Search Results (397)

Background/Objectives: Lightweight CNNs for medical imaging remain limited. We propose TurkerNeXtV2, a compact CNN that introduces two new blocks: a pooling-based attention with an inverted bottleneck (TNV2) and a hybrid downsampling module. These blocks improve stability and efficiency. The aim is to achieve transformer-level effectiveness while keeping the simplicity, low computational cost, and deployability of CNNs. Methods: The model was first pretrained on the Stable ImageNet-1k benchmark and then fine-tuned on a collected plantar-pressure OA dataset. We also evaluated the model on a public blood-cell image dataset. Performance was measured by accuracy, precision, recall, and F1-score. Inference time (images per second) was recorded on an RTX 5080 GPU. Grad-CAM was used for qualitative explainability. Results: During pretraining on Stable ImageNet-1k, the model reached a validation accuracy of 87.77%. On the OA test set, the model achieved 93.40% accuracy (95% CI: 91.3–95.2%) with balanced precision and recall above 90%. On the blood-cell dataset, the test accuracy was 98.52%. The average inference time was 0.0078 s per image (≈128.8 images/s), which is comparable to strong CNN baselines and faster than the transformer baselines tested under the same settings. Conclusions: TurkerNeXtV2 delivers high accuracy with low computational cost. The pooling-based attention (TNV2) and the hybrid downsampling enable a lightweight yet effective design. The model is suitable for real-time and clinical use. Future work will include multi-center validation and broader tests across imaging modalities. Full article

Women entrepreneurs in rural South Africa face structural and socio-cultural barriers in accessing funding. This study investigated how existing financial structures and support programs influence the sustainability and growth of female-owned businesses in rural areas. Using bibliometric analysis and sentiment mapping with ATLAS.ti, 36 documents were analyzed from a screened pool of 613, focusing on keywords, titles, and abstracts. Results reveal that over 65% of documents reflect themes of discrimination and systemic financial exclusion. Findings show that while government initiatives and non-governmental organizations’ (NGOs) efforts (e.g., Department of Small Business Development (DSBD Women’s Development Business, (WDB) are making strides, challenges, such as collateral requirements, limited financial literacy, and infrastructure gaps, persist. The originality of this research lies in its hybrid methodological approach and the emphasis on rural-centric funding misalignments. The study contributes to policy dialogues by recommending tailored financial products co-designed with rural women, improved outreach programs, and integration of gender-sensitive financing mechanisms. It also lays a foundation for further empirical studies on institutional responses to female entrepreneurship in marginal communities. This study applied a novel hybrid method, combining bibliometric analysis with sentiment mapping using ATLAS.ti to uncover both systemic patterns and discursive trends. Its policy relevance lies in offering evidence-based recommendations that align with G20 strategies on gender equity and financial inclusion. Full article

Background/Objectives: This study identifies novel dihydroorotate dehydrogenase (DHODH) inhibitors exhibiting potent broad-spectrum antiviral agents, particularly against influenza A virus (A/PR/8/34(H1N1)) and SARS-CoV-2. Methods: Structure-based virtual screening of 1.6 million compounds (ChemDiv and TargetMol databases) yielded 10 candidates, with compounds 6, 9, and 10 demonstrating significant anti-influenza activity (IC₅₀ = 4.85 ± 0.58, 7.35 ± 1.65, and 1.75 ± 0.28 μM, respectively). Building on these, molecular hybridization principles and scaffold hopping principles were applied to design and synthesize six novel compounds (11–16) through cyclization, coupling, and carboxylate deprotection. Prior to subsequent biological assays, the molecular structures of each compound were elucidated by NMR spectroscopy and MS. Their antiviral activities were subsequently assessed against both influenza virus and SARS-CoV-2. The compound 11, demonstrating the most potent antiviral activity, was further subjected to surface plasmon resonance (SPR) analysis to assess its binding affinity for human DHODH. Results: Compound 11 emerged as the most potent DHODH inhibitor (K_D = 6.06 μM), exhibiting superior broad-spectrum antiviral activities (IC₅₀ = 0.85 ± 0.05 μM, A/PR/8/34(H1N1); IC₅₀ = 3.60 ± 0.67 μM, SARS-CoV-2) to the reported DHODH inhibitor (Teriflunomide, IC₅₀ = 35.02 ± 3.33 μM, A/PR/8/34(H1N1); IC₅₀ = 26.06 ± 4.32 μM, SARS-CoV-2). Mechanistic evaluations via 100 ns MD simulations and QM/MM calculations revealed stable binding interactions, particularly hydrogen bonds with GLN47 and ARG136, while alanine scanning mutagenesis confirmed these residues’ critical roles in binding stability. Conclusions: This work identifies compound 11 as a potent broad-spectrum antiviral compound, offering a promising strategy for broad-spectrum antiviral therapy against RNA viruses by depleting pyrimidine pools essential for viral replication. Full article

The transition to a circular economy has increased the significance of reusable plastic container (RPC) pooling systems in green logistics. These systems are third-party reliant; selecting an appropriate service provider becomes crucial, particularly when measured against Environmental, Social, and Governance (ESG) principles. This study proposes a novel decision-making paradigm that incorporates ESG considerations into the evaluation process of RPC pooling service providers through an SF-RANCOM-ARLON (Spherical Fuzzy Sets-Ranking Comparison-Alternative Ranking Using Two-Step Logarithmic Normalization) hybrid method. A real-world case study involving multiple RPC service providers is presented to ensure that the proposed framework is appropriate. It determined 13 sub-criteria under 4 essential headings in the direction of assessing. Not only does this approach provide decision-makers with a methodical and unbiased approach for selecting the leading RPC pooling service provider within an uncertain environment, but it also helps in determining the necessary criteria for RPC pooling service provider selection. Based on rankings, the most critical criteria for service provider selection are delivery reliability, service flexibility, and customer relationship management, while less emphasis is placed on information disclosure. This research contributes to the emerging discourse on ESG-integrated supplier selection and offers a decision-support tool adaptable for sustainability-oriented supply chain networks. Full article

The construction industry is characterized by complexity and high risk, making effective risk management essential for project success. Traditional risk management methods, which often rely on expert judgment and historical data, are increasingly inadequate for addressing modern construction projects’ dynamic and multifaceted challenges. This study systematically reviews applications of artificial neural networks (ANNs) in construction risk management, covering studies published between 1990 and 2024. Following PRISMA 2020 guidelines, an initial TITLE-ABSTRACT-KEYWORD search in Scopus (1990–2024) yielded 4648 records. After applying subject area and publication-type filters, 2483 records remained. Following duplicate removal, title and abstract screening reduced the pool to 132. After a full-text eligibility assessment, 86 studies were retained. Two additional studies were identified through co-citation analysis, and after the exclusion of four retracted papers, 84 studies were included in the final synthesis. Relevant peer-reviewed studies were categorized to evaluate ANN models, their applications, and key findings. The results indicate that ANNs, including backpropagation and radial basis function networks, have been applied effectively in cost estimation, schedule prediction, safety assessment, and quality control tasks. They offer advantages compared with conventional approaches, such as improved pattern recognition, faster data processing, and more accurate risk evaluation. At the same time, critical challenges persist, including data quality, computational demands, and the interpretability of outputs. To address these issues, studies increasingly recommend integrating ANNs with hybrid approaches such as fuzzy logic, genetic algorithms, and Monte Carlo simulations, as well as leveraging real-time data through IoT and BIM frameworks. This review contributes to theory and practice by consolidating fragmented evidence, distinguishing theoretical and practical contributions, and offering practical recommendations for industry adoption. It also highlights future research directions, particularly the integration of hybrid models, explainable AI, and real-time data environments. Full article

Building maintenance decisions are complex and often influenced by various factors. Multi-criteria decision-making (MCDM) methods have been widely applied to address this complexity, yet guidance on selecting the most appropriate method for specific problems remains limited. Considering these, the purpose of this study is to provide a guidance for the nexus of MCDM methods and facilities management (FM) and building maintenance with the aim of supporting the selection of the most appropriate MCDM method for a specific problem. To achieve this, the study first offers a comprehensive overview of MCDM applications in FM and building maintenance through a systematic literature review guided by the PRISMA framework combined with scientometric analysis. This approach identifies key trends, reviews the methods most frequently employed, and outlines future research directions. From an initial pool of 4291 records retrieved from Scopus and Web of Science between 2000 and 2024, 107 studies were further analyzed. Using VOSviewer and Bibliometrix, the review maps the application of MCDM methods in FM and building maintenance over this period. As a major outcome of the study, a contextual MCDM Method Selection Matrix is developed, linking specific FM and maintenance problems to the most suitable MCDM methods. The findings reveal growing adoption of hybrid MCDM methods and highlight persistent challenges, including subjectivity, uncertainty, expert qualifications, methodological gaps, and technology integration in the decision-making process. By providing structured guidance on method selection, the contextual MCDM Method Selection Matrix supports researchers and practitioners in achieving consistent, data-driven, and context-sensitive decision-making, ultimately enhancing the longevity, efficiency, and sustainability of the built environment. Full article

Multi-threshold image segmentation plays an irreplaceable role in extracting discriminative structural information from complex images. It is one of the core technologies for achieving accurate target detection and regional analysis, and its segmentation accuracy directly affects the analysis quality and decision reliability in key fields such as medical imaging, remote sensing interpretation, and industrial inspection. However, most existing image segmentation algorithms suffer from slow convergence speeds and low solution accuracy. Therefore, this paper proposes an Adaptive Cooperative Pelican Optimization Algorithm (ACPOA), an improved version of the Pelican Optimization Algorithm (POA), and applies it to global optimization and multilevel threshold image segmentation tasks. ACPOA integrates three innovative strategies: the elite pool mutation strategy guides the population toward high-quality regions by constructing an elite pool composed of the three individuals with the best fitness, effectively preventing the premature loss of population diversity; the adaptive cooperative mechanism enhances search efficiency in high-dimensional spaces by dynamically allocating subgroups and dimensions and performing specialized updates to achieve division of labor and global information sharing; and the hybrid boundary handling technique adopts a probabilistic hybrid approach to deal with boundary violations, balancing exploitation, exploration, and diversity while retaining more useful search information. Comparative experiments with eight advanced algorithms on the CEC2017 and CEC2022 benchmark test suites validate the superior optimization performance of ACPOA. Moreover, when applied to multilevel threshold image segmentation tasks, ACPOA demonstrates better accuracy, stability, and efficiency in solving practical problems, providing an effective solution for complex optimization challenges. Full article

Laser Powder Bed Fusion (LPBF) has emerged as a leading additive manufacturing (AM) process for producing complex metal components. Despite its advantages, the inherent LPBF process complexity leads to challenges in achieving consistent quality and repeatability. To address these concerns, recent research efforts have focused on sensor fusion techniques for process monitoring, and on developing more elaborate control strategies. Sensor fusion combines information from multiple in situ sensors to provide more comprehensive insights into process characteristics such as melt pool behavior, spatter formation, and layer integrity. By leveraging multimodal data sources, sensor fusion enhances the detection and diagnosis of process anomalies in real-time. Closed-loop control systems may utilize this fused information to adjust key process parameters–such as laser power, focal depth, and scanning speed–to mitigate defect formation during the build process. This review focuses on the current state-of-the-art in sensor fusion monitoring and control strategies for LPBF. In terms of sensor fusion, recent advances extend beyond CNN-based approaches to include graph-based, attention, and transformer architectures. Among these, feature-level integration has shown the best balance between accuracy and computational cost. However, the limited volume of available experimental data, class-imbalance issues and lack of standardization still hinder further progress. In terms of control, a trend away from purely physics-based towards Machine Learning (ML)-assisted and hybrid strategies can be observed. These strategies show promise for more adaptive and effective quality enhancement. The biggest challenge is the broader validation on more complex part geometries and under realistic conditions using commercial LPBF systems. Full article

This paper proposes a novel intelligent optimization algorithm, ICPMSHOA, that effectively balances population diversity and convergence performance by integrating an iterative chaotic map with infinite collapses (ICMIC), centroid opposition-based learning, and periodic mutation strategy. To verify its performance, we adopted benchmark functions from the IEEE CEC 2017 and 2022 standard test suites and compared it with six algorithms, including OOA and BWO. The results show that ICPMSHOA has significant improvements in convergence speed, global search capability, and stability, with statistically significant advantages. Furthermore, the algorithm performs outstandingly in three practical engineering constrained optimization problems: Haverly’s pooling problem, hybrid pooling–preparation problem, and optimization design of industrial refrigeration systems. This study confirms that ICPMSHOA provides efficient and reliable solutions for complex optimization tasks and has strong practical value in engineering scenarios. Full article

Camouflaged object detection (COD) seeks to precisely detect and delineate objects that are concealed within complex and ambiguous backgrounds. However, due to subtle texture variations and semantic ambiguity, it remains a highly challenging task. Existing methods that rely solely on either convolutional neural network (CNN) or Transformer architectures often suffer from incomplete feature representations and the loss of boundary details. To address the aforementioned challenges, we propose an innovative hybrid architecture that synergistically leverages the strengths of CNNs and Transformers. In particular, we devise a Hybrid Feature Fusion Module (HFFM) that harmonizes hierarchical features extracted from CNN and Transformer pathways, ultimately boosting the representational quality of the combined features. Furthermore, we design a Combined Recursive Decoder (CRD) that adaptively aggregates hierarchical features through recursive pooling/upsampling operators and stage-wise mask-guided refinement, enabling precise structural detail capture across multiple scales. In addition, we propose a Foreground–Background Selection (FBS) module, which alternates attention between foreground objects and background boundary regions, progressively refining object contours while suppressing background interference. Evaluations on four widely used public COD datasets, CHAMELEON, CAMO, COD10K, and NC4K, demonstrate that our method achieves state-of-the-art performance. Full article

The self-starting capability of straight-bladed H-type Darrieus Vertical Axis Wind Turbines (VAWTs) remains a major constraint for deployment, particularly in urban, low speed, and turbulent environments. We conducted a systematic review of technological strategies to improve self-starting, grouped into five categories: (1) aerodynamic airfoil design, (2) rotor configuration, (3) passive flow control, (4) active flow control, and (5) incident flow augmentation. Searches in Scopus and IEEE Xplore (last search 20 August 2025) covered the period from 2019 to 2026 and included peer-reviewed journal articles in English reporting experimental or numerical interventions on H-type Darrieus VAWTs with at least one start-up metric. From 1212 records, 53 studies met the eligibility after title/abstract screening and full-text assessment. Data were synthesized qualitatively using a comparative thematic approach, highlighting design parameters, operating conditions, and performance metrics (torque and power coefficients) during start-up. Quantitatively, studies reported typical start-up torque gains of 20–30% for airfoil optimization and passive devices, about 25% for incident-flow augmentation, and larger but less certain improvements (around 30%) for active control. Among the strategies, airfoil optimization and passive devices consistently improved start-up torque at low TSR with minimal added systems; rotor-configuration tuning and incident-flow devices further reduced start-up time where structural or siting constraints allowed; and active control showed the largest laboratory gains but with uncertain regarding energy and durability. However, limitations included heterogeneity in designs and metrics, predominance of 2D-Computational Fluid Dynamics (CFDs), and limited 3D/field validation restricted quantitative pooling. Risk of bias was assessed using an ad hoc matrix; overall certainty was rated as low to moderate due to limited validation and inconsistent uncertainty reporting. In conclusions, no single solution is universally optimal; hybrid strategies, combining optimized airfoils with targeted passive or active control, appear most promising. Future work should standardize start-up metrics, adopt validated 3D Fluid–Structure Interaction (FSI) models, and expand wind-tunnel/field trials. Full article

This review explores the evolution and current state of machine learning (ML) and artificial intelligence (AI) applications in direct energy deposition (DED) and wire arc additive manufacturing (WAAM) processes. A Python-based automated search script was developed to systematically retrieve relevant literature using the Crossref API, yielding around 370 papers published between 2010 and July 2025. The study identifies significant growth in ML-related DED research starting in 2020, with increasing adoption of advanced techniques such as deep learning, fuzzy logic, and hybrid physics-informed models. A year-by-year trend analysis is presented, and a comprehensive categorization of the literature is provided to highlight dominant application areas, including process optimization, real-time monitoring, defect detection, and melt pool prediction. Key challenges, such as limited closed-loop control, lack of generalization across systems, and insufficient modeling of deposition-location effects, are discussed. Finally, future research directions are outlined, emphasizing the need for integrated thermo-mechanical models, uncertainty quantification, and adaptive control strategies. This review serves as a resource for researchers aiming to advance intelligent control and predictive modeling in DED-based additive manufacturing. Full article

The poultry industry, a globally fast growing agricultural sector, provides affordable animal protein due to high efficiency. Gallus gallus domesticus are the most common domestic birds. Hybrid chicken breeds (crosses) are widely used to achieve high productivity. Maintaining industry competitiveness requires constant genetic selection of parent stock to improve performance traits. Genetic studies, which are essential in modern breeding programs, help identify genome variants linked to economically important traits and preserve population health. Next-generation sequencing (NGS) has identified millions of single nucleotide polymorphisms (SNPs) and insertions/deletions (INDELs), enabling detection of genome-wide regions associated with selection traits. Recent studies have pinpointed such regions using broiler lines, laying hen lines, or pooled genomic data. This review discusses advances in chicken genomic and transcriptomic research focused on traits enhancing meat breed performance and reproductive abilities. Special attention is given to transcriptome studies revealing regulatory mechanisms and key signaling pathways involved in artificial molting, as well as metagenome studies investigating resistance to infectious diseases and climate adaptation. Finally, a dedicated section highlights CRISPR/Cas genomic editing techniques for targeted genome modification in chicken genomics. Full article

The energy management strategy of Hybrid Electric Vehicles (HEVs) plays a key role in improving fuel economy and reducing battery energy consumption. This paper proposes a Deep Reinforcement Learning-based energy management strategy optimized by the experience pool (P-HER-DDPG), aimed at improving the fuel efficiency of HEVs while accelerating the training speed. The method integrates the mechanisms of Prioritized Experience Replay (PER) and Hindsight Experience Replay (HER) to address the reward sparsity and slow convergence issues faced by the traditional Deep Deterministic Policy Gradient (DDPG) algorithm when handling continuous action spaces. Under various standard driving cycles, the P-HER-DDPG strategy outperforms the traditional DDPG strategy, achieving an average fuel economy improvement of 5.85%, with a maximum increase of 8.69%. Compared to the DQN strategy, it achieves an average improvement of 12.84%. In terms of training convergence, the P-HER-DDPG strategy converges in 140 episodes, 17.65% faster than DDPG and 24.32% faster than DQN. Additionally, the strategy demonstrates more stable State of Charge (SOC) control, effectively mitigating the risks of battery overcharging and deep discharging. Simulation results show that P-HER-DDPG can enhance fuel economy and training efficiency, offering an extended solution in the field of energy management strategies. Full article

Timely, objective pain recognition in dairy cattle is essential for welfare assurance, productivity, and ethical husbandry yet remains elusive because evolutionary pressure renders bovine distress signals brief and inconspicuous. Without verbal self-reporting, cows suppress overt cues, so automated vision is indispensable for on-farm triage. Although earlier systems tracked whole-body posture or static grimace scales, frame-level detection of facial micro-expressions has not been explored fully in livestock. We translate micro-expression analytics from automotive driver monitoring to the barn, linking modern computer vision with veterinary ethology. Our two-stage pipeline first detects faces and 30 landmarks using a custom You Only Look Once (YOLO) version 8-Pose network, achieving a 96.9% mean average precision ($mAP$) at an Intersection over the Union (IoU) threshold of 0.50 for detection and 83.8% Object Keypoint Similarity (OKS) for keypoint placement. Cropped eye, ear, and muzzle patches are encoded using a pretrained MobileNetV2, generating 3840-dimensional descriptors that capture millisecond muscle twitches. Sequences of five consecutive frames are fed into a 128-unit Long Short-Term Memory (LSTM) classifier that outputs pain probabilities. On a held-out validation set of 1700 frames, the system records 99.65% accuracy and an F1-score of 0.997, with only three false positives and three false negatives. Tested on 14 unseen barn videos, it attains 64.3% clip-level accuracy (i.e., overall accuracy for the whole video clip) and 83% precision for the pain class, using a hybrid aggregation rule that combines a 30% mean probability threshold with micro-burst counting to temper false alarms. As an early exploration from our proof-of-concept study on a subset of our custom dairy farm datasets, these results show that micro-expression mining can deliver scalable, non-invasive pain surveillance across variations in illumination, camera angle, background, and individual morphology. Future work will explore attention-based temporal pooling, curriculum learning for variable window lengths, domain-adaptive fine-tuning, and multimodal fusion with accelerometry on the complete datasets to elevate the performance toward clinical deployment. Full article