Search Results (4,078)

This study develops a quantitative risk assessment framework that explicitly incorporates site-dependent variability in NATM (New Austrian Tunneling Method) tunnel construction projects. The underlying motivation is that identical risk factors can exhibit substantially different risk levels depending on project-specific site conditions. Conventional risk assessment approaches, which rely primarily on probability and impact ratings, are inherently limited in their ability to capture such variations across different project environments. To address this gap, key site condition factors affecting NATM tunnel construction were systematically identified and integrated into the existing risk assessment framework through a structured scoring and weighting process. Eight site condition factors were selected based on an extensive review of domestic and international literature, underground safety evaluation reports, tunnel design standards, geotechnical information databases, standard cost data, and expert consultation. These factors—Geotechnical Condition, Construction Schedule Float, Construction Budget Contingency, Spoil Bank Location, Likelihood of Civil Petitions, Underground Water Level, Environmental (Noise, Vibration), and Site Accessibility (Traffic Constraints)—were each quantified using a five-level scale ranging from 0.6 (very favorable) to 1.4 (very unfavorable). Subsequently, a composite site condition index was derived by combining the assigned scores with corresponding weights, and this index was incorporated as an adjustment coefficient into the conventional risk scoring system. The results demonstrate that, when the composite site condition index is considered, both the final risk magnitude and management priority vary depending on site-specific conditions, even for identical risk factors. This indicates that the proposed framework provides a more refined representation of actual project environments than traditional probability–impact-based approaches. The model can also serve as an effective decision-support tool for developing risk mitigation strategies tailored to specific site characteristics. Accordingly, the proposed model enhances the accuracy of risk assessment in tunnel projects and facilitates the rational identification of critical risks requiring prioritized management. However, because certain evaluation criteria rely on expert judgment, further validation through diverse real-world case studies and improvements to the objectivity of the evaluation framework remain necessary. Full article

Vision–Language–Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as “fold the towel” or “fly to the red building” directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with $7+$ degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robotics faces a structurally similar challenge: a drone must coordinate thrust, attitude, and increasingly gripper commands from visual observations under strict latency and payload constraints. This review covers 183 contributions spanning 2017–2026 and organized along seven dimensions: VLA architectures, training recipes, action representations, bimanual coordination (2022–2026), unmanned aerial vehicle (UAV) navigation and control (2017–2026), language grounding, and cross-cutting concerns including memory and world models. We show that the coordination strategies, training recipes, and action representations developed for bimanual VLAs transfer to unmanned aerial systems and identify fourteen research directions across both domains. Full article

The intermittent nature of distributed generators based on renewable energy sources (DGs-RESs), together with the time-varying behavior of load demand, introduces significant uncertainty into the planning and operation of active distribution networks. These uncertainties make the optimal siting and sizing of DGs-RESs and D-STATCOMs a challenging multi-objective optimization problem. This paper proposes a multi-objective Coati Optimization Algorithm (MOCOA) for the coordinated allocation of DGs-RESs and D-STATCOMs in radial distribution networks under uncertainty. The proposed framework aims to minimize total active power losses (TAPLs) and enhance the voltage stability index (VSI) while satisfying the operational constraints of the distribution system. First, the load sensitivity factor (LSF) is employed to identify the most suitable candidate buses, thereby reducing the search space and improving the computational efficiency of the optimization process. Then, MOCOA is applied to determine the optimal placement and sizing of DGs-RESs and D-STATCOMs. The uncertainties associated with load demand, solar irradiance, and wind speed are modeled using probabilistic representations, and reduced representative scenarios are considered to evaluate system performance under uncertain operating conditions. The proposed method is validated using modified IEEE 33-bus and IEEE 69-bus radial distribution networks. The simulation results demonstrate that the coordinated integration of DGs-RESs and D-STATCOMs significantly reduces TAPLs, improves the VSI, and enhances the voltage profile. In particular, increasing the number of DG/D-STATCOM units and using wind energy reduces the TAPL by 26.95% and increases the 24 h cumulative VSI from 20.16781 p.u. to 20.4162 p.u. Comparative results with other optimization techniques confirm the effectiveness, robustness, and superior performance of the proposed MOCOA for uncertainty-aware planning of active distribution networks. Full article

3D multi-object tracking (MOT) in complex and dynamic environments remains challenging due to the time-varying reliability of sensor modalities, severe occlusions, and the difficulty of distinguishing instances with similar appearances. Existing methods mainly rely on coarse category-level semantics or heuristic multimodal fusion strategies, which limits fine-grained instance discrimination and leads to unstable trajectory association under complex scenarios. Moreover, current 3D MOT frameworks generally lack the ability to leverage attribute-level semantic information for robust tracking and semantic-aware target retrieval. To address these limitations, we propose AttriMOT, a semantic-aware multimodal 3D MOT framework. Specifically, a category semantic anchoring and competition suppression mechanism is introduced to preserve discriminative fine-grained attribute information among visually similar instances. An attribute-level multimodal alignment module establishes structured correspondences across 3D geometry, 2D appearance, and textual semantics, enabling robust cross-modal representation learning. Furthermore, a parameter-free adaptive confidence fusion strategy dynamically balances LiDAR- and camera-derived trajectory confidence to improve tracking stability under varying environmental conditions. In addition, a semantic-aware trajectory selector is designed to support text-specified target retrieval and trajectory locking, enabling controllable semantic-guided 3D tracking. Extensive experiments on challenging 3D MOT benchmarks demonstrate that AttriMOT consistently outperforms state-of-the-art methods in tracking accuracy and robustness. In particular, AttriMOT achieves 1.33% improvement in HOTA and 0.54% improvement in MOTA compared with the best existing method, while also providing enhanced semantic controllability and text-guided tracking capability. Full article

Background/Objectives: Due to the utility of knowing the pathway involvement of metabolites detected in biological experiments, knowledgebases such as the Kyoto Encyclopedia of Genes and Genomes (KEGG), Reactome, and MetaCyc have annotated compound entries to specific pathways defined by the knowledgebase. However, these compound-pathway annotations are largely incomplete and are costly to obtain experimentally or curate from published scientific literature. This metabolite-pathway annotation incompleteness problem is amenable to machine learning (ML)-based solutions. But to date, no machine learning model has been trained on all three knowledgebases to maximize its performance and robustness. This may be due to inconsistencies in chemical structure representation that can confuse a model and greatly reduce generalizability. Methods: We constructed a new training dataset with roughly 50,000,000 entries using compound-pathway annotations derived from KEGG, Reactome, and MetaCyc. We trained and tested a multitask classification, graph convolutional neural network-like model that classifies compound involvement with 8056 pathways that have unique pathway representations, based on annotated compound chemical structures represented with chemical substructure features. While the initial dataset contained inconsistencies in chemical structure representations across knowledgebases, we alleviated this issue by standardizing chemical structure representation using InChI (IUPAC International Chemical Identifier) canonicalization. We compared the performance of the non-standardized versus the standardized dataset and quantified their generalizability by comparing training set compounds to their knowledgebase cross-references. Results: While the non-standardized dataset scored a mean Matthews correlation coefficient (MCC) of 0.8725 ± 0.0064, the standardized dataset scored an MCC of 0.9036 ± 0.0033. When comparing model generalizability, the non-standardized chemical structure representations had a huge 0.2687 drop in mean MCC, while the standardized chemical structure representations only had a 0.0384 drop in mean MCC. Conclusions: We constructed the largest ML-ready dataset for predicting compound-pathway involvement to date. Next, we constructed, trained, and evaluated the highest performing ML model capable of predicting the highest number of pathway annotations to date. We discovered that standardizing chemical structure representation is an essential step when predicting novel chemical structures. Full article

In response to the challenges of drastic illumination variations, large differences in fruit scale, and severe occlusion in real-field environments, this paper proposes a lightweight end-to-end detection model, termed EMBS-DETR, for tomato maturity detection. The proposed method is built upon the RT-DETR-R18 baseline framework, retaining the advantages of global modeling and end-to-end detection enabled by the Transformer architecture, while introducing targeted improvements in feature extraction and multi-scale feature fusion. In the feature extraction stage, a C2f-FDConv module is incorporated to enhance the modeling capability of high-frequency fine-grained features, such as the surface texture and color gradients of tomatoes, while reducing redundant parameter overhead. For high-level semantic representation, an improved parameter-free attention mechanism, SimAM-TF, is designed. By jointly modeling neuron energy functions and color-aware modulation, it effectively enhances feature representation under complex lighting and occlusion conditions. For multi-scale feature fusion, a novel EMBS-FPN structure is proposed. Based on bidirectional feature flow and a multi-scale weighted fusion mechanism, this structure integrates multi-branch receptive field modeling with an efficient upsampling strategy, enabling adaptive fusion of P3–P5 feature layers. This design significantly improves representation stability for objects of varying scales while maintaining model lightweight characteristics. To evaluate the proposed method, a real-field tomato maturity dataset was constructed, consisting of 2327 images collected from facility-grown pink large-fruit tomato varieties widely cultivated in North China. According to agricultural industry standards and physicochemical properties, the dataset is categorized into three classes: immature (796 images), turning stage (718 images), and mature (813 images). Experiments were conducted on an Ubuntu 20.04 platform with an NVIDIA GeForce RTX 3080 Ti GPU. The input resolution was set to 640 × 640. Standard evaluation metrics, including Precision, Recall, mAP@0.5, mAP@0.5:0.95, as well as Params, GFLOPs, and Model Size, were used for comprehensive assessment. The experimental results demonstrate that EMBS-DETR achieves 90.9% Precision, 85.7% Recall, 89.9% mAP@0.5, and 79.8% mAP@0.5:0.95. Meanwhile, with only 37.03 M parameters, 25.2 GFLOPs computational cost, and a model size of 46.3 MB, the proposed model maintains low computational and storage overhead, achieving a favorable balance between accuracy and efficiency. Compared with mainstream YOLO-based models, the proposed method demonstrates superior overall performance in complex field environments, providing effective technical support for automated tomato maturity perception and intelligent visual understanding in precision agriculture. Full article

Climate variability, environmental uncertainty, and carbon-market dynamics increasingly challenge agricultural investment and resource allocation decisions worldwide. This study proposes an integrated hybrid decision-support framework combining Long Short-Term Memory (LSTM) deep learning, Interval Type-2 Fuzzy Logic Systems, and Genetic Algorithms to support climate-resilient agricultural investment analysis under uncertainty. The framework integrates predictive modeling, uncertainty representation, and multi-objective optimization within a unified computational architecture. The empirical analysis was conducted using agricultural, climate, and carbon-market datasets covering Europe, Asia, and Africa over the 2010–2025 period. Agricultural productivity indicators, commodity price variables, climate-risk parameters, and carbon-market data were integrated into the modeling process. LSTM models were employed to analyze temporal agricultural and climate-related dynamics, while Interval Type-2 fuzzy systems were used to represent ambiguity associated with environmental and market uncertainty. Genetic Algorithms were subsequently applied to optimize investment allocation under conflicting objectives related to profitability, sustainability, and risk. The findings suggest that the proposed hybrid framework may improve adaptive investment evaluation and optimization performance under uncertain climate conditions relative to standalone computational approaches within the scope of the analyzed datasets. The results further highlight the importance of integrating predictive analytics, uncertainty modeling, and sustainability-oriented optimization within agricultural decision-support systems. However, the framework should be interpreted as a climate-resilient decision-support architecture rather than a universally deterministic forecasting mechanism. Overall, the study contributes to the emerging literature on agricultural sustainability and climate-resilient investment by presenting a transparent and uncertainty-aware computational framework under evolving environmental and carbon-market conditions. Full article

Background/Objectives: Although deep learning methods have achieved promising performance in recent years, comparatively less attention has been given to explicitly modeling periodic and multi-scale temporal dynamics for ECG-specific representation learning within TimesNet-based frameworks. In this work, we propose an ECG-specific TimesNet-based framework for multi-label classification of multi-lead ECG recordings that incorporates periodicity-aware temporal modeling. Methods: The proposed framework utilizes Fast Fourier Transform (FFT)-guided temporal decomposition to identify dominant frequency components and reshapes ECG sequences into period-aligned representations to better capture intra-period morphological patterns and inter-period rhythm dependencies. Multi-scale convolutional TimesBlocks are further employed to learn rhythm-aware and morphology-aware temporal representations. Results: The proposed framework was evaluated on the PTB-XL dataset using two experimental settings: Three-Class classification (NORM, AFIB, PVC) and Five-Class classification (NORM, AFIB, MI, PVC, STTC). Experiments were conducted using a one-vs-rest multi-label learning strategy with independent class probability estimation. The framework achieved mean one-vs-rest test AUC values of 0.956 and 0.913 for the Three-Class and Five-Class settings, respectively. Experimental results indicated that the reduced classification complexity in the Three-Class setting was associated with improved feature separability, more stable decision boundaries, and enhanced discriminative representation learning. Latent-space visualization using UMAP and PCA demonstrated clearer clustering in the Three-Class configuration, while gradient-based interpretability analysis highlighted physiologically relevant ECG waveform regions contributing to model predictions. In addition, computational profiling demonstrated practical feasibility with approximately 1.957 million trainable parameters, 13.14 GFLOPs computational complexity, 5.230 ms average inference latency per ECG recording, and a throughput of approximately 191 ECG recordings per second on GPU hardware. Conclusions: These findings suggest that periodicity-aware temporal modeling can improve ECGF representation learning while demonstrating practical potential for computationally efficient and interpretable automated ECG analysis applications. Full article

Skin cancer image data often exhibit long-tailed distributions due to the inherent challenges in data collection and annotation. Specifically, a few predominant classes dominate a dataset of interest, while minority classes, referred to as tail classes, are underrepresented with only limited numbers of samples. Such imbalance is highly likely to adversely affect the performance of deep learning models. To address this issue, previous methods employ mixup techniques to synthesize tail-class images, thereby attempting to balance the training data. However, traditional mixup methods typically do not specifically pay attention to specific regions of interest, blending two images with indistinction between objects of interest and background. Such disregard for important semantic features may result in synthetic samples with broken or distorted diagnostic features. In this work, we introduce a novel framework, the Tail-synthetic Learning for Boosting Long-tailed Skin Cancer Image Classification (TailBoost) framework. Our approach generates a new tail-class image by combining a tail-class image with a head-class image under the guidance of their corresponding saliency maps. This strategy, namely SPMix, preserves and enhances the discriminative features of the tail-class image with minimum interference from the head-class image. We further refine the learned representations by incorporating supervised contrastive learning with class-center rebalance. Extensive experiments on the ISIC2018, ISIC2019, and PAD-UFES-20 datasets demonstrate that TailBoost outperforms existing state-of-the-art long-tailed learning methods. Full article

This article examines remittances not only as financial transfers but also as datafied political objects shaped by measurement, modelling and presentation infrastructures. Using the UK–Romania corridor, we compare observed personal remittance receipts published by the National Bank of Romania (NBR) with model-based bilateral estimates associated with World Bank/KNOMAD data. The article develops an analytical framework that links quantification, metric power, algorithmic governmentality, hybrid media circulation and emerging bottom-up social policies. It then shows how nominal values, real values at constant 2021 prices, year-by-year changes, moving-average smoothing, employment-scaled scenarios and transfer-balance indicators generate different representations of diaspora contribution, welfare substitution and national economic performance. Rather than assigning final authority to one dataset, the article demonstrates how calculation and presentation choices become communicative interventions. The conclusion emphasises methodological transparency and the need to connect remittance statistics to both political communication and community-level welfare practices. Full article

Objective: To develop and validate a fully automated deep learning workflow that localizes key anatomical landmarks on standard canine hindlimb lateral radiographs, derives the tibial plateau angle (TPA), and recommends a saw blade size for tibial plateau leveling osteotomy (TPLO) preoperative planning. Study Design: Retrospective validation study. Animals: Two hundred annotated lateral radiographs obtained from 130 dogs representing 14 breeds, with body weights ranging from 2.4 to 38.0 kg. Methods: A customized four-stage U-Net was trained using three complementary grayscale representations (normalized, contrast-enhanced, and gamma-adjusted images) to detect five TPLO-related landmarks. A deterministic geometric module then calculated TPA and mapped the derived osteotomy geometry to the nearest clinically available saw blade class. Results: The mean absolute error for TPA prediction was 1.34 ± 1.73°, and the median absolute error was 0.75°. Overall, 164/200 cases (82.0%) were within 2° and 188/200 cases (94.0%) were within 4.8° of the surgeon reference. Mean bias was −0.39°, the 95% limits of agreement ranged from −4.62° to 3.85°, and Pearson’s correlation coefficient was 0.87. For saw blade size prediction, mean absolute error was 0.32 ± 0.85 mm, exact agreement was achieved in 175/200 cases (87.5%), and all predictions remained within one adjacent class. Conclusions: The proposed pipeline provided clinically useful automated estimates of TPA and saw blade size from routine lateral radiographs. However, occasional high-impact landmark failures remained, indicating that the system should be positioned as an interpretable decision-support tool that requires surgeon verification rather than as an unsupervised autonomous planning system. Full article

Object detection in UAV remote sensing imagery is confronted with three primary challenges: severe scale variation, densely clustered small targets, and constrained computational resources. This work introduces a family of lightweight detection models guided by the “Capacity-Aware Configuration Regularity” and incorporates a Feature-Refinement C2f module to enhance representational efficiency. A dynamic coupling mechanism is identified between detection head capacity and the representational quality of Backbone features, which is further validated through systematic ablation studies spanning three parameter magnitudes. Evaluated on the VisDrone2019 benchmark, the proposed model family exhibits a progressive parameter scaling from 1.67 M to 6.15 M. The nano variant achieves 31.7% mAP₅₀ using only 55% of the parameter budget of YOLOv8n, surpassing it by 0.7 percentage points. The small variant, with a parameter budget comparable to YOLOv8n, attains 36.7% mAP₅₀, exceeding it by 5.7 points. The medium variant reaches 43.1% mAP₅₀ with 58% of the parameters of YOLOv8s, outperforming it by 4.1 points. The improvements are pronounced under the stricter mAP_50–95 metric, where the small variant outperforms YOLOv8n by 3.3 points and the medium variant surpasses YOLOv8s by 2.8 points, demonstrating robust localization accuracy across a wide range of IoU thresholds. This consistent superiority in the accuracy–efficiency trade-off extends to the DIOR dataset, confirming the robust generalization of the proposed models across diverse remote sensing scenarios. Moreover, the uncovered capacity-matching regularity offers transferable methodological guidance for designing lightweight detection models tailored to resource-constrained platforms. Full article

UAV object detection remains challenging due to large scale variation, dense small objects, frequent occlusion, and complex background interference. Existing CNN-based detectors are often limited by weak small-object representation, while Transformer-based detectors may not adequately preserve local details in dense aerial scenes. This paper proposes a dual-path detection framework that integrates frequency-domain enhancement with large-kernel convolution and Transformer-based global modeling. An FFT Large-Kernel Convolution (FFLKC) module is introduced to enhance high-frequency details and enlarge the effective receptive field. A Transformer pathway with Full-Process Feature Attention (FPFA) is designed to strengthen long-range dependency modeling and semantic representation. A Frequency-Semantic Memory-guided Adaptive Fusion (FMSAF) module is further employed to integrate local detail features and global contextual information. Experiments on UAVDT and VisDrone demonstrate that the proposed method achieves superior overall detection performance and stronger small-object perception than mainstream detectors. The method reaches 58.7 $AP$ and 51.8 $A{P}_S$ on UAVDT, and 39.4 $AP$ and 30.5 $A{P}_S$ on VisDrone. Qualitative and quantitative results verify the effectiveness of the proposed design in improving detection quality under complex UAV backgrounds. Full article

Previous studies have shown that, after postoperative recovery from upper and lower gastrointestinal surgery for cancer, patients use peculiar modalities to describe their health. The purpose of this study is to determine how upper and lower gastrointestinal cancer surgery is considered by patients when they set their health. A structured interview was developed and 47 consecutive patients were interviewed postoperatively. Answers were analyzed through M.A.D.I.T., a quantitative and qualitative methodology that allows for the detection of discursive processes comprising the text, beyond thematic analysis. Four dimensions have been analyzed: representation of the postoperative period in daily life; use of resources; participation in achieving the clinical objective after hospital discharge; and continuing to respect the surgeons’ indications. A corpus of 2374 text occurrences was analyzed. Without differences between types of surgery, surgical patients described the time after surgical intervention as a critical scenario. Patients expressed their personal opinions, expecting normality after surgery and having difficulty envisioning the future: their representation of inflexibility in the postoperative period prevented them from finding new coping strategies. Overall, across all four dimensions, participants used stabilization discursive modalities in more than 50% of cases, representative of a situation bound within strict ties and personal theories. When defining their health, cancer surgery patients tend not to consider their condition as a new and different one from before; they imagine that they will be able to fully resume their previous habits. However, this can risk undermining the achievement of the clinical objective. Thus, during early surgical consultations, as well as in surgical recovery, exploring differences after surgery and solutions could help patients in their engagement with surgical outcomes and consequences. Full article

Objectives: The rise in the frequency of mental health concerns (depression and suicide) expressed on social media calls for reliable, explainable, and efficient computational methods for mental health surveillance. In this paper, we propose an interpretable framework for text-based detection of post- and community-level mental health risk on social media. Methods: The framework combines (i) Secretary Bird Optimization (SBO) for feature selection of informative linguistic and psychological features, (ii) a BERT (Bidirectional Encoder Representations from Transformers)—CNN (Convolutional Neural Network) model for post-level reasoning, and (iii) a Graph Neural Network (GraphSAGE) for community-level reasoning. The graph is estimated based on semantic similarity between posts and author relations, instead of social interactions (e.g., mentions, replies) between authors. We use SHAP and LIME for model interpretability, uncertainty, and calibration analysis to evaluate the trustworthiness of predictions. Results: The model delivers 93.1% accuracy, 0.91 F1-score, and 0.944 ROC-AUC on the eRisk and CLPsych datasets using a strict user-disjoint validation strategy. SBO lowers the number of features by about 38%, leading to better generalization. The graph-based model enables improved learning of post and user representations by capturing relational dependencies. Conclusions: Our approach offers an explainable and robust means of detecting mental health risk from text. Graph-based representations of semantic and authorship interactions enable community-level analyses, while interpretability and uncertainty estimation facilitate possible human-in-the-loop decision-making. This research does not explicitly consider a human-in-the-loop experiment. Full article