The study used semi-structured interviews and a thematic analysis process to reach our two key findings. First, we highlight the three types of synergic action: (1) Non-systemic synergic action, (2) Non-systemic synergic action with multiple outcomes, and (3) Systemic synergic action. Differentiating types of synergic action can help identify where synergic action is already underway and guide more explicit efforts towards transformative change. The second key finding is the five essentials for synergic action, which are (1) leadership for synergic action; (2) networking, partnerships, and collaborations; (3) care and understanding; (4) a systems approach; and (5) intentionality for synergic action. This study brings to the fore the importance of intentionality, without which the first four essentials are less likely to coalesce. This is important to inform the reflection and learning of practitioners of systemic change about how they are currently and could be working more synergistically in the future, driven by clear intentionality. Full article