Search Results (45)

Field-programmable gate array (FPGA)-based reconfigurable system-on-chip (SoC) platforms are increasingly deployed in safety-critical domains such as autonomous driving and industrial automation, yet the existing literature lacks a systematic assessment of how these designs address functional safety requirements. This paper presents a systematic review of 36 peer-reviewed studies (core period 2010–2024, with historical context from 1998) on FPGA-based reconfigurable parallel processing SoCs, analyzed through three frameworks: a convergence–divergence analysis (CDA) that provides a structured exploratory lens for identifying research trajectory trends and informing hypothesis generation; a safety-critical gap analysis benchmarked against a three-layer standard framework comprising ISO 26262 (functional safety), ISO 21448/SOTIF (safety of the intended functionality), and ISO/PAS 8800 (AI safety properties); and a four-dimensional design space taxonomy spanning reconfigurability granularity, parallelism exploitation, design automation level, and safety criticality. The analysis reveals that 33 of the 36 surveyed studies (92%) ignore safety certification entirely. While recent work has begun establishing worst-case execution time (WCET) bounds for FPGA SoC platforms, none of the surveyed FPGA-based AI accelerator studies provide WCET bounds, although recent analytical models for multi-DPU architectures demonstrate the feasibility of such analysis. FPGA CNN accelerators achieve energy efficiencies of up to 60 GOPS/W, and dynamic partial reconfiguration (DPR) yields 2–5× throughput improvements, yet these gains remain unsupported by the formal verification or uncertainty quantification mandated for safety certification. The CDA framework reveals strong convergence between DPR, network-on-chip (NoC), and high-level synthesis research threads (scores 0.72–0.91), indicating maturation toward integrated design flows. We identify conformal prediction as a distribution-free hardware-compatible framework for uncertainty quantification on resource-constrained FPGAs, motivated by requirements from ISO 21448 (triggering event identification) and ISO/PAS 8800 (runtime confidence monitoring), and propose a prioritized research agenda to bridge the gap between FPGA performance optimization and safety-certified deployment in transportation systems. Full article

Hurdle technique analysis requires accurate identification of key phases and kinematic features, but conventional biomechanical methods are often costly, equipment-dependent, and difficult to apply in front-line training. This study developed a low-cost monocular-video-based framework for rapid hurdle clearance analysis in practical training settings. Thirty-seven physical education college students with different hurdling skill levels were recruited as participants, and side-view videos of their hurdle clearance were recorded. The proposed pipeline combined YOLO26 hurdle detection, RTMPose markerless pose estimation, rule-based key-event detection, phase segmentation, and phase-specific kinematic feature extraction. The results showed that the hurdle detection model achieved high accuracy, with bounding-box mAP@0.5 of 0.992 and mask mAP@0.5 of 0.971. Pose estimation showed good agreement with manual annotations, with an overall RMSE of 8.25 px and PCK of 97.64%. The rule-based phase segmentation method achieved an overall event localization MAE of 0.74 frames and RMSE of 1.55 frames, outperforming LSTM and TCN temporal baselines. Core distance and most angle variables also showed high agreement with manually recalculated values. These findings indicate that monocular video and markerless pose estimation can provide an accurate, low-cost, and practical tool for hurdle phase segmentation and kinematic assessment in routine training contexts. Full article

Dipeptidyl peptidase-4 (DPP-4) is an established therapeutic target in the treatment of type 2 diabetes mellitus (T2DM), primarily due to its role in regulating incretin activity and glucose homeostasis. Although clinically approved DPP-4 inhibitors are widely used, their moderate efficacy has driven the search for novel compounds with improved properties. In this context, natural products have attracted considerable attention as a source of structurally diverse and biologically active molecules. At the same time, molecular docking has emerged as a key computational tool for the identification and evaluation of potential DPP-4 inhibitors. This review summarizes and critically analyzes current molecular docking studies of natural compounds targeting DPP-4. Over 150 studies were evaluated with respect to docking methodologies, selection of protein structures, and validation strategies. The results reveal substantial variability in computational protocols. Frequently used protein structures include ligand-bound DPP-4 models such as 1X70 and 6B1E. Among the investigated compounds, flavonoids represent the most extensively studied class, followed by alkaloids, phenolics, terpenoids, and peptides. Despite numerous reports of favorable binding interactions within the DPP-4 active site, many studies rely solely on docking results without further validation. The limited use of molecular dynamics simulations and experimental assays highlights a significant gap in the current literature. Overall, while molecular docking provides valuable preliminary insights, improved standardization and integration with complementary approaches are essential to enhance the reliability and translational relevance of in silico findings. Full article

Melissopalynological analysis is essential for determining the botanical origin of honey, corbicular pollen and bee bread, as well as detecting adulteration. However, it traditionally relies on labor-intensive and subjective manual pollen identification. As a proof-of-concept preceding full honey analysis, this study evaluates artificial intelligence methods for automated pollen grain recognition under controlled conditions. Hazel (Corylus avellana L.) and dandelion (Taraxacum officinale F.H. Wigg.) were used as model taxa to validate the proposed approach before its application to real varietal honey samples. This study introduces a novel three-stage pipeline that decouples object detection from feature extraction, utilizing YOLOv12m for region-of-interest generation and, for the first time in melissopalynology, DINOv3 ConvNeXt-B for deep feature representation. Microscopic images acquired at 400× magnification yielded 2498 dandelion and 1941 hazel pollen grains. The detector achieved an mAP@0.5 of 0.936 with an F1 score of 0.88, while the classifier reached 98.1% accuracy with good class separability (Silhouette coefficient: 0.407). The primary technical contribution is the systematic optimization of the detection-to-classification interface. Context-aware bounding box expansion (12%) and an optimized IoU-NMS threshold (0.65) significantly improve the stability of morphological feature extraction, as confirmed by ablation studies. Computational cost reporting further supports reproducible, deployment-oriented comparison. The results confirm the feasibility of this AI-based framework as an intermediate step toward automated melissopalynological analysis, with future work focusing on standardized microscopy protocols and expanded pollen databases for varietal honey authentication. Full article

Precise identification of weeds at the maize seedling stage is pivotal for implementing Site-Specific Weed Management and minimizing herbicide environmental pollution. However, the performance of existing lightweight detectors is severely bottlenecked by unstructured field environments, characterized by the “green-on-green” spectral similarity between crops and weeds, diminutive seedling targets, and complex mutual occlusion of leaves. To address these challenges, this study proposes SLD-YOLO11, a topology-reconstructed lightweight detection model tailored for complex field environments. First, to mitigate the feature loss of tiny targets, a Lossless Downsampling Topology based on Space-to-Depth Convolution (SPD-Conv) is constructed, transforming spatial information into depth channels to preserve fine-grained features. Second, a Decomposed Large Kernel Attention (D-LKA) mechanism is designed to mimic the wide receptive field of human vision. By modeling long-range spatial dependencies with decomposed large-kernel attention, it enhances discrimination under severe occlusion by leveraging global structural context. Third, the DySample operator is introduced to replace static interpolation, enabling content-aware feature flow reconstruction. Experimental results demonstrate that SLD-YOLO11 achieves an mAP@0.5 of 97.4% on a self-collected maize field dataset, significantly outperforming YOLOv8n, YOLOv10n, YOLOv11n, and mainstream lightweight variants. Notably, the model achieves Zero Inter-class Misclassification between maize and weeds, establishing high safety standards for weeding operations. To further bridge the gap between visual perception and precision operations, a Visual Weed-Crop Competition Index (VWCI) is innovatively proposed. By integrating detection bounding boxes with species-specific morphological correction coefficients, the VWCI quantifies field weed pressure with low cost and high throughput. Regression analysis reveals a high consistency (R² = 0.70) between the automated VWCI and manual ground-truth coverage. This study not only provides a robust detector but also offers a reliable decision-making basis for real-time variable-rate spraying by intelligent weeding robots. Full article

Ensuring the quality and structural stability of industrial steel buildings requires precise geometric control during the execution stage, in accordance with assembly standards defined by EN 1090-2:2020. In this context, this work proposes a methodology that enables the automatic detection of geometric deviations by comparing the intended design with the actual as-built structure using a Terrestrial Laser Scanner. The integrated pipeline processes the 3D point cloud of the asset by projecting it into 2D images, on which a YOLOv8 segmentation model is trained to detect, classify and segment commercial steel cross-sections. Its application demonstrated improved identification and geometric representation of cross-sections, even in cases of incomplete or partially occluded geometries. To enhance generalisation, synthetic 3D data augmentation was applied, yielding promising results with segmentation metrics measured by mAp@50-95 reaching 70.20%. The methodology includes a systematic segmentation-based filtering step, followed by the computation of Oriented Bounding Boxes to quantify both positional and angular displacements. The effectiveness of the methodology was demonstrated in two field applications during the assembly of industrial steel structures. The results confirm the method’s effectiveness, achieving up to 94% of structural elements assessed in real assemblies, with 97% valid segmentations enabling reliable geometric verification under the standards. Full article

This interdisciplinary pilot study examines the use of Natural Language Processing (NLP) techniques, specifically Large Language Models (LLMs) with Prompt Engineering (PE), to analyze economic vulnerability from qualitative self-narratives. Seventy narratives from twenty-five women in the Palk Bay coastal region of Rameshwaram, India were analyzed using a schema adapted from a contextual empowerment framework. The study operationalizes theoretical constructs into structured Information Extraction (IE) templates, enabling systematic identification of multiple vulnerability aspects, contributing factors, and experiential expressions. Prompt templates were iteratively refined and validated through dual-annotator review, achieving an F1-score of 0.78 on a held-out subset. Extracted elements were examined through downstream analysis, including pattern grouping and graph-based visualization, to reveal co-occurrence structures and recurring vulnerability configurations across narratives. The findings demonstrate that LLMs, when aligned with domain-specific conceptual models and supported by human-in-the-loop validation, can enable interpretable and replicable analysis of self-narratives. While findings are bounded by the pilot scale and community-specific context, the approach supports translation of narrative evidence into community-level program design and targeted grassroots outreach, with planned expansion to multi-site, multilingual datasets for broader applicability. Full article

We introduce Causal Incentive Design (CID), a framework that applies causal inference to canonical single-stage principal–agent problems (PAPs) characterized by bilateral private information. Within CID, the operating rules of PAPs are formalized using an additive-noise causal graphical model (CGM). Incentives are modeled as interventions on a function space variable, $\Gamma$, which correspond to policy interventions in the principal–follower causal relation. The causal inference target estimand $V(\Gamma )$ is defined as the expected value of the principal’s utility variable under a specified policy intervention in the post-intervention distribution. In the context of additive-Gaussian independent noise, the estimand $V(\Gamma )$ decomposes into a two-layer expectation: (i) an inner Gaussian smoothing of the principal’s utility regression; and (ii) an outer averaging over the conditional probability of the follower’s action given the incentive policy. A Gauss–Hermite quadrature method is employed to efficiently estimate the first layer, while a policy-local kernel reweighting approach is used for the second. For offline selection of a single incentive policy, a Functional Causal Bayesian Optimization (FCBO) algorithm is introduced. This algorithm models the objective functional $\gamma \mapsto V\left(\gamma \right)$ using a functional Gaussian process surrogate defined on a Reproducing Kernel Hilbert Space (RKHS) domain and utilizes an Upper Confidence Bound (UCB) acquisition functional. Consequently, the policy value $V\left(\gamma \right)$ becomes an interventional query that can be answered using offline observational data under standard identifiability assumptions. High-probability cumulative-regret bounds are established in terms of differential information gain for the proposed FBO algorithm. Collectively, these elements constitute the central contributions of the CID framework, which integrates causal inference through identification and estimation with policy search in principal–agent problems under private information. This approach establishes a causal decision-making pipeline that enables commitment to a high-performing incentive in a single-shot game, supported by regret guarantees. Provided that the data used for estimation is sufficient, the resulting offline pipeline is appropriate for scenarios where adaptive deployment is impractical or costly. Beyond the methodological contribution, this work introduces a novel application of causal graphical models and causal reasoning to incentive design and principal–agent problems, which are central to economics and multi-agent systems. Full article

Aqueous semolina suspensions were reacted with spherical gold nanoparticles (AuNPs, nominal diameter, 20 nm) to assess the accessibility of cysteine thiols in durum wheat proteins, focusing on network-forming gluten proteins. Unlike small thiol reagents, covalent bond formation between gold ions on the AuNPs surface and protein thiols was greatly facilitated by the addition of 1% sodium dodecyl sulfate (SDS). SDS weakens non-covalent hydrophobic interactions within and among proteins, increasing the exposure of buried thiols without altering disulfide bonds. MS/MS analysis of proteolytic fragments from the isolated AuNP-protein covalent complexes allowed identification of the bound proteins. Proteomics data suggests that AuNPs also associate with gluten proteins lacking free thiols in their native structure, which are bound to AuNPs by forming disulfide bonds with other gluten proteins containing accessible thiols, via thiol-disulfide exchange reactions. This implies that thiol-disulfide reshuffling among gluten proteins occurs already in the grain, enabling proteins without free thiols to become part of AuNP-bound assemblies and revealing specific protein species involved in these early interactions. These observations highlight the role of thiol–disulfide exchange within the grain matrix, elucidating how such molecular rearrangements influence the topology and strength of protein networks in food and in related biopolymeric systems. Results of this exploratory study are discussed for their molecular relevance and for the potential use of size-based analytical and structural approaches in other biological contexts. Full article

This study presents the OGS-YOLOv8 model for coffee bean maturity identification, designed to enhance accuracy in identifying coffee beans at different maturity stages in complicated contexts, utilizing an upgraded version of YOLOv8. Initially, the ODConv (full-dimensional dynamic convolution) substitutes the convolutional layers in the backbone and neck networks to augment the network’s capacity to capture attributes of coffee bean images. Second, we replace the C2f layer in the neck networks with the CSGSPC (Convolutional Split Group-Shuffle Partial Convolution) module to reduce the computational load of the model. Lastly, to improve bounding box regression accuracy by concentrating on challenging samples, we substitute the Inner-FocalerIoU function for the CIoU loss function. According to experimental results, OGS-YOLO v8 outperforms the original model by 7.4%, achieving a detection accuracy of 73.7% for coffee bean maturity. Reaching 76% at mAP@0.5, it represents a 3.2% increase over the initial model. Furthermore, GFLOPs dropped 26.8%, from 8.2 to 6.0. For applications like coffee bean maturity monitoring and intelligent harvesting, OGS-YOLOv8 offers strong technical support and reference by striking a good balance between high detection accuracy and low computational cost. Full article

Smoke detection is a practical approach for early identification of wildfires and mitigating hazards that affect ecosystems, infrastructure, property, and the community. The existing deep learning (DL) object detection methods (e.g., Detection Transformer (DETR)) have demonstrated significant potential for early awareness of these events. However, their precision is influenced by the low visual salience of smoke and the reliability of the annotation, and collecting real-world and reliable datasets with precise annotations is a labor-intensive and time-consuming process. To address this challenge, we propose a weakly supervised Transformer-based approach with a teacher–student architecture designed explicitly for smoke detection while reducing the need for extensive labeling efforts. In the proposed approach, an expert model serves as the teacher, guiding the student model to learn from a variety of data annotations, including bounding boxes, point labels, and unlabeled images. This adaptability reduces the dependency on exhaustive manual annotation. The proposed approach integrates a Deformable-DETR backbone with a modified loss function to enhance the detection pipeline by improving spatial reasoning, supporting multi-scale feature learning, and facilitating a deeper understanding of the global context. The experimental results demonstrate performance comparable to, and in some cases exceeding, that of fully supervised models, including DETR and YOLOv8. Moreover, this study expands the existing datasets to offer a more comprehensive resource for the research community. Full article

Bud eye identification is a critical step in the intelligent seed cutting process for potatoes. This study focuses on the challenges of low testing accuracy and excessive weighted memory in testing models for potato bud eye detection. It proposes an improved potato bud eye detection method based on YOLOv5s, referred to as the YOLO-SCA model, which synergistically optimizing three main modules. The improved model introduces the ShuffleNetV2 module to reconstruct the backbone network. The channel shuffling mechanism reduces the model’s weighted memory and computational load, while enhancing bud eye features. Additionally, the CBAM attention mechanism is embedded at specific layers, using dual-path feature weighting (channel and spatial) to enhance sensitivity to key bud eye features in complex contexts. Then, the Alpha-IoU function is used to replace the CloU function as the bounding box regression loss function. Its single-parameter control mechanism and adaptive gradient amplification characteristics significantly improve the accuracy of bud eye positioning and strengthen the model’s anti-interference ability. Finally, we conduct pruning based on the channel evaluation after sparse training, accurately removing redundant channels, significantly reducing the amount of computation and weighted memory, and achieving real-time performance of the model. This study aims to address how potato bud eye detection models can achieve high-precision real-time detection under the conditions of limited computational resources and storage space. The improved YOLO-SCA model has a size of 3.6 MB, which is 35.3% of the original model; the number of parameters is 1.7 M, which is 25% of the original model; and the average accuracy rate is 95.3%, which is a 12.5% improvement over the original model. This study provides theoretical support for the development of potato bud eye recognition technology and intelligent cutting equipment. Full article

Although SAR systems can provide high-resolution aerial view images all-day, all-weather, the aspect and pose-sensitivity of the SAR target signatures, which defies the Gestalt perceptual principles, sets a frustrating performance upper bound for SAR Automatic Target Recognition (ATR). Therefore, we propose a network to support context-guided ATR by using aligned Electro-Optical (EO)-SAR image pairs. To realize EO-SAR image scene grammar alignment, the stable context features highly correlated to the parking patterns of the vehicle and aircraft targets are extracted from the EO images as prior knowledge, which is used to assist SAR-ATR. The proposed network consists of a Scene Recognition Module (SRM) and an instance-level Cross-modality ATR Module (CATRM). The SRM is based on a novel light-condition-driven adaptive EO-SAR decision weighting scheme, and the Outlier Exposure (OE) approach is employed for SRM training to realize Out-of-Distribution (OOD) scene detection. Once the scene depicted in the cut of interest is identified with the SRM, the image cut is sent to the CATRM for ATR. Considering that the EO-SAR images acquired from diverse observation angles often feature unbalanced quality, a novel class-incremental learning method based on the Context-Guided Re-Identification (ReID)-based Key-view (CGRID-Key) exemplar selection strategy is devised so that the network is capable of continuous learning in the open-world deployment environment. Vehicle ATR experimental results based on the UNICORN dataset, which consists of 360-degree EO-SAR images of an army base, show that the CGRID-Key exemplar strategy offers a classification accuracy 29.3% higher than the baseline model for the incremental vehicle category, SUV. Moreover, aircraft ATR experimental results based on the aligned EO-SAR images collected over several representative airports and the Arizona aircraft boneyard show that the proposed network achieves an F1 score of 0.987, which is 9% higher than YOLOv8. Full article

Existing frameworks for classifying the fidelity for object detection tasks do not consider false positive likelihood and object uniqueness. Inspired by the Detection, Recognition, Identification (DRI) framework proposed by Johnson 1958, we propose a new modified framework that defines three categories as visible anomaly, identifiable anomaly, and unique identifiable anomaly (AIU) as determined by human interpretation of imagery or geophysical data. These categories are designed to better capture false positive rates and emphasize the importance of identifying unique versus non-unique targets compared to the DRI Index. We then analyze visual, thermal, and multispectral UAV imagery collected over a seeded minefield and apply the AIU Index for the landmine detection use-case. We find that RGB imagery provided the most value per pixel, achieving a 100% identifiable anomaly rate at 125 pixels on target, and the highest unique target classification compared to thermal and multispectral imaging for the detection and identification of surface landmines and UXO. We also investigate how the AIU Index can be applied to machine learning for the selection of training data and informing the required action to take after object detection bounding boxes are predicted. Overall, the anomaly, identifiable anomaly, and unique identifiable anomaly index prescribes essential context for false-positive-sensitive or resolution-poor object detection tasks with applications in modality comparison, machine learning, and remote sensing data acquisition. Full article

Detecting small objects in remote sensing images is challenging due to their size, which results in limited distinctive features. This limitation necessitates the effective use of contextual information for accurate identification. Many existing methods often struggle because they do not dynamically adjust the contextual scope based on the specific characteristics of each target. To address this issue and improve the detection performance of small objects (typically defined as objects with a bounding box area of less than 1024 pixels), we propose a novel backbone network called the Dynamic Context Branch Attention Network (DCBANet). We present the Dynamic Context Scale-Aware (DCSA) Block, which utilizes a multi-branch architecture to generate features with diverse receptive fields. Within each branch, a Context Adaptive Selection Module (CASM) dynamically weights information, allowing the model to focus on the most relevant context. To further enhance performance, we introduce an Efficient Branch Attention (EBA) module that adaptively reweights the parallel branches, prioritizing the most discriminative ones. Finally, to ensure computational efficiency, we design a Dual-Gated Feedforward Network (DGFFN), a lightweight yet powerful replacement for standard FFNs. Extensive experiments conducted on four public remote sensing datasets demonstrate that the DCBANet achieves impressive mAP@0.5 scores of 80.79% on DOTA, 89.17% on NWPU VHR-10, 80.27% on SIMD, and a remarkable 42.4% mAP@0.5:0.95 on the specialized small object benchmark AI-TOD. These results surpass RetinaNet, YOLOF, FCOS, Faster R-CNN, Dynamic R-CNN, SKNet, and Cascade R-CNN, highlighting its effectiveness in detecting small objects in remote sensing images. However, there remains potential for further improvement in multi-scale and weak target detection. Future work will integrate local and global context to enhance multi-scale object detection performance. Full article