Search Results (33,302)

This work introduces the MassSeg-Framework, a fully automatic two-stage pipeline for breast mass analysis in mammography that integrates YOLOv11-based detection with Chan–Vese ACM refinement to achieve accurate mass localization and segmentation with a lightweight computational footprint. The framework was trained and evaluated on two publicly available datasets using consistent experimental protocols. In the detection stage, YOLOv11-nano was the most effective architecture, with a confidence threshold of 0.4, achieving statistically significant mAP50 values of 0.862 and 0.709 on the dINbreast and dCBIS datasets, respectively. These results confirm that a moderate threshold preserves clinically relevant true-positive candidates, which is particularly important for screening-oriented settings where missed lesions are costly. In the segmentation stage, the proposed framework achieved mean DICE scores of 0.721 and 0.700 on the test sets of the same datasets, demonstrating consistent overlap with expert annotations. Compared with state-of-the-art approaches that commonly assume lesion-centered ROIs or rely on heavier backbones, the proposed pipeline addresses a more realistic scenario by performing automatic detection followed by segmentation while maintaining substantially lower computational requirements. This balance between performance and efficiency makes the MassSeg-Framework a promising tool for scalable mammography analysis, particularly in resource-constrained environments or high-throughput screening workflows that require rapid processing. Full article

As optical access networks continue to evolve toward higher capacity, longer reach, and increased user density, accurately predicting transmission performance has become increasingly complex. Conventional physics-based models often struggle to capture the nonlinear and stochastic behavior of modern passive optical networks (PONs), particularly under diverse operating conditions. In this study, a hybrid deep learning (DL) framework is proposed for the prediction of key performance indicators, including Q-factor, receiver sensitivity, and bit error rate (BER), in asymmetric 160/80 Gbps TWDM-PON systems, which is the target capacity by ITU-T G.989.1 specifications. The proposed approach integrates Gradient Boosting Regression and Multi-Layer Perceptron models within an ensemble learning structure to enhance robustness and predictive accuracy. A synthetic dataset comprising 1000 samples was generated to emulate realistic transmission scenarios with variations in distance, power level, and noise conditions for both upstream and downstream channels. Experimental results demonstrate strong agreement between the proposed DL-based predictions and conventional optical simulation outcomes, while the proposed predictions achieve superior adaptability and reduced computational complexity. High coefficients of determination (R² > 0.94) and low error metrics confirm the effectiveness of the framework, highlighting its potential as a fast and reliable alternative to traditional performance evaluation methods in next-generation optical access networks. Full article

Open-pit mining operations rely heavily on visual inspection to identify indicators of slope instability such as surface cracks. Early identification of these geotechnical hazards enables timely safety interventions to protect both workers and assets in the event of slope failures or landslides. While computer vision (CV) approaches offer a promising avenue for autonomous crack detection, their effectiveness remains constrained by the scarcity of labelled geotechnical datasets. Deep learning (DL)-based models, in particular, require large amounts of representative training data to generalize to unseen conditions; however, collecting such data from operational mine sites is limited by safety, cost, and data confidentiality constraints. To address this challenge, this study proposes a novel hybrid game engine–generative artificial intelligence (AI) framework for large-scale dataset generation without requiring real-world training data. Leveraging a parameterized virtual environment developed in Unreal Engine 5 (UE5), the framework generates realistic images of open-pit surface cracks and enhances their fidelity and diversity using StyleGAN2-ADA. The synthesized datasets were used to train the YOLOv11 real-time object detection model and evaluated on a held-out real-world dataset of open-pit slope imagery to assess the effectiveness of the proposed framework in improving model generalizability under extreme data scarcity. Experimental results demonstrated that models trained using the proposed framework consistently outperformed the UE5 baseline, with average precision (AP) at intersection over union (IoU) thresholds of 0.5 and [0.5:0.95] increasing from 0.792 to 0.922 (+16.4%) and 0.536 to 0.722 (+34.7%), respectively, across the best-performing configurations. These findings demonstrate the effectiveness of hybrid generative AI frameworks in mitigating data scarcity in CV applications and supporting the development of scalable automated slope monitoring systems for improved worker safety and operational efficiency in open-pit mining. Full article

This paper presents a systematic methodology for time-domain modeling of three-phase power transformers aimed at electromagnetic transient analysis in shipboard and embedded electrical systems. Accurate modeling of transformers in such environments is critical, as naval power systems are subject to strict electromagnetic compatibility (EMC) requirements and are particularly susceptible to fast transients caused by switching operations, fault events, and nonlinear loads operating in confined and isolated grids. The proposed approach combines the Vector Fitting (VF) algorithm with Clarke modal decomposition to obtain stable, passive, and causal rational approximations of the frequency-dependent admittance matrix over a wide frequency range. The admittance matrix is first identified from frequency-domain measurements or simulations, capturing the transformer’s terminal behavior across multiple frequency sub-bands. Clarke’s transformation is then applied to decouple the three-phase system into independent modal components—namely the zero-sequence and positive-sequence modes, reducing the original multi-phase problem to a set of independent single-phase systems. This modal decoupling significantly improves computational efficiency without sacrificing accuracy, as each mode can be fitted and simulated independently. Full article

Polyhalite, K₂SO₄•MgSO₄•2CaSO₄•2H₂O, a ternary evaporite mineral, is commonly found in evaporitic rock salt strata, where it acts as an indicator mineral for potash evaporite deposits. As a directly exploitable mineral potash fertilizer, polyhalite serves as an important substitute for potassium resources. The thermodynamic properties of polyhalite remain poorly characterized experimentally; consequently, current estimates predominantly rely on predictive modeling and indirect experimental approaches. The Raman spectra of free SO₄²⁻ vibrational modes in various sulfate minerals are sensitive to the local symmetry and hydrogen-bonding environment within crystal hydrates, and are directly influenced by the surrounding crystal field. This sensitivity makes Raman spectroscopy a powerful tool for investigating and identifying the crystal structures of sulfate minerals. In this work, the thermodynamic and Raman vibrational properties of polyhalite were investigated using density functional theory (DFT). Phonon calculations at the optimized geometry were employed to compute polyhalite’s key thermodynamic properties—specific heat, entropy, enthalpy, Gibbs free energy, and Debye temperature—over a temperature range of 0–1000 K. The results showed that: (1) the computed volume exhibited minimal error, approximately 0.87%, compared to experimental data; (2) the calculated values for the isobaric heat capacity and entropy were 420.72 and 531.39 J·mol⁻¹·K⁻¹ at 298.15 K, respectively; and (3) the calculated value for the free energy of formation at 298.15 K was −5670 kJ·mol⁻¹. The computed Raman spectrum results showed that the typical spectral features of polyhalite are: (1) ν1 for 1024 cm⁻¹, symmetric stretching mode; (2) ν2 for 464 cm⁻¹, symmetry bending mode; and (3) ν4 for 627 cm⁻¹, anti-symmetry bending mode. Full article

The Internet of Things (IoT) comprises diverse devices connected through heterogeneous communication protocols to deliver a wide range of services. However, the complexity and scale of IoT networks make them difficult to secure. Network intrusion detection systems (NIDSs) have therefore become essential for identifying malicious activities and protecting IoT environments across many applications. Although recent deep learning (DL)-based IDS approaches achieve strong detection performance, they often require substantial computation and storage, which limits their practicality on resource-constrained IoT devices. To balance detection accuracy with computational efficiency, we propose a lightweight deep learning model for IoT intrusion detection. Specifically, our method learns compact, intrusion-relevant representations from traffic features using a two-layer multi-layer perceptron (MLP) embedding backbone, followed by a linear SoftMax classification head for multi-class attack detection. We evaluate the proposed approach on three benchmark datasets, CICIDS2017, NSL-KDD, and CICIoT2023, and the results show strong performance, achieving 99.85%, 99.21%, and 98.45% accuracy, respectively, while significantly reducing model size and computational overhead. The experimental results demonstrate that the proposed method achieves excellent classification performance while maintaining a lightweight design, with fewer parameters and lower FLOPs than existing approaches. Full article

Automated pavement distress classification using high-resolution Unmanned Aerial Vehicle (UAV) imagery is pivotal for intelligent transportation systems. However, long-term UAV monitoring faces a continuous stream of evolving distress types and changing remote sensing background textures, necessitating Class-Incremental Learning (CIL) capabilities. Existing methods struggle to balance stability and plasticity, especially under the severe storage limitations typical of local edge stations in air–ground collaborative systems. This data scarcity leads to catastrophic forgetting and confusion among fine-grained distress categories. To address these challenges, we propose a data-efficient approach named Analytic Geometric Alignment (AGA). Our framework mainly consists of three key components. First, to overcome the optimization gap between the feature extractor and the fixed geometric target, we introduce a Subspace-Aware Analytic Initialization (SAI) that computes a closed-form projection to instantly align the feature subspace with the ETF manifold before each task training. Second, on this aligned basis, a Decoupled Geometric Adapter (DGA) is incorporated to facilitate continuous non-linear adaptation to complex aerial textures. Finally, for stable incremental training, we design a Memory-Prioritized Regression (MPR) loss to enforce tighter geometric constraints on replay samples, significantly enhancing model stability. Extensive experiments on the UAV-PDD2023 dataset demonstrate that AGA significantly outperforms state-of-the-art methods, showcasing excellent robustness and data efficiency. Full article

To enhance fleet replenishment efficiency and ensure navigational safety, this paper investigates the Underway Replenishment Routing Problem (URRP), focusing on the dynamic characteristics of receiving ships. Mathematical models for replenishment ship travel time and formation vessel speed adjustment are formulated, explicitly considering navigational state transitions and formation stability (risk control). Consequently, a dynamic route optimization model is constructed to provide intelligent decision support for fleet commanders. An intelligent optimization algorithm, the Hybrid Genetic Algorithm with Adaptive Variable Neighborhood Search (HGA-AVNS), is proposed to solve this model. Computational results demonstrate that the proposed approach outperforms the traditional empirical replenishment strategy, validating its effectiveness in enhancing maritime safety and operational efficiency. Extensive sensitivity analyses further reveal that under the strict premise of maintaining formation stability, appropriately reducing the cruise speed can offset the increase in overall speed over ground (SOG) induced by following ocean currents, thereby preventing systematic time loss. Additionally, fine-tuning the execution timing of sudden tactical turning based on the replenishment ship’s real-time operational status can further maximize overall replenishment efficiency without compromising navigational safety. Full article

Guaranteeing equitable access to computational thinking (CT) remains a persistent challenge in computing education, particularly across socioeconomically diverse school contexts. Although prior research has demonstrated the effectiveness of block-based and physical computing environments, limited empirical evidence has examined whether structured instructional mediation can compensate for contextual disparities. This quasi-experimental pre–post study addresses this gap by analyzing CT development in three socioeconomically diverse primary schools in Chile ($N=88$, third grade), including private urban, public urban, and rural public institutions. Students engaged in scaffolded Scratch programming and Arduino simulation activities designed to explicitly support abstraction, sequencing, and debugging processes. These activities were framed within a broader STEAM learning approach, integrating computational thinking with problem-solving, experimentation, and interdisciplinary reasoning. Statistical analysis revealed significant differences in instructional time across contexts ($F(2,85)=14.62$, $p<0.001$, ${\eta }^2=0.26$), indicating structural disparities in pacing. However, no statistically significant differences were observed in CT gains ($F(2,85)=0.31$, $p=0.74$), suggesting that structured pedagogical scaffolding buffered contextual inequalities. These findings provide empirical evidence from a Latin American non-WEIRD context and advance the conceptualization of instructional mediation as a compensatory mechanism for equity in early computing education. This study contributes to digital equity research by demonstrating that instructional design quality may play a more decisive role than infrastructural availability in enabling computational thinking development for all learners. Full article

Onboard GNSS-based relative baseline determination has emerged as a primary solution for formation-flying satellites dedicated to mapping and remote sensing missions. For ambiguity resolution (AR), the double-difference (DD) method is widely adopted in relative baseline determination. However, this method entails relatively complex satellite pairing, which not only increases computational load and complicates the processing workflow but also imposes higher requirements on onboard embedded computing and storage resources, thereby introducing potential risks to engineering implementation. To address these issues, this paper proposes incremental refinements to the single-difference (SD) model by introducing the combined GPS/BDS uncombined SD method for closely spaced formation satellites. By leveraging the enhanced satellite visibility of the combined GPS/BDS constellation and adopting a purely geometric approach, high-precision real-time relative baseline determination results are achieved. Validation using onboard observation data from the Lutan-1 satellite mission of China demonstrates that centimeter-level relative baseline determination accuracy can be attained. Full article

This paper proposes an accelerated Riemannian conjugate gradient method based on the Barzilai-Borwein (BB) technique, termed ABBSRCG, for unconstrained optimization on Riemannian manifolds. Building upon classical Riemannian conjugate gradient frameworks, the method enhances step-size selection through a Wolfe-condition-informed strategy and incorporates a dynamic mechanism that adaptively adjusts the computed step length. The resulting algorithm achieves both high efficiency and numerical stability. Compared to conventional approaches such as the Fletcher-Reeves (FR)- type Riemannian conjugate gradient method, the Dai-Yuan (DY)- type Riemannian conjugate gradient method, ABBSRCG maintains the sufficient descent property regardless of whether a line search is used or not. Under mild assumptions, we establish the global convergence of ABBSRCG for u-strongly geodesically convex functions on Riemannian manifolds. Experiments on sphere and oblique manifolds show that ABBSRCG requires fewer iterations and achieves higher computational efficiency than existing Riemannian conjugate gradient methods, confirming its efficiency and reliability for large-scale Riemannian optimization problems. Full article

In this paper, we investigate the relative navigation of two underwater vehicles in a leader–follower configuration when the only available inter-vehicle acoustic measurement is Doppler-derived range-rate, i.e., the rate of change in range, with no direct range measurement. We show that, in this setting, estimation performance depends critically on motion geometry: under unfavorable configurations and overly “radial” relative motion, some uncertainty components cannot be effectively reduced, and the available information decays rapidly as the separation increases. We propose a practical, quantitative approach to assessing these effects over time, based on information measures computed in a sliding time window and the corresponding theoretical accuracy bounds. Building on this, we construct information maps for representative maneuvers that highlight regions of “good” and “poor” geometry and explain when and why the estimator loses stability. We complement Monte Carlo simulation results with a reinforcement learning experiment in which a control policy learns to both maintain the formation and generate maneuvers that improve estimation conditions in the Doppler-only regime. The results demonstrate that motion control explicitly accounting for trajectory informativeness can significantly increase task success compared with control strategies that ignore these limitations. Full article

Sentiment analysis of online game reviews has increasingly become important in understanding player experiences and supporting data-driven game development. However, research in this domain has continuously faced two unresolved challenges: (1) the extreme imbalance between positive and negative feedback, and (2) the inefficiency of existing feature-weighting schemes in capturing sentiment signals embedded in informal gaming discourses. Prior works demonstrated that negative feedback—though a few in number are highly influential—usually contain richer emotional content and longer textual structures; yet, prevailing classification models often perform poorly for these minorities (i.e., negative feedback). Numerous studies explored multimodal imbalance issues, class imbalance in cross-lingual ABSA (Aspect-Based Sentiment Analysis), reinforcement-learning-based architectures for imbalanced extraction tasks, and oversampling strategies like SMOTE (Synthetic Minority Over-sampling Technique) variants. Few investigations specifically addressed imbalanced sentiment classification in the contexts of online game reviews, where user-generated content exhibits unique lexical, structural, and emotional characteristics. To address these gaps, this study integrated TF-IDF (Term Frequency-Inverse Document Frequency), VADER (Valence Aware Dictionary and Sentiment Reasoner) lexicon features, and IGM (Inverse Gravity Moment) weightings with advanced oversampling methods such as ADASYN (Adaptive Synthetic Sampling Approach for Imbalanced Learning) and Borderline-SMOTE to improve the detection of minority sentiment classes. Ensemble models, including XGBoost (Extreme Gradient Boosting) and LightGBM (Light Gradient-Boosting Machine), were further employed to enhance the robustness of imbalance. Using a large-scale dataset of Steam game reviews, the proposed framework demonstrated substantial improvement in identifying negative sentiments, addressing a critical limitation in the existing computational game-analysis literature, and advancing the modeling for detecting the emotion-rich but imbalance-prone user feedback. Full article

Understanding and predicting how tourists move through a city is a challenging task, as it involves a complex interplay of spatial, temporal, and social factors. Traditional recommender systems often rely on structured data, trying to capture the nature of the problem. However, recent advances in Large Language Models (LLMs) open new possibilities for reasoning over richer, text-based representations of user context, even without a dedicated pre-training phase. In this study, we investigate the potential of LLMs to interpret and predict tourist movements in a real-world application scenario involving tourist visits to Verona, a municipality in Northern Italy, between 2014 and 2023. We propose an incremental prompt engineering approach that gradually enriches the model input, from spatial features alone to richer behavioral information, including visit histories, time information, and user cluster patterns. The approach is evaluated using six open-source models, enabling us to compare their accuracy and efficiency across various levels of contextual enrichment. The results provide a first insight about the abilities of LLMs to incorporate spatio-temporal contextual factors, thus improving predictions, while maintaining computational efficiency. The analysis of the model-generated explanations completes the picture by adding an interpretability dimension that most existing next-PoI prediction solutions lack. Overall, the study demonstrates the potential of LLMs to integrate multiple contextual dimensions in tourism mobility, highlighting the possibility of a more text-oriented, adaptive, and explainable T-RS. Full article

In Transformer-based image restoration models, the self-attention mechanism often introduces attention noise from irrelevant contextual feature, hindering the recovery of underlying clear content. Although many methods have been proposed to suppress attention noise, we note that most existing approaches are often developed for general vision tasks and fail to generalize across remote sensing image dehazing, where large-scale spatial structures pose additional challenges for attention modeling. How to effectively model scale-aware attention to suppress redundant activations becomes crucial for remote sensing image dehazing. In this paper, we propose a scale-adaptive differential Transformer (SDTformer), an architecture designed to suppress attention noise through a differential attention mechanism, thereby improving reconstruction fidelity. Specifically, the model incorporates a scale-adaptive differential self-attention module, which models contextual dependencies across different spatial scales and reduces redundant contextual interference by computing differential attention maps. Additionally, a dynamic differential feed-forward network is proposed to adaptively select informative spatial features, strengthening feature aggregation. To further enhance feature representation, a gated fusion module is introduced to aggregate multi-scale features generated by different encoder blocks, which facilitates the learning process of each decoder block and improves the final reconstruction performance. Extensive experimental results on the commonly used benchmarks show that our method achieves favorable performance against state-of-the-art approaches. Full article