Search Results (20,543)

Accurate detection of fresh jujube fruits plays a vital role in precision agriculture, enabling reliable yield estimation and supporting automation tasks such as robotic harvesting. To address the challenges of detecting such small targets (≤32 × 32 pixels) in complex orchard environments, this study proposes JFST-DETR, an efficient and robust detection model based on the Real-Time DEtection TRansformer (RT-DETR). First, to address the insufficient feature representation for small jujube fruit targets, a novel module called the Global Awareness Adaptive Module (GAAM) is designed. Building on GAAM and the innovative Spatial Coding Module (SCM), a new Spatial Enhancement Pyramid Network (SEPN) is proposed. Through the spatial-depth transformation domain and global awareness adaptive processing units, SEPN captures fine-grained features of small targets, enhancing the detection accuracy for small objects. Second, a Dynamic Sampling (DySample) operator is adopted, which optimizes feature space details via dynamic offset calculation and lightweight design, improving detection accuracy while reducing computational costs. Finally, to solve the problem of complex background interference caused by foliage occlusion and illumination variations, Pinwheel-Shaped Convolution (PSConv) is introduced. By using asymmetric padding and multi-directional convolution, PSConv enhances the robustness of feature extraction, ensuring reliable recognition in complex agricultural environments. Experimental results show that JFST-DETR achieves precision, recall, F1, mAP@50, and mAP@50:95 of 93%, 86.8%, 89.8%, 94.3%, and 75.2%. Compared to the baseline model, these metrics improve by 0.8%, 3.7%, 2.4%, 2.6%, and 3.1%, respectively. Cross-dataset evaluations further confirm its strong generalizability, demonstrating potential as a practical solution for small-target detection in intelligent horticulture. Full article

Background: Understanding visual context in images is essential for enhanced Point-of-Interest (POI) recommender systems. Traditional models often rely on global features, overlooking object-level information, which can limit contextual accuracy. Methods: This study introduces micro-level contextual tagging, a method for extracting metadata from individual objects in images, including object type, frequency, and color. This enriched information is used to train WORLDO, a Vision Transformer model designed for multi-task learning. The model performs scene classification, contextual tag prediction, and object presence detection. It is then integrated into a content-based recommender system that supports feature configurations. Results: The model was evaluated on its ability to classify scenes, predict tags, and detect objects within images. Ablation analysis confirmed the complementary role of tag, object, and scene features in representation learning, while benchmarking against CNN architectures showed the superior performance of the transformer-based model. Additionally, its integration with a POI recommender system demonstrated consistent performance across different feature settings. The recommender system produced relevant suggestions and maintained robustness even when specific components were disabled. Conclusions: Micro-level contextual tagging enhances the representation of scene context and supports more informative recommendations. WORLDO provides a practical framework for incorporating object-level semantics into POI applications through efficient visual modeling. Full article

Most existing virtual reality exergames rely on generic VR devices, which can limit the physical exertion in VR-based exercises. In contrast, physical props can enhance exercise intensity, yet their impact on users’ performance and experience remains understudied, particularly in skill-based tasks. Meanwhile, physical props offer richer tactile and kinesthetic feedback, which, combined with the visual effects of head-mounted displays, presents a potential solution for improving user experience in VR. To explore this, this study developed a sensor-driven experimental framework for investigating high-skill VR tasks. By integrating vision sensors with standard VR devices, we constructed a VR archery system that enables objective quantification of motor performance. Leveraging the sensor-driven framework, we investigate the effects of physical props and physics-associated visual feedback on players’ performance and experience in VR tasks through an experiment involving 33 participants. By objectively quantifying performance, we reveal a dual-pathway mechanism: physical props significantly increased hand tremor, which in turn impaired aiming accuracy, but this negative effect was effectively moderated by time and physics-associated visual feedback that enabled real-time sensorimotor compensation. While complex physical props reduced task performance, they substantially enhanced enjoyment and presence, particularly demonstrating a synergistic effect on users’ flow experience when combined with physics-associated visual feedback. These findings elucidate the complex interplay between physical prop interfaces and visual feedback in high-skill VR tasks, providing valuable insights for designing VR experiences which balance performance requirements and engagement enhancement. Full article

The Elche palm grove (Spain) produces large surpluses of fresh date fruits due to low industrial processing and strict market standards. This exploratory study assessed the potential of these fruits as sustainable ingredients through the production of freeze-dried date flour and its green hydroethanolic extracts. Computer vision analysis of nine local cultivars (D1–D9) revealed broad chromatic and phenotypic diversity. Mineral and heavy metal analyses in the flour indicated high nutritional value and overall safety: D8 was richest in Mg (1.23 mg/g), P (0.78 mg/g), Fe (15.32 mg/kg), Zn (9.20 mg/kg), Cu (5.22 mg/kg), and Se (68 µg/kg), while D4 showed the highest K (22.1 mg/g) and D1 the highest Ca (1.94 mg/g). Lead and cadmium were highest in D8 and arsenic in D1, although all values remained within the regulatory limits. Hydroethanolic extracts exhibited remarkable compositional variability: D4 and D5 had the greatest carbohydrates (737.70 ± 55.79 mg/g DM), D8 and D9 the highest proteins (up to 40.31 ± 1.33 mg/g DM), and D2 and D8 the highest carotenoids (up to 36.44 ± 1.55 μg/g DM). D8 also showed the highest phenolics (13.98 ± 2.93 mg GAE/g DM) and antioxidant capacity. Cytotoxicity assays in Caco-2 cells showed no significant effects up to 1000 µg/mL. These preliminary findings suggest that green-extracted date fractions may combine nutritional richness, antioxidant potential, and biological safety, providing a basis for future studies on their application as natural and sustainable food ingredients. Full article

The curation of large-scale, diverse datasets for robust weed detection is extremely time-consuming and resource-intensive in practice. Generative artificial intelligence (AI) opens up opportunities for image generation to supplement real-world image acquisition and annotation efforts. However, it is not a trial task to generate high-quality, multi-class weed images that capture the nuances and variations in visual representations for enhanced weed detection. This study presents a novel investigation of advanced stable diffusion (SD) integrated with a module with image prompt capability, IP-Adapter, for weed image generation. Using the IP-Adapter-based model, two image feature encoders, CLIP (contrastive language image pre-training) and BioCLIP (a vision foundation model for biological images), were utilized to generate weed instances, which were then inserted into existing weed images. Image generation and weed detection experiments are conducted on a 10-class weed dataset captured in vegetable fields. The perceptual quality of generated images is assessed in terms of Fréchet Inception Distance (FID) and Inception Score (IS). YOLOv11 (You Only Look Once version 11) models were trained for weed detection, achieving an improved mAP@50:95 of 1.26% on average when combining inserted weed instances with real ones in training, compared to using original images alone. Both the weed dataset and software programs in this study will be made publicly available. This study offers valuable perspectives into the use of IP-adapter-based SD for generating weed images and weed detection. Full article

This research focuses on vehicle Advanced Driver Assistance Systems (ADAS), with particular emphasis on Lane Keeping Assist (LKA) systems which is designed to help drivers keep a vehicle centered within its lane and reduce the risk of unintentional lane departures. These kinds of systems detect lane boundaries using computer vision algorithms applied to video data captured by a forward-facing camera and interpret this visual information to provide corrective steering inputs or driver alerts. The research investigates the performance, reliability, sustainability, and limitations of LKA systems under adverse road and environmental conditions, such as wet pavement and in the presence of degraded, partially visible, or missing horizontal road markings. Improving the reliability of lane detection and keeping systems enhances road safety, reducing traffic accidents caused by lane departures, which directly supports social sustainability. For the theoretical test, a modified road model using MATLAB software was used to simulate poor road markings and to investigate possible test outcomes. A series of field tests were conducted on multiple passenger vehicles equipped with LKA technologies to evaluate their response in real-world scenarios. The results show that it is very important to ensure high quality horizontal road markings as specified in UNECE Regulation No. 130, as lane keeping aids are not uniformly effective. Furthermore, the study highlights the need to develop more robust line detection algorithms capable of adapting to diverse road and weather conditions, thereby enhancing overall driving safety and system reliability. LKA system research supports sustainable mobility strategies promoted by international organizations—aiming to transition to safer, smarter, and less polluting transportation systems. Full article

The rapid development of unmanned aerial vehicles (UAVs) and deep learning has accelerated the application of semantic segmentation in precision agriculture (SSPA). A key driver of this progress lies in multimodal fusion, which leverages complementary structural, spectral, and physiological information to enhance the representation of complex agricultural scenes. Despite advancements, the efficacy of multimodal fusion in SSPA is limited by modality heterogeneity and the difficulty of simultaneously retaining fine details and capturing global context. To address these challenges, we propose AgriFusion, a dual-encoder framework based on convolutional and transformer architectures for SSPA tasks. Specifically, convolutional and transformer encoders are first used to extract crop-related local structural details and global contextual features from multimodal inputs. Then, an attention-based fusion module adaptively integrates these complementary features in a modality-aware manner. Finally, a MLP-based decoder aggregates multi-scale representations to generate accurate segmentation results efficiently. Experiments conducted on the Agriculture-Vision dataset demonstrate that AgriFusion achieves a mean Intersection over Union (mIoU) of 49.31%, Pixel Accuracy (PA) of 81.72%, and F1 score of 67.85%, outperforming competitive baselines including SegFormer, DeepLab, and AAFormer. Ablation studies further reveal that unimodal or shallow fusion strategies suffer from limited discriminative capacity, whereas AgriFusion adaptively integrates complementary multimodal features and balances fine-grained local detail with global contextual information, yielding consistent improvements in identifying planting anomalies and crop stresses. These findings validate our central claims that modality-aware spectral fusion and balanced multi-scale representation are critical to advancing agricultural semantic segmentation, and establish AgriFusion as a principled framework for enhancing remote sensing-based monitoring with practical implications for sustainable crop management and precision farming. Full article

Visual object tracking is a fundamental computer vision task recently extended to multimodal settings, where natural language descriptions complement visual information. Existing multimodal trackers typically rely on large-scale transformer architectures that jointly train visual and textual encoders, resulting in hundreds of millions of trainable parameters and substantial computational overhead. We propose a lightweight multimodal adapter that integrates textual descriptions into a state-of-the-art visual-only framework with minimal overhead. The pretrained visual and text encoders are frozen, and only a small projection network is trained to align text embeddings with visual features. The adapter is modular, can be toggled at inference, and has negligible impact on speed. Extensive experiments demonstrate that textual cues improve tracking robustness and enable efficient multimodal integration with over 100× fewer trainable parameters than heavy multimodal trackers, allowing training and deployment on resource-limited devices. Full article

Prestressing wedges are critical in bridge and road construction, but flaws in wedge threads lead to severe safety hazards, construction delays, and costly maintenance. Traditional manual inspection remains labor-intensive and inconsistent, particularly under variable illumination and complex surface conditions. However, few studies have investigated improving the inspection effectiveness. Therefore, this study aims to propose a lightweight FasterNET-YOLOv5 framework for accurate and robust prestress wedge flaw detection in industrial applications. The framework achieves a detection precision of 96.3%, recall of 96.2, and mAP@0.5 of 96.5 with 18% faster end-to-end inference speed, enabling deployable system configuration on portable or embedded devices, making the approach suitable for real-time industrial inspection. Further practical guidance for workshop inspection illumination conditions was confirmed by robustness evaluations, as white lighting background provides the most balanced performance for incomplete thread and scratch defects. Moreover, a mechanical model-based inverse method was exploited to link the detections from machine vision. The results also demonstrate the potential for broader 3D surface inspection tasks in threaded, machined, and curved components of intelligent, automated, and cost-effective quality control. In general, this research contributes to computational inspection systems by bridging deep learning-based flaw detection with engineering-grade reliability and deployment feasibility. Full article

How individuals and organizations interface with the digital economy has been largely influenced by transformations ushered in on the global financial map by the rapidly expanding Financial Technology (FinTech). This paper seeks to shed light on the successes of FinTech, namely on how it contributed to sustainability through financial inclusion, reduction in reliance on cash and the promotion of an innovation-driven economy known for being paperless. Based on contributions from students at Taif University in Saudi Arabia, determinants of FinTech adoption intentions are analyzed using data from n = 544. Our study focuses on evaluating the effects of financial, technical and external factors on adoption behavior by using a two-prong approach: first, we use the DeLone and McLean IS Success Model; then we employ a Second-Order Construct using Structural Equation Modelling (SEM). The results indicated that the strongest effects on attitudes stem from technical factors—information, system and service quality. Additionally, they also show that adoption intention is considerably shaped by financial as well as external dimensions. The Saudi Vision 2030 has set national goals of digital transformation, financial inclusion and human capital empowerment. This study provides a modest contribution to those goals by fostering FinTech adoption among the youth. Furthermore, its findings also offer educators, policymakers and Fintech providers a platform to enhance literacy, strengthen trust and develop sustainable digital finance ecosystems in line with the Kingdom’s Vision 2030 objectives. Full article

Age-related macular degeneration (AMD) is a leading cause of irreversible vision loss, primarily driven by oxidative stress–induced degeneration of retinal pigment epithelium (RPE). Erythropoietin (EPO), a hematopoietic cytokine with neuroprotective properties, has been shown to reduce apoptosis and retinal degeneration. In this study, we examined the cytoprotective role of a non-erythropoietic EPO variant, EPO-R76E, in suppressing oxidative stress and mitochondrial dysfunction related to oxidative stress in RPE cells. Stable ARPE-19 cell lines expressing EPO-R76E were generated via lentiviral transduction and exposed to paraquat to induce oxidative stress. Oxidative stress was induced using paraquat. EPO-R76E expression conferred increased cell viability and resistance to mitochondrial damage, as assessed by cytotoxicity assays. Western blot analysis revealed reduced expression of ferritin and p62/SQSTM1, diminished activation of p-AMPK and NRF2, and restoration of GPX4 levels, indicating enhanced antioxidant defenses. Moreover, intracellular iron accumulation and reactive oxygen species were significantly reduced in EPO-R76E-expressing cells exposed to paraquat. These findings suggest that EPO-R76E promotes mitochondrial homeostasis and modulates oxidative stress pathways. Our study positions EPO-R76E as a promising therapeutic candidate for halting RPE degeneration in AMD. Full article

This study evaluated regional and seasonal variations in cobalt (Co), cadmium (Cd), and lead (Pb) concentrations in the serum and milk of she-camels and their calves across five regions of Saudi Arabia to evaluate their potential as bioindicators of environmental contamination. A total of 450 biological and environmental samples (serum, milk, soil, water, and feed) were analyzed using inductively coupled plasma optical emission spectrometry (ICP–OES). Regional, seasonal, and physiological effects were assessed by analysis of variance and Pearson correlation. Serum Co varied significantly (p < 0.05) by region and season, with the highest values in the Eastern region during spring. She-camel cadmium showed significant regional differences, particularly higher concentrations in the Southern region, while Pb displayed pronounced seasonal variation, peaking in spring serum and milk of she-camel. In she-camel milk, Co, Cd, and Pb were significantly influenced by region and season interactions (p < 0.05). Correlation analysis revealed strong positive associations between Cd and Pb (r = 0.85, p < 0.001) and between Co and Pb (r = 0.70, p < 0.01), indicating shared exposure pathways. In conclusions, although all metal concentrations remained below FAO/WHO permissible limits, the observed variability highlights the camel’s value as a bioindicator of environmental contamination. Continued monitoring is recommended to safeguard food safety and support Saudi Vision 2030 sustainability goals. Full article

Background/Objectives: Oman Vision 2040, the national blueprint for socio-economic transformation, aims to elevate the Sultanate to developed nation status, with the “Health” priority committed to building a “Leading Healthcare System with International Standards” via a Health in All Policies (HiAP) approach. This paper critically reviews Oman’s strategic health directions and implementation frameworks under Vision 2040, assessing their alignment with global Sustainable Development Goals (SDGs) and serving as a case model for health system transformation. Methods: This study employs a critical narrative synthesis based on a comprehensive literature search that included academic, official government reports, and international organization sources. The analysis is guided by the World Health Organization’s (WHO) Health Systems Framework, providing a structured interpretation of progress across its six building blocks. Results: Key interventions implemented include integrated governance (e.g., Committee for Managing and Regulating Healthcare), diversified health financing (e.g., public private partnership (PPPs), Health Endowment Foundation), and strategic digital transformation (e.g., Al-Shifa system, AI diagnostics). Performance metrics show progress, with a rise in the Legatum Prosperity Index ranking and an increase in the Community Satisfaction Rate. However, critical challenges persist, including resistance to change during governance restructuring, cybersecurity risks from digital adoption, and system fragmentation that complicates a unified Non-Communicable Disease (NCD) response. Conclusions: Oman’s integrated approach, emphasizing decentralization, quality improvement, and investment in preventive health and human capital, positions it for sustained progress. The transformation offers generalizable insights. Successfully realizing Vision 2040 demands rigorous, evidence-informed policymaking to effectively address equity implications and optimize resource allocation. Full article

Shellfish aquaculture is considered a major pillar of the seafood industry for its high market value, which increases the value for global food security and sustainability, often constrained in terms of conventional, labor-intensive practices. This review outlines the importance of automation and its advances in the shellfish value chain, starting from the hatchery operations to harvesting, processing, traceability, and logistics. Emerging technologies such as imaging, computer vision, artificial intelligence, robotics, IoT, blockchain, and RFID provide a major impact in transforming the shellfish sector by improving the efficiency, reducing the labor costs and environmental impacts, enhancing the food safety, and providing transparency throughout the supply chain. The studies involving the bivalves and crustaceans on their automated feeding, harvesting, grading, depuration, non-destructive quality assessments, and smart monitoring in transportation are highlighted in this review to address concerns involved with conventional practices. The review puts forth the need for integrating automated technologies into farm management and post-harvest operations to scale shellfish aquaculture sustainably, meeting the rising global demand while aligning with the Sustainability Development Goals (SDGs). Full article

Recent technological advancements have made Large Language Models (LLMs) easily accessible through apps such as ChatGPT, Claude.ai, Google Gemini, and HuggingChat, allowing text generation on diverse topics with a simple prompt. Considering this scenario, we propose three machine–machine collaboration models to streamline and accelerate Delphi execution time by leveraging the extensive knowledge of LLMs. We then applied one of these models—the Iconic Minds Delphi—to run Delphi questionnaires focused on the future of work and higher education in Brazil. Therefore, we prompted ChatGPT to assume the role of well-known public figures from various knowledge areas. To validate the effectiveness of this approach, we asked one of the emulated experts to evaluate his responses. Although this individual validation was not sufficient to generalize the approach’s effectiveness, it revealed an 85% agreement rate, suggesting a promising alignment between the emulated persona and the real expert’s opinions. Our work contributes to leveraging Artificial Intelligence (AI) in Futures Research, emphasizing LLMs’ potential as collaborators in shaping future visions while discussing their limitations. In conclusion, our research demonstrates the synergy between Delphi and LLMs, providing a glimpse into a new method for exploring central themes, such as the future of work and higher education. Full article