Search Results (668)

This paper provides a systematic review of recent applications of NLP methods for analyzing traffic crash reports, with a focus on estimating crash severity, crash duration, and crash causation. The review covers prior research using probabilistic topic modeling methods such as LDA, STM, and hierarchical Dirichlet processes in addition to research using transformer-based language models, which include encoder-based models like BERT and PubMedBERT as well as decoder-based models like GPT, GPT2, ChatGPT, GPT-3, and LLaMA. The review starts with a systematic literature selection process with predefined inclusion criteria. We categorize the reviewed studies into the following application areas: crash severity prediction, risk factor identification in crashes, and road safety analysis. The results show several complementary advantages of using different NLP techniques to achieve different analytical goals. Topic models allow for interpretable and exploratory pattern discovery, while encoder models are well-suited for structured prediction problems. Decoder models have the additional flexibility to perform zero-shot and few-shot reasoning, which makes them useful for reasoning about under-sampled or under-reported data. Across the literature, hybrid methods that combine text and structured data outperform individual methods in terms of prediction accuracy and broad applicability. Challenges across the literature include class imbalance, lack of standardization in preprocessing and evaluation methods, and the tradeoff between prediction accuracy and interpretability of prediction models. These findings highlight the importance of aligning model selection with data availability and operational constraints, pointing toward future research directions in hybrid modeling frameworks, standardized evaluation protocols, and real-world deployment of NLP-driven traffic safety systems. Full article

Brain tumors (BTs) arise from the abnormal growth of cells within brain tissue and may spread rapidly, making them a major cause of mortality worldwide. Early detection of BTs remains highly challenging due to the brain’s complex structure and the heterogeneous nature of tumors. Magnetic Resonance Imaging (MRI) provides detailed information about tumor size, location, and shape, thereby supporting clinical decision-making for treatments such as chemotherapy, radiation therapy, and surgery. Traditional machine learning (ML) approaches mainly rely on manual feature extraction, whereas recent advances in Computer-Aided Diagnosis (CAD) and deep learning (DL) have enabled more accurate detection of small and complex tumor regions. To improve automated tumor detection, we propose a hybrid Swin–YOLO framework that combines the Swin Transformer (ST) with the latest CNN-based YOLOv12 model. In this framework, the Swin Transformer serves as the main backbone for feature extraction, while the Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) are employed in the neck to better capture multi-scale features. For training, we used the publicly available Br35H dataset and applied data augmentation to enhance the model’s robustness and generalization capability. The experimental results show that the proposed framework achieved 99.7% accuracy, 99.4% mAP@50, and 87.2% mAP@50:95. Furthermore, we incorporated Explainable Artificial Intelligence (XAI) techniques, including Grad-CAM and SHAP, to improve the interpretability of the model by visually highlighting the tumor regions that contributed most to the prediction. In addition, we developed NeuroVision AI, a web-based application designed to support faster and more accurate clinical decision-making. Although the proposed model demonstrated strong performance on the dataset, these results should be interpreted within the context of the current experimental setting. Full article

The Industrial Internet of Things (IIoT) has become a cornerstone of modern industrial automation, enabling real-time monitoring, intelligent decision-making, and large-scale connectivity across cyber–physical systems. However, the growing scale, heterogeneity, and dynamic behavior of IIoT environments significantly expand the attack surface and challenge the effectiveness of conventional security mechanisms. In this paper, we propose DeepSense, a hybrid and adaptive anomaly and intrusion detection framework specifically designed for resource-constrained and heterogeneous IIoT deployments. DeepSense integrates three complementary components: DataSense, a realistic data pipeline and experimental testbed supporting synchronized sensor and network data processing; RuleSense, a lightweight rule-based detection layer that provides fast, deterministic, and interpretable anomaly screening at the edge; and NeuroSense, a learning-driven detection module comprising an adaptive ensemble of 22 machine learning and deep learning models spanning classical, neural, hybrid, and Transformer-based architectures. NeuroSense operates as a second detection stage that validates suspicious events flagged by RuleSense and enables both coarse-grained and fine-grained attack classification. To support rigorous and practical assessment, this work further introduces a comprehensive performance evaluation framework that extends beyond accuracy-centric metrics by jointly considering detection quality, latency, resource efficiency, and detection coverage, alongside an optimization-based process for selecting Pareto-optimal model ensembles under realistic IIoT constraints. Extensive experiments across diverse detection scenarios demonstrate that DeepSense exhibits strong generalization, lower false positive rates, and robust performance under evolving attack behaviors. The proposed framework provides a scalable and efficient IIoT security solution that meets the operational requirements of Industry 4.0 and the resilience-oriented objectives of Industry 5.0. Full article

Croatia hosts one of the most intensive recreational boating activities in the Mediterranean, with over 134,600 registered vessels along 5835 km of Adriatic coastline. This paper presents an AI-driven simulation framework for evaluating electrification pathways for the Croatian recreational vessel fleet. A key contribution is the explicit treatment of the AIS data gap: recreational vessels in Croatia are not required to carry AIS transponders, so synthetic operational profiles calibrated from manufacturer specifications and verified economic data are used instead. Six machine learning architectures are compared for vessel energy demand forecasting, with a proposed Transformer-based model achieving the best simulated performance. Fleet-weighted Monte Carlo simulation across three electrification scenarios suggests that an AI-optimised hybrid configuration can, subject to use intensity, reduce per-vessel CO₂ emissions by up to 56.8% relative to conventional engines. Techno-economic analysis shows payback periods ranging from over 15 years for low-use private owners to 7–9 years for charter operators, supporting targeted incentive design. The framework is intended to be transferable to other Mediterranean coastal regions facing comparable data and operational constraints. Full article

The demand for flexible and wearable electronics has intensified the need for conformable, high-performance, and self-sustaining power sources. Flexible supercapacitors (FSCs) and flexible batteries (e.g., lithium-ion and lithium–sulfur) are promising owing to their high-power density, long cycle life, and mechanical flexibility. A transformative solution lies in integrating these storage devices with mechanical energy harvesters, particularly triboelectric nanogenerators (TENGs), to create autonomous self-charging power systems (SCPSs). TENGs exhibit high output, versatile operational modes, material flexibility, and efficient energy harvesting from body movements. This review provides an overview of the recent advances in flexible energy storage technologies, encompassing carbon-based materials, MXenes, polymers, metal oxides, metal–organic frameworks (MOFs), and their hybrid architectures. It discusses the synergistic integration of these storage devices with TENGs to realize multifunctional SCPSs. It also highlights the fundamental design principles of flexible devices, the critical interplay of materials and architecture, and the journey towards monolithic system integration. The review also underscores the importance of managing harvesters’ pulsed output for efficient storage. Finally, a critical analysis of the challenges, including the energy density–flexibility compromise, environmental stability, and safety, is presented, alongside a forward-looking perspective on commercialization pathways for these technologies to power the next generation of autonomous wearable and sustainable electronic systems. Full article

Dynamic multi-exposure high dynamic range (HDR) image reconstruction remains challenging because it must preserve globally consistent luminance and structure while recovering fine-grained local textures from low dynamic range (LDR) inputs corrupted by saturation, under-exposure, and motion-induced artifacts. Existing CNN-based methods are effective at local detail restoration but remain limited in global context modeling, whereas Transformer-based methods improve long-range interaction but can still weaken local-detail refinement. Current hybrid designs suggest that the two representation types are complementary, but they do not fully address branch specialization, cross-branch collaboration, and local-feature reliability control. To address this gap, we propose a dual-branch Transformer-CNN framework with a base branch built on Window-based Residual Transformer Blocks (WRTBs), a detail branch equipped with Detail-Aware Gating (DAG) for reliability-aware local refinement, and Bidirectional Cross-Branch Fusion (BCBF) for stage-wise collaboration between the two branches. Experiments on Kalantari17, the Tel benchmark, and Challenge123 show that the proposed design remains competitive on the standard benchmark, achieving the best HDR-VDP2 and tied best with $\mu$-SSIM on Kalantari17, while yielding clearer gains on the more challenging Tel and Challenge123 benchmarks. Full article

The growing interconnection of critical engineering infrastructure through IoT introduces unprecedented exposure to cyber threats. Emerging quantum computing capabilities pose a transformative risk to classical cryptographic primitives such as Rivest–Shamir–Adleman and Elliptic-Curve Cryptography, which underpin secure communication and device authentication in industrial control systems, power grids, transportation networks, and healthcare infrastructure. This paper investigates quantum-resistant encryption, often termed post-quantum cryptography (PQC), as a sustainable security paradigm for IoT communication within critical systems. By analyzing lattice-based, code-based, multivariate, and hash-based schemes, the study evaluates trade-offs between computational cost, memory footprint, and latency constraints intrinsic to resource-limited IoT nodes. A hybrid architectural framework integrating the National Institute of Standards and Technology-standardized algorithms (e.g., Cryptographic Suite for Algebraic Lattices—Kyber, Dilithium) with lightweight symmetric primitives (e.g., Ascon, GIFT block cipher in Combined Feedback mode) is proposed for secure data transmission across heterogeneous IoT layers. Experimental simulations benchmark key-exchange throughput, ciphertext expansion, and resilience against quantum-adversarial models, demonstrating up to 65% reduction in handshake latency compared to baseline lattice implementations under constrained conditions. The paper concludes with policy and engineering recommendations for the adoption of quantum-resistant IoT protocols in energy, transportation, and industrial automation sectors, highlighting alignment with global PQC migration roadmaps and IEC 62443 cybersecurity standards. Full article

This article presents an integrated design studio pedagogy for flood-resilient urban waterfronts that employs groundscape strategies, treating the ground as an active design medium to generate hybrid structures integrating landscape, architecture, and infrastructure. Implemented at the Fay Jones School of Architecture and Design (Fall 2024), the studio challenged students to transform North Little Rock’s flood-vulnerable riverfront by replacing conventional levee infrastructure with ground-based public architectural interventions. The study adopts a pedagogical case-study approach, examining a studio cohort in which all projects were developed under shared site conditions, design constraints, and instructional frameworks. Five assignments progressed from collaborative precedent analysis to individual technical development, integrating computational modeling, performance simulations, and expert consultations across structural, envelope, MEP, and site engineering. Student work is analyzed through comparative sectional diagrams and selected in-depth project studies to evaluate how groundscape functioned as a shared solution type for multiscalar integration. The results show that groundscape operates productively when tested against specific site constraints rather than deployed as a generalized esthetic. In response to flood elevations, degraded ecology, and limited public access, students developed distinct ground-based operations—such as embedding, lifting, and integrating flood walls as spatial thresholds—demonstrating architecture’s capacity to mediate between civic space, environmental performance, and flood protection. By situating groundscape within a problem-oriented pedagogy, the study consolidates modernist, postmodern, and contemporary groundscape discourse and demonstrates how architectural education can engage productively with climate-adaptation challenges. Full article

Background/Objectives: Diabetes is a chronic metabolic disorder affecting global health, where early prediction can significantly reduce disease severity. Methods: This research proposes an interpretable multi-metric fuzzy distance-based ensemble (MMFDE) that integrates multi-variant gradient-boosting classifiers (GBM, LightGBM, XGBoost, and AdaBoost) through a novel fuzzy fusion mechanism designed for intrinsic interpretability. Unlike conventional ensembles relying on opaque averaging or voting, MMFDE transforms base classifier predictions into a high-dimensional fuzzy space quantified via a weighted hybrid distance incorporating Euclidean, Manhattan, Chebyshev, and cosine metrics against ideal diabetic and non-diabetic reference vectors. These distances are translated into membership degrees with the help of exponentially decaying functions, which give clinicians calibrated confidence scores for every prediction. Comprehensive SHAP analysis identifies important clinical risk factors (glucose, BMI, and diabetes pedigree function), which show concordance with the medical literature, thereby giving greater clinical trust. Results: Experimental evaluations on two publicly available datasets, Hospital Frankfurt Germany Diabetes Dataset (HFGDD) and Pima Indians Diabetes Dataset (PIDD), show that MMFDE outperforms all base models with a significant accuracy of 94.83% and Area Under the Curve (AUC) of 97.66% on HFGDD and three different levels of interpretability: geometric transparency via distance-based decisions, confidence-calibrated uncertainty estimates, and feature-level explanations via SHAP. The confidence thresholds enabled in the framework support risk stratification clinical workflows with high-confidence predictions for automated screening and cases with moderate/low confidence flagged out for review by the clinician. Conclusions: By demonstrating that high performance and interpretability need not be mutually exclusive, MMFDE advances trustworthy AI for clinical decision support, addressing the critical need for transparent and clinically actionable diabetes prediction systems. Full article

Haul roads in surface mining are critical infrastructure directly influencing operational productivity, safety, and costs. However, these networks change frequently due to ongoing mining activities, making traditional mapping methods impractical for large-scale or rapidly evolving sites. Remote sensing imagery offers a scalable alternative, yet complex backgrounds, variable road widths, and spectral similarities between roads and surrounding surfaces make accurate extraction challenging. This study proposes HRM-Net, a hybrid transformer–CNN autoencoder framework for automated extraction of mine haul roads from remote sensing imagery. HRM-Net introduces inception-like patch embedding to capture local contextual information and employs a manifold-constrained hyper-connection strategy in the attention and fusion blocks to enhance information flow across the architecture. This hierarchical design enables progressive learning of discriminative semantic representations across multiple spatial resolutions, critical for road extraction in cluttered mining environments. Trained and evaluated on diverse mine sites, HRM-Net achieved 92.53% overall accuracy, 85.12% F1-score, 75.57% mIoU, 83.57% precision, and 86.94% recall, outperforming state-of-the-art transformer-based and CNN-based segmentation models. Furthermore, model interpretability was analyzed through linear probing and boundary alignment evaluations. Results demonstrate that discriminative features emerge at early network stages and are effectively preserved throughout the architecture, while boundary predictions exhibit superior consistency compared to existing approaches. Full article

Occupational safety analytics is increasingly moving toward data-driven methodologies; however, existing models often struggle to capture the multidimensional nature of accident causation. This study presents a multimodal Hybrid Transformer-LSTM framework for classifying occupational fatalities by jointly modeling unstructured narratives, cyclical temporal features, and regional spatial indicators. Utilizing a large-scale dataset of 14,914 OSHA fatality records, the proposed architecture leverages BERT-based embeddings for semantic extraction and Bidirectional LSTMs as non-linear pattern encoders for spatiotemporal context. Conceptually grounded in the Swiss Cheese Model, the framework treats different data modalities as proxies for distinct layers of system risk, ranging from proximal unsafe acts to environmental preconditions. Experimental results show that the multimodal architecture achieves an accuracy of 84.56%, representing a 5.33% gain over unimodal BERT baselines. To address the inherent “black-box” nature of deep learning, a SHAP-based explainability framework is incorporated to quantify the contributions of both textual tokens and environmental features to the model’s decision-making process. The results indicate that integrating narrative semantics with temporal and spatial context enhances discriminative performance and enables context-aware classification within a weakly supervised setting. By providing a scalable and interpretable classification framework, this study offers a data-driven decision-support approach for safety professionals and regulatory bodies seeking to implement evidence-based risk management strategies in high-risk industrial sectors. Full article

Efficient soil fertility monitoring is essential for sustainable agriculture, food security, and environmental management across Africa, yet conventional laboratory methods remain prohibitively costly and slow for continental-scale applications. Soil spectroscopy is considered as a rapid, non-destructive alternative with transformative potential. This review provides a systematic synthesis of spectroscopic applications across Africa, encompassing laboratory, field, airborne, and satellite-based platforms, while examining major data sources including the Africa Soil Information Service (AfSIS) and GEO-CRADLE spectral libraries. We critically evaluate the evolution of modeling approaches, revealing that Partial Least Squares Regression (PLSR) dominates, but a shift toward advanced frameworks like hybrid physically based models, ensemble learning and deep neural networks is essential. Critically, we identify a pronounced imbalance wherein laboratory spectroscopy prevails while imaging and satellite-based approaches remain comparatively underutilized, despite their unparalleled potential for scaling point measurements to continental extents. The review consolidates findings on key soil properties, demonstrating consistent successes for primary constituents with direct spectral responses (i.e., organic carbon), while revealing relative uncertainty for properties inferred indirectly via covariance (e.g., available phosphorus, potassium). Despite significant local and regional progress, the absence of a standardized pan-African spectral library and the intractable transferability problem remain formidable barriers. Future research must pivot decisively toward imaging spectroscopy and satellite platforms, mitigating PLSR dominance through systematic adoption of ensemble methods, transfer learning, and model harmonization frameworks to fully operationalize these technologies in support of Africa’s sustainable development goals. Full article

The craters on the moon hold important clues about the history of impacts in our solar system. To address the limitation of traditional intelligent methods in detecting buried craters, this study proposes a novel intelligent detection approach based on DEM and gravity data. We designed a hybrid network architecture (ResNet + ViT) that combines the local feature extraction strengths of Convolutional Neural Networks with the global context modeling capabilities of Vision Transformer. By combining the complementary information from DEM and gravity anomaly data, it achieves comprehensive detection of lunar craters—from those visible on the surface to buried subsurface structures. To mitigate the inherent sample imbalance in both gravity anomaly and DEM training data, we employ a U-Net architecture augmented with residual blocks and train it using a Focal Loss function with dynamic focusing parameters. Experimental results show that: (1) The proposed method attains high segmentation accuracy, achieving a mean Intersection over Union of 81.3% on the DEM test set and 82.6% on the gravity anomaly test set, respectively. (2) Our method outperforms U-Net and its mainstream variants, achieving a precision of 89.48% and superior detection completeness. (3) Application to representative geological units, including the Wugang Basin, Archimedes Crater, and Mare Moscoviense, validates the robustness and practical utility of our method. This study, thus, provides a novel technical framework for global-scale mapping of lunar impact craters and yields new insights into the evolutionary history of the lunar surface. Full article

Accurate photovoltaic (PV) power forecasting is essential for the efficient operation of residential energy systems and microgrids, as reliable short-term predictions enable improved energy scheduling, demand management, and operational planning in distributed energy environments. In this study, one-hour-ahead forecasting of residential PV power generation is investigated using real-world data collected from multiple households within an Irish energy community. Several deep-learning architectures, including long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNN), CNN–LSTM hybrid networks, and attention-based LSTM models, are evaluated and compared with a seasonal autoregressive integrated moving average (SARIMA) statistical model. A sliding-window approach is employed to transform the PV time series into a supervised learning problem. To ensure statistical robustness, deep-learning models are evaluated using a multi-run framework, and results are reported as mean ± standard deviation based on MAE, RMSE, MAPE, and R² metrics across multiple households. The results indicate that deep-learning models achieve consistently strong forecasting performance, with GRU frequently providing the most reliable predictions across several households. For instance, in House 5, GRU achieved an RMSE of 142.02 ± 1.87 W and an R² of 0.694 ± 0.008, while in Houses 11 and 13 it attained R² values of 0.837 ± 0.002 and 0.835 0.08, respectively. However, performance varied across households, reflecting the influence of data variability and generation patterns on model effectiveness. In comparison, the SARIMA model demonstrated competitive performance and, in certain cases, outperformed deep-learning models. For example, in House 4, it achieved the lowest RMSE of 90.68 W and the highest R² of 0.709. Overall, these findings highlight that while deep-learning models offer greater adaptability and stability, statistical models remain effective for more regular PV generation patterns. Consequently, the study emphasizes the importance of evaluating forecasting models under realistic household-level conditions and demonstrates that both deep-learning and statistical approaches can provide short-term PV forecasting. Full article

This study proposes a reproducible hybrid computational model for the explainable classification of territorial vulnerability using heterogeneous tabular data. The approach integrates fuzzy logic and extreme gradient boosting in a two-stage architecture that balances interpretability and predictive performance. First, a fuzzy transformation is applied to construct interpretable risk and resilience indicators based on multi-source administrative indicators. The analytical dataset was formed by integrating 11 heterogeneous administrative sources into a single matrix of 166 territorial units and 76 features. The model was evaluated on a stratified 75/25 split of the training and test sets using the F1 score, ROC-AUC, precision, recall, and integrated quality criterion. Experimental results show that the proposed Fuzzy-XGBoost framework achieved an F1 score of 0.7333 on the test dataset, an ROC-AUC of 0.8291, and an Integrated Score of 0.768, outperforming the strongest baseline and improving recall in highly vulnerable areas. Furthermore, probabilistic threshold optimization identified an operating point at τ = 0.35, reducing the number of missed high-risk cases while maintaining acceptable specificity. The results demonstrate that fuzzy feature expansion combined with gradient boosting provides an efficient and interpretable solution for tabular risk classification and decision support problems under heterogeneity and uncertainty. Full article